The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists: A pilot study

BACKGROUND AND AIM

Although endoscopic resection with careful surveillance instead of total proctocolectomy become to be permitted for visible low-grade dysplasia, it is unclear how accurately endoscopists can differentiate these lesions, as classifying neoplasias occurring in inflammatory bowel disease (IBDN) is exceedingly challenging due to background chronic inflammation. We evaluated a pilot model of an artificial intelligence (AI) system for classifying IBDN and compared it with the endoscopist's ability.

METHODS

This study used a deep convolutional neural network, the EfficientNet-B3. Among patients who underwent treatment for IBDN at two hospitals between 2003 and 2021, we selected 862 non-magnified endoscopic images from 99 IBDN lesions and utilized 6 375 352 images that were increased by data augmentation for the development of AI. We evaluated the diagnostic ability of AI using two classifications: the "adenocarcinoma/high-grade dysplasia" and "low-grade dysplasia/sporadic adenoma/normal mucosa" groups. We compared the diagnostic accuracy between AI and endoscopists (three non-experts and four experts) using 186 test set images.

RESULTS

The diagnostic ability of the experts/non-experts/AI for the two classifications in the test set images had a sensitivity of 60.5% (95% confidence interval [CI]: 54.5-66.3)/70.5% (95% CI: 63.8-76.6)/72.5% (95% CI: 60.4-82.5), specificity of 88.0% (95% CI: 84.7-90.8)/78.8% (95% CI: 74.3-83.1)/82.9% (95% CI: 74.8-89.2), and accuracy of 77.8% (95% CI: 74.7-80.8)/75.8% (95% CI: 72-79.3)/79.0% (95% CI: 72.5-84.6), respectively.

CONCLUSIONS

The diagnostic accuracy of the two classifications of IBDN was higher than that of the experts. Our AI system is valuable enough to contribute to the next generation of clinical practice.

Clinical porcine islet xenotransplantation under comprehensive regulation

BACKGROUND

Xenotransplantation with porcine islets is a promising approach to overcome the shortage of human donors. This is the first report of phase 1/2a xenotransplantation study of encapsulated neonatal porcine islets under the current framework of regulations for xenotransplantation in New Zealand.

METHODS

Newborn piglets were anesthetized and bled, and the pancreata were removed with the use of sterile technique and processed. Encapsulated neonatal porcine islets were implanted with the use of laparoscopy into the peritoneal cavity of 14 patients with unstable type 1 diabetes without any immunosuppressive drugs. The patients received encapsulated islets of 5,000 (n = 4; group 1), 10,000 (n = 4; group 2), 15,000 (n = 4; group 3), or 20,000 (n = 2; group 4) islet equivalents per kg body weight. Outcome was determined from adverse event reports, HbA1c, total daily insulin dose, and frequency of unaware hypoglycemic events. To assess graft function, transplant estimated function (TEF) scores were calculated. Sufficient or marginal numbers of encapsulated neonatal porcine islets were transplanted into streptozotocin-induced diabetic B6 mice as an in vivo functional assay.

RESULTS

There were 4 serious adverse events, of which 3 were considered to be possibly related to the procedure. Tests for porcine endogenous retrovirus DNA and RNA were all negative. The numbers of unaware hypoglycemia events were reduced after transplantation in all groups. Four of 14 patients attained HbA1c <7% compared with 1 at baseline. The average TEF scores were 0.17, 0.02, -0.01, and 0.08 in groups 1, 2, 3, and 4 respectively. The in vivo study demonstrated that a sufficient number of the transplanted group reversed diabetes with positive porcine C-peptide.

CONCLUSIONS

Transplantation of encapsulated neonatal porcine islets was safe and was followed by a reduction in unaware hypoglycemia events in unstable type 1 diabetic patients. The mouse in vivo assessment data demonstrated certain graft function.