Published by Histopathology
2023 Nov;83(5):771-781
Helicobacter pylori (HP) infection is the most common cause of chronic gastritis worldwide. Due to the small size of HP and limited resolution, diagnosing HP infections is more difficult when using digital slides.
This study aimed to develop a two-tier deep-learning-based model for diagnosing HP gastritis. The whole-slide model was trained on 885 whole-slide images (WSIs) with only slide-level labels (positive or negative slides). Additionally, an auxiliary model was trained on 824 areas with HP in nine positive WSIs and 446 negative WSIs for localizing HP.
The whole-slide model performed well, with an area under the receiver operating characteristic curve (AUC) of 0.9739 (95% confidence interval [CI], 0.9545–0.9932). The calculated sensitivity and specificity were 93.3% and 90.1%, respectively, whereas those of pathologists were 93.3% and 84.2%, respectively. Using the auxiliary model, the highlighted areas of the localization maps had an average precision of 0.5796.
HP gastritis can be diagnosed on haematoxylin-and-eosin-stained WSIs with human-level accuracy using a deep-learning-based model trained on slide-level labels and an auxiliary model for localizing HP and confirming the diagnosis. This two-tiered model can shorten the diagnostic process and reduce the need for special staining.
Graphical Abstract
We developed a whole-slide model for predicting Helicobacter pylori (HP) diagnosis and an auxiliary model for HP localization. This two-tiered diagnosis model can achieve human-level accuracy, shorten the time for diagnosis, and reduce the need for special staining.
Figure 2. Examples of key morphologic features for classifying Helicobacter pylori (HP) gastritis in the 59 magnified whole-slide image (WSI) model. (A–D) An example of HP-positive gastritis. (A) The original WSI. (B) Using class activation mapping, the relatively important areas for the positive predication of HP gastritis are highlighted in red. (C,D) A high-power view (C) and its highlighted areas (D) showed the WSI model classified gastritis images mainly based on the inflammation pattern. (E–H) An example of HP-negative gastritis. (G) and (H) are the high-power view and its highlighted areas.
Full Article: https://onlinelibrary.wiley.com/doi/10.1111/his.15018
Commenti