eess.IVNov 9, 2026

Is a CNN-Transformer Ensemble Worth It When a Chest X-Ray Foundation Model Is Available?

Authors: Aditya Seelaboyina, Irfan Khan

Organizations: Department of Computer Science and Engineering Texas A&M University College Station, TX, USA · Department of Marine Engineering Technology, in a courtesy joint appointment with the Department of Electrical & Computer Engineering Texas A&M University, TX, USA

Abstract

Ensembles of ImageNet-pretrained convolutional networks and Vision Transformers are a common way to improve multi-label chest X-ray classification. We ask whether such an ensemble is still worth its cost when a model pretrained on chest radiographs is available. On the official patient-disjoint split of NIH ChestX-ray14 (25,596 test images, 2,797 patients), we train five ImageNet-pretrained backbones and the EVA-X-S foundation model with validation-only model selection, compare five fusion rules, and estimate every difference with a patient-level paired bootstrap. EVA-X-S alone reached a test macro-AUROC of 0.828; the five-model ensemble reached 0.814 (difference -0.0136, 95% CI -0.0178 to -0.0098) at about 7.8 times the summed backbone latency and ten times the parameters. Averaging the five ImageNet models with EVA-X-S changed AUROC by -0.0056 (-0.0095 to -0.0021). With all five ImageNet backbones trained with the EVA-X-S recipe, their ensemble scored 0.817, still -0.0109 (-0.0142 to -0.0076) below EVA-X-S, and across three seeds EVA-X-S varied by at most 0.001 AUROC. Under the ImageNet models' recipe, however, EVA-X-S fell to 0.798. Our full-stacking configuration never outperformed calibrated averaging. In this setting, the tested ImageNet ensembles did not improve on a single chest X-ray foundation model fine-tuned with its own recipe.

Figures & tables

Explore similar work

Jun 10, 2026

Frozen Foundation-Model Embeddings Discard Small-Lesion Signal in Chest Radiography: Implications for Pre-Deployment Evaluation

Frozen vision-transformer (ViT) foundation-model embeddings increasingly serve as the substrate for downstream chest-radiography (CXR) pipelines, yet where small-scale, low-contrast signal is retained or lost in the frozen forward pass has not been systematically quantified across architectures, pretraining domains, and objectives. We probed five frozen ViTs (RAD-DINO, DINOv2-B/14, DINOv3 ViT-7B, BiomedCLIP, MedSigLIP) and a frozen DINO-pretrained ResNet-50 architectural control across three large CXR cohorts (NIH-CXR14, MIMIC-CXR, Emory-CXR; aggregate pool n=492,724) and ChestX-Det10 (n=3,543; 1,462 small-lesion bounding boxes across Calcification, Nodule, Mass). Each model was evaluated with a small-scale-perturbation panel and a region-aware bounding-box-stratified probe on real lesions, comparing three pooling modes from the same forward pass: classification token (CLS), patch-mean (mean over all final-layer patch tokens), and bounding-box-restricted patch-local. On the perturbation panel, CLS embeddings sat at the chance floor (area under the ROC curve [AUC] 0.500-0.524); patch-mean was indistinguishable from CLS on iso-blur and reticular-fine cells but rose with CLS on larger directional-blur footprints, while disease AUC on globally decided tasks ranged 0.642-0.913. Patch-local probes recovered AUC ~1.0 from the same forward pass (per-model mean improvement +0.412 to +0.488); the ResNet-50 control reproduced the chance floor. On ChestX-Det10, image-level CLS classification showed within-class small-versus-large stratum gaps up to +0.243 AUC; bounding-box-level patch-local pooling on the same forward pass recovered AUC >= 0.899 on every (model x class) cell. Frozen ViT embeddings silently suppress small-scale signal at the global-aggregation step; the signal is recoverable from patch tokens conditional on a region of interest.
Feb 26, 2026

A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling

Foundation models for medical imaging are typically pretrained on increasingly large datasets, following a "scale-at-all-costs" paradigm. However, this strategy faces two critical challenges: large-scale medical datasets often contain substantial redundancy and severe class imbalance that bias representation learning toward over-represented patterns, and indiscriminate training regardless of heterogeneity in data quality incurs considerable computational inefficiency. Here we demonstrate that active, principled data curation during pretraining can serve as a viable, cost-effective alternative to brute-force dataset enlargement. We introduce CheXficient, a chest X-ray (CXR) foundation model that selectively prioritizes informative training samples. CheXficient is pretrained on only 22.7% of 1,235,004 paired CXR images and reports while consuming under 27.3% of the total compute budget, yet achieving comparable or superior performance to its full-data counterpart and other large-scale pretrained models. We assess CheXficient across 20 individual benchmarks spanning 5 task types, including non-adapted off-the-shelf evaluations (zero-shot findings classification and crossmodal retrieval) and adapted downstream tasks (disease prediction, semantic segmentation, and radiology report generation). Further analyses show that CheXficient systematically prioritizes under-represented training samples, improving generalizability on long-tailed or rare conditions. Overall, our work offers practical insights into the data and computation demands for efficient pretraining and downstream adaptation of medical vision-language foundation models.
Jun 16, 2026

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.