Use of digital pathology and artificial intelligence for the diagnosis of Helicobacter pylori in gastric biopsies

Abstract

Summary Objective A common source of concern about digital pathology (DP) is that limited resolution could be a reason for an increased risk of malpractice. A frequent question being raised about this technology is whether it can be used to reliably detect Helicobacter pylori (HP) in gastric biopsies, which can be a significant burden in routine work. The main goal of this work is to show that a reliable diagnosis of HP infection can be made by DP even at low magnification. The secondary goal is to demonstrate that artificial intelligence (AI) algorithms can diagnose HP infections on virtual slides with sufficient accuracy. Methods The method we propose is based on the Warthin-Starry (W-S) silver stain which allows faster detection of HP in virtual slides. A software tool, based on regular expressions, performed a specific search to select 679 biopsies on which a W-S stain was done. From this dataset 185 virtual slides were selected to be assessed by WSI and compared with microscopy slide readings. To determine whether HP infections could be accurately diagnosed with machine learning. AI was used as a service (AIaaS) on a neural network-based web platform trained with 468 images. A test dataset of 210 images was used to assess the classifier performance. Results In 185 gastric biopsies read with DP we recorded only 4 false positives and 4 false negatives with an overall agreement of 95.6%. Compared with microscopy, defined as the “gold standard” for the diagnosis of HP infections, WSI had a sensitivity and specificity of 0.95 and 0.96, respectively. The ROC curve of our AI classifier generated on a testing dataset of 210 images had an AUC of 0.938. Conclusions This study demonstrates that DP and AI can be used to reliably identify HP at 20X resolution.

Two‐tiered deep‐learning‐based model for histologic diagnosis of Helicobacter gastritis

“…Liscia et al . used regular expressions to select cases on which a Warthin–Starry stain was done and developed an algorithm based on WSIs 12 . This AI classifier on 210 WSIs had an AUC of 0.938.…”

“…Deeplearning-based algorithms help identify HP in WSI. 12,13 These algorithms have high accuracy in identifying HP in Warthin-Starry and Giemsa stains. However, the performance on H&E slides is not satisfactory enough.…”

“…Therefore, identifying and differentiating HP from their mimics are more difficult in WSI. Deep‐learning‐based algorithms help identify HP in WSI 12,13 . These algorithms have high accuracy in identifying HP in Warthin–Starry and Giemsa stains.…”

Present State and Recent Developments of Artificial Intelligence and Machine Learning in Gastric Cancer Diagnosis and Prognosis: A Systematic Review

“…In a study, it was evident that AI algorithms exhibited superior accuracy in diagnosing HP infections on digital pathology images compared to traditional methods. This suggests promising prospects for integrating AI-driven diagnostic tools in pathology practices, particularly for identifying HP infections [7]. Additionally, detecting chronic atrophic gastritis (CAG) at an early stage is essential to prevent the progression to gastric cancer.…”

Personalized statistical medicine

“…Both these are data-intensive methods and have substantial statistical content. Liscia et al 22 have proposed AI for the diagnosis of Helicobacter pylori in gastric biopsies. Cross and Harding 23 have discussed AI in risk profiling in the treatment of chronic wounds.…”