Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images

Cheng, Yi-Ching; Hung, Yi-Chieh; Huang, Guan-Hua; Chen, Tai-Been; Lu, Nan-Han; Liu, Kuo-Ying; Lin, Kuo-Hsuan

doi:10.3390/diagnostics14232636

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images

by

Yi-Ching Cheng

¹,

Yi-Chieh Hung

¹,

Guan-Hua Huang

^1,*

,

Tai-Been Chen

^2,3,4

,

Nan-Han Lu

⁵

,

Kuo-Ying Liu

⁵

and

Kuo-Hsuan Lin

⁶

¹

Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan

²

Department of Radiological Technology, Faculty of Medical Technology, Teikyo University, Tokyo 173-8605, Japan

³

Infinity Co., Ltd., Taoyuan 320021, Taiwan

⁴

Der Lih Fuh Co., Ltd., Taoyuan 320021, Taiwan

⁵

Department of Radiology, E-Da Cancer Hospital, I-Shou University, Kaohsiung 824005, Taiwan

⁶

Department of Emergency Medicine, E-Da Hospital, I-Shou University, Kaohsiung 824005, Taiwan

^*

Author to whom correspondence should be addressed.

Diagnostics 2024, 14(23), 2636; https://doi.org/10.3390/diagnostics14232636

Submission received: 10 October 2024 / Revised: 15 November 2024 / Accepted: 18 November 2024 / Published: 22 November 2024

(This article belongs to the Special Issue Advances in Medical Image Processing, Segmentation and Classification)

Download Versions Notes

Abstract

Background and Objectives: Chest X-ray (CXR) images are commonly used to diagnose respiratory and cardiovascular diseases. However, traditional manual interpretation is often subjective, time-consuming, and prone to errors, leading to inconsistent detection accuracy and poor generalization. In this paper, we present deep learning-based object detection methods for automatically identifying and annotating abnormal regions in CXR images. Methods: We developed and tested our models using disease-labeled CXR images and location-bounding boxes from E-Da Hospital. Given the prevalence of normal images over diseased ones in clinical settings, we created various training datasets and approaches to assess how different proportions of background images impact model performance. To address the issue of limited examples for certain diseases, we also investigated few-shot object detection techniques. We compared convolutional neural networks (CNNs) and Transformer-based models to determine the most effective architecture for medical image analysis. Results: The findings show that background image proportions greatly influenced model inference. Moreover, schemes incorporating binary classification consistently improved performance, and CNN-based models outperformed Transformer-based models across all scenarios. Conclusions: We have developed a more efficient and reliable system for the automated detection of disease labels and location bounding boxes in CXR images.

Keywords: chest X-rays; deep learning; few-shot object detection; object detection

Share and Cite

MDPI and ACS Style

Cheng, Y.-C.; Hung, Y.-C.; Huang, G.-H.; Chen, T.-B.; Lu, N.-H.; Liu, K.-Y.; Lin, K.-H. Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images. Diagnostics 2024, 14, 2636. https://doi.org/10.3390/diagnostics14232636

AMA Style

Cheng Y-C, Hung Y-C, Huang G-H, Chen T-B, Lu N-H, Liu K-Y, Lin K-H. Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images. Diagnostics. 2024; 14(23):2636. https://doi.org/10.3390/diagnostics14232636

Chicago/Turabian Style

Cheng, Yi-Ching, Yi-Chieh Hung, Guan-Hua Huang, Tai-Been Chen, Nan-Han Lu, Kuo-Ying Liu, and Kuo-Hsuan Lin. 2024. "Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images" Diagnostics 14, no. 23: 2636. https://doi.org/10.3390/diagnostics14232636

APA Style

Cheng, Y. -C., Hung, Y. -C., Huang, G. -H., Chen, T. -B., Lu, N. -H., Liu, K. -Y., & Lin, K. -H. (2024). Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images. Diagnostics, 14(23), 2636. https://doi.org/10.3390/diagnostics14232636

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

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Deep Learning-Based Object Detection Strategies for Disease Detection and Localization in Chest X-Ray Images

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI