Dataset-Origin Signatures and Shortcut Learning in Screening Mammography AI: A Cross-Dataset Case Study

• URL: http://arxiv.org/abs/2607.15416v1
• Date: Thu, 16 Jul 2026 19:41:48 GMT
• Title: Dataset-Origin Signatures and Shortcut Learning in Screening Mammography AI: A Cross-Dataset Case Study
• Abstract summary: We examined whether supplementing such data with biopsy-confirmed cases from abnormal-enriched external datasets improves performance.<n>We evaluated an EfficientNet-B5 encoder with Mammo-CLIP weights as a frozen linear probe under consistent preprocessing.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable AI for screening mammography requires training data representative of the low cancer prevalence and subtle abnormalities found in screening populations. We examined whether supplementing such data with biopsy-confirmed cases from abnormal-enriched external datasets improves performance. Using the Newfoundland and Labrador Breast Screening Dataset (NLBSD) alongside CBIS-DDSM and CMMD, we evaluated an EfficientNet-B5 encoder initialized with Mammo-CLIP weights as a frozen linear probe under consistent preprocessing and patient-level splits. The NLBSD-only model achieved an AUC-ROC of 0.737 (95% CI [0.686, 0.785]). Adding external positive cases reduced performance in every configuration (AUC-ROC = 0.620--0.644; DeLong test, Holm-corrected $p < 0.05$), with degradation increasing as additional sources were introduced. Domain-matched evaluation produced modest gains only when the training and test domains coincided, and no configuration surpassed the NLBSD-only model. As a diagnostic, we reframed the task as predicting each examination's dataset of origin. The datasets were separated almost perfectly despite identical preprocessing, indicating that dataset-specific characteristics strongly influence the learned representation. These findings show that naïvely pooling abnormal-enriched mammography datasets can introduce domain shift that outweighs the benefit of additional positive cases. Differences in acquisition, intensity mapping, and dataset construction persist after normalization, motivating domain-aware strategies for combining heterogeneous mammography datasets.

Related papers

• Bridging the Applicator Gap with Data-Doping:Dual-Domain Learning for Precise Bladder Segmentation in CT-Guided Brachytherapy [0.3058685580689604]
  We investigate whether samples from a shifted distribution can effectively support learning when combined with limited target domain data.<n>While CT scans without brachytherapy applicators (no applicator: NA) are widely available, scans with applicators inserted (with applicator: WA) are scarce.<n>We propose a dual domain learning strategy that integrates NA and WA CT data to improve robustness and generalizability.
  arXiv  Detail & Related papers  (2026-01-28T06:50:37Z)
• SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification [0.4999814847776096]
  We introduce SpurBreast, a curated breast MRI dataset that intentionally incorporates spurious correlations to evaluate their impact on model performance.<n>We analyze over 100 features involving patient, device, and imaging protocol, and identify two dominant spurious signals: magnetic field strength and image orientation.<n>Through controlled dataset splits, we demonstrate that DNNs can exploit these non-clinical signals, achieving high validation accuracy while failing to generalize to unbiased test data.
  arXiv  Detail & Related papers  (2025-10-02T15:16:20Z)
• PCA for Enhanced Cross-Dataset Generalizability in Breast Ultrasound Tumor Segmentation [0.0]
  In medical image segmentation, limited external validity remains a critical obstacle when models are deployed across unseen datasets.<n>This paper presents a novel application of principal component analysis (PCA) to address this limitation.<n>PCA preprocessing reduces noise and emphasizes essential features by retaining approximately 90% of the dataset variance.
  arXiv  Detail & Related papers  (2025-05-29T15:59:01Z)
• Advancing Tabular Stroke Modelling Through a Novel Hybrid Architecture and Feature-Selection Synergy [0.9999629695552196]
  The present work develops and validates a data-driven and interpretable machine-learning framework designed to predict strokes.<n>Ten routinely gathered demographic, lifestyle, and clinical variables were sourced from a public cohort of 4,981 records.<n>The proposed model achieved an accuracy rate of 97.2% and an F1-score of 97.15%, indicating a significant enhancement compared to the leading individual model.
  arXiv  Detail & Related papers  (2025-05-18T21:46:45Z)
• The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease detection [51.697248252191265]
  This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation. We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare. Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
  arXiv  Detail & Related papers  (2023-09-13T10:40:41Z)
• Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [55.03872260158717]
  Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains. But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies. We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
  arXiv  Detail & Related papers  (2023-08-24T01:30:18Z)
• Learning brain MRI quality control: a multi-factorial generalization problem [0.0]
  This work aimed at evaluating the performances of the MRIQC pipeline on various large-scale datasets. We focused our analysis on the MRIQC preprocessing steps and tested the pipeline with and without them. We concluded that a model trained with data from a heterogeneous population, such as the CATI dataset, provides the best scores on unseen data.
  arXiv  Detail & Related papers  (2022-05-31T15:46:44Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• Deep learning-based COVID-19 pneumonia classification using chest CT images: model generalizability [54.86482395312936]
  Deep learning (DL) classification models were trained to identify COVID-19-positive patients on 3D computed tomography (CT) datasets from different countries. We trained nine identical DL-based classification models by using combinations of the datasets with a 72% train, 8% validation, and 20% test data split. The models trained on multiple datasets and evaluated on a test set from one of the datasets used for training performed better.
  arXiv  Detail & Related papers  (2021-02-18T21:14:52Z)
• Chest x-ray automated triage: a semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures [83.48996461770017]
  This work presents a Deep Learning method based on the late fusion of different convolutional architectures. We built four training datasets combining images from public chest x-ray datasets and our institutional archive. We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool.
  arXiv  Detail & Related papers  (2020-12-23T14:38:35Z)
• Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
  We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
  arXiv  Detail & Related papers  (2020-10-14T16:50:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.