Individualized and generalized learner models for predicting missed hepatic metastases

Parvathy Sudhir Pillai; Scott Hsieh; David Holmes III; Rickey Carter; Joel G. Fletcher; Cynthia McCollough

doi:10.1117/12.2612745

4 April 2022 Individualized and generalized learner models for predicting missed hepatic metastases

Parvathy Sudhir Pillai, Scott Hsieh, David Holmes III, Rickey Carter, Joel G. Fletcher, Cynthia McCollough

Proceedings Volume 12035, Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment; 120350C (2022) https://doi.org/10.1117/12.2612745
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

The diagnostic performance of radiologist readers exhibits substantial variation that cannot be explained by CT acquisition protocol differences. Studying reader detectability from CT images may help identify why certain types of lesions are missed by multiple or specific readers. Ten subspecialized abdominal radiologists marked all suspected metastases in a multi-reader-multi-case study of 102 deidentified contrast-enhanced CT liver scans at multiple radiation dose levels. A reference reader marked ground truth metastatic and benign lesions with the aid of histopathology or tumor progression on later scans. Multi-slice image patches and 3D radiomic features were extracted from the CT images. We trained deep convolutional neural networks (CNN) to predict whether an average (generalized) or individual radiologist reader would detect or miss a specific metastasis from an image patch containing it. The individualized CNN showed higher performance with an area under the receiver operating characteristic curve (AUC) of 0.82 compared to a generalized one (AUC = 0.78) in predicting reader-specific detectability. Random forests were used to build the respective versions from radiomic features. Both the individualized (AUC = 0.64) and generalized (AUC = 0.59) predictors from radiomic features showed limited ability to differentiate detected from missed lesions. This shows that CNN can identify and learn automated features that are better predictors of reader detectability of lesions than radiomic features. Individualized prediction of difficult lesions may allow targeted training of idiosyncratic weaknesses but requires substantial training data for each reader.

Conference Presentation

Citation Download Citation

Parvathy Sudhir Pillai, Scott Hsieh, David Holmes III, Rickey Carter, Joel G. Fletcher, and Cynthia McCollough "Individualized and generalized learner models for predicting missed hepatic metastases", Proc. SPIE 12035, Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment, 120350C (4 April 2022); https://doi.org/10.1117/12.2612745

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available