Artificial Intelligence–Based Screening for Mycobacteria in Whole-Slide Images of Tissue Samples

Abstract

Objectives This study aimed to develop and validate a deep learning algorithm to screen digitized acid fast–stained (AFS) slides for mycobacteria within tissue sections. Methods A total of 441 whole-slide images (WSIs) of AFS tissue material were used to develop a deep learning algorithm. Regions of interest with possible acid-fast bacilli (AFBs) were displayed in a web-based gallery format alongside corresponding WSIs for pathologist review. Artificial intelligence (AI)–assisted analysis of another 138 AFS slides was compared to manual light microscopy and WSI evaluation without AI support. Results Algorithm performance showed an area under the curve of 0.960 at the image patch level. More AI-assisted reviews identified AFBs than manual microscopy or WSI examination (P < .001). Sensitivity, negative predictive value, and accuracy were highest for AI-assisted reviews. AI-assisted reviews also had the highest rate of matching the original sign-out diagnosis, were less time-consuming, and were much easier for pathologists to perform (P < .001). Conclusions This study reports the successful development and clinical validation of an AI-based digital pathology system to screen for AFBs in anatomic pathology material. AI assistance proved to be more sensitive and accurate, took pathologists less time to screen cases, and was easier to use than either manual microscopy or viewing WSIs.

A New Artificial Intelligence-Based Method for Identifying Mycobacterium Tuberculosis in Ziehl–Neelsen Stain on Tissue

“…Its positive component is almost 3 times bigger than the next largest one (263,000 positive patches in ours vs. 96,530 in Xiong et al’s dataset [ 15 ]), which is 429 times bigger than the smallest ones (506 in Zaizen et al’s set [ 20 ]). Our negative patches are 7 times more numerous than the second largest one of Pantanowitz et al [ 18 ] (7,000,000 vs. 1,111,918). Further applied augmentation techniques (both as position—rotations, shifts, crops, etc.—and in image properties—brightness, contrast, saturation, etc.)…”

“…Its validation is solely made on patches. Xiong et al [ 15 ] present a completely automated method of diagnosis while Yang et al [ 16 ], Pantanowitz et al [ 18 ], and Zaizen et al [ 19 ] developed AI-assisted diagnostic methods as a tool in the hands (and eyes) of pathologists. In Yang et al’s method, the pathologist evaluates a score heatmap superposed on the WSI.…”

“…There are other studies published on automatic AFB detection on tissue using WSIs [ 15 , 16 , 17 , 18 , 19 ]. Analyzing tissue is more difficult than analyzing smears.…”

“…Pantanowitz et al (2021) [ 18 ] developed an algorithm based on a dataset created from 441 slides scanned with two types of scanners: Aperio AT2 (Leica Biosystems) and Hamamatsu Nanozoomer XR. The dataset included 1,117,586 patches (5678 positive and 1,111,918 negative) selected from 441 WSIs (62 positive and 379 negative) and was separated in three groups: the dataset used for training consisting of 1,054,395 patches (4629 positive and 1,049,766 negative) selected from 418 slides (47 positive and 371 negative); the dataset used for analytical validation (40,957 patches (449 positive and 40,508 negative) selected from 12 WSIs (9 positive and 3 negative)); and the dataset used for testing (22,244 patches (600 positive and 21,644 negative) selected from 11 WSIs (6 positive and 5 negative)).…”

Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests

“…However, this study detected AFB using comprehensive AI screening despite negative results when AI was not used. Notably, Pantanowitz et al reported easier diagnosis using AI-assisted review, due to its higher sensitivity, negative predictive value, and accuracy compared with light microscopy and WSI evaluation without AI [24]. The current study showed that pathological diagnosis may be better at detecting AFB than traditionally indicated.…”