arXiv subjects

Soroosh Tayebi Arasteh

Publications and source records attributed to Soroosh Tayebi Arasteh.

At least 19 recordsLinked to original sources

arXiv2026

The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis

Differential privacy limits how much each training image can influence a medical imaging model but lowers its diagnostic accuracy. Pretrained weights reduce this loss. It is unknown whether the pretraining objective or domain improves accuracy more. Here we train chest radiograph classifiers under differential privacy from five starting points on 591,884 radiographs from five datasets. We show that supervised pretraining on chest radiographs ranks first in 24 of 25 combinations of dataset and privacy setting. Measured by the area under the receiver operating characteristic curve, its lead over supervised pretraining on natural images is 2.6% without privacy and 15.3% at the strictest budget. From that starting point, changing the domain improves this area 2.2 to 3.7 times more than changing the objective. Private pretraining on chest radiographs lowers this area by about 5% under privacy but outperforms the three starting points without patient data at the strictest budget. Under privacy, supervised chest radiograph pretraining leads in the worst-performing demographic subgroup.

cs.CV↗

arXiv2026

Medical foundation models converge less under label supervision

Diagnostic classifiers and imaging biomarkers are fitted on the embeddings of medical foundation models. These models are replaced as new versions appear. This practice assumes that different models represent images alike. We tested this assumption with more than 750,000 images from 14 datasets in 5 imaging modalities, 18 public models, and 101 models trained on chest radiographs and histopathology that differ in pretraining objective, label type, size, random seed, initialization, training patients, or training recipe. Agreement was measured as the mutual k-nearest-neighbor overlap, the share of an image's nearest neighbors common to two models. Two public models shared on average 0.091 of the 10 nearest neighbors of a chest radiograph. A randomly initialized network shared 0.036 with them. In the four other modalities, they shared at most 0.300. On chest radiographs, agreement depended more on the source dataset and the radiographic view than on the findings. It was not significantly associated with accuracy. A linear mapping between the embeddings of two models, fitted on 4,096 unlabeled radiographs, transferred classifiers for 14 chest findings with 0.987 of their original area under the receiver operating characteristic curve. Convergence depended on the pretraining objective. Label-supervised models converged least at both model sizes in chest radiography and histopathology. On chest radiographs, two label-supervised models that differed only in their random seed shared 0.062 to 0.100 of their nearest neighbors. Two models trained with self-distillation, masked image modeling, or contrastive pretraining shared 0.411 to 0.802. Developers can therefore choose convergence when they choose the pretraining objective. Before replacing a model, users could test on unlabeled images whether its successor returns the same nearest neighbors.

cs.CV↗

arXiv2026

Vision-language models for chest radiography do not always need the image

Vision-language models that answer questions about chest radiographs are evaluated by their accuracy on labels derived from radiology reports. High benchmark accuracy is often interpreted as evidence that the model uses the image. A model that answers from the finding named in the question can score as well as a model that uses the radiograph. Keeping the question fixed, we audit eight open-weight systems by swapping in another patient's radiograph with the same or the opposite label, occluding the radiologist-marked region or an equal region elsewhere, and removing the radiograph or replacing it with noise or a photograph. On 2,548 yes-or-no questions from MIMIC-CXR, one multimodal model answers Yes regardless of the image, another multimodal model changes its answers without following the label, and four systems use the image but keep about half of their correct answers when the radiograph is swapped for an opposite-label radiograph. A medical model that receives only the question text scores 55.3% on the pooled questions, higher than two multimodal systems. It scores 91.8% where every finding is present, and answering Yes to every question scores 100% there. Where the image is necessary, the best multimodal system exceeds this model by 10.4% in balanced accuracy. The categories are unchanged on CheXpert. Confidence is not higher when a correct answer depends on the marked region. In a reader study with three radiologists, the two radiologists who read a balanced set of 200 cases score 86.0% and 82.0%, and the systems score 50.0% to 73.0%. Accuracy does not establish image use, but an intervention on the image can test it.

cs.CV↗

arXiv2026

FRAME: Separating sampling variation from performance disparities in medical image analysis

Fairness audits of medical imaging models commonly report the largest performance difference between demographic subgroups and treat any positive value as evidence of bias. Yet a perfectly fair model also produces a positive difference, which grows as subgroups shrink. Some mitigation methods remove demographic information from models because they assume that it produces the difference. Here we introduce Fair-model Reference And Mechanism Evaluation (FRAME). Its first step compares each reported difference with the difference expected from a perfectly fair model at the same subgroup counts. Its second step tests whether candidate causes of any excess over this fair-model reference change the difference when they are injected into model features. We evaluated 36 encoders on nine datasets in three modalities and audited 89 published differences across six modalities. For 10 frozen encoders and 13 chest radiograph findings, the reference is a median 41% of the race difference and 22% of the age difference. It is exceeded by 40 of 53 published differences in sensitivity or false positive rate and by one of 36 in the area under the receiver operating characteristic curve (AUROC). Adding race information to the features of two encoders does not change the race difference significantly. At matched disease performance, mitigation reduces the race difference by less than its spread across three pretraining seeds (medians 0.005 and 0.012) and the age difference by more (0.008 and 0.006). Image-text pretraining raises the worst-group AUROC for race by a median 0.049 over self-supervised pretraining. Reporting the fair-model reference beside every new and published subgroup difference could direct mitigation to the differences above it.

cs.CV↗

arXiv2026

CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging

A foundation encoder is pretrained once on a large image corpus and then reused with its weights frozen. Each new task is solved by training a small head on the features it produces. This setup is common in medical imaging, where labeled cases are scarce and a frozen encoder can be reused across findings. All downstream tasks then depend on the class separation present in that fixed feature space. Encoder selection usually uses the area under the receiver operating characteristic curve (AUROC) of a trained downstream head. AUROC measures the predictive information a head can extract from the features, but it does not measure class separation in the frozen feature space. A positive image that lies near a negative image in feature space has a bounded normalized margin under any Lipschitz head. Chance-calibrated neighborhood discordance (CANDOR) measures this feature-space separation without training a head. For a positive image, it compares the k nearest positive-label neighbors with the k nearest negative-label neighbors, among images acquired the same way. Discordance rate D is the share of positives whose opposite-label neighbors are nearer. Drawing the 2 candidate sets at equal size makes the labels interchangeable, so label-independent features have chance level D=1/2 without simulation. We apply CANDOR to 22 frozen encoders on 605,443 images from 20 public datasets, covering 8 binary tasks in 7 domains. On every task, the best encoder is below 1/2. A discordant image bounds the normalized margin of every Lipschitz head on that encoder. A selector that is shown the true label and chooses among 11 encoders reduces the miss rate from 0.359 to 0.028. Discordance is associated with occlusion retention and with none of pretraining objective, parameter count, release year, or finding size. The fixed chance level lets D be computed for a frozen encoder before any downstream head is trained.

cs.LG↗

arXiv2026

Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants

In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. Ensuring their reliability is challenging due to multi-turn interactions, the absence of explicit ground truth, and strict safety constraints. Existing evaluation techniques fall short, as they target single-turn settings and fail to capture constraint handling, context retention, and safety-critical behavior across turns. We propose an automated framework for testing the multi-turn conversational capabilities of ICAs. The system is treated as a black box and evaluated via closed-loop simulation with a strategy-guided user simulator, an adversarial strategy manager, and a two-tier LLM judge assessing turn-level failures and conversation-level quality. We evaluate the approach on an industrial ICA with six LLM backends and twelve human annotators. The automated judge shows substantial agreement with humans, and strategy guidance uncovers 2.96 times more unique failure types per conversation and more than doubles the number of unique failing conversations compared to unguided simulation.

cs.CL↗

arXiv2026

Differential privacy representation geometry for medical image analysis

Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We introduce Differential Privacy Representation Geometry for Medical Imaging (DP-RGMI), a framework that interprets DP as a structured transformation of representation space and decomposes performance degradation into encoder geometry and task-head utilization. Geometry is quantified by representation displacement from initialization and spectral effective dimension, while utilization is measured as the gap between linear-probe and end-to-end utility. Across over 594,000 images from four chest X-ray datasets and multiple pretrained initializations, we show that DP is consistently associated with a utilization gap even when linear separability is largely preserved. At the same time, displacement and spectral dimension exhibit non-monotonic, initialization- and dataset-dependent reshaping, indicating that DP alters representation anisotropy rather than uniformly collapsing features. Correlation analysis reveals that the association between end-to-end performance and utilization is robust across datasets but can vary by initialization, while geometric quantities capture additional prior- and dataset-conditioned variation. These findings position DP-RGMI as a reproducible framework for diagnosing privacy-induced failure modes and informing privacy model selection.

cs.CV↗

arXiv2026

The strength of clinical evidence is recoverable from language model representations but not from their stated grades

Large language models (LLMs) increasingly summarize clinical evidence, where a claim's weight depends on how strongly it is supported. Yet these models convey confidence poorly, and properties they never state, such as truth, are often readable from their activations. Whether a clinical model registers evidence strength, distinct from truth, and states it when asked is untested, and any such signal could be lexical. We compiled 45,134 clinical claims from six public sources, harmonized 20,611 into a four-level evidence grade under three independent frameworks, and tested 22 local, open-weight LLMs from several developers (0.6-70 billion parameters; general, medical, and reasoning), with lexical, truth, and cross-framework controls. A linear estimator recovered the grade in every model (median AUROC 71.8), yet decodability did not rise with scale and was weakest in reasoning models. The grade the models stated fell to chance, 25-27 percentage points below the estimator. The recoverable signal was largely lexical and did not transfer across topics or frameworks, yet it was distinct from factual truth and still flagged weakly supported claims (AUROC 69.2). Clinical LLMs thus carry an ordered evidence-strength signal they do not express, so their stated grades fail to convey a claim's support even when it is recoverable from their representations and text.

cs.CL↗

arXiv2026

Cross-modal linkage risk in clinical vision-language models

Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-level image-report correspondence. This poses a privacy risk in settings where radiographs and reports are deliberately kept separate after acquisition, such as image-only data sharing or access-controlled reports, because a de-identified image may be re-linked to its original narrative report through cosine similarity alone. We formalized this as image-to-report retrieval and used public paired cohorts, in which the true pairing is known by design, as ground-truth benchmarks to audit the risk rather than as the privacy scenario. Evaluating VLMs of increasing clinical specialization on 406,241 paired examples from 126,804 patients across MIMIC-CXR (43,793 held-out pairs) and external CheXpert Plus (29,296 pairs), we found that re-linkage rose systematically with specialization: the strongest VLM retrieved the correct report at 15 times chance at a candidate pool of N = 100, 50 times chance at N = 10,000, and well above chance at full-database scale. The signal persisted under pathology-matched hard negatives that removed disease-label shortcuts, indicating correspondence beyond broad diagnostic categories. To reduce it without retraining, we froze both encoders and applied differentially private optimization only to the projection heads defining the alignment layer (epsilon = 0.34, delta = 6x10-6). This reduced Recall@1 by 61.8% at N = 10,000 on MIMIC-CXR and transferred to CheXpert Plus without retraining, while image-side utility was largely preserved: macro AUROC for linear-probe classification across 14 labels shifted only from 79.63% to 79.43%. Targeted DP finetuning of the shared alignment layer can substantially reduce cross-modal re-linkage without materially degrading the image representations that make these models clinically useful.

cs.CV↗

arXiv2026

Perceptual implications of automatic anonymization in pathological speech

Automatic anonymization is increasingly used to enable ethical sharing of clinical speech, yet its perceptual and clinical consequences remain undercharacterized. We present a human-centered evaluation of automatically anonymized pathological speech, using a structured protocol with ten native and non-native German listeners spanning clinical and signal-processing expertise. The cohort comprised 180 German speakers from CLP, Dysarthria, Dysglossia, Dysphonia, and adult and child controls. Each original recording and its automatically-anonymized counterpart was evaluated on four tasks: zero-shot Turing-style discrimination, few-shot discrimination after brief familiarization, 5-point quality rating, and 4-point blinded clinical severity rating by a senior phoniatrician. Listeners detected anonymization at 91% zero-shot and 93% few-shot accuracy, with significant variation across disorders (p=0.008) that attenuated with familiarization. Perceived quality dropped by 30 ppts on a 0-100 scale (p<0.001), reorganizing the perceived-quality hierarchy across groups. Native language modulated detectability but not quality degradation, while domain expertise modulated quality degradation but not detectability, a double dissociation between the two listener attributes; speaker sex and age produced no detectable bias. Clinical severity ratings were preserved at near-perfect agreement in Dysarthria, Dysglossia, and Dysphonia (quadratic-weighted Cohen's kappa 0.87-0.94), with no recording shifting by more than one grade. Crucially, perceptual outcomes were decoupled from the standard computational privacy metric: the pathology with the strongest computational anonymization was the least perceptually conspicuous, and vice versa. These findings argue for disorder-stratified, listener-stratified, clinician-validated evaluation as the minimum standard for licensing anonymized speech for clinical use.

eess.AS↗

arXiv2026

Safety and accuracy follow different scaling laws in clinical large language models

Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies safer behavior. This assumption is incomplete in medicine, where a few confident, high-risk, or evidence-contradicting errors can matter more than average benchmark performance. We introduce SaFE-Scale, a framework for measuring how clinical LLM safety changes across model scale, evidence quality, retrieval strategy, context exposure, and inference-time compute. To instantiate this framework, we introduce RadSaFE-200, a Radiology Safety-Focused Evaluation benchmark of 200 multiple-choice questions with clinician-defined clean evidence, conflict evidence, and option-level labels for high-risk error, unsafe answer, and evidence contradiction. We evaluated 34 locally deployed LLMs across six deployment conditions: closed-book prompting (zero-shot), clean evidence, conflict evidence, standard RAG, agentic RAG, and max-context prompting. Clean evidence produced the strongest improvement, increasing mean accuracy from 73.5% to 94.1%, while reducing high-risk error from 12.0% to 2.6%, contradiction from 12.7% to 2.3%, and dangerous overconfidence from 8.0% to 1.6%. Standard RAG and agentic RAG did not reproduce this safety profile: agentic RAG improved accuracy over standard RAG and reduced contradiction, but high-risk error and dangerous overconfidence remained elevated. Max-context prompting increased latency without closing the safety gap, and additional inference-time compute produced only limited gains. Worst-case analysis showed that clinically consequential errors concentrated in a small subset of questions. Clinical LLM safety is therefore not a passive consequence of scaling, but a deployment property shaped by evidence quality, retrieval design, context construction, and collective failure behavior.

cs.CL↗

arXiv2026

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification

Self-supervised learning (SSL) has improved visual representation learning, but its value in chest radiography remains uncertain. DINOv3 extends earlier SSL models through Gram-anchored self-distillation and explicit high-resolution adaptation. Whether these changes improve transfer learning for chest radiograph classification has not been established. We benchmarked DINOv3 against DINOv2 and supervised ImageNet initialization across seven chest radiograph datasets comprising 816,183 radiographs from pediatric and adult cohorts. ViT-B/16 and ConvNeXt-B were evaluated under full fine-tuning at 224 and 512 pixels, with targeted 1024 experiments on three cohorts. Additional analyses examined parameter-efficient adaptation, synthetic label corruption, external validation, frozen 7B features, and computational efficiency. The primary outcome was mean AUROC across labels. In adult cohorts, DINOv3 did not consistently outperform DINOv2 at 224 x 224 pixels, but became the strongest initialization at 512 x 512, especially with ConvNeXt-B. Gains were greatest for small focal and boundary-dependent abnormalities, whereas large-structure findings changed little. The pediatric cohort showed no significant benefit from DINOv3, higher resolution, or backbone choice. Scaling to 1024 x 1024 rarely improved performance and markedly increased computational cost. ConvNeXt-B remained superior to ViT-B/16 under both full and parameter-efficient adaptation. External validation preserved the 512 x 512 DINOv3 advantage, whereas synthetic label corruption showed that this benefit should not be interpreted simply as superior noise robustness. For adult chest radiograph classification, DINOv3 provides its most reliable benefit at 512 x 512 pixels, particularly with ConvNeXt-B. Fully adapted mid-sized models at 512 x 512 pixels provided the best performance-cost trade-off in our benchmark.

cs.CV↗

arXiv2026

Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision

Evidence-grounded reasoning requires more than attaching retrieved text to a prediction: a model should make decisions that depend on whether the provided evidence supports the target claim. In practice, this often fails because supervision is weak, evidence is only loosely tied to the claim, and evaluation does not test evidence dependence directly. We introduce case-grounded evidence verification, a general framework in which a model receives a local case context, external evidence, and a structured claim, and must decide whether the evidence supports the claim for that case. Our key contribution is a supervision construction procedure that generates explicit support examples together with semantically controlled non-support examples, including counterfactual wrong-state and topic-related negatives, without manual evidence annotation. We instantiate the framework in radiology and train a standard verifier on the resulting support task. The learned verifier substantially outperforms both case-only and evidence-only baselines, remains strong under correct evidence, and collapses when evidence is removed or swapped, indicating genuine evidence dependence. This behavior transfers across unseen evidence articles and an external case distribution, though performance degrades under evidence-source shift and remains sensitive to backbone choice. Overall, the results suggest that a major bottleneck in evidence grounding is not only model capacity, but the lack of supervision that encodes the causal role of evidence.

cs.CL↗

arXiv2026

Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering

Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and synthesize it into structured reports before answer selection. Although such pipelines can improve performance, their impact on reliability under model variability remains unclear. In real-world deployment, heterogeneous models may align, diverge, or synchronize errors in ways not captured by accuracy. We evaluated 34 LLMs on 169 expert-curated publicly available radiology questions, comparing zero-shot inference with a radiology-specific multi-step agentic retrieval condition in which all models received identical structured evidence reports derived from curated radiology knowledge. Agentic inference reduced inter-model decision dispersion (median entropy 0.48 vs. 0.13) and increased robustness of correctness across models (mean 0.74 vs. 0.81). Majority consensus also increased overall (P<0.001). Consensus strength and robust correctness remained correlated under both strategies (\r{ho}=0.88 for zero-shot; \r{ho}=0.87 for agentic), although high agreement did not guarantee correctness. Response verbosity showed no meaningful association with correctness. Among 572 incorrect outputs, 72% were associated with moderate or high clinically assessed severity, although inter-rater agreement was low (\k{appa}=0.02). Agentic retrieval therefore was associated with more concentrated decision distributions, stronger consensus, and higher cross-model robustness of correctness. These findings suggest that evaluating agentic systems through accuracy or agreement alone may not always be sufficient, and that complementary analyses of stability, cross-model robustness, and potential clinical impact are needed to characterize reliability under model variability.

cs.LG↗

arXiv2026

SteuerLLM: Local specialized large language model for German tax law analysis

Large language models (LLMs) demonstrate strong general reasoning and language understanding, yet their performance degrades in domains governed by strict formal rules, precise terminology, and legally binding structure. Tax law exemplifies these challenges, as correct answers require exact statutory citation, structured legal argumentation, and numerical accuracy under rigid grading schemes. We algorithmically generate SteuerEx, the first open benchmark derived from authentic German university tax law examinations. SteuerEx comprises 115 expert-validated examination questions spanning six core tax law domains and multiple academic levels, and employs a statement-level, partial-credit evaluation framework that closely mirrors real examination practice. We further present SteuerLLM, a domain-adapted LLM for German tax law trained on a large-scale synthetic dataset generated from authentic examination material using a controlled retrieval-augmented pipeline. SteuerLLM (28B parameters) consistently outperforms general-purpose instruction-tuned models of comparable size and, in several cases, substantially larger systems, demonstrating that domain-specific data and architectural adaptation are more decisive than parameter scale for performance on realistic legal reasoning tasks. All benchmark data, training datasets, model weights, and evaluation code are released openly to support reproducible research in domain-specific legal artificial intelligence. A web-based demo of SteuerLLM is available at https://steuerllm.i5.ai.fau.de.

cs.CL↗

arXiv2025

Multi-step retrieval and reasoning improves radiology question answering with large language models

Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (RAG) systems for radiology question answering (QA) typically rely on single-step retrieval, limiting their ability to handle complex clinical reasoning tasks. Here we propose radiology Retrieval and Reasoning (RaR), a multi-step retrieval and reasoning framework designed to improve diagnostic accuracy, factual consistency, and clinical reliability of LLMs in radiology question answering. We evaluated 25 LLMs spanning diverse architectures, parameter scales (0.5B to >670B), and training paradigms (general-purpose, reasoning-optimized, clinically fine-tuned), using 104 expert-curated radiology questions from previously established RSNA-RadioQA and ExtendedQA datasets. To assess generalizability, we additionally tested on an unseen internal dataset of 65 real-world radiology board examination questions. RaR significantly improved mean diagnostic accuracy over zero-shot prompting and conventional online RAG. The greatest gains occurred in small-scale models, while very large models (>200B parameters) demonstrated minimal changes (<2% improvement). Additionally, RaR retrieval reduced hallucinations (mean 9.4%) and retrieved clinically relevant context in 46% of cases, substantially aiding factual grounding. Even clinically fine-tuned models showed gains from RaR (e.g., MedGemma-27B), indicating that retrieval remains beneficial despite embedded domain knowledge. These results highlight the potential of RaR to enhance factuality and diagnostic accuracy in radiology QA, warranting future studies to validate their clinical utility. All datasets, code, and the full RaR framework are publicly available to support open research and clinical translation.

cs.CL↗

arXiv2025

Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications

Differential privacy (DP) is a key technique for protecting sensitive patient data in medical deep learning (DL). As clinical models grow more data-dependent, balancing privacy with utility and fairness has become a critical challenge. This scoping review synthesizes recent developments in applying DP to medical DL, with a particular focus on DP-SGD and alternative mechanisms across centralized and federated settings. Using a structured search strategy, we identified 74 studies published up to March 2025. Our analysis spans diverse data modalities, training setups, and downstream tasks, and highlights the tradeoffs between privacy guarantees, model accuracy, and subgroup fairness. We find that while DP-especially at strong privacy budgets-can preserve performance in well-structured imaging tasks, severe degradation often occurs under strict privacy, particularly in underrepresented or complex modalities. Furthermore, privacy-induced performance gaps disproportionately affect demographic subgroups, with fairness impacts varying by data type and task. A small subset of studies explicitly addresses these tradeoffs through subgroup analysis or fairness metrics, but most omit them entirely. Beyond DP-SGD, emerging approaches leverage alternative mechanisms, generative models, and hybrid federated designs, though reporting remains inconsistent. We conclude by outlining key gaps in fairness auditing, standardization, and evaluation protocols, offering guidance for future work toward equitable and clinically robust privacy-preserving DL systems in medicine.

cs.LG↗

arXiv2025

Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations

Reliable artificial intelligence (AI) models for medical image analysis often depend on large and diverse labeled datasets. Federated learning (FL) offers a decentralized and privacy-preserving approach to training but struggles in highly non-independent and identically distributed (non-IID) settings, where institutions with more representative data may experience degraded performance. Moreover, existing large-scale FL studies have been limited to adult datasets, neglecting the unique challenges posed by pediatric data, which introduces additional non-IID variability. To address these limitations, we analyzed n=398,523 adult chest radiographs from diverse institutions across multiple countries and n=9,125 pediatric images, leveraging transfer learning from general-purpose self-supervised image representations to classify pneumonia and cases with no abnormality. Using state-of-the-art vision transformers, we found that FL improved performance only for smaller adult datasets (P<0.001) but degraded performance for larger datasets (P<0.064) and pediatric cases (P=0.242). However, equipping FL with self-supervised weights significantly enhanced outcomes across pediatric cases (P=0.031) and most adult datasets (P<0.008), except the largest dataset (P=0.052). These findings underscore the potential of easily deployable general-purpose self-supervised image representations to address non-IID challenges in clinical FL applications and highlight their promise for enhancing patient outcomes and advancing pediatric healthcare, where data scarcity and variability remain persistent obstacles.

cs.CV↗