Alireza Ahmadian - Academia.edu (original) (raw)

Papers by Alireza Ahmadian

Iranian Journal of Medical Physics, 2005

Introduction: A major problem facing the patients with chronic liver diseases is the diagnostic p... more Introduction: A major problem facing the patients with chronic liver diseases is the diagnostic procedure. The conventional diagnostic method depends mainly on needle biopsy which is an invasive method. There are some approaches to develop a reliable noninvasive method of evaluating histological changes in sonograms. The main characteristic used to distinguish between the normal, hepatitis and cirrhosis liver is the texture of liver surface. The problem of defining a set of meaningful features that explores the characteristics of the texture, leads to several methods of determining tissue texture. Some of these methods, which have been developed so far, are based on wavelet transform. The selection of wavelet transform type affects the accuracy of determining the texture. In this study, an optimal wavelet transform called Gabor wavelet was introduced and three different methods of determining tissue texture were evaluated. These include statistical, dyadic wave...

In this study, the need of a CAD system and its capabilities has been investigated and then a sam... more In this study, the need of a CAD system and its capabilities has been investigated and then a sample program for a mammographic CAD system proper to Iranian tropical patients was designed. In the first step, the analog mammographic images were digitized by 56 and 112 mm spatial resolution and then were processed by the designed sample program. Analysis and technical details for designing and implementing the program included for following steps: The capability of the program image displayer consisting of viewing four mammographic images from four breast views (RCC, RMLO, LCC, LMLO) in one window, determining breast region by background removing and other conventional preprocessing application tools; Software processing tools including theresholding, histogram, ROI determination; Patient information fields such as clinical information, conventional reporting section as used in radiological department in Iran; Computer-aided diagnostic section including proper diagnostic processing algorithm to automatic detection of breast abnormality. For instance the application of wavelet and fuzzy logic for detecting malignant clusters of microcalcification. The introduced mammographic CAD system can provide the collection, organizing and the availability of the patient local information. Therefore by using the prepared database the evaluation of the sensitivity and specifity of the detecting algorithm for comparison of different research methods would be possible.

Frontiers in Biomedical Technologies, 2021

The article's abstract is not available.

arXiv (Cornell University), Aug 19, 2020

Volume visualization is a method that displays three-dimensional (3D) data in two-dimensional (2D... more Volume visualization is a method that displays three-dimensional (3D) data in two-dimensional (2D) space. Using 3D datasets instead of 2D traditional images improves the visualization of anatomical structures, and volume visualization helps radiologists and surgeons to review large datasets comprehensively so that diagnosis and treatment can be enhanced. In liver surgery, blood vessel detection is important. Liver vessels have various shapes and due to the presence of noise in the ultrasound images, they can be confused with noise. Suboptimal images can sometimes lead to surgical errors where the surgeon may cut the blood vessel in error. The ultrasound system is versatile and portable and has the advantage of being able to be used in the operating theatre. Due to the nature of B-mode ultrasound, 1-D transfer function volume visualization of images cannot abrogate shadow artifacts. While multi-dimensional transfer function improves the ability to define features of interest, the high dimensionality in the parameter domain renders it unwieldy and difficult for clinicians to work with. To overcome these limitations, an algorithm for volume visualization that can provide effective 3D visualization of noisy B-mode ultrasound images, which can be useful for clinicians, is proposed. We propose a method that is appropriate for liver ultrasound images focusing on vessels and tumors (if present) in order to delineate their structure and positions clearly to preempt surgical error during operation. This method can prevent possible errors during liver surgery by providing more detailed high quality 3D images for clinicians.

Glioma is a highly invasive type of brain tumor with an irregular morphology and blurred infiltra... more Glioma is a highly invasive type of brain tumor with an irregular morphology and blurred infiltrative borders that may affect different parts of the brain. Therefore, it is a challenging task to identify the exact boundaries of the tumor in an MR image. In recent years, deep learning-based Convolutional Neural Networks (CNNs) have gained popularity in the field of image processing and have been utilized for accurate image segmentation in medical applications. However, due to the inherent constraints of CNNs, tens of thousands of images are required for training, and collecting and annotating such a large number of images poses a serious challenge for their practical implementation. Here, for the first time, we have optimized a network based on the capsule neural network called SegCaps, to achieve accurate glioma segmentation on MR images. We have compared our results with a similar experiment conducted using the commonly utilized U-Net. Both experiments were performed on the BraTS20...

Brain shift is an important obstacle to the application of image guidance during neurosurgical in... more Brain shift is an important obstacle to the application of image guidance during neurosurgical interventions. There has been a growing interest in intra-operative imaging to update the image-guided surgery systems. However, due to the innate limitations of the current imaging modalities, accurate brain shift compensation continues to be a challenging task. In this study, the application of intra-operative photoacoustic imaging and registration of the intra-operative photoacoustic with pre-operative MR images is proposed to compensate for brain deformation. Finding a satisfactory registration method is challenging due to the unpredictable nature of brain deformation. In this study, the co-sparse analysis model is proposed for photoacoustic -MR image registration, which can capture the interdependency of the two modalities. The proposed algorithm works based on the minimization of the mapping transform via a pair of analysis operators that are learned by the alternating direction meth...

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnos... more Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of Pancreatic Ductal Adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and L...

Journal of Biomedical Optics, 2020

Significance: Photoacoustic imaging (PAI) has been greatly developed in a broad range of diagnost... more Significance: Photoacoustic imaging (PAI) has been greatly developed in a broad range of diagnostic applications. The efficiency of light to sound conversion in PAI is limited by the ubiquitous noise arising from the tissue background, leading to a low signal-to-noise ratio (SNR), and thus a poor quality of images. Frame averaging has been widely used to reduce the noise; however, it compromises the temporal resolution of PAI. Aim: We propose an approach for photoacoustic (PA) signal denoising based on a combination of low-pass filtering and sparse coding (LPFSC). Approach: LPFSC method is based on the fact that PA signal can be modeled as the sum of low frequency and sparse components, which allows for the reduction of noise levels using a hybrid alternating direction method of multipliers in an optimization process. Results: LPFSC method was evaluated using in-silico and experimental phantoms. The results show a 26% improvement in the peak SNR of PA signal compared to the averaging method for in-silico data. On average, LPFSC method offers a 63% improvement in the image contrast-tonoise ratio and a 33% improvement in the structural similarity index compared to the averaging method for objects located at three different depths, ranging from 10 to 20 mm, in a porcine tissue phantom. Conclusions: The proposed method is an effective tool for PA signal denoising, whereas it ultimately improves the quality of reconstructed images, especially at higher depths, without limiting the image acquisition speed.

Iranian Journal of Radiology, 2019

Background: Bronchoscopy is a difficult procedure for physicians to relate CT slices to bronchosc... more Background: Bronchoscopy is a difficult procedure for physicians to relate CT slices to bronchoscopic video images and maneuver the bronchoscope inside the airway tree. CT-guided bronchoscopy systems have been developed in the last decades to help physicians maneuver the bronchoscope inside the airway tree in a fast and precise way. Objectives: We aimed to develop a continuous guiding method for bronchoscopy with high tracking accuracy by matching bronchoscopy image contours with CT contours, and speed it up by using synchronous electromagnetic tracker (EMT) data, and to evaluate it on airway phantom with simulated respiratory motion. Materials and Methods: This method works based on two approaches combined together: 1) Contours detected in real bronchoscopy images and finding their equivalents in CT space. Contours are detected by a fast algorithm and CT contours are mapped by them in a perspective scheme. 2) EMT data which is used in a frame by frame approach to approximate the position of bronchoscope compared to its previous position. This differential approach causes a small search space and as a result higher tracking speed. The novelty of this work is using bronchoscopy image contours instead of the whole image combined with synchronous EMT data. This approach causes faster tracking and there is no need for landmark selection or centerline consideration before performing the main bronchoscopy. Results: The experimental results of implementing the proposed method show that this method can track the bronchoscope continuously. For evaluating the accuracy and robustness of tracking, virtual bronchoscopy images were generated at each frame position reported by the method and compared to corresponding real bronchoscopy image using mutual information. The experimental results present that this method can track a bronchoscope accurately and robustly in 96.3% of frames. Conclusion: Using contours instead of the whole image for registration can provide a continuous real-time bronchoscopy tracking procedure. Using EMT data in differential mode makes the proposed method robust to simulated respiratory motion.

Frontiers in Biomedical Technologies, 2019

Purpose: Dental caries is known as one of the most common oral diseases in the world. Tooth decay... more Purpose: Dental caries is known as one of the most common oral diseases in the world. Tooth decay progresses slowly, and the symptoms are not regularly visible until it reaches an irreversible phase and needs to be removed with extensive restoration treatment. If the lesions could be diagnosed at an initial stage, the progress of dental diseases would be stopped through preventive treatments. Conventional methods for caries detection are visual examinations and X-Ray imaging methods that have significant limitations such as poor sensitivity and specificity at the earliest stages of the disease due to the small size of the lesions. Materials and Methods: Photoacoustic imaging as a non-invasive hybrid imaging modality combines the high spatial resolution of ultrasound with the rich optical contrasts of optical imaging, and it is much safer than the ionizing radiation like X-ray imaging. In this study, the simulation of the light propagation and energy deposition in the tooth was done ...

TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2017

In recent years, an increasing number of various surgeries are observed utilizing fluoroscopy. Th... more In recent years, an increasing number of various surgeries are observed utilizing fluoroscopy. The radiation exposure received by patients and medical staff and the surgical guidance in multiple planes frequently necessitate the positioning of a mobile C-arm. Operative navigation enables a mobile C-arm to provide multiplanar surgical guidance and decreases the radiation dose to the patient and operating room personnel. In this study, we propose a videobased tracked mobile C-arm (referred to as a "tracked C-arm system") to position the system. This system defines a reference framework to maintain the video-optical tracker data and computed tomography (CT) or cone-beam CT images' alignment as fine as possible despite patient or tracker movement. By employing our uniquely designed "sixfacet" reference marker attached to the spine phantom, registration between the video-optical tracker and the spine phantom is maintained at arbitrary angles of the mobile C-arm. The tracked C-arm system provides a statistically significant improvement (P < 0.001) in target registration error in comparison with the conventional system: 0.80 ± 0.34 mm versus 1.60 ± 0.43 mm, respectively. The tracked C-arm system is designed to generate digitally reconstructed radiograph images from the mobile C-arm perspective, with projection error on the order of 0.74 ± 0.13 mm. Integration of the hybrid tracking system with mobile C-arm guidance has the capability to provide registration, reduce radiation exposure, and improve target registration accuracy.

NMR in biomedicine, Jan 4, 2017

MRS is an analytical approach used for both quantitative and qualitative analysis of human body m... more MRS is an analytical approach used for both quantitative and qualitative analysis of human body metabolites. The accurate and robust quantification capability of proton MRS ((1) H-MRS) enables the accurate estimation of living tissue metabolite concentrations. However, such methods can be efficiently employed for quantification of metabolite concentrations only if the overlapping nature of metabolites, existing static field inhomogeneity and low signal-to-noise ratio (SNR) are taken into consideration. Representation of (1) H-MRS signals in the time-frequency domain enables us to handle the baseline and noise better. This is possible because the MRS signal of each metabolite is sparsely represented, with only a few peaks, in the frequency domain, but still along with specific time-domain features such as distinct decay constant associated with T2 relaxation rate. The baseline, however, has a smooth behavior in the frequency domain. In this study, we proposed a quantification method ...

2011 IEEE Nuclear Science Symposium Conference Record, 2011

2009 3rd International Conference on Bioinformatics and Biomedical Engineering, 2009

Journal of applied clinical medical physics / American College of Medical Physics, 2013

Multimodality image registration plays a crucial role in various clinical and research applicatio... more Multimodality image registration plays a crucial role in various clinical and research applications. The aim of this study is to present an optimized MR to CT whole-body deformable image registration algorithm and its validation using clinical studies. A 3D intermodality registration technique based on B-spline transformation was performed using optimized parameters of the elastix package based on the Insight Toolkit (ITK) framework. Twenty-eight (17 male and 11 female) clinical studies were used in this work. The registration was evaluated using anatomical landmarks and segmented organs. In addition to 16 anatomical landmarks, three key organs (brain, lungs, and kidneys) and the entire body volume were segmented for evaluation. Several parameters--such as the Euclidean distance between anatomical landmarks, target overlap, Dice and Jaccard coefficients, false positives and false negatives, volume similarity, distance error, and Hausdorff distance--were calculated to quantify the qu...

International Journal of Biomedical Science and Engineering, 2013

IFMBE Proceedings, 2009

Reliable attenuation correction methods in PET require accurate determination of the attenuation ... more Reliable attenuation correction methods in PET require accurate determination of the attenuation map (µmap), which represents the spatial distribution of linear attenuation coefficients (LACs) at 511 keV for the region under study. Since CT image pixel intensities are directly related to the LAC of the corresponding tissue calculated from the effective CT energy, the µmap at 511 keV can be directly generated from the CT images. The presence of high density dental fillings material in head and neck CT imaging is known to generate strong streak artifacts in the µmap which will likely propagate to the resulting PET images during CT-based attenuation correction (CATC). The purpose of this work is to develop a fast approach for reduction of dental filling artifacts in the generated µmap. Currently available sinogram based metal artifact reduction (MAR) algorithms are based on correction of raw data sinograms which are huge files usually stored in proprietary format not generally disclosed by manufacturers and thus are not straightforward to handle. Our method uses the concept of virtual sinograms for implementation of MAR, which are produced by forward projection of CT images in Dicom format. The projection data affected by metallic objects are detected in the sinogram space by segmentation of metallic objects in the CT image followed by forward projection of the metal-only image. Thereafter the affected projections are replaced by interpolated values from adjacent projections using the spline interpolation technique. The algorithm was applied to a dedicated phantom experiment scanned before and after metal insertion, where the corrected and non-corrected µmaps were compared to the artifact-free µmap. It was observed that by using this fast method, the mean relative error in regions close to metallic objects is ~35% without correction and decreases to ~5% after correction.

2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, 2005

Intra-operative Ultrasound imaging as a real time imaging device is found very applicable for int... more Intra-operative Ultrasound imaging as a real time imaging device is found very applicable for intraoperative updates of patient data in neurosurgery. One of the main challenges here is the accuracy of intra and preoperative image registration which is highly influenced by the level of speckle reduction and the accuracy of segmentation method. In this paper the effect of segmentation method on the accuracy of point-based registration of intraoperative US image with preoperative MR image using Iterative Closest Point (ICP) algorithm and Coherent Point Drift (CPD) are considered. To perform this study, a Poly Vinyl Alcohol-Cryogel brain phantom is made that allows simulating the brain deformation. As the results showed CPD algorithm is found more robust than ICP in the presence of outliers. In addition, the role of Chan-Vese as a nonparametric active contour based segmentation of US images has shown a reasonable improvement in the performance of the conventional ICP and CPD in order of 45% and 30%, respectively.

Definition of a proper similarity measure to be adapted to a specific application is a crucial st... more Definition of a proper similarity measure to be adapted to a specific application is a crucial step in registration of medical images. The problem with most commonly used similarity measures in medical applications is that they perform registration in spatial domain based on simplifying assumptions about the interdependencies of the pixel intensity values. Therefore, they are incapable of decorrelating spatially-varying intensity inhomogeneity, occurring in MR imaging. To overcome this problem, Residual Complexity (RC) has been introduced for correcting intensity inhomogeneity in the Discrete Cosine Transform(DCT) domain. In this work, it is proposed to employ Discrete Wavelet Transformation(DWT) instead of DCT which is more efficient in representing the final residual image between the two registered images with minimum compression complexity. Here, the performance of Wavelet based RC (WRC) is compared to RC and some well-known similarity measure. WRC shows more than 30% improvement in the registration result in comparison with RC.