An intelligent decision support system for quantitative assessment of gastric atrophy

Diagnosing and grading gastric atrophy and intestinal metaplasia using semi-supervised deep learning on pathological images: development and validation study

OBJECTIVE

Patients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and validate a diagnostic approach for gastric biopsy specimens using deep learning and OLGA/OLGIM for individual gastric cancer risk classification.

METHODS

In this study, we prospectively enrolled 545 patients suspected of atrophic gastritis during endoscopy from 13 tertiary hospitals between December 22, 2017, to September 25, 2020, with a total of 2725 whole-slide images (WSIs). Patients were randomly divided into a training set (n = 349), an internal validation set (n = 87), and an external validation set (n = 109). Sixty patients from the external validation set were randomly selected and divided into two groups for an observer study, one with the assistance of algorithm results and the other without. We proposed a semi-supervised deep learning algorithm to diagnose and grade IM and atrophy, and we compared it with the assessments of 10 pathologists. The model's performance was evaluated based on the area under the curve (AUC), sensitivity, specificity, and weighted kappa value.

RESULTS

The algorithm, named GasMIL, was established and demonstrated encouraging performance in diagnosing IM (AUC 0.884, 95% CI 0.862-0.902) and atrophy (AUC 0.877, 95% CI 0.855-0.897) in the external test set. In the observer study, GasMIL achieved an 80% sensitivity, 85% specificity, a weighted kappa value of 0.61, and an AUC of 0.953, surpassing the performance of all ten pathologists in diagnosing atrophy. Among the 10 pathologists, GasMIL's AUC ranked second in OLGA (0.729, 95% CI 0.625-0.833) and fifth in OLGIM (0.792, 95% CI 0.688-0.896). With the assistance of GasMIL, pathologists demonstrated improved AUC (p = 0.013), sensitivity (p = 0.014), and weighted kappa (p = 0.016) in diagnosing IM, and improved specificity (p = 0.007) in diagnosing atrophy compared to pathologists working alone.

CONCLUSION

GasMIL shows the best overall performance in diagnosing IM and atrophy when compared to pathologists, significantly enhancing their diagnostic capabilities.

The role of computer-assisted systems for upper-endoscopy quality monitoring and assessment of gastric lesions

This article analyses the literature regarding the value of computer-assisted systems in esogastroduodenoscopy-quality monitoring and the assessment of gastric lesions. Current data show promising results in upper-endoscopy quality control and a satisfactory detection accuracy of gastric premalignant and malignant lesions, similar or even exceeding that of experienced endoscopists. Moreover, artificial systems enable the decision for the best treatment strategies in gastric-cancer patient care, namely endoscopic vs surgical resection according to tumor depth. In so doing, unnecessary surgical interventions would be avoided whilst providing a better quality of life and prognosis for these patients. All these performance data have been revealed by numerous studies using different artificial intelligence (AI) algorithms in addition to white-light endoscopy or novel endoscopic techniques that are available in expert endoscopy centers. It is expected that ongoing clinical trials involving AI and the embedding of computer-assisted diagnosis systems into endoscopic devices will enable real-life implementation of AI endoscopic systems in the near future and at the same time will help to overcome the current limits of the computer-assisted systems leading to an improvement in performance. These benefits should lead to better diagnostic and treatment strategies for gastric-cancer patients. Furthermore, the incorporation of AI algorithms in endoscopic tools along with the development of large electronic databases containing endoscopic images might help in upper-endoscopy assistance and could be used for telemedicine purposes and second opinion for difficult cases.

Diagnosing chronic atrophic gastritis by gastroscopy using artificial intelligence

BACKGROUND

The sensitivity of endoscopy in diagnosing chronic atrophic gastritis is only 42%, and multipoint biopsy, despite being more accurate, is not always available.

AIMS

This study aimed to construct a convolutional neural network to improve the diagnostic rate of chronic atrophic gastritis.

METHODS

We collected 5470 images of the gastric antrums of 1699 patients and labeled them with their pathological findings. Of these, 3042 images depicted atrophic gastritis and 2428 did not. We designed and trained a convolutional neural network-chronic atrophic gastritis model to diagnose atrophic gastritis accurately, verified by five-fold cross-validation. Moreover, the diagnoses of the deep learning model were compared with those of three experts.

RESULTS

The diagnostic accuracy, sensitivity, and specificity of the convolutional neural network-chronic atrophic gastritis model in diagnosing atrophic gastritis were 0.942, 0.945, and 0.940, respectively, which were higher than those of the experts. The detection rates of mild, moderate, and severe atrophic gastritis were 93%, 95%, and 99%, respectively.

CONCLUSION

Chronic atrophic gastritis could be diagnosed by gastroscopic images using the convolutional neural network-chronic atrophic gastritis model. This may greatly reduce the burden on endoscopy physicians, simplify diagnostic routines, and reduce costs for doctors and patients.

Review of Medical Decision Support and Machine-Learning Methods

Machine-learning methods can assist with the medical decision-making processes at the both the clinical and diagnostic levels. In this article, we first review historical milestones and specific applications of computer-based medical decision support tools in both veterinary and human medicine. Next, we take a mechanistic look at 3 archetypal learning algorithms—naive Bayes, decision trees, and neural network—commonly used to power these medical decision support tools. Last, we focus our discussion on the data sets used to train these algorithms and examine methods for validation, data representation, transformation, and feature selection. From this review, the reader should gain some appreciation for how these decision support tools have and can be used in medicine along with insight on their inner workings.

Identifying free-text features to improve automated classification of structured histopathology reports for feline small intestinal disease

The histologic evaluation of gastrointestinal (GI) biopsies is the standard for diagnosis of a variety of GI diseases (e.g., inflammatory bowel disease [IBD] and alimentary lymphoma [ALA]). The World Small Animal Veterinary Association (WSAVA) Gastrointestinal International Standardization Group proposed a reporting standard for GI biopsies consisting of a defined set of microscopic features. We compared the machine classification accuracy of free-text microscopic findings with those represented in the WSAVA format with a diagnosis of IBD and ALA. Unstructured free-text duodenal biopsy pathology reports from cats ( n = 60) with a diagnosis of IBD ( n = 20), ALA ( n = 20), or normal ( n = 20) were identified. Biopsy samples from these cases were then scored following the WSAVA guidelines to create a set of structured reports. Three supervised machine-learning algorithms were trained using the structured and then the unstructured reports. Diagnosis classification accuracy for the 3 algorithms was compared using the structured and unstructured reports. Using naive Bayes and neural networks, unstructured information-based models achieved higher diagnostic accuracy (0.90 and 0.88, respectively) compared to the structured information-based models (0.74 and 0.72, respectively). Results suggest that discriminating diagnostic information was lost using current WSAVA microscopic guideline features. Addition of free-text features (number of plasma cells) increased WSAVA auto-classification performance. The methodologies reported in our study represent a way of identifying candidate microscopic features for use in structured histopathology reports.

Evaluation of supervised machine-learning algorithms to distinguish between inflammatory bowel disease and alimentary lymphoma in cats

Inflammatory bowel disease (IBD) and alimentary lymphoma (ALA) are common gastrointestinal diseases in cats. The very similar clinical signs and histopathologic features of these diseases make the distinction between them diagnostically challenging. We tested the use of supervised machine-learning algorithms to differentiate between the 2 diseases using data generated from noninvasive diagnostic tests. Three prediction models were developed using 3 machine-learning algorithms: naive Bayes, decision trees, and artificial neural networks. The models were trained and tested on data from complete blood count (CBC) and serum chemistry (SC) results for the following 3 groups of client-owned cats: normal, inflammatory bowel disease (IBD), or alimentary lymphoma (ALA). Naive Bayes and artificial neural networks achieved higher classification accuracy (sensitivities of 70.8% and 69.2%, respectively) than the decision tree algorithm (63%, p < 0.0001). The areas under the receiver-operating characteristic curve for classifying cases into the 3 categories was 83% by naive Bayes, 79% by decision tree, and 82% by artificial neural networks. Prediction models using machine learning provided a method for distinguishing between ALA–IBD, ALA–normal, and IBD–normal. The naive Bayes and artificial neural networks classifiers used 10 and 4 of the CBC and SC variables, respectively, to outperform the C4.5 decision tree, which used 5 CBC and SC variables in classifying cats into the 3 classes. These models can provide another noninvasive diagnostic tool to assist clinicians with differentiating between IBD and ALA, and between diseased and nondiseased cats.