AI Model can Predict whether Crohn Disease will Recur After Surgery

Using an artificial intelligence (AI) tool that emulates how humans visualize and is trained to recognize and classify images, investigators constructed a model that predicts the postoperative recurrence of Crohn disease with high accuracy by evaluating histological images. The AI tool also revealed previously unrecognized differences in adipose cells and significant differences in the extent of mast cell infiltration in the subserosa, or outer lining of the intestine, comparing patients with and without disease recurrence. The findings appear in The American Journal of Pathology, published by Elsevier.

The 10-year rate of postoperative symptomatic recurrence of Crohn disease, a chronic inflammatory gastrointestinal disease, is estimated at 40%. Although there are scoring systems to evaluate Crohn disease activity and the existence of postoperative recurrence, no scoring system had been developed to predict whether Crohn disease might recur.

"Most of the analysis of histopathological images using AI in the past have targeted malignant tumors," explained lead investigators Takahiro Matsui, MD, PhD, and Eiichi Morii, MD, PhD, Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan. "We aimed to obtain clinically useful information for a wider variety of diseases by analyzing histopathology images using AI. We focused on Crohn disease, in which postoperative recurrence is a clinical problem."

Sixty-eight patients with Crohn disease who underwent bowel resection between January 2007 and July 2018 were included in the study. They were classified into two groups according to the presence or absence of postoperative disease recurrence within two years after surgery. Each group was sorted into two subgroups, one for training an AI model and the other for validation. For training, whole slide images of surgical specimens were cropped into tile images, labelled for presence or absence of postsurgical recurrence, and then processed by EfficientNet-b5, a commercially available AI model designed to perform image classification. When the model was tested with unlabeled images, the results indicated that the deep learning model accurately classified the unlabeled images according to the presence or absence of disease occurrence.

Next, predictive heat maps were generated to identify areas and histological features from which the machine learning model could predict recurrence with high accuracy. The images included all layers of the intestinal wall. The heatmaps showed that the machine learning model yielded correct predictions in the subserosal adipose tissue layer. However, in other areas, such as the mucosal and proper muscular layers, the model was less accurate. Images with the most accurate predictions were extracted from the test datasets of the non-recurrence and recurrence groups. Among these images, the best predictive results all contained adipose tissue.

Because the machine learning model achieved accurate predictions from images of subserosal tissue, the investigators hypothesized that subserosal adipose cell morphologies differed between the recurrence and the nonrecurrence groups. Adipose cells in the recurrence group had a significantly smaller cell size, higher flattening, and smaller center to center cell distance values than those in the nonrecurrence group.

"These features, defined as 'adipocyte shrinkage,' are important histological characteristics associated with Crohn disease recurrence," said Dr. Matsui and Dr. Morii.

The investigators also hypothesized that the differences in adipocyte morphology between the two groups were associated with some degree or type of inflammatory condition in the tissue. They found that the recurrence group had a significantly higher number of mast cells infiltrating the subserosal adipose tissue, indicating that the cells are associated with the recurrence of Crohn disease and the "adipocyte shrinkage" phenomenon.

To the investigators' knowledge, these findings are the first to link postoperative recurrence of Crohn disease with the histology of subserosal adipose cells and mast cell infiltration. Dr. Matsui and Dr. Morii observed, "Our findings enable stratification by prognosis of postoperative Crohn disease patients. Many drugs, including biologicals, are used to prevent Crohn disease recurrence, and proper stratification can enable more intensive and successful treatment of high-risk patients."

Kiyokawa H, Abe M, Matsui T, Kurashige M, Ohshima K, Tahara S, Nojima S, Ogino T, Sekido Y, Mizushima T, Morii E.
Deep Learning Analysis of Histologic Images from Intestinal Specimen Reveals Adipocyte Shrinkage and Mast Cell Infiltration to Predict Postoperative Crohn Disease.
Am J Pathol. 2022 Mar 28:S0002-9440(22)00106-7. doi: 10.1016/j.ajpath.2022.03.006

Most Popular Now

AI Helps Physicians Better Assess the Ef…

In a small but multi-institutional study, an artificial intelligence (AI)-based system improved providers' assessments of whether patients with bladder cancer had complete response to chemotherapy before a radical cystectomy (bladder...

Smartwatches and Fitness Bands Reveal In…

A new digital health study by researchers at Scripps Research shows how data from wearable sensors, such as smartwatches and fitness bands, can track a person’s physiological response to the...

AI may Detect Earliest Signs of Pancreat…

An artificial intelligence (AI) tool developed by Cedars-Sinai investigators accurately predicted who would develop pancreatic cancer based on what their CT scan images looked like years prior to being diagnosed...

Open Call U4H-2022-PJ2: Call for Proposa…

The Ukraine crisis has an unprecedented impact on the mental health of the displaced people in the EU coming from Ukraine. The conflict and experiences of people in war zones...

AI Reduces Miss Rate of Precancerous Pol…

Artificial intelligence reduced by twofold the rate at which precancerous polyps were missed in colorectal cancer screening, reported a team of international researchers led by Mayo Clinic. The study is...

Medical Valley EMN & Volitan Global …

The two healthcare innovation experts Medical Valley EMN and Volitan Global strengthen their existing inbound- and outbound activities through a strategic partnership. The aim is to offer companies access to...

DMEA - Connecting Digital Health Opens w…

26 - 28 April 2022, Berlin, Germany. What plans does the new federal government have concerning the digital transformation of the healthcare sector? What are the initial experiences of doctors regarding...

AI can Predict Probability of COVID-19 v…

Testing shortages, long waits for results, and an over-taxed health care system have made headlines throughout the COVID-19 pandemic. These issues can be further exacerbated in small or rural communities...

Using AI to Detect Cancer from Patient D…

A new way of using artificial intelligence to predict cancer from patient data without putting personal information at risk has been developed by a team including University of Leeds medical...

Oulu University Hospital Expands Partner…

Siemens Healthineers and Oulu University Hospital in Finland have entered a strategic partnership for the next ten years, adding to an existing radiotherapy collaboration to jointly expand and modernize the...

Positive Conclusion to DMEA - Connecting…

26 - 28 April 2022, Berlin, Germany. After three days DMEA, Europe's leading digital health event, came to a successful conclusion - with around 11,000 visitors, more than 500 exhibitors and...

AI-Enabled ECGs may Identify Patients at…

Atrial fibrillation, the most common cardiac rhythm abnormality, has been linked to one-third of ischemic strokes, the most common type of stroke. But atrial fibrillation is underdiagnosed, partly because many...