Next Article in Journal
Interpretable Multi-Cancer Early Detection Using SHAP-Based Machine Learning on Tumor-Educated Platelet RNA
Previous Article in Journal
Multiparametric Quantitative Ultrasound as a Potential Imaging Biomarker for Noninvasive Detection of Nonalcoholic Steatohepatitis: A Clinical Feasibility Study
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Diagnostics
Volume 15
Issue 17
10.3390/diagnostics15172215
diagnostics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset

by
Erdem Yanar
1,*,
Furkan Kutan
2,
Kubilay Ayturan
3,
Uğurhan Kutbay
3,
Oktay Algın
4,
Fırat Hardalaç
3 and
Ahmet Muhteşem Ağıldere
5
1
Department of Healthcare Systems System Engineering, ASELSAN, 06200 Ankara, Turkey
2
Department of Test and Verification Engineering, ASELSAN, 06200 Ankara, Turkey
3
Department of Electrical and Electronics Engineering, Gazi University, 06570 Ankara, Turkey
4
Department of Radiology, Medical Faculty, Ankara University, 06230 Ankara, Turkey
5
Department of Radiology, Faculty of Medicine, Baskent University, 06490 Ankara, Turkey
*
Author to whom correspondence should be addressed.
Diagnostics 2025, 15(17), 2215; https://doi.org/10.3390/diagnostics15172215
Submission received: 23 July 2025 / Revised: 21 August 2025 / Accepted: 27 August 2025 / Published: 1 September 2025
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Versions Notes

Abstract

Background/Objectives: Recent state-of-the-art advances in deep learning have significantly improved diagnostic accuracy in medical imaging, particularly in chest radiograph (CXR) analysis. Motivated by these developments, a comprehensive comparison was conducted to investigate how architectural choices affect performance of 14 deep learning models across Convolutional Neural Networks (CNNs), Transformer-based models, and Mamba-based State Space Models. Methods: These models were trained and evaluated under identical conditions on the NIH ChestX-ray14 dataset, a large-scale and widely used benchmark comprising 112,120 labeled CXR images with 14 thoracic disease categories. Results: It was found that recent hybrid architectures—particularly ConvFormer, CaFormer, and EfficientNet—deliver superior performance in both common and rare pathologies. ConvFormer achieved the highest mean AUROC of 0.841 when averaged across all 14 thoracic disease classes, closely followed by EfficientNet and CaFormer. Notably, AUROC scores of 0.94 for hernia, 0.91 for cardiomegaly, and 0.88 for edema and effusion were achieved by the proposed models, surpassing previously reported benchmarks.Conclusions: These results not only highlight the continued strength of CNNs but also demonstrate the growing potential of Transformer-based architectures in medical image analysis. This work contributes to the literature by providing a unified, state-of-the-art benchmarking of diverse deep learning models, offering valuable guidance for researchers and practitioners developing clinically robust AI systems for radiology.
Keywords: chest X-ray; thoracic disease detection; multi-label classification; transformer architectures; mamba architecture; NIH ChestX-ray14; AUROC evaluation; diagnostic decision support chest X-ray; thoracic disease detection; multi-label classification; transformer architectures; mamba architecture; NIH ChestX-ray14; AUROC evaluation; diagnostic decision support

Share and Cite

MDPI and ACS Style

Yanar, E.; Kutan, F.; Ayturan, K.; Kutbay, U.; Algın, O.; Hardalaç, F.; Ağıldere, A.M. A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset. Diagnostics 2025, 15, 2215. https://doi.org/10.3390/diagnostics15172215

AMA Style

Yanar E, Kutan F, Ayturan K, Kutbay U, Algın O, Hardalaç F, Ağıldere AM. A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset. Diagnostics. 2025; 15(17):2215. https://doi.org/10.3390/diagnostics15172215

Chicago/Turabian Style

Yanar, Erdem, Furkan Kutan, Kubilay Ayturan, Uğurhan Kutbay, Oktay Algın, Fırat Hardalaç, and Ahmet Muhteşem Ağıldere. 2025. "A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset" Diagnostics 15, no. 17: 2215. https://doi.org/10.3390/diagnostics15172215

APA Style

Yanar, E., Kutan, F., Ayturan, K., Kutbay, U., Algın, O., Hardalaç, F., & Ağıldere, A. M. (2025). A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset. Diagnostics, 15(17), 2215. https://doi.org/10.3390/diagnostics15172215

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop