Biomarker Localization From Deep Learning Regression Networks

Please use this identifier to cite or link to this item:
Información del item - Informació de l'item - Item information
Title: Biomarker Localization From Deep Learning Regression Networks
Authors: Cano Espinosa, Carlos | González, Germán | Washko, George R. | Cazorla, Miguel | San José Estépar, Raúl
Research Group/s: Robótica y Visión Tridimensional (RoViT)
Center, Department or Service: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Keywords: Biomarker direct regression | Biomarker localization | Coronary artery calcification | Convolutional neural networks
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial
Issue Date: Jun-2020
Publisher: IEEE
Citation: IEEE Transactions on Medical Imaging. 2020, 39(6): 2121-2132. doi:10.1109/TMI.2020.2965486
Abstract: Biomarker estimation methods from medical images have traditionally followed a segment-and-measure strategy. Deep-learning regression networks have changed such a paradigm, enabling the direct estimation of biomarkers in databases where segmentation masks are not present. While such methods achieve high performance, they operate as a black-box. In this work, we present a novel deep learning network structure that, when trained with only the value of the biomarker, can perform biomarker regression and the generation of an accurate localization mask simultaneously, thus enabling a qualitative assessment of the image locus that relates to the quantitative result. We showcase the proposed method with three different network structures and compare their performance against direct regression networks in four different problems: pectoralis muscle area (PMA), subcutaneous fat area (SFA), liver mass area in single slice computed tomography (CT), and Agatston score estimated from non-contrast thoracic CT images (CAC). Our results show that the proposed method improves the performance with respect to direct biomarker regression methods (correlation coefficient of 0.978, 0.998, and 0.950 for the proposed method in comparison to 0.971, 0.982, and 0.936 for the reference regression methods on PMA, SFA and CAC respectively) while achieving good localization (DICE coefficients of 0.875, 0.914 for PMA and SFA respectively, p < 0.05 for all pairs). We observe the same improvement in regression results comparing the proposed method with those obtained by quantify the outputs using an U-Net segmentation network (0.989 and 0.951 respectively). We, therefore, conclude that it is possible to obtain simultaneously good biomarker regression and localization when training biomarker regression networks using only the biomarker value.
Sponsor: This work was supported in part by the National Institutes of Health (NHLBI) under Grant R01HL116931, Grant R21HL14042, and Grant R01HL149877, in part by the COPDGene Study through the NHLBI under Grant NCT00608764, Grant U01 HL089897, and Grant U01 HL089856, and in part by the COPD Foundation through contributions made to the Industry Advisory Committee comprised of AstraZeneca, Boehringer-Ingelheim, GlaxoSmithKline, Novartis, and Sunovion.
ISSN: 0278-0062 (Print) | 1558-254X (Online)
DOI: 10.1109/TMI.2020.2965486
Language: eng
Type: info:eu-repo/semantics/article
Rights: © 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See for more information.
Peer Review: si
Publisher version:
Appears in Collections:INV - RoViT - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
ThumbnailCano-Espinosa_etal_2020_IEEE-TMI_final.pdfVersión final (acceso restringido)3,79 MBAdobe PDFOpen    Request a copy
ThumbnailCano-Espinosa_etal_2020_IEEE-TMI_accepted.pdfAccepted Manuscript (acceso abierto)3,5 MBAdobe PDFOpen Preview

Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.