Convolutional neural network with a hybrid loss function for fully automated segmentation of lymphoma lesions in FDG PET images

Fereshteh Yousefirizi; Natalia Dubljevic; Shadab Ahamed; Ingrid Bloise; Claire Gowdy; Joo Hyun O; Youssef Farag; Rodrigue de Schaetzen; Patrick Martineau; Don Wilson; Carlos F. Uribe; Arman Rahmim

doi:10.1117/12.2612675

4 April 2022 Convolutional neural network with a hybrid loss function for fully automated segmentation of lymphoma lesions in FDG PET images

Fereshteh Yousefirizi, Natalia Dubljevic, Shadab Ahamed, Ingrid Bloise, Claire Gowdy, Joo Hyun O, Youssef Farag, Rodrigue de Schaetzen, Patrick Martineau, Don Wilson, Carlos F. Uribe, Arman Rahmim

Author Affiliations +

Proceedings Volume 12032, Medical Imaging 2022: Image Processing; 120320V (2022) https://doi.org/10.1117/12.2612675
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

Segmentation of lymphoma lesions is challenging due to their varied sizes and locations in whole-body PET scans. In this work, we present a fully-automated segmentation technique using a multi-center dataset of diffuse large B-cell lymphoma (DLBCL) with heterogeneous characteristics. We utilized a dataset of [18F]FDG-PET scans (n=194) from two different imaging centers including cases with primary mediastinal large B-cell lymphoma (PMBCL) (n=104). Automated brain and bladder removal approaches were utilized as preprocessing steps, to tackle false positives caused by normal hypermetabolic uptake in these organs. Our segmentation model is a convolutional neural network (CNN), based on a 3D U-Net architecture that includes squeeze and excitation (SE) modules. Hybrid distribution, region, and boundary-based losses (Unified Focal and Mumford-Shah (MS)) were utilized that showed the best performance compared to other combinations (p<0.05). Cross-validation between different centers, DLBCL and PMBCL cases, and three random splits were applied on train/validation data. The ensemble of these six models achieved a Dice similarity coefficient (DSC) of 0.77 ± 0.08 and Hausdorff distance (HD) of 16.5 ±12.5. Our 3D U-net model with SE modules for segmentation with hybrid loss performed significantly better (p<0.05) as compared to the 3D U-Net (without SE modules) using the same loss function (Unified Focal and MS loss) (DSC= 0.64 ± 0.21 and HD= 26.3 ± 18.7). Our model can facilitate a fully automated quantification pipeline in a multi-center context that opens the possibility for routine reporting of total metabolic tumor volume (TMTV) and other metrics shown useful for the management of lymphoma.

Conference Presentation

Citation Download Citation

Fereshteh Yousefirizi, Natalia Dubljevic, Shadab Ahamed, Ingrid Bloise, Claire Gowdy, Joo Hyun O, Youssef Farag, Rodrigue de Schaetzen, Patrick Martineau, Don Wilson, Carlos F. Uribe, and Arman Rahmim "Convolutional neural network with a hybrid loss function for fully automated segmentation of lymphoma lesions in FDG PET images", Proc. SPIE 12032, Medical Imaging 2022: Image Processing, 120320V (4 April 2022); https://doi.org/10.1117/12.2612675

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