15 papers
False Confidence: Automated Labels Confound Fairness Audits in Cervical Spine Segmentation
Linus Juni, Aasa Feragen, Aditya Parikh
Automated segmentation of cervical-spine MRI is increasingly used in clinical workflows, yet no fairness audit exists for this anatomy. We show that auditing these segmentation tas…
Effect of Demographic Bias on Skin Lesion Classification
Ralf Raumanns, Gerard Schouten, Veronika Cheplygina +1
In this study, we evaluate the performance of skin lesion classification using ResNet-based convolutional models, focusing on the impact of demographic bias in training data, parti…
Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
Aditya Parikh, Stella Frank, Sneha Das +1
Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparitie…
Intersectional Disentangling of Temporal and Acquisition Bias in Fetal Ultrasound
Aya Elgebaly, Joris Fournel, Benjamin Laine Jønch Jurgensen +6
Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data. We show that intersectional analysis can disentang…
Fair Lung Disease Diagnosis from Chest CT via Gender-Adversarial Attention Multiple Instance Learning
Aditya Parikh, Aasa Feragen
We present a fairness-aware framework for multi-class lung disease diagnosis from chest CT volumes, developed for the Fair Disease Diagnosis Challenge at the PHAROS-AIF-MIH Worksho…
Measuring What VLMs Don't Say: Validation Metrics Hide Clinical Terminology Erasure in Radiology Report Generation
Aditya Parikh, Aasa Feragen, Sneha Das +1
Reliable deployment of Vision-Language Models (VLMs) in radiology requires validation metrics that go beyond surface-level text similarity to ensure clinical fidelity and demograph…