PuSH - Publikationsserver des Helmholtz Zentrums München

Baltatzis, V.* ; Le Folgoc, L.* ; Ellis, S.* ; Manzanera, O.E.M.* ; Bintsi, K.M.* ; Nair, A.* ; Desai, S.* ; Glocker, B.* ; Schnabel, J.A.

The effect of the loss on generalization: Empirical study on synthetic lung nodule data.

In: (4th International Workshop on Interpretability of Machine Intelligence in Medical Image Computing, iMIMIC 2020 and 1st International Workshop on Topological Data Analysis and Its Applications for Medical Data, TDA4MedicalData 2021 held in conjunction, 27 September 2021, Strasbourg). Berlin [u.a.]: Springer, 2021. 56-64 (Lect. Notes Comput. Sc. ; 12929 LNCS)
Postprint DOI
Open Access Green
Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss function in such tasks, a growing number of approaches have turned to a family of contrastive learning-based losses. Even though performance metrics such as accuracy, sensitivity and specificity are regularly used for the evaluation of CNN classifiers, the features that these classifiers actually learn are rarely identified and their effect on the classification performance on out-of-distribution test samples is insufficiently explored. In this paper, motivated by the real-world task of lung nodule classification, we investigate the features that a CNN learns when trained and tested on different distributions of a synthetic dataset with controlled modes of variation. We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Contrastive Learning ; Distribution Shift ; Interpretability
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Bandtitel IMIMIC 2021, TDA4MedicalData 2021: Interpretability of Machine Intelligence in Medical Image Computing, and Topological Data Analysis and Its Applications for Medical Data
Konferenztitel 4th International Workshop on Interpretability of Machine Intelligence in Medical Image Computing, iMIMIC 2020 and 1st International Workshop on Topological Data Analysis and Its Applications for Medical Data, TDA4MedicalData 2021 held in conjunction
Konferzenzdatum 27 September 2021
Konferenzort Strasbourg
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 12929 LNCS, Heft: , Seiten: 56-64 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Nichtpatentliteratur Publikationen
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)