A. Ruggeri - Academia.edu (original) (raw)

Papers by A. Ruggeri

British Journal of Ophthalmology, 2010

Background/aims. A computer program for the automatic estimation of morphometric parameters (cell... more Background/aims. A computer program for the automatic estimation of morphometric parameters (cell density, pleomorphism, polymegethism) in alizarine red stained images is presented and evaluated. Methods. Images of corneal endothelium from 30 porcine eyes stained with alizarine red were acquired with an optical microscope and saved as grey-level digital images. Each image was at first pre-processed for luminosity correction and contrast enhancement. An artificial neural network was used to classify all pixels as cell contour or cell body pixels. The segmented cell contours were then used to obtain estimates of morphometric parameters. The central area was assessed and the mean area per cornea was 0.54±0.07 mm 2. The whole system was implemented as a computer program using the Matlab ® language. Estimated parameters were compared with the corresponding values derived from manual contour detection on the same images used for the automatic estimation. Results. On the 30 images of our data set, mean differences of automatic parameters vs. manual ones were-12±52 cells/mm 2 (range-103 to +145) for density; 0.5±2.6 per cent (range-5.6 to +5.6) for pleomorphism;-0.7±1.9 per cent (range-4.1 to +2.8) for polymegethism. Conclusion. The evaluation of the automatic system on 30 images from porcine eyes confirmed its capability of reliably estimating morphometric parameters with respect to parameter values derived by manual analysis.

Medical Imaging, IEEE …, 2004

We present here a new method to identify the position of the optic disc (OD) in retinal fundus im... more We present here a new method to identify the position of the optic disc (OD) in retinal fundus images. The method is based on the preliminary detection of the main retinal vessels. All retinal vessels originate from the OD and their path follows a similar directional pattern (parabolic course) in all images. To describe the general direction of retinal vessels at any given position in the image, a geometrical parametric model was proposed, where two of the model parameters are the coordinates of the OD center. Using as experimental data samples of vessel centerline points and corresponding vessel directions, provided by any vessel identification procedure, model parameters were identified by means of a simulated annealing optimization technique. These estimated values provide the coordinates of the center of OD. A Matlab ® prototype implementing this method was developed. An evaluation of the proposed procedure was performed using the set of 81 images from the STARE project, containing images from both normal and pathological subjects. The OD position was correctly identified in 79 out of 81 images (98%), even in rather difficult pathological situations.

1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes

In this paper some criteria for testing model structures are used for choosing the best among a s... more In this paper some criteria for testing model structures are used for choosing the best among a set of rival dynamical models of two metabolic processes. The considered criteria are based on the residual sum of squares, the final prediction error, the Akaike information criterion and the inverse of the information matrix. Linear time invariant structured models and input-output descriptions

Acta Ophthalmologica, 2015

Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439), 2003

A new method is proposed for the automatic detection of cell contour in images of corneal endothe... more A new method is proposed for the automatic detection of cell contour in images of corneal endothelium. The main drawback of the systems proposed so far in the literature, which mainly rely on classical image segmentation techniques, is the impossibility to embed prior information on the object being segmented, i.e., the regular hexagon pattern of endothelial cells. In our approach, the introduction and use of a-priori information is obtained by means of the Bayesian modelling framework, which allows to combine prior information on the applied model with experimental data through a statistical description of the model given the data. The resulting posterior probability density function is then optimized by a maximum a posteriori (MAP) estimator, using the simulated annealing maximization algorithm. Preliminary results on a few images showed that the developed system is capable of correctly recognizing the contour of cells. The developed theoretical framework is extremely flexible and can be easily adapted to different prior distributions or even to different object detection applications involving shape prior information.

3rd IEEE International Symposium on Biomedical Imaging: Macro to Nano, 2006., 2006

Retinal images are routinely acquired and assessed to provide diagnostic evidence for many import... more Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used. We propose here a new method to

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2008

The manual analysis of the karyogram is a complex, wearing and time-consuming operation. It requi... more The manual analysis of the karyogram is a complex, wearing and time-consuming operation. It requires a very meticulous attention to details and calls for well-trained personnel. Even though existing commercial software packages provide a reasonable support to cytogenetists, they very often require human intervention to correct challenging situations. We developed a robust automatic classification system conceived to cope with routine images in which chromosomes are randomly rotated, possibly blurred or also corrupted by overlapping or by dye stains. It consists in a sequence of modules comprising robust feature extraction based on medial axis, chromosome polarization, feature pre-processing, and Neural Network classification followed by a class reassigning algorithm.We show the effectiveness of the proposed method on data comprising karyotypes belonging to slightly different stage of the prometaphase. This dataset contains 119 karyotypes (5474 chromosomes), 70 of which were used for...

Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of g... more Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of genetics defects. The procedure is lengthy and repetitive, so that an automatic analysis would greatly help the cytogeneticist routine work. Still, automatic segmentation and full disentangling of chromosomes are open issues. We propose an automatic procedure to obtain the separated chromosomes, which are then ready for a subsequent classification step. The segmentation is carried out by means of a space variant thresholding scheme, which proved to be successful even in presence of hyper-or hypo-fluorescent regions in the image. Then a greedy approach is used to identify and resolve touching and overlapping chromosomes, based on geometric evidence and image information. We show the effectiveness of the proposed method on routine data: 90% of the overlaps and 92% of the adjacencies are resolved, resulting in a correct segmentation of 96% of the chromosomes.

Due to its blood microcirculation, the retina is one of the first organs affected by hypertension... more Due to its blood microcirculation, the retina is one of the first organs affected by hypertension and diabetes: retinal damages can lead to serious visual loss, that can be avoided by an early diagnosis. The most distinctive sign of diabetic retinopathy or severe hypertensive retinopathy are dark lesions such as haemorrhages and microaneurysms (HM), and bright lesions such as hard exudates (HE) and cotton wool spots (CWS). Automatic detection of their presence in the retina is thus of paramount importance for assessing the presence of retinopathy, and therefore relieve the burden of image examination by retinal experts. The most widespread scheme for automatically detect retinal lesion rely on a initial segmentation and a subsequent refinement stage, usually by means of a supervised classification or based on heuristic rules. The first step is therefore required not to lose any possible lesions, at the same time discarding as much of the normal retina as possible. In this work we propose a simple and effective method to detect and identify haemorrhagic (dark) lesions in retinal images, by using a simple local thresholding followed by an evaluation of a measure of the spatial density of the pixels selected at the first step. We evaluate the algorithm on 6 images presenting dark lesions extracted from a database of 60 annotated images, resulting in a mean detection rate of 94% the lesions present in an image, with good performance in term of false candidate rejection.

ABSTRACT Due to its blood microcirculation, the retina is one of the first organs affected by hyp... more ABSTRACT Due to its blood microcirculation, the retina is one of the first organs affected by hypertension and diabetes: retinal damages can lead to serious visual loss, that can be avoided by an early diagnosis. The most distinctive sign of diabetic retinopathy or severe hypertensive retinopathy are dark lesions such as haemorrhages and microaneurysms (HM), and bright lesions such as hard exudates (HE) and cotton wool spots (CWS). Automatic detection of their presence in the retina is thus of paramount importance for assessing the presence of retinopathy, and therefore relieve the burden of image examination by retinal experts. The first step for the automatic detection of retinal lesions has to identify candidate lesions, not losing any of them, and providing with accurate outlines, so to allow the extraction of meaningful features for a possible subsequent classification. To accomplish this, we propose a two stage approach. The first stage identifies the rough location of candidate lesions with one or more seed points, evaluating a measure of the spatial density of pixels selected by a local thresholding. The second stage has the objective of outlining as accurately as possible the lesions surrounding each seed. Due to the high variability of lesions and background appearance, classical region growing approaches often fail and are difficult to calibrate, since in retinal imaging the noisy and highly variable background hides the small homogenous regions representing lesions. To tackle this, we rely on a stochastic modelling of a region of interest around a seed as a Markov random field: This is particularly suited to separate objects with different textures, since it combines feature distribution and spatial connectivity. Responses to a Gabor filters bank spanning different orientations and scales provide the description of the local texture, and the final classification is obtained via a simulated annealing optimization. Along with the classification, we propose a simple post-optimization measure to discard regions where no lesions are present despite the presence of seeds. We show results of the proposed method on a data set of manually segmented 60 images, 6 of which containing retinal lesions.

ABSTRACT Karyotype analysis is a widespread procedure in cytogenetics to assess the possible pres... more ABSTRACT Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of genetics defects. The procedure is lengthy and repetitive, so that an automatic analysis would greatly help the cytogeneticist routine work. Still, automatic segmentation and full disentangling of chromosomes are open issues. The first step in every automatic procedure, is the segmentation of the chromosomes, as either single entities or in clusters, in the image. The better the segmentation step, the easier the subsequent disentanglement. We propose for the segmentation step a region based level set algorithm that is able to address the variability in the image background due to the presence of hyper- or hypo-fluorescent regions in the image. We compare its performance with other algorithms proposed in the literature for the segmentation of chromosomes, over a set of 11 manually annotated images. We show the superiority of the proposed approach both in terms of pixel sensitivity, and in terms of number of separate clusters with respect to the manual segmentation. The images used in the paper are available for public download.

ABSTRACT We wish to assess the performance of an automatic analysis of video sequences of conjunc... more ABSTRACT We wish to assess the performance of an automatic analysis of video sequences of conjunctival vessels, digitally imaged with high enough magnification to resolve movement of the blood within the vessel. With a previously developed algorithm, from each vessel and from each frame we extract a one dimensional signal representing the longitudinal variation of gray level along the vessel, which is related to the presence of red blood cells. Then we estimate the local shift of the signals of a vessel between different frames, using a modified dynamic-time-warping approach. Since manual tracking of cells on a large batch of real video is unfeasible, we assess the performance of the algorithm on set of simulated vessels, where the mean cell velocity is known. By this means, we are also able to vary the mean blood cells velocity and the frequency of their velocity variation in time, so as to study the error variation with regard to these variables. We show the effectiveness of our method comparing it with a cross correlation approach. Moreover, along with the estimation error and robustness toward changes in the mean cells velocity, we show that at variance with the cross correlation method, the proposed algorithm is able to provide estimates on instantaneous velocity with an acceptable error, even if suffering from an overestimation bias that increases with the cells mean velocity. Keywordscell velocity-dynamic time warping-cross-correlation

Ocular fundus images provide important information about retinal degeneration, which may be relat... more Ocular fundus images provide important information about retinal degeneration, which may be related to acute pathologies or to early signs of systemic diseases. An automatic and quantitative assessment of vessel morphological features, such as diameters and tortuosity, can improve clinical diagnosis and evaluation of retinopathy. We propose a new method to accurately evaluate vessel diameters and centerline starting from an

The analysis of blood vessels in images of retinal fundus is an important non-invasive procedure ... more The analysis of blood vessels in images of retinal fundus is an important non-invasive procedure that allows early diagnosis and the effective monitoring of therapies in retinopathy. In order to derive a quantitative evaluation of the clinical features, such as vessel diameter and tortuosity, an accurate segmentation of the vessel network has to be performed. A new system for the

Karyotyping, or the automatic classification of human chromosomes, is mostly based on the analysi... more Karyotyping, or the automatic classification of human chromosomes, is mostly based on the analysis of the chromosome specific banding pattern. Unfortunately, the most informative phases of the cell division cycle are composed of long chromosomes that easily overlap: the involved banding pattern information is corrupted, resulting in a drastic increase of the classification error. Assuming the availability of a probabilistic classifier, the improvement of the classification of chromosomes with corrupted data would require the additional estimation of the joint probability density of the observed and missing data for each chromosome class. Given the number of classes, the possible position and extension of the corrupted data within a chromosome, and the dimensionality of the feature space, a reliable estimation would need an impossible number of training samples. We chose to circumvent the estimation problem by developing a statistical generative model of the pattern of each class, so that the corrupted part can be substituted with a partial pattern synthetically generated from the model. This allows to obtain a Monte Carlo estimate of the maximum a posteriori probability for the class given the observation and the missing data, which reduces to a simple voting scheme if the a priori probability for each class is equal. Moreover, this Monte Carlo classification is superior to the voting scheme based on the simple imputation of the classes mean to the missing data.

The earliest signs of Retinopathy of Prematurity (ROP) are tortuosity and dilation of retinal ves... more The earliest signs of Retinopathy of Prematurity (ROP) are tortuosity and dilation of retinal vessels. Such vascular changes are considered of primary importance for the diagnosis and the follow-up of the disease. However, a widely accepted computerized system for their quantitative measurement is still missing. Images taken from a preterm baby's eye are often low-contrast, noisy, and blurred. Algorithms that have been successfully applied to analyze adult retinal images do not work well in ROP images. We propose here a novel method for the automatic extraction of vessel centerline in wide-field ROP retinal images, based on a sparse tracking scheme. After a set of seed points is identified all over the image, vessels are traced by connecting those seeds by means of minimum cost paths, whose weights depend on similarity features and alignment evaluated by a custom line operator. The performance of the method was assessed on a dataset of 20 images acquired with the RetCam fundus camera. A sensitivity of 0.78 and a false detection rate of 0.15 were obtained with respect to manual ground truth reference.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2014

We present and discuss a computerized system able to provide a wide-range mosaic of the sub-basal... more We present and discuss a computerized system able to provide a wide-range mosaic of the sub-basal nerve layer of central cornea, built from several images acquired in-vivo with confocal microscopy. The montage is performed by a fast, reliable and fully automatic computerized system that does not require any expedient or manual adjustment during the acquisition process. The resulting mosaic provides a large high quality image, which should significantly aid clinicians in evaluating and assessing in a more reliable way the pathologic signs of interest.

IEEE Transactions on Medical Imaging, 2000

Tortuosity is among the first alterations in the retinal vessel network to appear in many retinop... more Tortuosity is among the first alterations in the retinal vessel network to appear in many retinopathies, such as those due to hypertension. An automatic evaluation of retinal vessel tortuosity would help the early detection of such retinopathies. Quite a few techniques for tortuosity measurement and classification have been proposed, but they do not always match the clinical concept of tortuosity. This justifies the need for a new definition, able to express in mathematical terms the tortuosity as perceived by ophthalmologists. We propose here a new algorithm for the evaluation of tortuosity in vessels recognized in digital fundus images. It is based on partitioning each vessel in segments of constant-sign curvature and then combining together each evaluation of such segments and their number. The algorithm has been compared with other available tortuosity measures on a set of 30 arteries and one of 30 veins from 60 different images. These vessels had been preliminarily ordered by a retina specialist by increasing perceived tortuosity. The proposed algorithm proved to be the best one in matching the clinically perceived vessel tortuosity.

IEEE Transactions on Information Technology in Biomedicine, 2000

Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of g... more Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of genetics defects. The procedure is lengthy and repetitive, so that an automatic analysis would greatly help the cytogeneticist routine work. Still, automatic segmentation and full disentangling of chromosomes are open issues. We propose an automatic procedure to obtain the separated chromosomes, which are then ready for a subsequent classification step. The segmentation is carried out by means of a space-variant thresholding scheme, which proved to be successful even in presence of hyper-or hypofluorescent regions in the image. Then, the tree of choices to resolve touching and overlapping chromosomes is recursively explored, choosing the best combination of cuts and overlaps based on geometric evidence and image information. We show the effectiveness of the proposed method on routine data acquired with different microscope-camera setup at different laboratories: from 162 images of 117 cells totaling 6683 chromosomes, 94% of the chromosomes were correctly segmented, solving 90% of the overlaps and 90% of the touchings. In order to provide the scientific community with a public dataset, the data used in this paper are available for public download.

Computer Methods and Programs in Biomedicine, 2000

Cyclosporine is one of the most widely used immunosuppressive agents in organ transplantation. Du... more Cyclosporine is one of the most widely used immunosuppressive agents in organ transplantation. Due to large inter- and intra-individual variations, its behavior in the specific patient is still difficult to predict. Dosage optimization is thus mainly performed on a trial-and-error basis. In this paper, we present a new program based on the population kinetics approach, which was designed to help physicians in the difficult task of adjusting patient specific cyclosporine dosing regimens. Dose optimization is carried out by model simulation, using a two-compartment mathematical model of cyclosporine kinetics to predict the drug behavior in the patient. Two of the model parameters are assumed from the literature, the other two are estimated from the patient data through a Bayesian estimation procedure. Previous information needed by the Bayesian algorithm is derived by a population analysis, performed beforehand and based on a nonlinear mixed effect model. A user-friendly graphical interface written in Delphi under Windows makes the program easily accessible to physicians. A preliminary retrospective validation of the program, performed on data from 18 renal transplanted patients, yielded very satisfactory results.

British Journal of Ophthalmology, 2010

Background/aims. A computer program for the automatic estimation of morphometric parameters (cell... more Background/aims. A computer program for the automatic estimation of morphometric parameters (cell density, pleomorphism, polymegethism) in alizarine red stained images is presented and evaluated. Methods. Images of corneal endothelium from 30 porcine eyes stained with alizarine red were acquired with an optical microscope and saved as grey-level digital images. Each image was at first pre-processed for luminosity correction and contrast enhancement. An artificial neural network was used to classify all pixels as cell contour or cell body pixels. The segmented cell contours were then used to obtain estimates of morphometric parameters. The central area was assessed and the mean area per cornea was 0.54±0.07 mm 2. The whole system was implemented as a computer program using the Matlab ® language. Estimated parameters were compared with the corresponding values derived from manual contour detection on the same images used for the automatic estimation. Results. On the 30 images of our data set, mean differences of automatic parameters vs. manual ones were-12±52 cells/mm 2 (range-103 to +145) for density; 0.5±2.6 per cent (range-5.6 to +5.6) for pleomorphism;-0.7±1.9 per cent (range-4.1 to +2.8) for polymegethism. Conclusion. The evaluation of the automatic system on 30 images from porcine eyes confirmed its capability of reliably estimating morphometric parameters with respect to parameter values derived by manual analysis.

Medical Imaging, IEEE …, 2004

We present here a new method to identify the position of the optic disc (OD) in retinal fundus im... more We present here a new method to identify the position of the optic disc (OD) in retinal fundus images. The method is based on the preliminary detection of the main retinal vessels. All retinal vessels originate from the OD and their path follows a similar directional pattern (parabolic course) in all images. To describe the general direction of retinal vessels at any given position in the image, a geometrical parametric model was proposed, where two of the model parameters are the coordinates of the OD center. Using as experimental data samples of vessel centerline points and corresponding vessel directions, provided by any vessel identification procedure, model parameters were identified by means of a simulated annealing optimization technique. These estimated values provide the coordinates of the center of OD. A Matlab ® prototype implementing this method was developed. An evaluation of the proposed procedure was performed using the set of 81 images from the STARE project, containing images from both normal and pathological subjects. The OD position was correctly identified in 79 out of 81 images (98%), even in rather difficult pathological situations.

1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes

In this paper some criteria for testing model structures are used for choosing the best among a s... more In this paper some criteria for testing model structures are used for choosing the best among a set of rival dynamical models of two metabolic processes. The considered criteria are based on the residual sum of squares, the final prediction error, the Akaike information criterion and the inverse of the information matrix. Linear time invariant structured models and input-output descriptions

Acta Ophthalmologica, 2015

Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439), 2003

A new method is proposed for the automatic detection of cell contour in images of corneal endothe... more A new method is proposed for the automatic detection of cell contour in images of corneal endothelium. The main drawback of the systems proposed so far in the literature, which mainly rely on classical image segmentation techniques, is the impossibility to embed prior information on the object being segmented, i.e., the regular hexagon pattern of endothelial cells. In our approach, the introduction and use of a-priori information is obtained by means of the Bayesian modelling framework, which allows to combine prior information on the applied model with experimental data through a statistical description of the model given the data. The resulting posterior probability density function is then optimized by a maximum a posteriori (MAP) estimator, using the simulated annealing maximization algorithm. Preliminary results on a few images showed that the developed system is capable of correctly recognizing the contour of cells. The developed theoretical framework is extremely flexible and can be easily adapted to different prior distributions or even to different object detection applications involving shape prior information.

3rd IEEE International Symposium on Biomedical Imaging: Macro to Nano, 2006., 2006

Retinal images are routinely acquired and assessed to provide diagnostic evidence for many import... more Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used. We propose here a new method to

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2008

The manual analysis of the karyogram is a complex, wearing and time-consuming operation. It requi... more The manual analysis of the karyogram is a complex, wearing and time-consuming operation. It requires a very meticulous attention to details and calls for well-trained personnel. Even though existing commercial software packages provide a reasonable support to cytogenetists, they very often require human intervention to correct challenging situations. We developed a robust automatic classification system conceived to cope with routine images in which chromosomes are randomly rotated, possibly blurred or also corrupted by overlapping or by dye stains. It consists in a sequence of modules comprising robust feature extraction based on medial axis, chromosome polarization, feature pre-processing, and Neural Network classification followed by a class reassigning algorithm.We show the effectiveness of the proposed method on data comprising karyotypes belonging to slightly different stage of the prometaphase. This dataset contains 119 karyotypes (5474 chromosomes), 70 of which were used for...

Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of g... more Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of genetics defects. The procedure is lengthy and repetitive, so that an automatic analysis would greatly help the cytogeneticist routine work. Still, automatic segmentation and full disentangling of chromosomes are open issues. We propose an automatic procedure to obtain the separated chromosomes, which are then ready for a subsequent classification step. The segmentation is carried out by means of a space variant thresholding scheme, which proved to be successful even in presence of hyper-or hypo-fluorescent regions in the image. Then a greedy approach is used to identify and resolve touching and overlapping chromosomes, based on geometric evidence and image information. We show the effectiveness of the proposed method on routine data: 90% of the overlaps and 92% of the adjacencies are resolved, resulting in a correct segmentation of 96% of the chromosomes.

Due to its blood microcirculation, the retina is one of the first organs affected by hypertension... more Due to its blood microcirculation, the retina is one of the first organs affected by hypertension and diabetes: retinal damages can lead to serious visual loss, that can be avoided by an early diagnosis. The most distinctive sign of diabetic retinopathy or severe hypertensive retinopathy are dark lesions such as haemorrhages and microaneurysms (HM), and bright lesions such as hard exudates (HE) and cotton wool spots (CWS). Automatic detection of their presence in the retina is thus of paramount importance for assessing the presence of retinopathy, and therefore relieve the burden of image examination by retinal experts. The most widespread scheme for automatically detect retinal lesion rely on a initial segmentation and a subsequent refinement stage, usually by means of a supervised classification or based on heuristic rules. The first step is therefore required not to lose any possible lesions, at the same time discarding as much of the normal retina as possible. In this work we propose a simple and effective method to detect and identify haemorrhagic (dark) lesions in retinal images, by using a simple local thresholding followed by an evaluation of a measure of the spatial density of the pixels selected at the first step. We evaluate the algorithm on 6 images presenting dark lesions extracted from a database of 60 annotated images, resulting in a mean detection rate of 94% the lesions present in an image, with good performance in term of false candidate rejection.

ABSTRACT Due to its blood microcirculation, the retina is one of the first organs affected by hyp... more ABSTRACT Due to its blood microcirculation, the retina is one of the first organs affected by hypertension and diabetes: retinal damages can lead to serious visual loss, that can be avoided by an early diagnosis. The most distinctive sign of diabetic retinopathy or severe hypertensive retinopathy are dark lesions such as haemorrhages and microaneurysms (HM), and bright lesions such as hard exudates (HE) and cotton wool spots (CWS). Automatic detection of their presence in the retina is thus of paramount importance for assessing the presence of retinopathy, and therefore relieve the burden of image examination by retinal experts. The first step for the automatic detection of retinal lesions has to identify candidate lesions, not losing any of them, and providing with accurate outlines, so to allow the extraction of meaningful features for a possible subsequent classification. To accomplish this, we propose a two stage approach. The first stage identifies the rough location of candidate lesions with one or more seed points, evaluating a measure of the spatial density of pixels selected by a local thresholding. The second stage has the objective of outlining as accurately as possible the lesions surrounding each seed. Due to the high variability of lesions and background appearance, classical region growing approaches often fail and are difficult to calibrate, since in retinal imaging the noisy and highly variable background hides the small homogenous regions representing lesions. To tackle this, we rely on a stochastic modelling of a region of interest around a seed as a Markov random field: This is particularly suited to separate objects with different textures, since it combines feature distribution and spatial connectivity. Responses to a Gabor filters bank spanning different orientations and scales provide the description of the local texture, and the final classification is obtained via a simulated annealing optimization. Along with the classification, we propose a simple post-optimization measure to discard regions where no lesions are present despite the presence of seeds. We show results of the proposed method on a data set of manually segmented 60 images, 6 of which containing retinal lesions.

ABSTRACT Karyotype analysis is a widespread procedure in cytogenetics to assess the possible pres... more ABSTRACT Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of genetics defects. The procedure is lengthy and repetitive, so that an automatic analysis would greatly help the cytogeneticist routine work. Still, automatic segmentation and full disentangling of chromosomes are open issues. The first step in every automatic procedure, is the segmentation of the chromosomes, as either single entities or in clusters, in the image. The better the segmentation step, the easier the subsequent disentanglement. We propose for the segmentation step a region based level set algorithm that is able to address the variability in the image background due to the presence of hyper- or hypo-fluorescent regions in the image. We compare its performance with other algorithms proposed in the literature for the segmentation of chromosomes, over a set of 11 manually annotated images. We show the superiority of the proposed approach both in terms of pixel sensitivity, and in terms of number of separate clusters with respect to the manual segmentation. The images used in the paper are available for public download.

ABSTRACT We wish to assess the performance of an automatic analysis of video sequences of conjunc... more ABSTRACT We wish to assess the performance of an automatic analysis of video sequences of conjunctival vessels, digitally imaged with high enough magnification to resolve movement of the blood within the vessel. With a previously developed algorithm, from each vessel and from each frame we extract a one dimensional signal representing the longitudinal variation of gray level along the vessel, which is related to the presence of red blood cells. Then we estimate the local shift of the signals of a vessel between different frames, using a modified dynamic-time-warping approach. Since manual tracking of cells on a large batch of real video is unfeasible, we assess the performance of the algorithm on set of simulated vessels, where the mean cell velocity is known. By this means, we are also able to vary the mean blood cells velocity and the frequency of their velocity variation in time, so as to study the error variation with regard to these variables. We show the effectiveness of our method comparing it with a cross correlation approach. Moreover, along with the estimation error and robustness toward changes in the mean cells velocity, we show that at variance with the cross correlation method, the proposed algorithm is able to provide estimates on instantaneous velocity with an acceptable error, even if suffering from an overestimation bias that increases with the cells mean velocity. Keywordscell velocity-dynamic time warping-cross-correlation

Ocular fundus images provide important information about retinal degeneration, which may be relat... more Ocular fundus images provide important information about retinal degeneration, which may be related to acute pathologies or to early signs of systemic diseases. An automatic and quantitative assessment of vessel morphological features, such as diameters and tortuosity, can improve clinical diagnosis and evaluation of retinopathy. We propose a new method to accurately evaluate vessel diameters and centerline starting from an

The analysis of blood vessels in images of retinal fundus is an important non-invasive procedure ... more The analysis of blood vessels in images of retinal fundus is an important non-invasive procedure that allows early diagnosis and the effective monitoring of therapies in retinopathy. In order to derive a quantitative evaluation of the clinical features, such as vessel diameter and tortuosity, an accurate segmentation of the vessel network has to be performed. A new system for the

Karyotyping, or the automatic classification of human chromosomes, is mostly based on the analysi... more Karyotyping, or the automatic classification of human chromosomes, is mostly based on the analysis of the chromosome specific banding pattern. Unfortunately, the most informative phases of the cell division cycle are composed of long chromosomes that easily overlap: the involved banding pattern information is corrupted, resulting in a drastic increase of the classification error. Assuming the availability of a probabilistic classifier, the improvement of the classification of chromosomes with corrupted data would require the additional estimation of the joint probability density of the observed and missing data for each chromosome class. Given the number of classes, the possible position and extension of the corrupted data within a chromosome, and the dimensionality of the feature space, a reliable estimation would need an impossible number of training samples. We chose to circumvent the estimation problem by developing a statistical generative model of the pattern of each class, so that the corrupted part can be substituted with a partial pattern synthetically generated from the model. This allows to obtain a Monte Carlo estimate of the maximum a posteriori probability for the class given the observation and the missing data, which reduces to a simple voting scheme if the a priori probability for each class is equal. Moreover, this Monte Carlo classification is superior to the voting scheme based on the simple imputation of the classes mean to the missing data.

The earliest signs of Retinopathy of Prematurity (ROP) are tortuosity and dilation of retinal ves... more The earliest signs of Retinopathy of Prematurity (ROP) are tortuosity and dilation of retinal vessels. Such vascular changes are considered of primary importance for the diagnosis and the follow-up of the disease. However, a widely accepted computerized system for their quantitative measurement is still missing. Images taken from a preterm baby's eye are often low-contrast, noisy, and blurred. Algorithms that have been successfully applied to analyze adult retinal images do not work well in ROP images. We propose here a novel method for the automatic extraction of vessel centerline in wide-field ROP retinal images, based on a sparse tracking scheme. After a set of seed points is identified all over the image, vessels are traced by connecting those seeds by means of minimum cost paths, whose weights depend on similarity features and alignment evaluated by a custom line operator. The performance of the method was assessed on a dataset of 20 images acquired with the RetCam fundus camera. A sensitivity of 0.78 and a false detection rate of 0.15 were obtained with respect to manual ground truth reference.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2014

We present and discuss a computerized system able to provide a wide-range mosaic of the sub-basal... more We present and discuss a computerized system able to provide a wide-range mosaic of the sub-basal nerve layer of central cornea, built from several images acquired in-vivo with confocal microscopy. The montage is performed by a fast, reliable and fully automatic computerized system that does not require any expedient or manual adjustment during the acquisition process. The resulting mosaic provides a large high quality image, which should significantly aid clinicians in evaluating and assessing in a more reliable way the pathologic signs of interest.

IEEE Transactions on Medical Imaging, 2000

Tortuosity is among the first alterations in the retinal vessel network to appear in many retinop... more Tortuosity is among the first alterations in the retinal vessel network to appear in many retinopathies, such as those due to hypertension. An automatic evaluation of retinal vessel tortuosity would help the early detection of such retinopathies. Quite a few techniques for tortuosity measurement and classification have been proposed, but they do not always match the clinical concept of tortuosity. This justifies the need for a new definition, able to express in mathematical terms the tortuosity as perceived by ophthalmologists. We propose here a new algorithm for the evaluation of tortuosity in vessels recognized in digital fundus images. It is based on partitioning each vessel in segments of constant-sign curvature and then combining together each evaluation of such segments and their number. The algorithm has been compared with other available tortuosity measures on a set of 30 arteries and one of 30 veins from 60 different images. These vessels had been preliminarily ordered by a retina specialist by increasing perceived tortuosity. The proposed algorithm proved to be the best one in matching the clinically perceived vessel tortuosity.

IEEE Transactions on Information Technology in Biomedicine, 2000

Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of g... more Karyotype analysis is a widespread procedure in cytogenetics to assess the possible presence of genetics defects. The procedure is lengthy and repetitive, so that an automatic analysis would greatly help the cytogeneticist routine work. Still, automatic segmentation and full disentangling of chromosomes are open issues. We propose an automatic procedure to obtain the separated chromosomes, which are then ready for a subsequent classification step. The segmentation is carried out by means of a space-variant thresholding scheme, which proved to be successful even in presence of hyper-or hypofluorescent regions in the image. Then, the tree of choices to resolve touching and overlapping chromosomes is recursively explored, choosing the best combination of cuts and overlaps based on geometric evidence and image information. We show the effectiveness of the proposed method on routine data acquired with different microscope-camera setup at different laboratories: from 162 images of 117 cells totaling 6683 chromosomes, 94% of the chromosomes were correctly segmented, solving 90% of the overlaps and 90% of the touchings. In order to provide the scientific community with a public dataset, the data used in this paper are available for public download.

Computer Methods and Programs in Biomedicine, 2000

Cyclosporine is one of the most widely used immunosuppressive agents in organ transplantation. Du... more Cyclosporine is one of the most widely used immunosuppressive agents in organ transplantation. Due to large inter- and intra-individual variations, its behavior in the specific patient is still difficult to predict. Dosage optimization is thus mainly performed on a trial-and-error basis. In this paper, we present a new program based on the population kinetics approach, which was designed to help physicians in the difficult task of adjusting patient specific cyclosporine dosing regimens. Dose optimization is carried out by model simulation, using a two-compartment mathematical model of cyclosporine kinetics to predict the drug behavior in the patient. Two of the model parameters are assumed from the literature, the other two are estimated from the patient data through a Bayesian estimation procedure. Previous information needed by the Bayesian algorithm is derived by a population analysis, performed beforehand and based on a nonlinear mixed effect model. A user-friendly graphical interface written in Delphi under Windows makes the program easily accessible to physicians. A preliminary retrospective validation of the program, performed on data from 18 renal transplanted patients, yielded very satisfactory results.