guest ::
| Home > Publications database > Shortcut learning leads to sex bias in deep learning models for photoacoustic tomography. > print |
| Home > Publications database > Shortcut learning leads to sex bias in deep learning models for photoacoustic tomography. > print |
| 001 | 301270 | ||
| 005 | 20250803021806.0 | ||
| 024 | 7 | _ | |a 10.1007/s11548-025-03370-9 |2 doi |
| 024 | 7 | _ | |a pmid:40343639 |2 pmid |
| 024 | 7 | _ | |a 1861-6410 |2 ISSN |
| 024 | 7 | _ | |a 1861-6429 |2 ISSN |
| 024 | 7 | _ | |a altmetric:178328022 |2 altmetric |
| 037 | _ | _ | |a DKFZ-2025-00955 |
| 041 | _ | _ | |a English |
| 082 | _ | _ | |a 610 |
| 100 | 1 | _ | |a Knopp, Marcel |0 P:(DE-He78)494ff43d7941675bb715dbe497f23f22 |b 0 |e First author |u dkfz |
| 245 | _ | _ | |a Shortcut learning leads to sex bias in deep learning models for photoacoustic tomography. |
| 260 | _ | _ | |a Heidelberg [u.a.] |c 2025 |b Springer |
| 336 | 7 | _ | |a article |2 DRIVER |
| 336 | 7 | _ | |a Output Types/Journal article |2 DataCite |
| 336 | 7 | _ | |a Journal Article |b journal |m journal |0 PUB:(DE-HGF)16 |s 1753779007_3430 |2 PUB:(DE-HGF) |
| 336 | 7 | _ | |a ARTICLE |2 BibTeX |
| 336 | 7 | _ | |a JOURNAL_ARTICLE |2 ORCID |
| 336 | 7 | _ | |a Journal Article |0 0 |2 EndNote |
| 500 | _ | _ | |a #EA:E130#LA:E130# / 2025 Jul;20(7):1325-1333 |
| 520 | _ | _ | |a Shortcut learning has been identified as a source of algorithmic unfairness in medical imaging artificial intelligence (AI), but its impact on photoacoustic tomography (PAT), particularly concerning sex bias, remains underexplored. This study investigates this issue using peripheral artery disease (PAD) diagnosis as a specific clinical application.To examine the potential for sex bias due to shortcut learning in convolutional neural network (CNNs) and assess how such biases might affect diagnostic predictions, we created training and test datasets with varying PAD prevalence between sexes. Using these datasets, we explored (1) whether CNNs can classify the sex from imaging data, (2) how sex-specific prevalence shifts impact PAD diagnosis performance and underdiagnosis disparity between sexes, and (3) how similarly CNNs encode sex and PAD features.Our study with 147 individuals demonstrates that CNNs can classify the sex from calf muscle PAT images, achieving an AUROC of 0.75. For PAD diagnosis, models trained on data with imbalanced sex-specific disease prevalence experienced significant performance drops (up to 0.21 AUROC) when applied to balanced test sets. Additionally, greater imbalances in sex-specific prevalence within the training data exacerbated underdiagnosis disparities between sexes. Finally, we identify evidence of shortcut learning by demonstrating the effective reuse of learned feature representations between PAD diagnosis and sex classification tasks.CNN-based models trained on PAT data may engage in shortcut learning by leveraging sex-related features, leading to biased and unreliable diagnostic predictions. Addressing demographic-specific prevalence imbalances and preventing shortcut learning is critical for developing models in the medical field that are both accurate and equitable across diverse patient populations. |
| 536 | _ | _ | |a 315 - Bildgebung und Radioonkologie (POF4-315) |0 G:(DE-HGF)POF4-315 |c POF4-315 |f POF IV |x 0 |
| 588 | _ | _ | |a Dataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de |
| 650 | _ | 7 | |a Peripheral artery disease (PAD) |2 Other |
| 650 | _ | 7 | |a Photoacoustic tomography (PAT) |2 Other |
| 650 | _ | 7 | |a Sex Bias in AI |2 Other |
| 650 | _ | 7 | |a Shortcut learning |2 Other |
| 700 | 1 | _ | |a Bender, Christoph Julien |0 P:(DE-He78)d9c9ea92e3b697685f4b4c3bd6d063ad |b 1 |e First author |u dkfz |
| 700 | 1 | _ | |a Holzwarth, Niklas |0 P:(DE-He78)1c47bf7bdef42ec57b194723ccfb2946 |b 2 |u dkfz |
| 700 | 1 | _ | |a Li, Yi |b 3 |
| 700 | 1 | _ | |a Kempf, Julius |b 4 |
| 700 | 1 | _ | |a Caranovic, Milenko |b 5 |
| 700 | 1 | _ | |a Knieling, Ferdinand |0 0000-0002-3535-2626 |b 6 |
| 700 | 1 | _ | |a Lang, Werner |0 0000-0003-4114-7589 |b 7 |
| 700 | 1 | _ | |a Rother, Ulrich |0 0000-0002-4016-5673 |b 8 |
| 700 | 1 | _ | |a Seitel, Alexander |0 P:(DE-He78)a83df473f58a6a8ef43263ec9783ecf0 |b 9 |e Last author |u dkfz |
| 700 | 1 | _ | |a Maier-Hein, Lena |0 P:(DE-He78)26a1176cd8450660333a012075050072 |b 10 |e Last author |u dkfz |
| 700 | 1 | _ | |a Dreher, Kris |0 P:(DE-He78)84acbc6406dd178828f87a8150d40951 |b 11 |e Last author |u dkfz |
| 773 | _ | _ | |a 10.1007/s11548-025-03370-9 |0 PERI:(DE-600)2235881-X |n 7 |p 1325-1333 |t International journal of computer assisted radiology and surgery |v 20 |y 2025 |x 1861-6410 |
| 909 | C | O | |p VDB |o oai:inrepo02.dkfz.de:301270 |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 0 |6 P:(DE-He78)494ff43d7941675bb715dbe497f23f22 |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 1 |6 P:(DE-He78)d9c9ea92e3b697685f4b4c3bd6d063ad |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 2 |6 P:(DE-He78)1c47bf7bdef42ec57b194723ccfb2946 |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 9 |6 P:(DE-He78)a83df473f58a6a8ef43263ec9783ecf0 |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 10 |6 P:(DE-He78)26a1176cd8450660333a012075050072 |
| 910 | 1 | _ | |a Deutsches Krebsforschungszentrum |0 I:(DE-588b)2036810-0 |k DKFZ |b 11 |6 P:(DE-He78)84acbc6406dd178828f87a8150d40951 |
| 913 | 1 | _ | |a DE-HGF |b Gesundheit |l Krebsforschung |1 G:(DE-HGF)POF4-310 |0 G:(DE-HGF)POF4-315 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-300 |4 G:(DE-HGF)POF |v Bildgebung und Radioonkologie |x 0 |
| 914 | 1 | _ | |y 2025 |
| 915 | _ | _ | |a DEAL Springer |0 StatID:(DE-HGF)3002 |2 StatID |d 2024-12-18 |w ger |
| 915 | _ | _ | |a DEAL Springer |0 StatID:(DE-HGF)3002 |2 StatID |d 2024-12-18 |w ger |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0200 |2 StatID |b SCOPUS |d 2024-12-18 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0300 |2 StatID |b Medline |d 2024-12-18 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0199 |2 StatID |b Clarivate Analytics Master Journal List |d 2024-12-18 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0160 |2 StatID |b Essential Science Indicators |d 2024-12-18 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1110 |2 StatID |b Current Contents - Clinical Medicine |d 2024-12-18 |
| 915 | _ | _ | |a WoS |0 StatID:(DE-HGF)0113 |2 StatID |b Science Citation Index Expanded |d 2024-12-18 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0150 |2 StatID |b Web of Science Core Collection |d 2024-12-18 |
| 915 | _ | _ | |a JCR |0 StatID:(DE-HGF)0100 |2 StatID |b INT J COMPUT ASS RAD : 2022 |d 2024-12-18 |
| 915 | _ | _ | |a IF < 5 |0 StatID:(DE-HGF)9900 |2 StatID |d 2024-12-18 |
| 920 | 2 | _ | |0 I:(DE-He78)E130-20160331 |k E130 |l E130 Intelligente Medizinische Systeme |x 0 |
| 920 | 1 | _ | |0 I:(DE-He78)E130-20160331 |k E130 |l E130 Intelligente Medizinische Systeme |x 0 |
| 920 | 0 | _ | |0 I:(DE-He78)E130-20160331 |k E130 |l E130 Intelligente Medizinische Systeme |x 0 |
| 980 | _ | _ | |a journal |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a I:(DE-He78)E130-20160331 |
| 980 | _ | _ | |a UNRESTRICTED |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|