CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

• URL: http://arxiv.org/abs/2606.23487v1
• Date: Mon, 22 Jun 2026 15:34:32 GMT
• Title: CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift
• Abstract summary: Updating a deployed model for a new imaging modality can fail silently in two ways that harm patients.<n>We study parameter-efficient continual adaptation through these two properties rather than forgetting leaderboard accuracy.<n>We present CADRE: a frozen-backbone framework combining low-rank adaptation (LoRA) with an online, self-scaling, similarity-aware elastic weight consolidation term.
• Score: 0.10742675209112622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one. Updating a deployed model for a new imaging modality can fail silently in two ways that harm patients: it can forget modalities it already handled (catastrophic forgetting), and it can drift from its trustworthy pretrained prior toward modality-specific shortcuts. We study parameter-efficient continual adaptation through these two properties rather than leaderboard accuracy, presenting CADRE: a frozen-backbone framework combining low-rank adaptation (LoRA) with an online, self-scaling, similarity-aware elastic weight consolidation term that bounds retained-competence loss, and an anchor-to-prior penalty bounding embedding drift from the frozen prior. Two short guarantees, a bound on total consolidation mass and a scale-invariance property, remove the scale-related sources of vanilla EWC's order fragility. Using breast cancer across three maximally dissimilar modalities (histopathology, ultrasound, chest radiography) as a controlled cross-modality stress test, under a multi-seed, multi-order protocol with paired significance testing and training approximately 0.23% of parameters, CADRE attains the highest accuracy, SPQ, and backward transfer and the lowest forgetting among adapting methods, reducing forgetting roughly sevenfold versus the strongest regularized baseline (0.075 to 0.011; paired p=0.023) and achieving positive backward transfer where every baseline is negative. We frame these as stability properties aligned with clinical-safety desiderata, not a deployment guarantee; robustness to distribution shift and adversarial inputs is out of scope.

Related papers

• Test-time Adaptation of Pelvic Bone Segmentation Models via Dynamic Reliability-Guided [62.10276009853225]
  Reliable pelvic bone segmentation from CT is essential for robot-assisted pelvic trauma surgery.<n>Existing methods show limited effectiveness for PBS.<n>We propose a novel closed-loop dynamic Reliability-Guided framework (ReGA) for PBS.
  arXiv  Detail & Related papers  (2026-08-01T08:13:20Z)
• CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation [3.5083700786844876]
  Two failure modes threaten reliability of medical world models in clinical deployment.<n>We argue that both problems admit a unified treatment via a lightweight regularisation objective.<n>We derive the combined objective, establish which proof steps transfer from the classification setting without modification, and evaluate it on the PhysioNet 2019 Sepsis Challenge.
  arXiv  Detail & Related papers  (2026-07-29T10:47:52Z)
• Transferable Low-Rank Convolutional Bases for Onboarding Unseen Medical Imaging Modalities [0.0]
  We study the emphonboarding problem under a strict leave-one-domain-out protocol.<n>A convolutional backbone is pre-trained on source modalities, frozen permanently, and then required to accommodate an unseen modality.<n>Full fine-tuning reaches the highest target accuracy only by catastrophically degrading the source modalities.
  arXiv  Detail & Related papers  (2026-07-18T17:09:05Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregation [0.2283362795949404]
  Probabilistic Feature Imputation Network produces uncertainty estimates alongside imputed features.<n>Experiments on federated chest X-ray classification using CheXpert, NIH Open-I, and PadChest demonstrate consistent improvements over deterministic baselines.
  arXiv  Detail & Related papers  (2026-04-14T17:03:14Z)
• Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering [58.85421622061983]
  We propose StsPatient for the fine-grained simulation of cognitively impaired patients.<n>We capture domain-specific features by extracting steering vectors from contrastive pairs of instructions and responses.<n>StsPatient significantly outperforms baselines in both clinical authenticity and severity controllability.
  arXiv  Detail & Related papers  (2026-04-14T02:37:46Z)
• PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities [86.63247982275396]
  PRIME is a missing-aware multimodal self-supervised pretraining framework.<n>It learns robust and transferable representations from partially observed cohorts.<n>We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types.
  arXiv  Detail & Related papers  (2026-04-05T21:14:27Z)
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs [61.06744611795341]
  Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging.<n>We propose texttttextbfLATA (Laplacian-Assisted Transductive Adaptation), a textittraining- and label-free refinement.<n>texttttextbfLATA sharpens zero-shot predictions without compromising exchangeability.
  arXiv  Detail & Related papers  (2026-02-19T16:45:38Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• BMDS-Net: A Bayesian Multi-Modal Deep Supervision Network for Robust Brain Tumor Segmentation [21.538098924595754]
  We propose BMDS-Net, a unified framework that prioritizes clinical robustness and trustworthiness over simple metric.<n>Our contribution is three-fold. First, we construct a robust deterministic backbone by integrating a Zero-Init Multimodal Conmodal Fusion (MMCF) module and a Residual-Gated Deep Decoder Supervision (DDS) mechanism.<n>Second, we introduce a memory-efficient Bayesian fine-tuning strategy that transforms the network into a probabilistic predictor, providing voxel-wise uncertainty maps.<n>Third, comprehensive experiments on the BraTS 2021 dataset demonstrate that BMDS-Net not only maintains competitive accuracy
  arXiv  Detail & Related papers  (2026-01-24T16:06:43Z)
• ClinNet: Evidential Ordinal Regression with Bilateral Asymmetry and Prototype Memory for Knee Osteoarthritis Grading [3.337151338735509]
  Knee osteoarthritis (KOA) grading based on radiographic images is a critical yet challenging task.<n>In this work, we propose ClinNet, a novel trustworthy framework that addresses KOA grading as evidential ordinal regression problem.
  arXiv  Detail & Related papers  (2026-01-24T05:49:41Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift [12.373281238541296]
  Medical vision-language models (VLMs) offer promise for clinical decision support, yet their reliability under distribution shifts remains a major concern for safe deployment.<n>We propose DRiFt, a structured feature decoupling framework that explicitly separates clinically relevant signals from task-agnostic noise.<n>Our approach improves in-distribution performance by +11.4% Top-1 accuracy and +3.3% Macro-F1 over prior prompt-based methods.
  arXiv  Detail & Related papers  (2025-09-11T12:26:57Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)

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.