1.3k citations · 1.5k across the 18 of their papers we have counts for
7 papers · 1 filter
ATCON: Attention Consistency for Vision Models
Ali Mirzazadeh, Florian Dubost, Maxwell Pike +4
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention ma…
Self-Attention Capsule Networks for Object Classification
Assaf Hoogi, Brian Wilcox, Yachee Gupta +1
We propose a novel architecture for object classification, called Self-Attention Capsule Networks (SACN). SACN is the first model that incorporates the Self-Attention mechanism as…
Institutionally Distributed Deep Learning Networks
Ken Chang, Niranjan Balachandar, Carson K Lam +6
Deep learning has become a promising approach for automated medical diagnoses. When medical data samples are limited, collaboration among multiple institutions is necessary to achi…
Optimizing and Visualizing Deep Learning for Benign/Malignant Classification in Breast Tumors
Darvin Yi, Rebecca Lynn Sawyer, David Cohn +4
Breast cancer has the highest incidence and second highest mortality rate for women in the US. Our study aims to utilize deep learning for benign/malignant classification of mammog…
A Fully-Automated Pipeline for Detection and Segmentation of Liver Lesions and Pathological Lymph Nodes
Assaf Hoogi, John W. Lambert, Yefeng Zheng +2
We propose a fully-automated method for accurate and robust detection and segmentation of potentially cancerous lesions found in the liver and in lymph nodes. The process is perfor…
Adaptive Local Window for Level Set Segmentation of CT and MRI Liver Lesions
Assaf Hoogi, Christopher F. Beaulieu, Guilherme M. Cunha +4
We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of…