Oliver Diaz - Academia.edu (original) (raw)

Papers by Oliver Diaz

Research paper thumbnail of Realistic compressed breast phantoms for medical physics applications

15th International Workshop on Breast Imaging (IWBI2020)

Anthropomorphic digital breast phantoms are an essential part in the development, simulation, and... more Anthropomorphic digital breast phantoms are an essential part in the development, simulation, and optimisation of x-ray breast imaging systems. They could be used in many applications, such as running virtual clinical trials or developing dosimetry methods. 3D image modalities, such as breast computed tomography (BCT), provide high resolution images to help produce breast models with realistic internal tissue distribution. However, in order to mimic X-ray imaging procedures such as mammography or digital breast tomosynthesis, the breast model needs to be compressed. In this work, we describe a method to generate compressed breast phantoms using a biomechanical finite element (FE) model from BCT volumes, by simulating physically realistic tissue deformation. Unlike prior literature, we propose a new tissue interpolation methodology which avoids interpolating the deformation fields, resulting in the preservation of the breast tissue amount during the compression process and therefore increasing the accuracy of the deformation. In this study, a total of 88 BCT images were compressed in order to obtain a set of realistic phantoms. The information associated with the phantom (i.e. amount of glandular tissue and adipose tissue and total breast volume) is compared before and after compression (showing a correlation R of 0.99). Also, the same metrics were evaluated between compressed phantoms and VolparaTM measurements from breast tomosynthesis images (R=0.81 − 0.85). Furthermore, we include a 3D surface analysis and describe several medical physics applications in which our phantoms have been used: x-ray dosimetry, scattered radiation estimation or glandular tissue assessment.

Research paper thumbnail of A Review of Kate Daloz\u27s We Are As Gods

Research paper thumbnail of Breast tomosynthesis reconstruction using TIGRE software tool

14th International Workshop on Breast Imaging (IWBI 2018)

This article shows the feasibility of using the open source Tomographic Iterative GPU-based Recon... more This article shows the feasibility of using the open source Tomographic Iterative GPU-based Reconstruction (TIGRE) Toolbox, originally developed for cone-beam x-ray computed tomography (CBCT), to reconstruct images from a Digital Breast Tomosynthesis (DBT) system. We present reconstructed images of simple simulated phantoms as well as the commercially available breast phantoms CIRS models 013 and 073; acquired by a Hologic Selenia Dimensions system. Initial results have shown the ability of TIGRE to reconstruct images using several reconstruction algorithms (FDK, OSSART, MLEM), although a wider variety of iterative algorithms could be also considered. This is the first work that uses the TIGRE reconstruction tool for DBT geometries, opening new possibilities for free, fast and reliable reconstruction algorithms to other research groups.

Research paper thumbnail of Battling Epidemics & Disparity with Modeling

Letters in Biomathematics

Policymakers are under intense pressure to respond effectively to the ongoing COVID-19 situation.... more Policymakers are under intense pressure to respond effectively to the ongoing COVID-19 situation. Epidemiological models, which have been helpful in many previous infectious diseases’ epidemics, have been inconsistent and often incorrect in predicting burden of COVID-19 outbreak. Modelers are struggling to identify and capture appropriate drivers of the current outbreak giving conflicting conclusions. COVID-19 is not only exerting unprecedented social pressure on the vulnerable population but also its patterns are getting impacted by existing and aggravating social problems. The present article stresses the role of this dual nature of the impact of COVID-19 and suggests modelers to incorporate challenges at the interface of COVID-19 preparedness and social epidemics such as homelessness and opioid use. There is an urgent need to encourage social distancing policies to protect people and prevent the spread of the virus, while ensuring that other social crises and vulnerable populations are not ignored.

Research paper thumbnail of A Fully Automatic Method for Vascular Tortuosity Feature Extraction in the Supra-Aortic Region: Unraveling Possibilities in Stroke Treatment Planning

SSRN Electronic Journal, 2022

Research paper thumbnail of A study of rigid registration methods for ABUS temporal studies

Poster: "ECR 2016 / C-0532 / A study of rigid registration methods for ABUS temporal studies... more Poster: "ECR 2016 / C-0532 / A study of rigid registration methods for ABUS temporal studies" by: "Y. Diez1, A. Maroto Gonzalez2, O. Diaz2, A. Gubern-Merida3, R. Marti2; 1Sendai/JP, 2Girona/ES, 3Nijmegen/NL"

Research paper thumbnail of A deep learning framework for micro-calcification detection in 2D mammography and C-view

14th International Workshop on Breast Imaging (IWBI 2018), 2018

The aim of this paper is to propose a deep learning framework for micro-calcification detection i... more The aim of this paper is to propose a deep learning framework for micro-calcification detection in 2D mammography and in 2D synthetic mammography (C-view) from digital breast tomosynthesis (DBT). The dataset analyzed for 2D mammograms is the INbreast dataset that consists of 410 digital images and we used 360 images with annotated micro-calcifications. For the synthetic views in DBT, we used a private dataset of 245 images, where micro-calcifications were validated by an experienced radiologist. The network is trained in a patch-based fashion, where micro-calcifications are considered positive samples, while patches containing other breast tissues are considered negative. For evaluating the entire dataset, a 2-fold cross validation was performed. In addition, a sliding window method was used to classify new patches within an image with those from the trained model. Considering 5,656 positive samples and 18,000,000 of negative samples, results for the 2D mammography, on the entire dataset, showed an area under the curve (AUC) of 0.9998 and a logarithmic partial area under the curve (logPAUC), in the interval (10−6 , 1), of 0.8252. Results for the C-View, considering 3,420 positive samples and 11,395,939 of negative samples, showed an AUC, on the entire dataset, of 0.9997 and a logPAUC, in the interval (10−6 , 1), of 0.8178. In this paper, we illustrate the applied methodologies, the network architecture used for training and test, and the results obtained.

Research paper thumbnail of Automated detection of motion in breast DCE-MRI to assess study quality and prevent unnecessary call-backs

Poster: "ECR 2015 / C-1845 / Automated detection of motion in breast DCE-MRI to assess study... more Poster: "ECR 2015 / C-1845 / Automated detection of motion in breast DCE-MRI to assess study quality and prevent unnecessary call-backs" by: "L. Wang1, A. Gubern Merida2, O. Diaz3, Y. Diez3, R. M. Mann2, S. Diekmann1, F. Zohrer1, H. Laue1, J. Schwaab4; 1Bremen/DE, 2Nijmegen/NL, 3Girona/ES, 4Heidelberg/DE"

Research paper thumbnail of How do medical physicists perceive artificial intelligence?

Research paper thumbnail of Can breast models be simplified to estimate scattered radiation in breast tomosythesis?

Medical Imaging 2019: Physics of Medical Imaging, 2019

Scattered radiation can represent a large portion of the total signal recorded at the image recep... more Scattered radiation can represent a large portion of the total signal recorded at the image receptor in certain x-ray breast imaging systems, such as digital breast tomosynthesis (DBT). For many years, Monte Carlo (MC) simulations have represented the golden approach to estimate the scatter field, initially with simple models and more recently with anthropomorphic phantoms. However, it is unclear how the scattered radiation varies between such models. Further knowledge of the scatter behaviour can help to develop faster and simpler scatter field estimation approaches, which are highly demanded in virtual clinical trial (VCT) strategies. In this work, the scattered radiation estimated for several homogeneous breast models is compared against that from textured breast phantoms. By means of MC simulations, scatter fields are investigated under the same DBT scenario. Results for a quasi-realistic breast model suggest that homogeneous models with same shape and glandularity can approximate the scattered radiation produced by a heterogeneous phantom with a median error of 2%. Simpler models with semi-circular shapes, which reduces the complexity in the scatter field estimation and decrease the computational time, show good approximation in the central region of the breast although larger discrepancies are observed in the peripheral region of the breast image.

Research paper thumbnail of Mass detection in mammograms using pre-trained deep learning models

14th International Workshop on Breast Imaging (IWBI 2018), 2018

Mammography is a gold standard imaging modality and is widely used for breast cancer screening. W... more Mammography is a gold standard imaging modality and is widely used for breast cancer screening. With recent advances in the field of deep learning, the use of deep convolution neural networks (CNNs) in medical image analysis has become very encouraging. The aim of this study is to exploit CNNs for mass detection in mammograms using pre-trained networks. We use the resnet-50 CNN architecture pre-trained with the ImageNet database to perform mass detection on two publicly available image datasets: CBIS-DDSM and INbreast. We demonstrate that the CNN model pretrained using natural image database (ImageNet) can be effectively finetuned to yield better results, compared to randomly initialized models. Further, the benefit of applying transfer learning on a smaller dataset is demonstrated by using the best model obtained from CBIS-DDSM training to finetune on the INbreast database. We analyzed the adaptability of the CNN’s last fully connected (FC) layer and the all convolutional layers to detect masses. The results showed a testing accuracy of 0.92 and an area under the receiver operating characteristic curve (AUC) of 0.98 for the model finetuned on all convolutional layers, while testing accuracy of 0.86 and AUC=0.93 when the model is trained only on the last FC layer.

Research paper thumbnail of Quantifying spillover benefits in value assessment: a case study of increased graft survival on the US kidney transplant waitlist

Journal of Medical Economics, 2021

Abstract Aim To quantify the wider impacts of increased graft survival on the size of the kidney ... more Abstract Aim To quantify the wider impacts of increased graft survival on the size of the kidney transplant waitlist and health and economic outcomes. Materials and methods The analysis employed known steady-state solutions to a double-queueing system as well as simulations of this system. Baseline input parameters were sourced from the Organ Procurement and Transplant Network and the United States Renal Data System. Three increased graft survival scenarios were modeled: decreases in repeat transplant candidates joining the waitlist of 25%, 50%, and 100%. Results Under the three scenarios, we estimated that the US waitlist size would decrease from 91,822 to 85,461 (6.9% decrease), 80,073 (12.8% decrease), and 69,340 (24.4% decrease), respectively. Patient outcomes improved, with lifetime quality-adjusted life years (QALYs) for a 1-year cohort of transplant recipients increasing by 10,010, 16,888, and 43,345 over the three scenarios. Discounted lifetime costs for the cohort in the new steady state were lower by 1.6billion,1.6 billion, 1.6billion,2.3 billion, and $9.0 billion for each scenario, respectively. Spillover impacts (i.e. benefits that accrued beyond the patients who directly experienced increased graft survival) accounted for 58–65% of the QALY gains and ranged from cost increases of 3.3% to decreases of 5.5%. Limitations The model is a simplification of reality and does not account for the full degree of patient heterogeneity occurring in the real world. Health economic outcomes are extrapolated based on the assumption that the median patient is representative of the overall population. Conclusions Increasing graft survival reduces demand from repeat transplants candidates, allowing additional candidates to receive transplants. These spillover impacts decrease waitlist size and shorten wait times, leading to improvements in graft and patient survival as well as quality-of-life. Cost-effectiveness analyses of treatments that increase kidney graft survival should incorporate spillover benefits that accrue beyond the direct recipient of an intervention.

Research paper thumbnail of Evaluation of elastic parameters for breast compression using a MRI-mammography registration approach

15th International Workshop on Breast Imaging (IWBI2020), 2020

Patient-specific finite element (FE) models of the breast have received increasing attention due ... more Patient-specific finite element (FE) models of the breast have received increasing attention due to the potential capability of fusing information from different image modalities. During the Magnetic Resonance Imaging (MRI) to X-ray mammography (MG) registration procedure, a FE model is compressed mimicking the mammographic acquisition. To develop an accurate model of the breast, the elastic properties and stress-strain relationship of breast tissues need to be properly defined. Several studies (in vivo and ex vivo experiments) have proposed a range of values associated to the mechanical properties of different tissues. This work analyse the elastic parameters (Young Modulus and Poisson ratio) obtained during the process of registering MRI to X-ray MG images. Position, orientation, elastic parameters and amount of compression are optimised using a simulated annealing algorithm, until the biomechanical model reaches a suitable position with respect to the corresponding mammogram. FE models obtained from 29 patients, 46 MRI-MG studies, were used to extract the optimal elastic parameters for breast compression. The optimal Young modulus obtained in the entire dataset correspond to 4.46 ± 1.81 kP a for adipose and 16.32 ± 8.36 kP a for glandular tissue, while the average Poisson ratio was 0.0492 ± 0.004. Furthermore, we did not find a correlation between the elastic parameters and other patient-specific factors such as breast density or patient age.

Research paper thumbnail of Validation and application of a new image reconstruction software toolbox (TIGRE) for breast cone-beam computed tomography

A new image reconstruction software toolbox TIGRE (Tomographic Iterative GPU-based Reconstruction... more A new image reconstruction software toolbox TIGRE (Tomographic Iterative GPU-based Reconstruction) has been evaluated for use in breast cone-beam computed tomography (CBCT) studies. This new software toolbox TIGRE has been compared to a standard Matlab-based implementation previously validated for X-ray mammography imaging. In particular, the image projection generator algorithm in the TIGRE toolbox, which is based on the Siddon ray-tracing algorithm, has been studied. The quantitative evaluation in terms of histograms and profile analyses, illustrates that TIGRE’s image projection show good agreement with our in-house validated X-ray ray tracing tool. In addition, it has been observed that since TIGRE uses GPU-based calculations, it produces projections approximately 90 times faster than CPU-based algorithms, dependent on choice of GPU. The breast CT images have also been reconstructed and evaluated using the two projection tools. The analyses show that the projections taken by TIG...

Research paper thumbnail of First approach to estimate breast radiation dose in a DBT prone biopsy table

Stereotactic breast biopsy (SBB) is a common clinical procedure for suspicious breast lesion anal... more Stereotactic breast biopsy (SBB) is a common clinical procedure for suspicious breast lesion analysis. With the arrival of DBT-guided biopsy systems, the clinical performance of such procedures has improved enormously since breast lesions are better detected. However, little information is found in the literature regarding the patient’s radiation dose during these clinical procedures. This work presents, for the first time, a first approach to estimate the mean glandular dose (MGD) within the biopsy window for 101 patients who underwent breast biopsy in a commercially available DBT-guided prone table. This study is supported by the calculation of normalised glandular dose (DgN) coefficients from Monte Carlo simulations. Preliminary results show that the total MGD of the biopsy procedure varies between 10.2 mGy and 19.2 mGy for patients with breast thickness between 2 cm and 8 cm. Furthermore, a great variability in the number of acquisitions (tomo scan or stereo projections) of the ...

Research paper thumbnail of Comparison of three breast imaging techniques using 4-AFC human observation study

X-ray mammography is the gold standard for detecting malignancies in a breast cancer screening co... more X-ray mammography is the gold standard for detecting malignancies in a breast cancer screening context. However, limited angle tomosynthesis has now started to be used in screening due to its ability to remove overlying image clutter. However, breast CT is a method, which can potentially remove all overlying clutter through the use of tomographic image reconstruction. The aim of this work is to investigate whether breast cone-beam computed tomography (CBCT) can provide better lesion detectability compared to 2D mammography or digital breast tomosynthesis (DBT). Lesions with a diameter of 4 mm, 5 mm and 6 mm have been inserted in a simulated breast phantom. In total 180 images are analysed, out of which 90 images contain lesions (equally divided between the 4 mm, 5mm and 6mm diameter lesions) and the rest represent normal breast tissues. The TIGRE (Tomographic Iterative GPU-based Reconstruction) has been used to simulate 360 projections and to reconstruct the images using the FeldKam...

Research paper thumbnail of Monte Carlo dose evaluation of different fibroglandular tissue distribution in breast imaging

15th International Workshop on Breast Imaging (IWBI2020), 2020

This work compares estimates of the radiation dose in mammography obtained using three different ... more This work compares estimates of the radiation dose in mammography obtained using three different fibroglandular tissue distributions. Ninety volumetric images of patient breasts were acquired with a dedicated breast CT system and the voxels automatically classified as containing skin, adipose, or glandular tissue. The classified images underwent simulated mechanical compression to mimic the mammographic cranio-caudal acquisition. The voxels containing fibroglandular and adipose tissue were then distributed in the breast phantoms following three different methods: patient-based (i.e., maintaining the original distribution), homogeneous (i.e., each voxel is a homogeneous mixture of adipose and glandular tissue) and newly-proposed continuous (i.e., the glandular tissue is distributed according to a general model, derived from the patient breast CT data). All breast phantoms were used in Monte Carlo simulations to estimate the radiation dose. The results show that the doses estimated using the continuous fibroglandular tissue distribution agree within 3% of the doses estimated using the heterogeneous patient-based distribution, and that it leads to a dose reduction of 27% compared to the homogeneous distribution.

Research paper thumbnail of A semi-empirical model for scatter field reduction in digital mammography

Physics in Medicine & Biology, 2021

X-ray mammography is the gold standard technique in breast cancer screening programmes. One of th... more X-ray mammography is the gold standard technique in breast cancer screening programmes. One of the main challenges that mammography is still facing is scattered radiation, which degrades the quality of the image and complicates the diagnosis process. Anti-scatter grids, the main standard physical scattering reduction technique, have some unresolved challenges as they increase the dose delivered to the patient, do not remove all the scattered radiation and increase the cost of the equipment. Alternative scattering reduction methods based on post-processing algorithms, have lately been under investigation. This study is concerned with the use of image post-processing to reduce the scatter contribution in the image, by convolving the primary plus scatter image with kernels obtained from simplified Monte Carlo (MC) simulations. The proposed semi-empirical approach uses up to five thickness-dependant symmetric kernels to accurately estimate the scatter contribution of different areas of ...

Research paper thumbnail of Validation of modelling tools for simulating wide-angle DBT systems

Medical Imaging 2019: Physics of Medical Imaging, 2019

Full-field 2D digital mammography is used for breast cancer screening throughout the world. Digit... more Full-field 2D digital mammography is used for breast cancer screening throughout the world. Digital breast tomosynthesis (DBT) is now widely available and has shown promise as a breast cancer screening modality. Rigorous evaluation and comparison studies must be conducted before considering the new modality for routine breast cancer screening. Conventional clinical trials involving human subjects are time consuming and expensive and are limited to commercially-available system designs. Alternatively, Virtual Clinical Trials (VCTs) can be used to conduct such studies using modelling tools by simulating clinically-realistic images and experimental system designs. The OPTIMAM image simulation toolbox contains a suite of tools that can used to simulate visually and clinically realistic images for VCTs. Recently, tools for simulating a wide-angle DBT system were added to the toolbox. In this paper, we present the simulation methodology and validation results for a wide-angle DBT system. The validation was performed by simulating images of standard test objects and comparing these with real images acquired using identical settings on the simulated real system. The comparison of the contrast-to-noise ratios, geometrical distortion (z-resolution) and image blurring for real and simulated images of test objects showed good agreement. This suggests that the images of a wide-angle DBT system produced using our simulation approach are comparable to real images.

Research paper thumbnail of Similarity Metrics for Intensity-Based Registration Using Breast Density Maps

Pattern Recognition and Image Analysis, 2017

Intensity-based registration algorithms have been widely used in medical image applications. This... more Intensity-based registration algorithms have been widely used in medical image applications. This type of registration algorithms uses an object function to compute a transformation and optimizes a measure of similarity between the images being registered. The most common similarity metrics used in registration are sum of squared differences, mutual information and normalized cross-correlation. This paper aims to compare these similarity metrics, using common registration algorithms applied to breast density maps registration. To evaluate the results, we use the protocols for evaluation of similarity measures proposed byŠkerl et al. They consist in defining a set of random directions in the parameter space of the registration algorithm and compute statistical measures, such as the accuracy, capture range, number of maxima and risk of non-convergence, along these directions. The obtained results show a better performance corresponding to normalized cross-correlation for the rigid registration algorithm, while the sum of squared difference obtains the best result for the B-Spline method.

Research paper thumbnail of Realistic compressed breast phantoms for medical physics applications

15th International Workshop on Breast Imaging (IWBI2020)

Anthropomorphic digital breast phantoms are an essential part in the development, simulation, and... more Anthropomorphic digital breast phantoms are an essential part in the development, simulation, and optimisation of x-ray breast imaging systems. They could be used in many applications, such as running virtual clinical trials or developing dosimetry methods. 3D image modalities, such as breast computed tomography (BCT), provide high resolution images to help produce breast models with realistic internal tissue distribution. However, in order to mimic X-ray imaging procedures such as mammography or digital breast tomosynthesis, the breast model needs to be compressed. In this work, we describe a method to generate compressed breast phantoms using a biomechanical finite element (FE) model from BCT volumes, by simulating physically realistic tissue deformation. Unlike prior literature, we propose a new tissue interpolation methodology which avoids interpolating the deformation fields, resulting in the preservation of the breast tissue amount during the compression process and therefore increasing the accuracy of the deformation. In this study, a total of 88 BCT images were compressed in order to obtain a set of realistic phantoms. The information associated with the phantom (i.e. amount of glandular tissue and adipose tissue and total breast volume) is compared before and after compression (showing a correlation R of 0.99). Also, the same metrics were evaluated between compressed phantoms and VolparaTM measurements from breast tomosynthesis images (R=0.81 − 0.85). Furthermore, we include a 3D surface analysis and describe several medical physics applications in which our phantoms have been used: x-ray dosimetry, scattered radiation estimation or glandular tissue assessment.

Research paper thumbnail of A Review of Kate Daloz\u27s We Are As Gods

Research paper thumbnail of Breast tomosynthesis reconstruction using TIGRE software tool

14th International Workshop on Breast Imaging (IWBI 2018)

This article shows the feasibility of using the open source Tomographic Iterative GPU-based Recon... more This article shows the feasibility of using the open source Tomographic Iterative GPU-based Reconstruction (TIGRE) Toolbox, originally developed for cone-beam x-ray computed tomography (CBCT), to reconstruct images from a Digital Breast Tomosynthesis (DBT) system. We present reconstructed images of simple simulated phantoms as well as the commercially available breast phantoms CIRS models 013 and 073; acquired by a Hologic Selenia Dimensions system. Initial results have shown the ability of TIGRE to reconstruct images using several reconstruction algorithms (FDK, OSSART, MLEM), although a wider variety of iterative algorithms could be also considered. This is the first work that uses the TIGRE reconstruction tool for DBT geometries, opening new possibilities for free, fast and reliable reconstruction algorithms to other research groups.

Research paper thumbnail of Battling Epidemics & Disparity with Modeling

Letters in Biomathematics

Policymakers are under intense pressure to respond effectively to the ongoing COVID-19 situation.... more Policymakers are under intense pressure to respond effectively to the ongoing COVID-19 situation. Epidemiological models, which have been helpful in many previous infectious diseases’ epidemics, have been inconsistent and often incorrect in predicting burden of COVID-19 outbreak. Modelers are struggling to identify and capture appropriate drivers of the current outbreak giving conflicting conclusions. COVID-19 is not only exerting unprecedented social pressure on the vulnerable population but also its patterns are getting impacted by existing and aggravating social problems. The present article stresses the role of this dual nature of the impact of COVID-19 and suggests modelers to incorporate challenges at the interface of COVID-19 preparedness and social epidemics such as homelessness and opioid use. There is an urgent need to encourage social distancing policies to protect people and prevent the spread of the virus, while ensuring that other social crises and vulnerable populations are not ignored.

Research paper thumbnail of A Fully Automatic Method for Vascular Tortuosity Feature Extraction in the Supra-Aortic Region: Unraveling Possibilities in Stroke Treatment Planning

SSRN Electronic Journal, 2022

Research paper thumbnail of A study of rigid registration methods for ABUS temporal studies

Poster: "ECR 2016 / C-0532 / A study of rigid registration methods for ABUS temporal studies... more Poster: "ECR 2016 / C-0532 / A study of rigid registration methods for ABUS temporal studies" by: "Y. Diez1, A. Maroto Gonzalez2, O. Diaz2, A. Gubern-Merida3, R. Marti2; 1Sendai/JP, 2Girona/ES, 3Nijmegen/NL"

Research paper thumbnail of A deep learning framework for micro-calcification detection in 2D mammography and C-view

14th International Workshop on Breast Imaging (IWBI 2018), 2018

The aim of this paper is to propose a deep learning framework for micro-calcification detection i... more The aim of this paper is to propose a deep learning framework for micro-calcification detection in 2D mammography and in 2D synthetic mammography (C-view) from digital breast tomosynthesis (DBT). The dataset analyzed for 2D mammograms is the INbreast dataset that consists of 410 digital images and we used 360 images with annotated micro-calcifications. For the synthetic views in DBT, we used a private dataset of 245 images, where micro-calcifications were validated by an experienced radiologist. The network is trained in a patch-based fashion, where micro-calcifications are considered positive samples, while patches containing other breast tissues are considered negative. For evaluating the entire dataset, a 2-fold cross validation was performed. In addition, a sliding window method was used to classify new patches within an image with those from the trained model. Considering 5,656 positive samples and 18,000,000 of negative samples, results for the 2D mammography, on the entire dataset, showed an area under the curve (AUC) of 0.9998 and a logarithmic partial area under the curve (logPAUC), in the interval (10−6 , 1), of 0.8252. Results for the C-View, considering 3,420 positive samples and 11,395,939 of negative samples, showed an AUC, on the entire dataset, of 0.9997 and a logPAUC, in the interval (10−6 , 1), of 0.8178. In this paper, we illustrate the applied methodologies, the network architecture used for training and test, and the results obtained.

Research paper thumbnail of Automated detection of motion in breast DCE-MRI to assess study quality and prevent unnecessary call-backs

Poster: "ECR 2015 / C-1845 / Automated detection of motion in breast DCE-MRI to assess study... more Poster: "ECR 2015 / C-1845 / Automated detection of motion in breast DCE-MRI to assess study quality and prevent unnecessary call-backs" by: "L. Wang1, A. Gubern Merida2, O. Diaz3, Y. Diez3, R. M. Mann2, S. Diekmann1, F. Zohrer1, H. Laue1, J. Schwaab4; 1Bremen/DE, 2Nijmegen/NL, 3Girona/ES, 4Heidelberg/DE"

Research paper thumbnail of How do medical physicists perceive artificial intelligence?

Research paper thumbnail of Can breast models be simplified to estimate scattered radiation in breast tomosythesis?

Medical Imaging 2019: Physics of Medical Imaging, 2019

Scattered radiation can represent a large portion of the total signal recorded at the image recep... more Scattered radiation can represent a large portion of the total signal recorded at the image receptor in certain x-ray breast imaging systems, such as digital breast tomosynthesis (DBT). For many years, Monte Carlo (MC) simulations have represented the golden approach to estimate the scatter field, initially with simple models and more recently with anthropomorphic phantoms. However, it is unclear how the scattered radiation varies between such models. Further knowledge of the scatter behaviour can help to develop faster and simpler scatter field estimation approaches, which are highly demanded in virtual clinical trial (VCT) strategies. In this work, the scattered radiation estimated for several homogeneous breast models is compared against that from textured breast phantoms. By means of MC simulations, scatter fields are investigated under the same DBT scenario. Results for a quasi-realistic breast model suggest that homogeneous models with same shape and glandularity can approximate the scattered radiation produced by a heterogeneous phantom with a median error of 2%. Simpler models with semi-circular shapes, which reduces the complexity in the scatter field estimation and decrease the computational time, show good approximation in the central region of the breast although larger discrepancies are observed in the peripheral region of the breast image.

Research paper thumbnail of Mass detection in mammograms using pre-trained deep learning models

14th International Workshop on Breast Imaging (IWBI 2018), 2018

Mammography is a gold standard imaging modality and is widely used for breast cancer screening. W... more Mammography is a gold standard imaging modality and is widely used for breast cancer screening. With recent advances in the field of deep learning, the use of deep convolution neural networks (CNNs) in medical image analysis has become very encouraging. The aim of this study is to exploit CNNs for mass detection in mammograms using pre-trained networks. We use the resnet-50 CNN architecture pre-trained with the ImageNet database to perform mass detection on two publicly available image datasets: CBIS-DDSM and INbreast. We demonstrate that the CNN model pretrained using natural image database (ImageNet) can be effectively finetuned to yield better results, compared to randomly initialized models. Further, the benefit of applying transfer learning on a smaller dataset is demonstrated by using the best model obtained from CBIS-DDSM training to finetune on the INbreast database. We analyzed the adaptability of the CNN’s last fully connected (FC) layer and the all convolutional layers to detect masses. The results showed a testing accuracy of 0.92 and an area under the receiver operating characteristic curve (AUC) of 0.98 for the model finetuned on all convolutional layers, while testing accuracy of 0.86 and AUC=0.93 when the model is trained only on the last FC layer.

Research paper thumbnail of Quantifying spillover benefits in value assessment: a case study of increased graft survival on the US kidney transplant waitlist

Journal of Medical Economics, 2021

Abstract Aim To quantify the wider impacts of increased graft survival on the size of the kidney ... more Abstract Aim To quantify the wider impacts of increased graft survival on the size of the kidney transplant waitlist and health and economic outcomes. Materials and methods The analysis employed known steady-state solutions to a double-queueing system as well as simulations of this system. Baseline input parameters were sourced from the Organ Procurement and Transplant Network and the United States Renal Data System. Three increased graft survival scenarios were modeled: decreases in repeat transplant candidates joining the waitlist of 25%, 50%, and 100%. Results Under the three scenarios, we estimated that the US waitlist size would decrease from 91,822 to 85,461 (6.9% decrease), 80,073 (12.8% decrease), and 69,340 (24.4% decrease), respectively. Patient outcomes improved, with lifetime quality-adjusted life years (QALYs) for a 1-year cohort of transplant recipients increasing by 10,010, 16,888, and 43,345 over the three scenarios. Discounted lifetime costs for the cohort in the new steady state were lower by 1.6billion,1.6 billion, 1.6billion,2.3 billion, and $9.0 billion for each scenario, respectively. Spillover impacts (i.e. benefits that accrued beyond the patients who directly experienced increased graft survival) accounted for 58–65% of the QALY gains and ranged from cost increases of 3.3% to decreases of 5.5%. Limitations The model is a simplification of reality and does not account for the full degree of patient heterogeneity occurring in the real world. Health economic outcomes are extrapolated based on the assumption that the median patient is representative of the overall population. Conclusions Increasing graft survival reduces demand from repeat transplants candidates, allowing additional candidates to receive transplants. These spillover impacts decrease waitlist size and shorten wait times, leading to improvements in graft and patient survival as well as quality-of-life. Cost-effectiveness analyses of treatments that increase kidney graft survival should incorporate spillover benefits that accrue beyond the direct recipient of an intervention.

Research paper thumbnail of Evaluation of elastic parameters for breast compression using a MRI-mammography registration approach

15th International Workshop on Breast Imaging (IWBI2020), 2020

Patient-specific finite element (FE) models of the breast have received increasing attention due ... more Patient-specific finite element (FE) models of the breast have received increasing attention due to the potential capability of fusing information from different image modalities. During the Magnetic Resonance Imaging (MRI) to X-ray mammography (MG) registration procedure, a FE model is compressed mimicking the mammographic acquisition. To develop an accurate model of the breast, the elastic properties and stress-strain relationship of breast tissues need to be properly defined. Several studies (in vivo and ex vivo experiments) have proposed a range of values associated to the mechanical properties of different tissues. This work analyse the elastic parameters (Young Modulus and Poisson ratio) obtained during the process of registering MRI to X-ray MG images. Position, orientation, elastic parameters and amount of compression are optimised using a simulated annealing algorithm, until the biomechanical model reaches a suitable position with respect to the corresponding mammogram. FE models obtained from 29 patients, 46 MRI-MG studies, were used to extract the optimal elastic parameters for breast compression. The optimal Young modulus obtained in the entire dataset correspond to 4.46 ± 1.81 kP a for adipose and 16.32 ± 8.36 kP a for glandular tissue, while the average Poisson ratio was 0.0492 ± 0.004. Furthermore, we did not find a correlation between the elastic parameters and other patient-specific factors such as breast density or patient age.

Research paper thumbnail of Validation and application of a new image reconstruction software toolbox (TIGRE) for breast cone-beam computed tomography

A new image reconstruction software toolbox TIGRE (Tomographic Iterative GPU-based Reconstruction... more A new image reconstruction software toolbox TIGRE (Tomographic Iterative GPU-based Reconstruction) has been evaluated for use in breast cone-beam computed tomography (CBCT) studies. This new software toolbox TIGRE has been compared to a standard Matlab-based implementation previously validated for X-ray mammography imaging. In particular, the image projection generator algorithm in the TIGRE toolbox, which is based on the Siddon ray-tracing algorithm, has been studied. The quantitative evaluation in terms of histograms and profile analyses, illustrates that TIGRE’s image projection show good agreement with our in-house validated X-ray ray tracing tool. In addition, it has been observed that since TIGRE uses GPU-based calculations, it produces projections approximately 90 times faster than CPU-based algorithms, dependent on choice of GPU. The breast CT images have also been reconstructed and evaluated using the two projection tools. The analyses show that the projections taken by TIG...

Research paper thumbnail of First approach to estimate breast radiation dose in a DBT prone biopsy table

Stereotactic breast biopsy (SBB) is a common clinical procedure for suspicious breast lesion anal... more Stereotactic breast biopsy (SBB) is a common clinical procedure for suspicious breast lesion analysis. With the arrival of DBT-guided biopsy systems, the clinical performance of such procedures has improved enormously since breast lesions are better detected. However, little information is found in the literature regarding the patient’s radiation dose during these clinical procedures. This work presents, for the first time, a first approach to estimate the mean glandular dose (MGD) within the biopsy window for 101 patients who underwent breast biopsy in a commercially available DBT-guided prone table. This study is supported by the calculation of normalised glandular dose (DgN) coefficients from Monte Carlo simulations. Preliminary results show that the total MGD of the biopsy procedure varies between 10.2 mGy and 19.2 mGy for patients with breast thickness between 2 cm and 8 cm. Furthermore, a great variability in the number of acquisitions (tomo scan or stereo projections) of the ...

Research paper thumbnail of Comparison of three breast imaging techniques using 4-AFC human observation study

X-ray mammography is the gold standard for detecting malignancies in a breast cancer screening co... more X-ray mammography is the gold standard for detecting malignancies in a breast cancer screening context. However, limited angle tomosynthesis has now started to be used in screening due to its ability to remove overlying image clutter. However, breast CT is a method, which can potentially remove all overlying clutter through the use of tomographic image reconstruction. The aim of this work is to investigate whether breast cone-beam computed tomography (CBCT) can provide better lesion detectability compared to 2D mammography or digital breast tomosynthesis (DBT). Lesions with a diameter of 4 mm, 5 mm and 6 mm have been inserted in a simulated breast phantom. In total 180 images are analysed, out of which 90 images contain lesions (equally divided between the 4 mm, 5mm and 6mm diameter lesions) and the rest represent normal breast tissues. The TIGRE (Tomographic Iterative GPU-based Reconstruction) has been used to simulate 360 projections and to reconstruct the images using the FeldKam...

Research paper thumbnail of Monte Carlo dose evaluation of different fibroglandular tissue distribution in breast imaging

15th International Workshop on Breast Imaging (IWBI2020), 2020

This work compares estimates of the radiation dose in mammography obtained using three different ... more This work compares estimates of the radiation dose in mammography obtained using three different fibroglandular tissue distributions. Ninety volumetric images of patient breasts were acquired with a dedicated breast CT system and the voxels automatically classified as containing skin, adipose, or glandular tissue. The classified images underwent simulated mechanical compression to mimic the mammographic cranio-caudal acquisition. The voxels containing fibroglandular and adipose tissue were then distributed in the breast phantoms following three different methods: patient-based (i.e., maintaining the original distribution), homogeneous (i.e., each voxel is a homogeneous mixture of adipose and glandular tissue) and newly-proposed continuous (i.e., the glandular tissue is distributed according to a general model, derived from the patient breast CT data). All breast phantoms were used in Monte Carlo simulations to estimate the radiation dose. The results show that the doses estimated using the continuous fibroglandular tissue distribution agree within 3% of the doses estimated using the heterogeneous patient-based distribution, and that it leads to a dose reduction of 27% compared to the homogeneous distribution.

Research paper thumbnail of A semi-empirical model for scatter field reduction in digital mammography

Physics in Medicine & Biology, 2021

X-ray mammography is the gold standard technique in breast cancer screening programmes. One of th... more X-ray mammography is the gold standard technique in breast cancer screening programmes. One of the main challenges that mammography is still facing is scattered radiation, which degrades the quality of the image and complicates the diagnosis process. Anti-scatter grids, the main standard physical scattering reduction technique, have some unresolved challenges as they increase the dose delivered to the patient, do not remove all the scattered radiation and increase the cost of the equipment. Alternative scattering reduction methods based on post-processing algorithms, have lately been under investigation. This study is concerned with the use of image post-processing to reduce the scatter contribution in the image, by convolving the primary plus scatter image with kernels obtained from simplified Monte Carlo (MC) simulations. The proposed semi-empirical approach uses up to five thickness-dependant symmetric kernels to accurately estimate the scatter contribution of different areas of ...

Research paper thumbnail of Validation of modelling tools for simulating wide-angle DBT systems

Medical Imaging 2019: Physics of Medical Imaging, 2019

Full-field 2D digital mammography is used for breast cancer screening throughout the world. Digit... more Full-field 2D digital mammography is used for breast cancer screening throughout the world. Digital breast tomosynthesis (DBT) is now widely available and has shown promise as a breast cancer screening modality. Rigorous evaluation and comparison studies must be conducted before considering the new modality for routine breast cancer screening. Conventional clinical trials involving human subjects are time consuming and expensive and are limited to commercially-available system designs. Alternatively, Virtual Clinical Trials (VCTs) can be used to conduct such studies using modelling tools by simulating clinically-realistic images and experimental system designs. The OPTIMAM image simulation toolbox contains a suite of tools that can used to simulate visually and clinically realistic images for VCTs. Recently, tools for simulating a wide-angle DBT system were added to the toolbox. In this paper, we present the simulation methodology and validation results for a wide-angle DBT system. The validation was performed by simulating images of standard test objects and comparing these with real images acquired using identical settings on the simulated real system. The comparison of the contrast-to-noise ratios, geometrical distortion (z-resolution) and image blurring for real and simulated images of test objects showed good agreement. This suggests that the images of a wide-angle DBT system produced using our simulation approach are comparable to real images.

Research paper thumbnail of Similarity Metrics for Intensity-Based Registration Using Breast Density Maps

Pattern Recognition and Image Analysis, 2017

Intensity-based registration algorithms have been widely used in medical image applications. This... more Intensity-based registration algorithms have been widely used in medical image applications. This type of registration algorithms uses an object function to compute a transformation and optimizes a measure of similarity between the images being registered. The most common similarity metrics used in registration are sum of squared differences, mutual information and normalized cross-correlation. This paper aims to compare these similarity metrics, using common registration algorithms applied to breast density maps registration. To evaluate the results, we use the protocols for evaluation of similarity measures proposed byŠkerl et al. They consist in defining a set of random directions in the parameter space of the registration algorithm and compute statistical measures, such as the accuracy, capture range, number of maxima and risk of non-convergence, along these directions. The obtained results show a better performance corresponding to normalized cross-correlation for the rigid registration algorithm, while the sum of squared difference obtains the best result for the B-Spline method.