Less is More: Selective reduction of CT data for self-supervised pre-training of deep learning models with contrastive learning improves downstream classification performance

In conclusion, the proposed approach highlights the importance of dataset quality and provides a transferable approach to improve contrastive pre-training for classification downstream tasks on medical images.

Authors

Michael Götz (ORCID: https://orcid.org/0000-0003-0984-224X)
Christoph Gerhard Lisson
Meinrad Beer (ORCID: https://orcid.org/0000-0001-7523-1979)
Timo Ropinski (ORCID: https://orcid.org/0000-0002-7857-5512)
Catharina Silvia Lisson
Daniel Wolf (ORCID: https://orcid.org/0000-0002-8584-5189)
Tristan Payer

Institutions

Universität Ulm (DE)
Technische Hochschule Ulm (DE)

Publication Details

Journal: Computers in Biology and Medicine
Published: 2024-10-10
DOI: https://doi.org/10.1016/j.compbiomed.2024.109242
Citations: 5
Primary Topic: Radiomics and Machine Learning in Medical Imaging
Type: article
Field-Weighted Citation Impact: 2.02

Funders

Medizinische Fakultät, Universität Ulm

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

Less is More: Selective reduction of CT data for self-supervised pre-training of deep learning models with contrastive learning improves downstream classification performance

Michael Götz, Christoph Gerhard Lisson, Meinrad Beer, Timo Ropinski et al.

Oct 10, 2024

5 citations

Computers in Biology and Medicine

Radiomics and Machine Learning in Medical Imaging

2.02

article

Less is More: Selective reduction of CT data for self-supervised pre-training of deep learning models with contrastive learning improves downstream classification performance

Michael Götz, Christoph Gerhard Lisson, Meinrad Beer, Timo Ropinski, Catharina Silvia Lisson, Daniel Wolf, Tristan Payer

October 10, 2024article en

5 citations

Abstract

In conclusion, the proposed approach highlights the importance of dataset quality and provides a transferable approach to improve contrastive pre-training for classification downstream tasks on medical images.

Computers in Biology and MedicineVol. 183

Universität Ulm (DE), Technische Hochschule Ulm (DE)

Medizinische Fakultät, Universität Ulm

Openalex Percentile: Top 13%

Radiomics and Machine Learning in Medical Imaging

2.02

DOI Open Access PDF OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Less is More: Selective reduction of CT data for self-supervised pre-training of deep learning models with contrastive learning improves downstream classification performance — Michael Götz, Christoph Gerhard Lisson, et al. · Computers in Biology and Medicine (2024) | TGRS Research Map | TGRS