Translational Vision Science & Technology, 2022
Purpose The purpose of this study was to evaluate the long-term rate of progression and baseline ... more Purpose The purpose of this study was to evaluate the long-term rate of progression and baseline predictors of geographic atrophy (GA) using complete retinal pigment epithelium and outer retinal atrophy (cRORA) annotation criteria. Methods This is a retrospective study. Columns of GA were manually annotated by two graders using a self-developed software on optical coherence tomography (OCT) B-scans and projected onto the infrared images. The primary outcomes were: (1) rate of area progression, (2) rate of square root area progression, and (3) rate of radial progression towards the fovea. The effects of 11 additional baseline predictors on the primary outcomes were analyzed: total area, focality (defined as the number of lesions whose area is >0.05 mm2), circularity, total lesion perimeter, minimum diameter, maximum diameter, minimum distance from the center, sex, age, presence/absence of hypertension, and lens status. Results GA was annotated in 33 pairs of baseline and follow-up OCT scans from 33 eyes of 18 patients with dry age-related macular degeneration (AMD) followed for at least 6 months. The mean rate of area progression was 1.49 ± 0.86 mm2/year (P < 0.0001 vs. baseline), and the mean rate of square root area progression was 0.33 ± 0.15 mm/year (P < 0.0001 vs. baseline). The mean rate of radial progression toward the fovea was 0.07 ± 0.11 mm/year. A multiple variable linear regression model (adjusted r2 = 0.522) revealed that baseline focality and female sex were significantly correlated with the rate of GA area progression. Conclusions GA area progression was quantified using OCT as an alternative to conventional measurements performed on fundus autofluorescence images. Baseline focality correlated with GA area progression rate and lesion's minimal distance from the center correlated with GA radial progression rate toward the center. These may be important markers for the assessment of GA activity. Translational Relevance Advanced method linking specific retinal micro-anatomy to GA area progression analysis.
The objective quantification of retinal atrophy associated with age-related macular degeneration ... more The objective quantification of retinal atrophy associated with age-related macular degeneration (AMD) is required for clinical diagnosis, follow-up, treatment efficacy evaluation, and clinical research. Spectral Domain Optical Coherence Tomography (OCT) has become an essential imaging technology to evaluate the macula. This paper describes a novel automatic method for the identification and quantification of atrophy associated with AMD in OCT scans and its visualization in the corresponding infrared imaging (IR) image. The method is based on the classification of light scattering patterns in vertical pixel-wide columns (A-scans) in OCT slices (B-scans) in which atrophy appears with a custom column-based convolutional neural network (CNN). The network classifies individual columns with 3D column patches formed by adjacent neighboring columns from the volumetric OCT scan. Subsequent atrophy columns form atrophy segments which are then projected onto the IR image and are used to identify and segment atrophy lesions in the IR image and to measure their areas and distances from the fovea. Experimental results on 106 clinical OCT scans (5,207 slices) in which cRORA atrophy (the end point of advanced dry AMD) was identified in 2,952 atrophy segments and 1,046 atrophy lesions yield a mean F1 score of 0.78 (std 0.06) and an AUC of 0.937, both close to the observer variability. Automated computer-based detection and quantification of atrophy associated with AMD using a column-based CNN classification in OCT scans can be performed at expert level and may be a useful clinical decision support and research tool for the diagnosis, follow-up and treatment of retinal degenerations and dystrophies.
We present a deep learning system for testing graphics units by detecting novel visual corruption... more We present a deep learning system for testing graphics units by detecting novel visual corruptions in videos. Unlike previous work in which manual tagging was required to collect labeled training data, our weak supervision method is fully automatic and needs no human labelling. This is achieved by reproducing driver bugs that increase the probability of generating corruptions, and by making use of ideas and methods from the Multiple Instance Learning (MIL) setting. In our experiments, we significantly outperform unsupervised methods such as GAN-based models and discover novel corruptions undetected by baselines, while adhering to strict requirements on accuracy and efficiency of our real-time system.
During in vitro fertilization (IVF) cycles, multiple mature oocytes are retrieved from the ovary ... more During in vitro fertilization (IVF) cycles, multiple mature oocytes are retrieved from the ovary and are fertilized in the lab. The newly generated embryos can be transferred into the uterus on day-3,-4, or-5 of incubation, cryopreserved for subsequent transfers or discarded. Lacking a reliable noninvasive evaluation method of the potential to implant, pregnancy rates can be improved by cotransferring multiple embryos thus introducing health risks that are associated with multiple pregnancies. [1] Hence, the evaluation of embryo quality is required for improving live birth rates while minimizing medical complications and shortening time to pregnancy. [2-6] Machine learning was used for assessing the potential of embryos to blastulate [7,8] and to implant [9-11] based on manually annotated morphological and/or morphokientic features. Deep learning, which offers a powerful toolbox for carrying out automated and standardized classification tasks
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021
We present a novel system for performing real-time detection of diverse visual corruptions in vid... more We present a novel system for performing real-time detection of diverse visual corruptions in videos, for validating the quality of graphics units in our company. The system is used for several types of content, including movies and 3D graphics, with strict constraints on low false alert rates and real-time processing of millions of video frames per day. These constraints required novel solutions involving both hardware and software, including new supervised and weakly-supervised methods we developed. Our deployed system has enabled a 20X reduction of human effort and discovering new corruptions missed by humans and existing approaches. CCS CONCEPTS • Computing methodologies → Visual inspection; Scene anomaly detection; • Hardware → Bug detection, localization and diagnosis; • Software and its engineering → Empirical software validation.
Early diagnosis of sacroiliitis may lead to preventive treatment which can significantly improve ... more Early diagnosis of sacroiliitis may lead to preventive treatment which can significantly improve the patient's quality of life in the long run. Oftentimes, a CT scan of the lower back or abdomen is acquired for suspected back pain. However, since the differences between a healthy and an inflamed sacroiliac joint in the early stages are subtle, the condition may be missed. We have developed a new automatic algorithm for the diagnosis and grading of sacroiliitis CT scans as incidental findings, for patients who underwent CT scanning as part of their lower back pain workout. The method is based on supervised machine and deep learning techniques. The input is a CT scan that includes the patient's pelvis. The output is a diagnosis for each sacroiliac joint. The algorithm consists of four steps: 1) computation of an initial region of interest (ROI) that includes the pelvic joints region using heuristics and a U-Net classifier; 2) refinement of the ROI to detect both sacroiliac joints using a four-tree random forest; 3) individual sacroiliitis grading of each sacroiliac joint in each CT slice with a custom slice CNN classifier, and; 4) sacroiliitis diagnosis and grading by combining the individual slice grades using a random forest. Experimental results on 484 sacroiliac joints yield a binary and a 3-class case classification accuracy of 91.9% and 86%, a sensitivity of 95% and 82%, and an Area-Under-the-Curve of 0.97 and 0.57, respectively. Automatic computer-based analysis of CT scans has the potential of being a useful method for the diagnosis and grading of sacroiliitis as an incidental finding.
International Journal of Computer Assisted Radiology and Surgery, 2017
Purpose Radiological longitudinal follow-up of liver tumors in CT scans is the standard of care f... more Purpose Radiological longitudinal follow-up of liver tumors in CT scans is the standard of care for disease progression assessment and for liver tumor therapy. Finding new tumors in the follow-up scan is essential to determine malignancy, to evaluate the total tumor burden, and to determine treatment efficacy. Since new tumors are typically small, they may be missed by examining radiologists. Methods We describe a new method for the automatic detection and segmentation of new tumors in longitudinal liver CT studies and for liver tumors burden quantification. Its inputs are the baseline and follow-up CT scans, the baseline tumors delineation, and a tumor appearance prior model. Its outputs are the new tumors segmentations in the follow-up scan, the tumor burden quantification in both scans, and the tumor burden change. Our method is the first comprehensive method that is explicitly designed to find new liver tumors. It integrates information from the scans, the baseline known tumors delineations, and a tumor appearance prior model in the form of a global convolutional neural network classifier. Unlike other deep learning-based methods, it does not require large tagged training sets. Results Our experimental results on 246 tumors, of which 97 were new tumors, from 37 longitudinal liver CT studies with radiologist approved ground-truth segmentations, yields a true positive new tumors detection rate of 86 versus 72%
We present a novel process to fabricate conductive patterns by a new copper precursor ink. In thi... more We present a novel process to fabricate conductive patterns by a new copper precursor ink. In this method, an ink with copper formate, a self-reducible copper precursor, is printed, and subsequently heated under high pressure in a hot-press, which is commonly used in the PCB industry. The heating leads to decomposition of the precursor, and results in copper patterns with good electrical conductivity. The application of pressure enables the formation of a dense copper film. 5-15 micron thick copper patterns were obtained on FR4 sheets with an equivalent specific resistivity as low as 5.3±0.3 µΩ•cm, which is about 3 times copper bulk resistivity. Unlike most methods for copper precursor inks, this ink and process do not require an inert environment, and can be performed with instrumentation already used in the industry. Finally, we demonstrate the applicability of this method by printing functional Radio Frequency (RF) components; i.e. antennas for near Field Communication (NFC) and Wi-Fi.
In this work, we report the setup and results of the Liver Tumor Segmentation Benchmark (LiTS) or... more In this work, we report the setup and results of the Liver Tumor Segmentation Benchmark (LiTS) organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and International Conference On Medical Image Computing & Computer Assisted Intervention (MICCAI) 2017. Twenty-four valid state-of-the-art liver and liver tumor segmentation algorithms were applied to a set of 131 computed tomography (CT) volumes with different types of tumor contrast levels (hyper-/hypo-intense), abnormalities in tissues (metastasectomie) size and varying amount of lesions. The submitted algorithms have been tested on 70 undisclosed volumes. The dataset is created in collaboration with seven hospitals and research institutions and manually blind reviewed by independent three radiologists. We found that not a single algorithm performed best for liver and tumors. The best liver segmentation algorithm achieved a Dice score of 0.96(MICCAI) whereas for tumor segmentation the best algorithm evaluated at 0.67(ISBI) and 0.70(MICCAI). The LiTS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource.
Translational Vision Science & Technology, 2022
Purpose The purpose of this study was to evaluate the long-term rate of progression and baseline ... more Purpose The purpose of this study was to evaluate the long-term rate of progression and baseline predictors of geographic atrophy (GA) using complete retinal pigment epithelium and outer retinal atrophy (cRORA) annotation criteria. Methods This is a retrospective study. Columns of GA were manually annotated by two graders using a self-developed software on optical coherence tomography (OCT) B-scans and projected onto the infrared images. The primary outcomes were: (1) rate of area progression, (2) rate of square root area progression, and (3) rate of radial progression towards the fovea. The effects of 11 additional baseline predictors on the primary outcomes were analyzed: total area, focality (defined as the number of lesions whose area is >0.05 mm2), circularity, total lesion perimeter, minimum diameter, maximum diameter, minimum distance from the center, sex, age, presence/absence of hypertension, and lens status. Results GA was annotated in 33 pairs of baseline and follow-up OCT scans from 33 eyes of 18 patients with dry age-related macular degeneration (AMD) followed for at least 6 months. The mean rate of area progression was 1.49 ± 0.86 mm2/year (P < 0.0001 vs. baseline), and the mean rate of square root area progression was 0.33 ± 0.15 mm/year (P < 0.0001 vs. baseline). The mean rate of radial progression toward the fovea was 0.07 ± 0.11 mm/year. A multiple variable linear regression model (adjusted r2 = 0.522) revealed that baseline focality and female sex were significantly correlated with the rate of GA area progression. Conclusions GA area progression was quantified using OCT as an alternative to conventional measurements performed on fundus autofluorescence images. Baseline focality correlated with GA area progression rate and lesion's minimal distance from the center correlated with GA radial progression rate toward the center. These may be important markers for the assessment of GA activity. Translational Relevance Advanced method linking specific retinal micro-anatomy to GA area progression analysis.
The objective quantification of retinal atrophy associated with age-related macular degeneration ... more The objective quantification of retinal atrophy associated with age-related macular degeneration (AMD) is required for clinical diagnosis, follow-up, treatment efficacy evaluation, and clinical research. Spectral Domain Optical Coherence Tomography (OCT) has become an essential imaging technology to evaluate the macula. This paper describes a novel automatic method for the identification and quantification of atrophy associated with AMD in OCT scans and its visualization in the corresponding infrared imaging (IR) image. The method is based on the classification of light scattering patterns in vertical pixel-wide columns (A-scans) in OCT slices (B-scans) in which atrophy appears with a custom column-based convolutional neural network (CNN). The network classifies individual columns with 3D column patches formed by adjacent neighboring columns from the volumetric OCT scan. Subsequent atrophy columns form atrophy segments which are then projected onto the IR image and are used to identify and segment atrophy lesions in the IR image and to measure their areas and distances from the fovea. Experimental results on 106 clinical OCT scans (5,207 slices) in which cRORA atrophy (the end point of advanced dry AMD) was identified in 2,952 atrophy segments and 1,046 atrophy lesions yield a mean F1 score of 0.78 (std 0.06) and an AUC of 0.937, both close to the observer variability. Automated computer-based detection and quantification of atrophy associated with AMD using a column-based CNN classification in OCT scans can be performed at expert level and may be a useful clinical decision support and research tool for the diagnosis, follow-up and treatment of retinal degenerations and dystrophies.
We present a deep learning system for testing graphics units by detecting novel visual corruption... more We present a deep learning system for testing graphics units by detecting novel visual corruptions in videos. Unlike previous work in which manual tagging was required to collect labeled training data, our weak supervision method is fully automatic and needs no human labelling. This is achieved by reproducing driver bugs that increase the probability of generating corruptions, and by making use of ideas and methods from the Multiple Instance Learning (MIL) setting. In our experiments, we significantly outperform unsupervised methods such as GAN-based models and discover novel corruptions undetected by baselines, while adhering to strict requirements on accuracy and efficiency of our real-time system.
During in vitro fertilization (IVF) cycles, multiple mature oocytes are retrieved from the ovary ... more During in vitro fertilization (IVF) cycles, multiple mature oocytes are retrieved from the ovary and are fertilized in the lab. The newly generated embryos can be transferred into the uterus on day-3,-4, or-5 of incubation, cryopreserved for subsequent transfers or discarded. Lacking a reliable noninvasive evaluation method of the potential to implant, pregnancy rates can be improved by cotransferring multiple embryos thus introducing health risks that are associated with multiple pregnancies. [1] Hence, the evaluation of embryo quality is required for improving live birth rates while minimizing medical complications and shortening time to pregnancy. [2-6] Machine learning was used for assessing the potential of embryos to blastulate [7,8] and to implant [9-11] based on manually annotated morphological and/or morphokientic features. Deep learning, which offers a powerful toolbox for carrying out automated and standardized classification tasks
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021
We present a novel system for performing real-time detection of diverse visual corruptions in vid... more We present a novel system for performing real-time detection of diverse visual corruptions in videos, for validating the quality of graphics units in our company. The system is used for several types of content, including movies and 3D graphics, with strict constraints on low false alert rates and real-time processing of millions of video frames per day. These constraints required novel solutions involving both hardware and software, including new supervised and weakly-supervised methods we developed. Our deployed system has enabled a 20X reduction of human effort and discovering new corruptions missed by humans and existing approaches. CCS CONCEPTS • Computing methodologies → Visual inspection; Scene anomaly detection; • Hardware → Bug detection, localization and diagnosis; • Software and its engineering → Empirical software validation.
Early diagnosis of sacroiliitis may lead to preventive treatment which can significantly improve ... more Early diagnosis of sacroiliitis may lead to preventive treatment which can significantly improve the patient's quality of life in the long run. Oftentimes, a CT scan of the lower back or abdomen is acquired for suspected back pain. However, since the differences between a healthy and an inflamed sacroiliac joint in the early stages are subtle, the condition may be missed. We have developed a new automatic algorithm for the diagnosis and grading of sacroiliitis CT scans as incidental findings, for patients who underwent CT scanning as part of their lower back pain workout. The method is based on supervised machine and deep learning techniques. The input is a CT scan that includes the patient's pelvis. The output is a diagnosis for each sacroiliac joint. The algorithm consists of four steps: 1) computation of an initial region of interest (ROI) that includes the pelvic joints region using heuristics and a U-Net classifier; 2) refinement of the ROI to detect both sacroiliac joints using a four-tree random forest; 3) individual sacroiliitis grading of each sacroiliac joint in each CT slice with a custom slice CNN classifier, and; 4) sacroiliitis diagnosis and grading by combining the individual slice grades using a random forest. Experimental results on 484 sacroiliac joints yield a binary and a 3-class case classification accuracy of 91.9% and 86%, a sensitivity of 95% and 82%, and an Area-Under-the-Curve of 0.97 and 0.57, respectively. Automatic computer-based analysis of CT scans has the potential of being a useful method for the diagnosis and grading of sacroiliitis as an incidental finding.
International Journal of Computer Assisted Radiology and Surgery, 2017
Purpose Radiological longitudinal follow-up of liver tumors in CT scans is the standard of care f... more Purpose Radiological longitudinal follow-up of liver tumors in CT scans is the standard of care for disease progression assessment and for liver tumor therapy. Finding new tumors in the follow-up scan is essential to determine malignancy, to evaluate the total tumor burden, and to determine treatment efficacy. Since new tumors are typically small, they may be missed by examining radiologists. Methods We describe a new method for the automatic detection and segmentation of new tumors in longitudinal liver CT studies and for liver tumors burden quantification. Its inputs are the baseline and follow-up CT scans, the baseline tumors delineation, and a tumor appearance prior model. Its outputs are the new tumors segmentations in the follow-up scan, the tumor burden quantification in both scans, and the tumor burden change. Our method is the first comprehensive method that is explicitly designed to find new liver tumors. It integrates information from the scans, the baseline known tumors delineations, and a tumor appearance prior model in the form of a global convolutional neural network classifier. Unlike other deep learning-based methods, it does not require large tagged training sets. Results Our experimental results on 246 tumors, of which 97 were new tumors, from 37 longitudinal liver CT studies with radiologist approved ground-truth segmentations, yields a true positive new tumors detection rate of 86 versus 72%
We present a novel process to fabricate conductive patterns by a new copper precursor ink. In thi... more We present a novel process to fabricate conductive patterns by a new copper precursor ink. In this method, an ink with copper formate, a self-reducible copper precursor, is printed, and subsequently heated under high pressure in a hot-press, which is commonly used in the PCB industry. The heating leads to decomposition of the precursor, and results in copper patterns with good electrical conductivity. The application of pressure enables the formation of a dense copper film. 5-15 micron thick copper patterns were obtained on FR4 sheets with an equivalent specific resistivity as low as 5.3±0.3 µΩ•cm, which is about 3 times copper bulk resistivity. Unlike most methods for copper precursor inks, this ink and process do not require an inert environment, and can be performed with instrumentation already used in the industry. Finally, we demonstrate the applicability of this method by printing functional Radio Frequency (RF) components; i.e. antennas for near Field Communication (NFC) and Wi-Fi.
In this work, we report the setup and results of the Liver Tumor Segmentation Benchmark (LiTS) or... more In this work, we report the setup and results of the Liver Tumor Segmentation Benchmark (LiTS) organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and International Conference On Medical Image Computing & Computer Assisted Intervention (MICCAI) 2017. Twenty-four valid state-of-the-art liver and liver tumor segmentation algorithms were applied to a set of 131 computed tomography (CT) volumes with different types of tumor contrast levels (hyper-/hypo-intense), abnormalities in tissues (metastasectomie) size and varying amount of lesions. The submitted algorithms have been tested on 70 undisclosed volumes. The dataset is created in collaboration with seven hospitals and research institutions and manually blind reviewed by independent three radiologists. We found that not a single algorithm performed best for liver and tumors. The best liver segmentation algorithm achieved a Dice score of 0.96(MICCAI) whereas for tumor segmentation the best algorithm evaluated at 0.67(ISBI) and 0.70(MICCAI). The LiTS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource.
Uploads
Papers by Adi Szeskin