Artificial Intelligence Solutions for Analysis of X-ray Images

Abstract

Artificial intelligence (AI) presents a key opportunity for radiologists to improve quality of care and enhance the value of radiology in patient care and population health. The potential opportunity of AI to aid in triage and interpretation of conventional radiographs (X-ray images) is particularly significant, as radiographs are the most common imaging examinations performed in most radiology departments. Substantial progress has been made in the past few years in the development of AI algorithms for analysis of chest and musculoskeletal (MSK) radiographs, with deep learning now the dominant approach for image analysis. Large public and proprietary image data sets have been compiled and have aided the development of AI algorithms for analysis of radiographs, many of which demonstrate accuracy equivalent to radiologists for specific, focused tasks. This article describes (1) the basis for the development of AI solutions for radiograph analysis, (2) current AI solutions to aid in the triage and interpretation of chest radiographs and MSK radiographs, (3) opportunities for AI to aid in noninterpretive tasks related to radiographs, and (4) considerations for radiology practices selecting AI solutions for radiograph analysis and integrating them into existing IT systems. Although comprehensive AI solutions across modalities have yet to be developed, institutions can begin to select and integrate focused solutions which increase efficiency, increase quality and patient safety, and add value for their patients.

Pediatric chest radiograph interpretation: how far has artificial intelligence come? A systematic literature review

“…While commercial software is increasingly becoming available for adult imaging, our review highlights that progress for pediatric chest radiographs interpretation lags. Many commercially available United States Food and Drug Administration (FDA) approved/cleared tools are not at this time applicable to pediatric populations [ 97 , 98 ]. In addition to common use cases such as pneumonia detection, there are a number of distinct use cases for AI development in pediatric imaging, such as neonatal catheter and tube assessment and cystic fibrosis scoring.…”

UK reporting radiographers’ perceptions of AI in radiographic image interpretation – Current perspectives and future developments

“…9 Computers have been used in image interpretation for many years, however new systems using advanced technologies are now more prevalent clinically, enabling improved performance with reduced false positive rates compared with earlier human programmed machines. 10,11 However, the complexity of these systems mean that the system processes are not transparent, sometimes even to the developer. 12,13 Computer vision A paradigm shift in computer vision occurred in 2012 when a convolutional neural network (CNN) won the ImageNet challenge for identification of common objects, far outperforming its next nearest competitor.…”

“…This demand, coupled with the availability and relative simplicity of plain radiographic images may mean that this area will be targeted for continued development of AI systems. 10 International consensus among radiologists is that AI will aid diagnostic accuracy, with systems acting as a second reader. 24,41,42 Reporting radiographer respondents, in contrast, feel that interpretation should remain a mainly human task; perhaps influenced by their professional background of values-based radiography 43 and humanistic models of care assuring that care is tailored to the person during the acquisition of images.…”

Technology of the Surround

“…Unambiguous category membership has its virtues-for example, when aimed at accurate and speedy identification of pneumonia in a lung X-ray (Adams et al 2020). But in other contexts, particularly ones steeped in historical exclusions and harm, supervised learning produces a deficit, borrowing from the past to convene the future.…”