Pulmonary Abnormality Screening on Chest X-Rays from Different Machine Specifications: A Generalized AI-Based Image Manipulation Pipeline

Published

European Radiology Experimental, 2023, 7.1: 68

Authors

Heejun Shin¹, Taehee Kim¹, Juhyung Park², Hruthvik Raj¹, Muhammad Shahid Jabbar¹,
Zeleke Desalegn Abebaw¹, Jongho Lee², Cong Cung Van³, Hyungjin Kim⁴, and Dongmyung Shin¹

Affiliations

¹Artifcial Intelligence Engineering Division, RadiSen Co., Ltd, Seoul, Korea.
²Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea.
³Department of Radiology, National Lung Hospital, Hanoi, Vietnam.
⁴Department of Radiology, Seoul National University Hospital, Seoul, Korea.

Background

Chest x-ray is commonly used for pulmonary abnormality screening. However, since the image characteristics of x-rays highly depend on the machine specifcations, an artifcial intelligence (AI) model developed for specifc equipment usually fails when clinically applied to various machines. To overcome this problem, we propose an image manipulation pipeline.

Methods

A total of 15,010 chest x-rays from systems with diferent generators/detectors were retrospectively collected from fve institutions from May 2020 to February 2021. We developed an AI model to classify pulmonary abnormalities using x-rays from a single system. Then, we externally tested its performance on chest x-rays from various machine specifcations. We compared the area under the receiver operating characteristics curve (AUC) of AI models
developed using conventional image processing pipelines (histogram equalization [HE], contrast-limited histogram equalization [CLAHE], and unsharp masking [UM] with common data augmentations) with that of the proposed manipulation pipeline (XM-pipeline).

Results

The XM-pipeline model showed the highest performance for all the datasets of diferent machine specifcations, such as chest x-rays acquired from a computed radiography system (n=356, AUC 0.944 for XM-pipeline versus 0.917 for HE, 0.705 for CLAHE, 0.544 for UM, p≤ 0.001, for all) and from a mobile x-ray generator (n=204, AUC 0.949
for XM-pipeline versus 0.933 for HE, p=0.042, 0.932 for CLAHE (p=0.009), 0.925 for UM (p=0.001).

Conclusions

Applying the XM-pipeline to AI training increased the diagnostic performance of the AI model
on the chest x-rays of diferent machine confgurations.