Self-Supervision for Medical Image Classification: State-of-the-Art Performance with ~100 Labeled Training Samples per Class

Maximilian Nielsen; Laura Wenderoth; Thilo Sentker; René Werner

doi:10.3390/bioengineering10080895

Self-Supervision for Medical Image Classification

Standard

Self-Supervision for Medical Image Classification : State-of-the-Art Performance with ~100 Labeled Training Samples per Class. / Nielsen, Maximilian; Wenderoth, Laura; Sentker, Thilo ; Werner, René.

In: BIOENGINEERING-BASEL, Vol. 10, No. 8, 895, 28.07.2023.

Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review

Harvard

Nielsen, M, Wenderoth, L, Sentker, T & Werner, R 2023, 'Self-Supervision for Medical Image Classification: State-of-the-Art Performance with ~100 Labeled Training Samples per Class', BIOENGINEERING-BASEL, vol. 10, no. 8, 895. https://doi.org/10.3390/bioengineering10080895

APA

Nielsen, M., Wenderoth, L., Sentker, T., & Werner, R. (2023). Self-Supervision for Medical Image Classification: State-of-the-Art Performance with ~100 Labeled Training Samples per Class. BIOENGINEERING-BASEL, 10(8), [895]. https://doi.org/10.3390/bioengineering10080895

Vancouver

Nielsen M, Wenderoth L, Sentker T , Werner R. Self-Supervision for Medical Image Classification: State-of-the-Art Performance with ~100 Labeled Training Samples per Class. BIOENGINEERING-BASEL. 2023 Jul 28;10(8). 895. https://doi.org/10.3390/bioengineering10080895

Bibtex

@article{97983ab57974431faf50bcd3052f7ee5,

title = "Self-Supervision for Medical Image Classification: State-of-the-Art Performance with ~100 Labeled Training Samples per Class",

abstract = "Is self-supervised deep learning (DL) for medical image analysis already a serious alternative to the de facto standard of end-to-end trained supervised DL? We tackle this question for medical image classification, with a particular focus on one of the currently most limiting factor of the field: the (non-)availability of labeled data. Based on three common medical imaging modalities (bone marrow microscopy, gastrointestinal endoscopy, dermoscopy) and publicly available data sets, we analyze the performance of self-supervised DL within the self-distillation with no labels (DINO) framework. After learning an image representation without use of image labels, conventional machine learning classifiers are applied. The classifiers are fit using a systematically varied number of labeled data (1-1000 samples per class). Exploiting the learned image representation, we achieve state-of-the-art classification performance for all three imaging modalities and data sets with only a fraction of between 1% and 10% of the available labeled data and about 100 labeled samples per class.",

author = "Maximilian Nielsen and Laura Wenderoth and Thilo Sentker and Ren{\'e} Werner",

year = "2023",

month = jul,

day = "28",

doi = "10.3390/bioengineering10080895",

language = "English",

volume = "10",

journal = "BIOENGINEERING-BASEL",

issn = "2306-5354",

publisher = "MDPI AG",

number = "8",

}

RIS

TY - JOUR

T1 - Self-Supervision for Medical Image Classification

T2 - State-of-the-Art Performance with ~100 Labeled Training Samples per Class

AU - Nielsen, Maximilian

AU - Wenderoth, Laura

AU - Sentker, Thilo

AU - Werner, René

PY - 2023/7/28

Y1 - 2023/7/28

N2 - Is self-supervised deep learning (DL) for medical image analysis already a serious alternative to the de facto standard of end-to-end trained supervised DL? We tackle this question for medical image classification, with a particular focus on one of the currently most limiting factor of the field: the (non-)availability of labeled data. Based on three common medical imaging modalities (bone marrow microscopy, gastrointestinal endoscopy, dermoscopy) and publicly available data sets, we analyze the performance of self-supervised DL within the self-distillation with no labels (DINO) framework. After learning an image representation without use of image labels, conventional machine learning classifiers are applied. The classifiers are fit using a systematically varied number of labeled data (1-1000 samples per class). Exploiting the learned image representation, we achieve state-of-the-art classification performance for all three imaging modalities and data sets with only a fraction of between 1% and 10% of the available labeled data and about 100 labeled samples per class.

AB - Is self-supervised deep learning (DL) for medical image analysis already a serious alternative to the de facto standard of end-to-end trained supervised DL? We tackle this question for medical image classification, with a particular focus on one of the currently most limiting factor of the field: the (non-)availability of labeled data. Based on three common medical imaging modalities (bone marrow microscopy, gastrointestinal endoscopy, dermoscopy) and publicly available data sets, we analyze the performance of self-supervised DL within the self-distillation with no labels (DINO) framework. After learning an image representation without use of image labels, conventional machine learning classifiers are applied. The classifiers are fit using a systematically varied number of labeled data (1-1000 samples per class). Exploiting the learned image representation, we achieve state-of-the-art classification performance for all three imaging modalities and data sets with only a fraction of between 1% and 10% of the available labeled data and about 100 labeled samples per class.

U2 - 10.3390/bioengineering10080895

DO - 10.3390/bioengineering10080895

M3 - SCORING: Journal article

C2 - 37627780

VL - 10

JO - BIOENGINEERING-BASEL

JF - BIOENGINEERING-BASEL

SN - 2306-5354

IS - 8

M1 - 895

ER -