Source: Okayama University (JAPAN), Public Relations Division
For immediate release: 15 July 2019
Okayama University research: Early gastric cancer endoscopic diagnosis system using artificial intelligence

(Okayama, 15 July) Researchers at Okayama University have developed an early gastric cancer endoscopic diagnosis system using artificial intelligence (AI). The details were presented at the Congress of the Japan Gastroenterological Endoscopy Society (JGES), May 31 – June 2, 2019, Tokyo.

According to data released in 2017 by Japan’s Ministry of Health, Labor, gastric cancer ranks third in cancer deaths in Japan: second in men and fourth in women.

Treatment of early-stage gastric cancer includes endoscopic surgery (ESD), which can save the stomach, and surgical procedures that require gastrectomy.

However, although advances in endoscopic treatment technology has led to the early detection of gastric cancer, decisions on whether to use endoscopy treatment or surgery mainly depend on how deep the cancer has invaded the stomach wall. Furthermore, these decisions are made by careful examination of endoscopic images by experienced physicians. At present, there are many cases where endoscopic treatment is performed first where surgery would have been more appropriate and vice versa.

With this background, Professor Yoshiro Kawahara of the Graduate School of Medical and Dental Sciences, Okayama University, and colleagues have developed artificial intelligence (AI)-based endoscope for early detection of gastric cancer. These research results were presented at the 97th Congress of the Japan Gastroenterological Endoscopy Society (JGES), May 31 – June 2, 2019, Tokyo.

First the prototype of the system to obtain the depth of early gastric cancer was constructed with GoogLeNet to match purpose (metastatic learning) by using the image recognition ability of CNN (Convolutional Neural Network) published by Google on numerical analysis software MATLAB.

Next, the researchers used the ResNet, which is a 152-layer convolutional neural network, to conduct intramucosal endoscopic resection among patients treated for early gastric cancer at Okayama University Hospital.

Using endoscopic images of 100 cancers (M group) and 50 submucosal invasion cancers (SM-ESD group) and 50 submucosal invasion cancers (SM-OPE group) who had undergone surgery from the beginning, the researchers built the AI system and verified its diagnostic accuracy.

The diagnostic accuracy of intramucosal cancer by artificial intelligence diagnostic system was sensitivity 82.7%, specificity 63.0%, positive predictive value 69.1%, negative predictive rate 78.4% in image unit, and sensitivity 82.0% in case unit. The specificity was 71.0%, the positive predictive value was 73.9%, and the negative predictive value was 79.8%.

In addition, the correct diagnosis rate for deep-seated diagnosis of early gastric cancer as a combination of intramucosal cancer and submucosal invasion cancer was 72.8% in image units and 76.5% in case units.

Implications of the research
At present, gastroenterological endoscope medical diagnosis and treatment is based on experienced practicing physicians examining images.

As a result, the diagnostic ability of individual doctors varies, and with increases in the number of medical services in the future, there is concern about the possibility of oversight of cancer and increases in misdiagnosis. If automatic diagnosis of digestive tract endoscope images by AI is realized, then ‘automated diagnosis logic’ will be added to endoscope technology for real time diagnosis.

Automatic diagnosis will be possible and it will greatly improve the current status of relying on the diagnostic ability of individual endoscopy physicians.

Reference
Yoshiro Kawahara, Kenta Hamada, Hiroyuki Okada. 97th JGES, Tokyo , 2019 Mar 31.

Correspondence to
Professor Yoshiro Kawahara, M.D., Ph.D.
Department of Practical Gastrointestinal Endoscopy
Okayama University Graduate School of Medicine,
Dentistry, and Pharmaceutical Sciences, 2-5-1,
Shikata-cho, Kita-ku, Okayama 700-8558, Japan.
E-mail: yoshirok(a)md.okayama-u.ac.jp
For inquiries, please contact us by replacing (a) with the @ mark.

Further information
Okayama University
1-1-1 Tsushima-naka , Kita-ku , Okayama 700-8530, Japan
Public Relations and Information Division
E-mail: www-adm (a) adm.okayama-u.ac.jp
For inquiries, please contact us by replacing (a) with the @ mark.
Website: www.okayama-u.ac.jp/index_e.html
Okayama Univ. e-Bulletin: www.okayama-u.ac.jp/user/kouhou/ebulletin/
About Okayama University (You Tube): https://www.youtube.com/watch?v=iDL1coqPRYI
Okayama University Image Movie (You Tube): https://www.youtube.com/watch?v=KU3hOIXS5kk

Okayama University Medical Research Updates （OU-MRU）
The whole volume : OU-MRU (1- )
Vol.1：Innovative non-invasive ‘liquid biopsy’ method to capture circulating tumor cells from blood samples for genetic testing
Vol.2：Ensuring a cool recovery from cardiac arrest
Vol.3：Organ regeneration research leaps forward
Vol.4：Cardiac mechanosensitive integrator
Vol.5：Cell injections get to the heart of congenital defects
Vol.6：Fourth key molecule identified in bone development
Vol.7：Anticancer virus solution provides an alternative to surgery
Vol.8：Light-responsive dye stimulates sight in genetically blind patients
Vol.9：Diabetes drug helps towards immunity against cancer
Vol.10：Enzyme-inhibitors treat drug-resistant epilepsy
Vol.11：Compound-protein combination shows promise for arthritis treatment
Vol.12：Molecular features of the circadian clock system in fruit flies
Vol.13：Peptide directs artificial tissue growth
Vol.14：Simplified boron compound may treat brain tumours
Vol.15：Metamaterial absorbers for infrared inspection technologies
Vol.16：Epigenetics research traces how crickets restore lost limbs
Vol.17：Cell research shows pathway for suppressing hepatitis B virus
Vol.18：Therapeutic protein targets liver disease
Vol.19：Study links signalling protein to osteoarthritis
Vol.20：Lack of enzyme promotes fatty liver disease in thin patients
Vol.21：Combined gene transduction and light therapy targets gastric cancer
Vol.22：Medical supportive device for hemodialysis catheter puncture
Vol.23：Development of low cost oral inactivated vaccines for dysentery
Vol.24：Sticky molecules to tackle obesity and diabetes
Vol.25：Self-administered aroma foot massage may reduce symptoms of anxiety
Vol.26：Protein for preventing heart failure
Vol.27：Keeping cells in shape to fight sepsis
Vol.28：Viral-based therapy for bone cancer
Vol.29：Photoreactive compound allows protein synthesis control with light
Vol.30：Cancer stem cells’ role in tumor growth revealed
Vol.31：Prevention of RNA virus replication
Vol.32：Enzyme target for slowing bladder cancer invasion
Vol.33：Attacking tumors from the inside
Vol.34：Novel mouse model for studying pancreatic cancer
Vol.35：Potential cause of Lafora disease revealed
Vol.36：Overloading of protein localization triggers cellular defects
Vol.37：Protein dosage compensation mechanism unravelled
Vol.38：Bioengineered tooth restoration in a large mammal
Vol.39：Successful test of retinal prosthesis implanted in rats
Vol.40：Antibodies prolong seizure latency in epileptic mice
Vol.41：Inorganic biomaterials for soft-tissue adhesion
Vol.42：Potential drug for treating chronic pain with few side effects
Vol.43：Potential origin of cancer-associated cells revealed
Vol.44：Protection from plant extracts
Vol.45：Link between biological-clock disturbance and brain dysfunction uncovered
Vol.46：New method for suppressing lung cancer oncogene
Vol.47：Candidate genes for eye misalignment identified
Vol.48：Nanotechnology-based approach to cancer virotherapy
Vol.49：Cell membrane as material for bone formation
Vol.50：Iron removal as a potential cancer therapy
Vol.51：Potential of 3D nanoenvironments for experimental cancer
Vol.52：A protein found on the surface of cells plays an integral role in tumor growth and sustenance
Vol.53：Successful implantation and testing of retinal prosthesis in monkey eyes with retinal degeneration
Vol.54：Measuring ion concentration in solutions for clinical and environmental research
Vol.55：Diabetic kidney disease: new biomarkers improve the prediction of the renal prognosis
Vol.56：New device for assisting accurate hemodialysis catheter placement
Vol.57：Possible link between excess chewing muscle activity and dental disease
Vol.58：Insights into mechanisms governing the resistance to the anti-cancer medication cetuximab
Vol.59：Role of commensal flora in periodontal immune response investigated
Vol.60：Role of commensal microbiota in bone remodeling
Vol.61：Mechanical stress affects normal bone development
Vol.62：3D tissue model offers insights into treating pancreatic cancer
Vol.63：Promising biomarker for vascular disease relapse revealed
Vol.64：Inflammation in the brain enhances the side-effects of hypnotic medication
Vol.65：Game changer: How do bacteria play Tag ?
Vol.66：Is too much protein a bad thing?
Vol.67：Technology to rapidly detect cancer markers for cancer diagnosis
Vol.68：Improving the diagnosis of pancreatic cancer