Impact of a content-based image retrieval system on the interpretation of chest CTs of patients with diffuse parenchymal lung disease

Abstract

Objectives: Content-based image retrieval systems (CBIRS) are a new and potentially impactful tool for radiological reporting, but their clinical evaluation is largely missing. This study aimed at assessing the effect of CBIRS on the interpretation of chest CT scans from patients with suspected diffuse parenchymal lung disease (DPLD).

Materials and methods: A total of 108 retrospectively included chest CT scans with 22 unique, clinically and/or histopathologically verified diagnoses were read by eight radiologists (four residents, four attending, median years reading chest CT scans 2.1± 0.7 and 12 ± 1.8, respectively). The radiologists read and provided the suspected diagnosis at a certified radiological workstation to simulate clinical routine. Half of the readings were done without CBIRS and half with the additional support of the CBIRS. The CBIRS retrieved the most likely of 19 lung-specific patterns from a large database of 6542 thin-section CT scans and provided relevant information (e.g., a list of potential differential diagnoses).

Results: Reading time decreased by 31.3% (p < 0.001) despite the radiologists searching for additional information more frequently when the CBIRS was available (154 [72%] vs. 95 [43%], p < 0.001). There was a trend towards higher overall diagnostic accuracy (42.2% vs 34.7%, p = 0.083) when the CBIRS was available.

Conclusion: The use of the CBIRS had a beneficial impact on the reading time of chest CT scans in cases with DPLD. In addition, both resident and attending radiologists were more likely to consult informational resources if they had access to the CBIRS. Further studies are needed to confirm the observed trend towards increased diagnostic accuracy with the use of a CBIRS in practice.

Key points: • A content-based image retrieval system for supporting the diagnostic process of reading chest CT scans can decrease reading time by 31.3% (p < 0.001). • The decrease in reading time was present despite frequent usage of the content-based image retrieval system. • Additionally, a trend towards higher diagnostic accuracy was observed when using the content-based image retrieval system (42.2% vs 34.7%, p = 0.083).

Keywords: Artificial intelligence; Diagnosis, Computer assisted; Lung diseases, Interstitial; Tomography, X-ray computed.

Fig. 1

Left: exclusion and inclusion criteria. Right: distribution of cases — 108 distinct cases were distributed to 8 participants (4 junior and 4 senior radiologists), balancing out diseases between sets, where possible. Each participant read 54 distinct cases (27 during baseline and intervention phase). This way, each case was read 4 times (2 times during each phase) resulting in a total of 432 readings. Each of the 27-case sets included 2 cases without pathological lung findings. The sets were randomly assigned to the radiologists. Participants were allowed to use their own means of information gathering (internet, books, etc.) during both phases with the addition of the CBIR system as an option during the intervention phase. DLPD, diffuse parenchymal lung disease; CBIRS, content-based image retrieval system

Fig. 2

The content-based image retrieval system (CBIRS), which was used during the intervention phase, is a web application executable from the local picture archiving and communication system (PACS). (1) The radiologist initiates the search for similar cases by drawing a ROI in the current CT scan. (2) A heatmap visualizes and quantifies the distribution of one of 19 selectable lung patterns for the current scan. (3) Similar cases based on the 3 most predominant patterns in the ROI are shown arranged according to the highest lung pattern classification probability. Choosing one case leads to: (4) more detailed information from the visually similar case. (5) Content relevant to the predominant pattern is presented as a list of differential diagnoses with links to the respective Radiopaedia [2] page, tips and pitfalls for the patterns and additional in-product content for differential diagnoses

Fig. 3

Modeled overall reading time during baseline and intervention phase in seconds with 95% confidence intervals