Transductive Image Segmentation : Self-training and Effect of Uncertainty Estimation

Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model generalization to unseen data. In some applications, however, our primary interest is not generalization but to obtain optimal predictions on a specific unlabeled database that is fully available during model development. Examples include population studies for extracting imaging phenotypes. This work investigates an often overlooked aspect of SSL, transduction. It focuses on the quality of predictions made on the unlabeled data of interest when they are included for optimization during training, rather than improving generalization. We focus on the self-training framework and explore its potential for transduction. We analyze it through the lens of Information Gain and reveal that learning benefits from the use of calibrated or under-confident models. Our extensive experiments on a large MRI database for multi-class segmentation of traumatic brain lesions shows promising results when comparing transductive with inductive predictions. We believe this study will inspire further research on transductive learning, a well-suited paradigm for medical image analysis.

Winzeck, StefanImperial College London (author)
Kornaropoulos, Evgenios N.Lund University,Lunds universitet,Diagnostisk radiologi, Lund,Sektion V,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Diagnostic Radiology, (Lund),Section V,Department of Clinical Sciences, Lund,Faculty of Medicine(Swepub:lu)ev2115ko (author)
Whitehouse, DanielUniversity of Cambridge (author)
Englman, CameronUniversity of Cambridge (author)
Phyu, PoeCambridge University Hospitals NHS Foundation Trust (author)
Pao, NormanCambridge University Hospitals NHS Foundation Trust (author)
Menon, David K.University of Cambridge (author)
Rueckert, DanielKlinikum rechts der Isar,Imperial College London (author)
Das, TilakCambridge University Hospitals NHS Foundation Trust (author)
Newcombe, Virginia F.J. (author)
Glocker, BenImperial College London (author)
Albarqouni, Shadi (editor)
Cardoso, M. Jorge (editor)
Dou, Qi (editor)
Kamnitsas, Konstantinos (editor)
Khanal, Bishesh (editor)
Rekik, Islem (editor)
Rieke, Nicola (editor)
Sheet, Debdoot (editor)
Tsaftaris, Sotirios (editor)
Xu, Daguang (editor)
Xu, Ziyue (editor)
Imperial College LondonDiagnostisk radiologi, Lund (creator_code:org_t)

In:Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health - 3rd MICCAI Workshop, DART 2021, and 1st MICCAI Workshop, FAIR 2021, Held in Conjunction with MICCAI 2021, ProceedingsCham : Springer International Publishing12968 LNCS, s. 79-891611-33490302-97439783030877217

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Medical Engineer ...; and Medical Image Pr ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.