Deep learning for sensitive detection of Helicobacter Pylori in gastric biopsies
- PDF / 2,719,169 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 161 Views
Open Access
RESEARCH ARTICLE
Deep learning for sensitive detection of Helicobacter Pylori in gastric biopsies Sebastian Klein1,2*†, Jacob Gildenblat3†, Michaele Angelika Ihle2, Sabine Merkelbach‑Bruse2, Ka‑Won Noh2, Martin Peifer4, Alexander Quaas2 and Reinhard Büttner2*
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 eradi‑ cation. 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 pres‑ ence. 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. Keywords: Artificial intelligence, Deep learning, Convolutional neural networks, Gastric cancer prevention, Screening, Helicobacter pylori Background Helicobacter pylori is a gram-negative bacterium, measuring 2–4 μm in length and 1 μm in width, usually presented in a spiral-shaped structure [1–3]. Clinically, H. pylori has been classified as a WHO class 1 carcinogen and represents the most common cause of gastric *Correspondence: Sebastian.Klein@uk‑koeln.de; Reinhard.Buettner@uk‑koeln.de † Sebastian Klein and Jacob Gildenblat have contributed equally to this works 1 Else‑Kröner‑Forschungskolleg, Clonal Evolution in Cancer, University Hospital Cologne, Cologne, Germany 2 Institute for Pathology, University Hospital Cologne, Cologne, Germany Full list of author information is available at the end of the article
cancer worldwide [4, 5]. Importantly, the vast majority of all gastric cancers outside the cardia arise within H. pylori infected gastric mucosa [6, 7]. It has been shown that eradication of H. pylori can reduce the risk of gastric cancer in both retrospective-, as well as prospective clinical trials [8–10]. Although the incidence of gastric cancer itself is declining in Western countries, the disease is usually diagnosed in late stages, where individuals face a dismal prognosis—due to li
Data Loading...
