Medmain Inc. launches “PidPort”, A Digital Pathology Platform

Medmain Inc. a Japanese health tech startup has launched its service “PidPort, a platform service for pathological image diagnosis, which includes Deep Learning driven pathological analysis*.

*The ”pathological analysis” function is only available for use in selected countries.

▶ Worldwide pathologist shortage

“Pathologists” are physicians who specialize in the study of body tissue to see if it is normal or abnormal. They identify diseases by examining cells and tissues under a microscope.

Pathologists play important roles in the medical field since most of medical decisions rely on Pathology.

Although globally, there is a chronic shortage of pathologists and is getting more serious.

In some countries, it even takes for a few months for patients to receive pathological diagnostic results.

This is why expectations on computational pathology techniques based on AI has been in more demand than ever before.

▶ Our paper about the development of AI Pathological Classification

First, our team has successfully developed an AI model for pathological classification.This is described in our manuscript entitled*“Deep learning models for histopathological classification of gastric and colonic epithelial tumours”*published in authoritative***Scientific Reports***, a journal of the*Nature Research*on Jan 30th 2020.

Medmain developed deep learning models that can detect and discriminate epithelial tumours in biopsy specimen whole slide images of stomach and colon with over 4000 dataset each.

AUC*(Area Under Curve) ,a metric for binary classification which is used to measure accuracy in machine learning achieved up to 0.97 and 0.99 for gastric adenocarcinoma and adenoma, respectively, and 0.96 and 0.99 for colonic adenocarcinoma and adenoma respectively.

The study concluded that the classification accuracy done by the AI model is high enough to be deployed in actual medical sites and to be utilized as a screening tool for histology judgment, as well as a double-check tool.

(*AUC ranges in value from 0 to 1. A model whose predictions are 100% wrong has an AUC of 0.0; one whose predictions are 100% correct has an AUC of 1.0.)

“Deep learning models for histopathological classification of gastric and colonic epithelial tumours”

by Koji Arihiro M.D., Ph.D. and Kei Kato from Hiroshima University along with Medmain members Osamu Iizuka, Fahdi Kanavati, Michael Rambeau, Masayuki Tsuneki

www.nature.com/articles/s41598-020-58467-9

DOI: 10.1038/s41598-020-58467-9

Pubmed link:https://www.ncbi.nlm.nih.gov/pubmed/32001752

▶About our service “PidPort”

We developed the service”PidPort”. It is a platform service for pathological image diagnosis, which includes Deep Learning driven immediate pathological analysis.

PidPort has been designed to be used with ease for healthcare professionals and pathologists. As long as there is Internet connection, our cloud service can be accessed any time, without any initial fee such as the introduction of equipments.

Additionally, by concurrently utilizing our pathology specimen slide digitization service (Medmain Imaging Center), we provide a total digital pathology solution from specimen slide digitization to storage to diagnosis.

We have already developed AI screening models for histopathological evaluation to differentiate among malignant epithelial tumor, benign epithelial tumor, and non-neoplastic lesions in stomach, colon, and breast specimens as well as cytopathological evaluation to determine neoplastic cells in uterine cervix and urine liquid-based cytology (LBC) specimens.

We will continue developing AI models on other organs and tissues.

We hope this will assist and alleviate medical practitioners’ harsh daily workflow.

By leveraging the power of technology, we aim to create a society where everyone can attain immediate high standard pathological diagnosis.