A Diagnostic Gap Framework for Evaluating Reconstruction Fidelity in Weakly Supervised Mammography

• URL: http://arxiv.org/abs/2607.22740v1
• Date: Wed, 22 Jul 2026 19:59:26 GMT
• Title: A Diagnostic Gap Framework for Evaluating Reconstruction Fidelity in Weakly Supervised Mammography
• Abstract summary: We present the diagnostic gap framework, a practical evaluation tool that measures decision preservation and explanation preservation.<n>We evaluate on curated lesion ROI crops using a fidelity ladder of three class-conditional reconstructors.<n>The framework provides an architecture-agnostic instrument for identifying when and where multi-stage pipelines lose diagnostic signal.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weakly supervised pipelines for medical imaging have become increasingly popular over the years. These systems often include multiple stages and components, such as reconstruction, generation, and localization, yet standard evaluation metrics provide limited insight into whether clinically relevant information is preserved across each stage. We present the diagnostic gap framework, a practical evaluation tool that measures decision preservation and explanation preservation as a function of measured reconstruction fidelity. To isolate the effect of reconstruction from localization, we evaluate on curated lesion ROI crops using a fidelity ladder of three class-conditional reconstructors---VQ-VAE-GAN, VAE-GAN, and diffusion (SDEdit)---spanning a twenty-fold range in perceptual distance (LPIPS 0.029--0.584). At autoencoder fidelity, both decision and explanation are preserved: AUC changes remain within $\pm$0.005 and attribution similarity (HiResCAM, Grad-CAM++) stays high. At diffusion fidelity, both collapse: pooled AUC drops by 0.253 and mass-pathology AUC falls below chance. The diagnostic gap is thus a measurable function of reconstruction fidelity rather than an intrinsic cost of reconstruction, and the framework provides an architecture-agnostic instrument for identifying when and where multi-stage pipelines lose diagnostic signal.

Related papers

• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning? [49.14050864978079]
  We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning, and structured localization guidance.<n>The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints.
  arXiv  Detail & Related papers  (2026-08-13T14:35:20Z)
• PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring [18.918947215697205]
  This study presents a compact framework for continuous rehabilitation quality assessment that combines a temporal backbone with phase- and body-group descriptors.<n>PhaseAware achieved an RMSE of 0.0230, corresponding to an 88.9% reduction relative to the accepted baseline.<n>It also maintained favorable performance on KIMORE, suggesting that the phase-aware design transfers across related squatting protocols.
  arXiv  Detail & Related papers  (2026-07-22T14:57:42Z)
• MaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring [2.0480448867367476]
  We introduce MaRS, a label-free OOD detector that learns an in-distribution manifold using a lightweight autoencoder and measures deviation via a Mahalanobis distance on reconstruction residuals.<n>MaRS outperforms established confidence-, distance-, and reconstruction-based baselines, while remaining fully post-hoc and lightweight.
  arXiv  Detail & Related papers  (2026-06-21T19:45:41Z)
• Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification [5.127836966483091]
  Class Activation Mapping (CAM) methods are widely used to generate visual explanations for deep learning classifiers in medical imaging.<n>Existing evaluation frameworks assess whether explanations are correct, measured by localisation fidelity against radiologist annotations.<n>We propose the C-Score (Consistency Score), a confidence-weighted, annotation-free metric that quantifies intra-class explanation via intensity-emphasised pairwise soft IoU.
  arXiv  Detail & Related papers  (2026-04-09T17:47:31Z)
• FDP: A Frequency-Decomposition Preprocessing Pipeline for Unsupervised Anomaly Detection in Brain MRI [44.4791295950757]
  We develop an unsupervised anomaly detection (UAD) approach for brain MRI.<n>We conduct the first systematic frequency-domain analysis of pathological signatures.<n>We show that Frequency-Decomposition Preprocessing (FDP) framework can leverage frequency-domain reconstruction for simultaneous pathology suppression and anatomical preservation.
  arXiv  Detail & Related papers  (2025-11-17T02:40:14Z)
• Cancer-Net PCa-MultiSeg: Multimodal Enhancement of Prostate Cancer Lesion Segmentation Using Synthetic Correlated Diffusion Imaging [55.62977326180104]
  Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance.<n>We investigate synthetic correlated diffusion imaging (CDI$s$) as an enhancement to standard diffusion-based protocols.<n>Our results establish validated integration pathways for CDI$s$ as a practical drop-in enhancement for PCa lesion segmentation tasks.
  arXiv  Detail & Related papers  (2025-11-11T04:16:12Z)
• PF-DAformer: Proximal Femur Segmentation via Domain Adaptive Transformer for Dual-Center QCT [8.358409792893278]
  We develop a domain-adaptive transformer segmentation framework tailored for multi-institutional Quantitative computed tomography (QCT)<n>Our model is trained and validated on one of the largest hip fracture related research cohorts to date, comprising 1,024 QCT images scans from Tulane University and 384 scans from Rochester, Minnesota for proximal femur segmentation.
  arXiv  Detail & Related papers  (2025-10-30T18:07:56Z)
• Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction? [61.48804987263701]
  We propose a suite of anatomy-aware evaluation metrics to assess structural completeness across anatomical structures.<n> CARE incorporates structural penalties during training to encourage anatomical preservation of significant structures.<n> CARE substantially improves structural completeness in CT reconstructions, achieving up to +32% improvement for large organs, +22% for small organs, +40% for intestines, and +36% for vessels.
  arXiv  Detail & Related papers  (2025-06-02T17:07:10Z)
• Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging [41.446379453352534]
  Latent Diffusion Autoencoder (LDAE) is a novel encoder-decoder diffusion-based framework for efficient and meaningful unsupervised learning in medical imaging.<n>This study focuses on Alzheimer disease (AD) using brain MR from the ADNI database as a case study.
  arXiv  Detail & Related papers  (2025-04-11T15:37:46Z)
• U2AD: Uncertainty-based Unsupervised Anomaly Detection Framework for Detecting T2 Hyperintensity in MRI Spinal Cord [7.811634659561162]
  T2 hyperintensities in spinal cord MR images are crucial biomarkers for conditions such as degenerative cervical myelopathy.<n>Deep learning methods have shown promise in lesion detection, but most supervised approaches are heavily dependent on large, annotated datasets.<n>We propose an Uncertainty-based Unsupervised Anomaly Detection framework, termed U2AD, to address these limitations.
  arXiv  Detail & Related papers  (2025-03-17T17:33:32Z)
• Shifting Focus: From Global Semantics to Local Prominent Features in Swin-Transformer for Knee Osteoarthritis Severity Assessment [42.09313885494969]
  We harness the Swin Transformer's capacity to discern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. Our model demonstrates significant robustness and precision, as evidenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification.
  arXiv  Detail & Related papers  (2024-03-15T01:09:58Z)
• Modeling Barrett's Esophagus Progression using Geometric Variational Autoencoders [6.72834963752212]
  Early detection of Barrett's Esophagus (BE) is crucial for effectively preventing and treating esophageal cancer.<n>We show that hyperspherical VAE (S-VAE) and Shape Kendall VAE show improved classification accuracy, reconstruction loss, and generative capacity.
  arXiv  Detail & Related papers  (2023-03-17T14:08:16Z)

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.