# CXR-CMFA: A Cross-Modal Feature Aggregation Network for Chest X-Ray Pathology Classification

DevFeed: [CXR-CMFA: A Cross-Modal Feature Aggregation Network for Chest X-Ray Pathology Classification](<https://devfeed.tech/articles/cxr-cmfa-a-cross-modal-feature-aggregation-network-for-chest-x-ray-pathology-classification-125892.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10174>)

Author: Talukder Hasnat Zadid, Jahin Sultana, Felipe Bochini Brisola, Kishore Roy, Mysha Rahman, Syeda Asrafa Islam, Md. Abdullah-Al-Jubair

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [mlp](<https://devfeed.tech/topics/mlp.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [attention](<https://devfeed.tech/tags/attention.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [report](<https://devfeed.tech/tags/report.md>), [stream](<https://devfeed.tech/tags/stream.md>), [vision-language-models](<https://devfeed.tech/tags/vision-language-models.md>)

## AI overview

CXR-CMFA combines global and local chest X-ray features with radiology-report text for binary pathology classification. EfficientNet-B0 and DenseNet-121 form the visual encoder, while a TF-IDF-MLP encodes reports. DMSAM uses report embeddings to gate visual features, and CGFF assigns per-instance weights to visual and textual contributions. On the provided MIMIC-CXR test split, the paper reports 93.45% accuracy, 99.88% precision, 91.8% recall, 95.7% F1, and 99.19% AUC; it reports four false positives among 984 normal cases. An ablation reports a 22.47 percentage-point AUC gain over a global-image-only variant. The evidence describes benchmark results for binary classification, not broader clinical validation.

## Source excerpt

arXiv:2611.10174v1 Announce Type: cross Abstract: Chest X-ray (CXR) interpretation remains challenging because subtle pathology can be obscured by overlapping anatomy, image-quality variation, and limited visual evidence in isolated radiographs. Although image-only deep learning models provide useful baselines, they discard the complementary diagnostic context available in radiology reports, while large vision-language models can be computationally expensive for practical deployment. This paper presents CXR-CMFA, a lightweight cross-modal feature aggregation network for binary CXR pathology classification. The proposed framework combines a dual-stream visual encoder, using EfficientNet-B0 for global anatomical representation and DenseNet-121 for local pathological detail, with a TF-IDF-MLP report encoder. Two fusion modules integrate these modalities: the Dual-Modal Spatial Attention Module (DMSAM) uses the report embedding to gate global and local visual features, and the Cross-Modal Gated Feature Fusion (CGFF) module learns per-instance weights for visual and textual contributions. Experiments on the MIMIC-CXR benchmark, using the provided train, validation, and test splits, show that CXR-CMFA achieves 93.45% accuracy, 99.88% precision, 91.8% recall, 95.7% F1-score, and 99.19% AUC on the held-out test set. The model produces only four false positives among 984 normal test cases, supporting its suitability for high-specificity screening workflows. An ablation study further demonstrates a 22.47 percentage-point AUC improvement over the global-image-only variant, confirming the value of adaptive cross-modal fusion. These results indicate that compact report-conditioned fusion can provide strong discriminative performance without relying on large pretrained language models.