Deep learning for sensitive detection of Helicobacter Pylori in gastric biopsies

Abstract

Background Helicobacter pylori, a 2 × 1 μm spiral-shaped bacterium, is the most common risk factor for gastric cancer worldwide. Clinically, patients presenting with symptoms of gastritis, routinely undergo gastric biopsies. The following histo-morphological evaluation dictates therapeutic decisions, where antibiotics are used for H. pylori eradication. There is a strong rational to accelerate the detection process of H. pylori on histological specimens, using novel technologies, such as deep learning. Methods We designed a deep-learning-based decision support algorithm that can be applied on regular whole slide images of gastric biopsies. In detail, we can detect H. pylori both on Giemsa- and regular H&E stained whole slide images. Results With the help of our decision support algorithm, we show an increased sensitivity in a subset of 87 cases that underwent additional PCR- and immunohistochemical testing to define a sensitive ground truth of HP presence. For Giemsa stained sections, the decision support algorithm achieved a sensitivity of 100% compared to 68.4% (microscopic diagnosis), with a tolerable specificity of 66.2% for the decision support algorithm compared to 92.6 (microscopic diagnosis). Conclusion Together, we provide the first evidence of a decision support algorithm proving as a sensitive screening option for H. pylori that can potentially aid pathologists to accurately diagnose H. pylori presence on gastric biopsies.

State of machine and deep learning in histopathological applications in digestive diseases

“…Klein et al [ 45 ] developed a model that combines image processing techniques with DL. The authors utilized image processing techniques on both Giemsa- and HE-stained slides to identify potential Helicobacter pylori regions, then had experts review these as being positive or negative for Helicobacter pylori presence.…”

Role of artificial intelligence in multidisciplinary imaging diagnosis of gastrointestinal diseases

“…H. pylori cells can be visualized in histology sections of gastric biopsy samples using different staining techniques, such as H&E, Giemsa or Warthin-Starry silver stains (Figure 6 ). Klein et al [ 82 ] published a DL algorithm for automatic H. pylori screening in Giemsa stains, with a sensitivity of 100% and a specificity of 66%[ 82 ]. In parallel, Zhou et al [ 83 ] used a CNN to assist pathologists in the detection of H. pylori cells in H&E-stained WSI, but failed to demonstrate significant improvements in diagnostic accuracy and turnaround times in comparison with unassisted case studies[ 83 ].…”

Shifting Gears in Precision Oncology—Challenges and Opportunities of Integrative Data Analysis

“…Detection of cancer traits, including relevant prognostic information, molecular subtypes and even origins of cancers have been proposed as proof-of-concepts using regular H&E brightfield images [86][87][88][89]. Images may be used to detect cellular features, like cell types and (anatomical) structures, that may be illustrated to a human reader or provided as prognostic biomarkers or as decision support algorithms [90,91]. What seems especially interesting is that the visual confirmation of results is of high interest to specialties like pathology, to mimic their working routine of interpretation of histological images [92].…”