Image analysis techniques are becoming invaluable in the medical field, as they have been shown to help physicians better diagnose and treat diseases and expand the utility of medical imaging. Transfer learning, in particular, is one of the most practical paradigms in deep learning for medical image analysis. In conventional transfer learning, source...

Fully convolutional networks (FCN) and variants of U-Net are the state-of-the-art models for medical image segmentation. However, these models have limitations, namely 1. their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models and 2. their skip connections impose a restrictive fusion scheme,...

Pulmonary embolism (PE) is a common cardiovascular emergency. Mortality rates approaching 30% are common with undiagnosed PE, but they fall to 2% with early diagnosis and treatment, thus, quick and accurate diagnosis is critical. Suspected PE is typically diagnosed with CT pulmonary angiography (CTPA), but this technique has issues with interpretation...

Generative adversarial networks (GANs) are revolutionizing image-to-image translation, which is attractive to researchers in the medical imaging community. While using GANs to reveal diseased regions in a medical image is appealing, it requires a GAN to identify a minimal subset of target pixels for domain translation, also known as fixed-point translation,...

Convolutional neural networks (CNN) are useful in a variety of applications ranging from computer vision to signal processing. Segmenting organs and lesions in medical images for computer aided diagnoses (CAD) is an area in which CNNs are becoming the state-of-the-art. In particular, U-Net and other U-Net-like CNN architectures have shown great promise...

Carotid Intima-Media Thickness (CIMT) measurement is a non-invasive, sensitive, and highly reproducible technique for cardiovascular risk stratification. Interpreting a CIMT video involves three operations: (1) select three end-diastolic ultrasound frames (EUFs) in each video; (2) localize a region of interest (ROI) approximately 1 cm distal from the...

Colorectal cancer is the second leading cause of cancer death in the United States and fourth worldwide. Colorectal cancer often develops from precancerous polyps which, when found early, may be easily and safely removed. Colorectal polyps are often asymptomatic and are typically detected through routine optical colonoscopy (OC) screening. While there...

Colorectal cancer is the second leading cause of cancer death in the United States and fourth worldwide. Colorectal cancer often develops from precancerous polyps which, when found early, may be easily and safely removed. Colorectal polyps are often asymptomatic and are typically detected through routine optical colonoscopy (OC) screening. While there...

Colorectal cancer is the second leading cause of cancer death in the United States and fourth worldwide. Colorectal cancer often develops from precancerous polyps, which, when found through optical colonoscopy screening, may be easily and safely removed. Unfortunately, colonoscopies are operator dependent and the quality is greatly affected by diligence,...

Colorectal cancer is the second leading cause of cancer death in the United States and fourth worldwide. Colorectal cancer often develops from precancerous polyps which, when found early, may be easily and safely removed. Colorectal polyps are often asymptomatic and are typically detected through routine optical colonoscopy (OC) screening. While there...