A Collaborative Computer Aided Diagnosis (C-CAD) System with Eye-Tracking, Sparse Attentional Model, and Deep Learning

There are at least two categories of errors in radiology screening that can lead to suboptimal diagnostic decisions and interventions: (i) human fallibility and (ii) complexity of visual search. Computer aided diagnostic (CAD) tools are developed to help radiologists to compensate for some of these errors. However, despite their significant improvements over conventional screening strategies, most CAD systems do not go beyond their use as second opinion tools due to producing a high number of false positives, which human interpreters need to correct. In parallel with efforts in computerized analysis of radiology scans, several researchers have examined behaviors of radiologists while screening medical images to better understand how and why they miss tumors, how they interact with the information in an image, and how they search for unknown pathology in the images. Eye-tracking tools have been instrumental in exploring answers to these fundamental questions. However, most of the studies that utilize eye-tracking technology in radiology screening were not compatible with realistic radiology reading rooms. In this paper, we aim to develop a paradigm shift CAD system, called collaborative CAD (C-CAD), that unifies both of the above mentioned research lines: CAD and eye-tracking. We first design an eye-tracking interface providing radiologists with a real radiology reading room experience. Then, we propose a novel algorithm that unifies eye-tracking data and a CAD system. Specifically, we present a new graph based clustering and sparsification algorithm to transform eye-tracking data (gaze) into a signal model to interpret gaze patterns quantitatively and qualitatively. The proposed C-CAD collaborates with raPreprint submitted to Medical Image Analysis February 20, 2018 ar X iv :1 80 2. 06 26 0v 1 [ cs .C V ] 1 7 Fe b 20 18 diologists via eye-tracking technology and helps them to improve diagnostic decisions. The C-CAD learns radiologists’ search efficiency by processing their gaze patterns. To do this, the C-CAD uses a deep learning algorithm in a newly designed multi-task learning platform to segment and diagnose cancers simultaneously. The proposed C-CAD system has been tested in a lung cancer screening process (using low dose chest CTs) with multiple radiologists. Promising results support the efficiency, accuracy and applicability of the proposed C-CAD system in a real radiology room setting. We have also shown that our framework is generalizable to other, even more complex, applications with a different screening example: prostate cancer screening with multi-parametric magnetic resonance imaging (MRI). Feasibility of the C-CAD in addressing the unique challenges of MRI and the use of multiple modalities and screens for eye-tracking is presented.