iCAP: An Individualized Model Combining Gaze Parameters and Image-Based Features to Predict Radiologists' Decisions While Reading Mammograms

Ziba Gandomkar; Kevin Tay; Will Ryder; Patrick C Brennan; Claudia Mello-Thoms

doi:10.1109/TMI.2016.2645881

Back

iCAP: An Individualized Model Combining Gaze Parameters and Image-Based Features to Predict Radiologists' Decisions While Reading Mammograms

Journal article

Peer reviewed

iCAP: An Individualized Model Combining Gaze Parameters and Image-Based Features to Predict Radiologists' Decisions While Reading Mammograms

Ziba Gandomkar, Kevin Tay, Will Ryder, Patrick C Brennan and Claudia Mello-Thoms

IEEE transactions on medical imaging, Vol.36(5), pp.1066-1075

05/2017

DOI: 10.1109/TMI.2016.2645881

PMID: 28055858

View Online

Abstract

This study introduces an individualized tool for identifying mammogram interpretation errors, called eye-Computer Assisted Perception (iCAP). iCAP consists of two modules, one which processes areas marked by radiologists as suspicious for cancer and classifies these as False Positive (FP) or True Positive (TP) decisions, while the second module classifies fixated but not marked locations as False Negative (FN) or True-Negative (TN) decisions. iCAP relies on both radiologists' gaze-related parameters, extracted from eye tracking data, and image-based features. In order to evaluate iCAP, eye tracking data from eight breast radiologists reading 120 two-view digital mammograms were collected. Fifty-nine cases had biopsy proven cancer. For each radiologist, a user-specific support vector machine model was built to classify the radiologist' s reported areas as TPs or FPs and fixated locations as TNs or FNs. The performances of the classifiers were evaluated by utilizing leave-one-out cross validation. iCAP was tested retrospectively in a simulated scenario in which it was assumed that the radiologists would accept all iCAP decisions. Using iCAP led to an average increase of 12%±6% in the number of correctly localized cancer and an average decrease of 44.5%±22.7% in the number of FPs per image.

Solid modeling

Computer-assisted perception

Gaze tracking

Breast

Feature extraction

Mammography

Lesions

Cancer

Details

Title: Subtitle: iCAP: An Individualized Model Combining Gaze Parameters and Image-Based Features to Predict Radiologists' Decisions While Reading Mammograms
Creators: Ziba Gandomkar - Univ. of Sydney, Sydney, NSW, Australia
Kevin Tay - Med. Imaging Dept., Prince of Wales Hosp. & Community Health Services, Randwick, NSW, Australia
Will Ryder - Univ. of Sydney, Sydney, NSW, Australia
Patrick C Brennan - Univ. of Sydney, Sydney, NSW, Australia
Claudia Mello-Thoms - Univ. of Sydney, Sydney, NSW, Australia
Resource Type: Journal article
Publication Details: IEEE transactions on medical imaging, Vol.36(5), pp.1066-1075
DOI: 10.1109/TMI.2016.2645881
PMID: 28055858
NLM abbreviation: IEEE Trans Med Imaging
ISSN: 0278-0062
eISSN: 1558-254X
Publisher: Institute of Electrical and Electronics Engineers
Grant note: The Australian Government under the Diagnostic Imaging Quality
Language: English
Date published: 05/2017
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology
Record Identifier: 9984051777602771

Metrics

10 Record Views

15 Times Cited - Web of Science