About
60
Publications
58,176
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
17,015
Citations
Introduction
Skills and Expertise
Publications
Publications (60)
Text-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or stylistically undesirable images that are not aligned with human preferences. To address this, recent approaches have incorporated h...
Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or adaptation. However, with the absence of paired and annotated images, most domain transfer methods mainly rely on adv...
Annotation-efficient deep learning refers to methods and practices that yield high-performance deep learning models without the use of massive carefully labeled training datasets. This paradigm has recently attracted attention from the medical imaging research community because (1) it is difficult to collect large, representative medical imaging da...
Despite the tremendous success of deep neural networks in medical image segmentation, they typically require a large amount of costly, expert-level annotated data. Few-shot segmentation approaches address this issue by learning to transfer knowledge from limited quantities of labeled examples. Incorporating appropriate prior knowledge is critical i...
Despite the tremendous success of deep neural networks in medical image segmentation, they typically require a large amount of costly, expert-level annotated data. Few-shot segmentation approaches address this issue by learning to transfer knowledge from limited quantities of labeled examples. Incorporating appropriate prior knowledge is critical i...
Supervised learning has proved effective for medical image analysis. However, it can utilize only the small labeled portion of data; it fails to leverage the large amounts of unlabeled data that is often available in medical image datasets. Supervised models are further handicapped by domain shifts, when the labeled dataset fails to cover different...
Supervised learning has proved effective for medical image analysis. However, it can utilize only the small labeled portion of data; it fails to leverage the large amounts of unlabeled data that is often available in medical image datasets. Supervised models are further handicapped by domain shifts, when the labeled dataset, despite being large eno...
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large, representative, and high quality annotated datasets. However, rarely do we have a perfect training dataset, pa...
Rationale: Computer aided detection (CAD) algorithms for Pulmonary Embolism (PE) algorithms have been shown to increase radiologists' sensitivity with a small increase in specificity. However, CAD for PE has not been adopted into clinical practice, likely because of the high number of false positives current CAD software produces. Objective: To gen...
The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths; and (2) their skip connections imp...
The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths; and (2) their skip connections imp...
Automatic, reliable lobe segmentation is crucial to the diagnosis, assessment, and quantification of pulmonary diseases. Existing pulmonary lobe segmentation techniques are prohibitively slow, undesirably rely on prior (airway/vessel) segmentation, and/or require user interactions for optimal results. We introduce a reliable, fast, and fully automa...
Deep convolutional neural networks have proved effective in segmenting lesions and anatomies in various medical imaging modalities. However, in the presence of small sample size and domain shift problems, these models often produce masks with non-intuitive segmentation mistakes. In this paper, we propose a segmentation framework called ErrorNet, wh...
Transfer learning from natural image to medical image has established as one of the most practical paradigms in deep learning for medical image analysis. However, to fit this paradigm, 3D imaging tasks in the most prominent imaging modalities (e.g., CT and MRI) have to be reformulated and solved in 2D, losing rich 3D anatomical information and inev...
Generative adversarial networks (GANs) have ushered in a revolution in image-to-image translation. The development and proliferation of GANs raises an interesting question: can we train a GAN to remove an object, if present, from an image while otherwise preserving the image? Specifically, can a GAN "virtually heal" anyone by turning his medical im...
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large, representative, and high quality annotated datasets. However, rarely do we have a perfect training dataset, pa...
Transfer learning from natural image to medical image has established as one of the most practical paradigms in deep learning for medical image analysis. However, to fit this paradigm, 3D imaging tasks in the most prominent imaging modalities (e.g., CT and MRI) have to be reformulated and solved in 2D, losing rich 3D anatomical information and inev...
Transfer learning from natural image to medical image has established as one of the most practical paradigms in deep learning for medical image analysis. However, to fit this paradigm, 3D imaging tasks in the most prominent imaging modalities (e.g., CT and MRI) have to be reformulated and solved in 2D, losing rich 3D anatomical information and inev...
Generative adversarial networks (GANs) have ushered in a revolution in image-to-image translation. The development and proliferation of GANs raises an interesting question: can we train a GAN to remove an object, if present, from an image while otherwise preserving the image? Specifically, can a GAN "virtually heal" anyone by turning his medical im...
Diagnosing pulmonary embolism (PE) and excluding disorders that may clinically and radiologically simulate PE poses a challenging task for both human and machine perception. In this paper, we propose a novel vessel-oriented image representation (VOIR) that can improve the machine perception of PE through a consistent, compact, and discriminative im...
Reliable and automatic segmentation of lung lobes is important for diagnosis, assessment, and quantification of pulmonary diseases. The existing techniques are prohibitively slow, undesirably rely on prior (airway/vessel) segmentation, and/or require user interactions for optimal results. This work presents a reliable, fast, and fully automated lun...
We investigate the effectiveness of a simple solution to the common problem of deep learning in medical image analysis with limited quantities of labeled training data. The underlying idea is to assign artificial labels to abundantly available unlabeled medical images and, through a process known as surrogate supervision, pre-train a deep neural ne...
Reliable and automatic segmentation of lung lobes is important for diagnosis, assessment, and quantification of pulmonary diseases.
The existing techniques are prohibitively slow, undesirably rely on prior
(airway/vessel) segmentation, and/or require user interactions for optimal results. This work presents a reliable, fast, and fully automated lun...
Reliable and automatic segmentation of lung lobes is important for diagnosis, assessment, and quantification of pulmonary diseases. The existing techniques are prohibitively slow, undesirably rely on prior (airway/vessel) segmentation, and/or require user interactions for optimal results. This work presents a reliable, fast, and fully automated lun...
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at reducing the semantic gap betwe...
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at reducing the semantic gap betwe...
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at reducing the semantic gap betwe...
Two dominant classes of modern approaches for the detection and classification of focal lesions are a bag of visual words and end-to-end learning machines. In this study, we reviewed and compared these approaches for lung nodule detection, colorectal polyp detection, and lung nodule classification in CT images. Specifically, we considered massive-t...
Cardiovascular disease (CVD) is the leading cause of death in the United States, yet it is largely preventable. But a critical part of prevention is identification of at-risk persons before adverse events. For predicting individual CVD risk, carotid intima–media thickness (CIMT), a noninvasive ultrasonography method, has proven to be valuable. Howe...
Thisstudyaimstoaddresstwocentral questions. First, are fine-tuned convolutional neural networks (CNNs) necessary for medical imaging applications? In response, we considered four medical vision tasks from three different medical imaging modalities, and studied the necessity of fine-tuned CNNs under varying amounts of training data. Second, to what...
Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronar...
Colonoscopy is the gold standard for colon cancer screening though still some polyps are missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it...
End-to-end learning machines enable a direct mapping from the raw input data to the desired outputs, eliminating the need for hand-crafted features. Despite less engineering effort than the hand-crafted counterparts, these learning machines achieve extremely good results for many computer vision and medical image analysis tasks. Two dominant classe...
Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substant...
Colorectal cancer is the second leading cause of cancer death in the US. The primary method for screening and prevention of colorectal cancer is colonoscopy. However, during a colonoscopy, a significant fraction of polyps is missed. Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rates. This paper presents the culmina...
Computer-aided detection (CAD) can play a major role in diagnosing pulmonary embolism (PE) at CT pulmonary angiography (CTPA). However, despite their demonstrated utility, to achieve a clinically acceptable sensitivity, existing PE CAD systems generate a high number of false positives, imposing extra burdens on radiologists to adjudicate these supe...
Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp featu...
Computer-aided polyp detection in colonoscopy videos has been the subject of research for over the past decade. However, despite significant advances, automatic polyp detection is still an unsolved problem. In this paper, we propose a new polyp detection method based on a unique 3-way image presentation and convolutional neural networks. Our method...
This paper presents a new method for detecting polyps in colonoscopy. Its novelty lies in integrating the global geometric constraints of polyps with the local patterns of intensity variation across polyp boundaries: the former drives the detector towards the objects with curvy boundaries, while the latter minimizes the misleading effects of polyp-...
Optical colonoscopy is the preferred method for colon cancer screening and prevention. The goal of colonoscopy is to find and remove colonic polyps, precursors to colon cancer. However, colonoscopy is not a perfect procedure. Recent clinical studies report a significant polyp miss due to insufficient quality of colonoscopy. To complicate the proble...
Colonoscopy is the primary method for detecting and removing polyps — precursors to colon cancer, but during colonoscopy, a significant number of polyps are missed — the pooled miss-rate for all polyps is 22% (95% CI, 19%–26%). This paper presents an automatic polyp detection system for colonoscopy, aiming to alert colonoscopists to possible polyps...
Carotid intima-media thickness (CIMT) has proven to be sensitive for predicting individual risk of cardiovascular diseases (CVD). The CIMT is measured based on region of interest (ROIs) in end-diastolic ultrasound frames (EUFs). To interpret CIMT videos, in the current practice, the EUFs and ROIs must be manually selected, a process that is tedious...
This paper presents a novel online learning method for automatically detecting anatomic structures in medical images. Conventional off-line learning methods require collecting a complete set of representative samples prior to training a detector. Once the detector is trained, its performance is fixed. To improve the performance, the detector must b...
Colorectal cancer most often begins as abnormal growth of the colon wall, commonly referred to as polyps. It has been shown that the timely removal of polyps with optical colonoscopy (OC) significantly reduces the incidence and mortality of colorectal cancer. However, a significant number of polyps are missed during OC in clinical practice—the pool...
Acute pulmonary embolism (APE) is the third most common cause of death in the United States. Appearing as a sudden blockage in a major pulmonary artery, APE may cause mild, moderate or severe right ventricular (RV) overload. Although severe RV overload produces diagnostically obvious RV mechanical failure, little progress has been made in gaining a...
Acute pulmonary embolism (APE) is known as one of the major causes of
sudden death. However, high level of mortality caused by APE can be
reduced, if detected in early stages of development. Hence, biomarkers
capable of early detection of APE are of utmost importance. This study
investigates how APE affects the biomechanics of the cardiac right
ven...
In this paper, we propose a self-adaptive, asymmetric on-line boosting
(SAAOB) method for detecting anatomical structures in CT pulmonary
angiography (CTPA). SAAOB is novel in that it exploits a new asymmetric
loss criterion with self-adaptability according to the ratio of exposed
positive and negative samples and in that it has an advanced rule to...
This paper presents a novel on-line learning method for automatically detecting anatomic structures in medical images. Conventional off-line learning requires collecting all representative samples before the commencement of training. Our presented approach eliminates the need for storing historical training samples and is capable of continuously en...
This work addresses the increasing demand for a sensitive and user-friendly iris based authentication system. We aim at reducing False Rejection Rate (FRR). The primary source of high FRR is the presence of degradation factors in iris texture. To reduce FRR, we propose a feature extraction method robust against such adverse factors. Founded on loca...
This work addresses the increasing demand for a sensitive and user-friendly iris based authentication system. We aim at reducing False Rejection Rate (FRR). The primary source of high FRR is the presence of degradation factors in iris texture. To reduce FRR, we propose a feature extraction method robust against such adverse factors. Founded on loca...
Despite significant progress made in iris recognition, handling noisy and degraded iris images is still an open problem and
deserves further investigation. This paper proposes a feature extraction method to cope with degraded iris images. This method
is founded on applying the 2D-wavelet transform on overlapped blocks of the iris texture. The propo...
In this paper, a modified version of local intensity variation method is proposed to enhance the efficiency of identification
system while dealing with degradation factors presented in iris texture. Our contributions to improve the robustness and performance
of local intensity variation method consist of defining overlapped patches to compensate fo...
In noncooperative Iris recognition one should deal with uncontrolled behavior of the subject as well as uncontrolled lighting conditions. That means imperfect focus, contrast, brightness, and orientation among the others. To cope with this situation we propose to take iris images at both near infrared (NIR) and visible light (VL) and use them simul...
In despite of successful implementation of iris recognition systems, noncooperative recognition is still remained as an unsolved problem. Unexpected behavior of the subjects and uncontrolled lighting conditions as the main aspects of noncooperative iris recognition result in blurred and noisy captured images. This issue can degrade the performance...