Share Email Print
cover

Proceedings Paper • new

Improved interpretability for computer-aided severity assessment of retinopathy of prematurity
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Computer-aided diagnosis tools for Retinopathy of Prematurity (ROP) base their decisions on handcrafted retinal features that highly correlate with expert diagnoses, such as arterial and venous curvature, tortuosity and dilation. Deep learning leads to performance comparable to those of expert physicians, albeit not ensuring that the same clinical factors are learned in the deep representations. In this paper, we investigate the relationship between the handcrafted and the deep learning features in the context of ROP diagnosis. Average statistics on the handcrafted features for each input image were expressed as retinal concept measures. Three disease severity grades, i.e. normal, pre-plus and plus, were classified by a deep convolutional neural network. Regression Concept Vectors (RCV) were computed in the network feature space for each retinal concept measure. Relevant concept measures were identified by bidirectional relevance scores for the normal and plus classes. Results show that the curvature, diameter and tortuosity of the segmented vessels are indeed relevant to the classification. Among the potential applications of this method, the analysis of borderline cases between the classes and of network faults, in particular, can be used to improve the performance.

Paper Details

Date Published: 13 March 2019
PDF: 11 pages
Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 109501R (13 March 2019); doi: 10.1117/12.2512584
Show Author Affiliations
Mara Graziani, Univ. of Applied Sciences Western Switzerland (HESSO) (Switzerland)
Univ. of Geneva (Switzerland)
James M. Brown, Martinos Ctr. for Biomedical Imaging (United States)
Vincent Andrearczyk, Univ. of Applied Sciences Western Switzerland (HESSO) (Switzerland)
Veysi Yildiz, Northeastern Univ. (United States)
J. Peter Campbell, Casey Eye Institute, Oregon Health & Science Univ. (United States)
Deniz Erdogmus, Northeastern Univ. (United States)
Stratis Ioannidis, Northeastern Univ. (United States)
Michael F. Chiang, Casey Eye Institute, Oregon Health & Science Univ. (United States)
Jayashree Kalpathy-Cramer, Martinos Ctr. for Biomedical Imaging (United States)
Henning Müller, Univ. of Applied Sciences Western Switzerland (HESSO) (Switzerland)
Martinos Ctr. for Biomedical Imaging (United States)
Univ. of Geneva (Switzerland)


Published in SPIE Proceedings Vol. 10950:
Medical Imaging 2019: Computer-Aided Diagnosis
Kensaku Mori; Horst K. Hahn, Editor(s)

© SPIE. Terms of Use
Back to Top