Diagnosis of ulcerative colitis from endoscopic images based on deep learning

A novel lightweight deep learning based approaches for the automatic diagnosis of gastrointestinal disease using image processing and knowledge distillation techniques

BACKGROUND

Gastrointestinal (GI) diseases pose significant challenges for healthcare systems, largely due to the complexities involved in their detection and treatment. Despite the advancements in deep neural networks, their high computational demands hinder their practical use in clinical environments.

OBJECTIVE

This study aims to address the computational inefficiencies of deep neural networks by proposing a lightweight model that integrates model compression techniques, ConvLSTM layers, and ConvNext Blocks, all optimized through Knowledge Distillation (KD).

METHODS

A dataset of 6000 endoscopic images of various GI diseases was utilized. Advanced image preprocessing techniques, including adaptive noise reduction and image detail enhancement, were employed to improve accuracy and interpretability. The model's performance was assessed in terms of accuracy, computational cost, and disk space usage.

RESULTS

The proposed lightweight model achieved an exceptional overall accuracy of 99.38 %. It operates efficiently with a computational cost of 0.61 GFLOPs and occupies only 3.09 MB of disk space. Additionally, Grad-CAM visualizations demonstrated enhanced model saliency and interpretability, offering insights into the decision-making process of the model post-KD.

CONCLUSION

The proposed model represents a significant advancement in the diagnosis of GI diseases. It provides a cost-effective and efficient alternative to traditional deep neural network methods, overcoming their computational limitations and contributing valuable insights for improved clinical application.

Improving image classification of gastrointestinal endoscopy using curriculum self-supervised learning

Endoscopy, a widely used medical procedure for examining the gastrointestinal (GI) tract to detect potential disorders, poses challenges in manual diagnosis due to non-specific symptoms and difficulties in accessing affected areas. While supervised machine learning models have proven effective in assisting clinical diagnosis of GI disorders, the scarcity of image-label pairs created by medical experts limits their availability. To address these limitations, we propose a curriculum self-supervised learning framework inspired by human curriculum learning. Our approach leverages the HyperKvasir dataset, which comprises 100k unlabeled GI images for pre-training and 10k labeled GI images for fine-tuning. By adopting our proposed method, we achieved an impressive top-1 accuracy of 88.92% and an F1 score of 73.39%. This represents a 2.1% increase over vanilla SimSiam for the top-1 accuracy and a 1.9% increase for the F1 score. The combination of self-supervised learning and a curriculum-based approach demonstrates the efficacy of our framework in advancing the diagnosis of GI disorders. Our study highlights the potential of curriculum self-supervised learning in utilizing unlabeled GI tract images to improve the diagnosis of GI disorders, paving the way for more accurate and efficient diagnosis in GI endoscopy.

Artificial intelligence image-based prediction models in IBD exhibit high risk of bias: A systematic review

BACKGROUND

There has been an increase in the development of both machine learning (ML) and deep learning (DL) prediction models in Inflammatory Bowel Disease. We aim in this systematic review to assess the methodological quality and risk of bias of ML and DL IBD image-based prediction studies.

METHODS

We searched three databases, PubMed, Scopus and Embase, to identify ML and DL diagnostic or prognostic predictive models using imaging data in IBD, to Dec 31, 2022. We restricted our search to include studies that primarily used conventional imaging data, were undertaken in human participants, and published in English. Two reviewers independently reviewed the abstracts. The methodological quality of the studies was determined, and risk of bias evaluated using the prediction risk of bias assessment tool (PROBAST).

RESULTS

Forty studies were included, thirty-nine developed diagnostic models. Seven studies utilized ML approaches, six were retrospective and none used multicenter data for model development. Thirty-three studies utilized DL approaches, ten were prospective, and twelve multicenter studies. Overall, all studies demonstrated high risk of bias. ML studies were evaluated in 4 domains all rated as high risk of bias: participants (6/7), predictors (1/7), outcome (3/7), and analysis (7/7), and DL studies evaluated in 3 domains: participants (24/33), outcome (10/33), and analysis (18/33). The majority of image-based studies used colonoscopy images.

CONCLUSION

The risk of bias was high in AI IBD image-based prediction models, owing to insufficient sample size, unreported missingness and lack of an external validation cohort. Models with a high risk of bias are unlikely to be generalizable and suitable for clinical implementation.

Artificial intelligence in endoscopy related to inflammatory bowel disease: A systematic review

BACKGROUND AND OBJECTIVES

In spite of rapid growth of artificial intelligence (AI) in digestive endoscopy in lesion detection and characterization, the role of AI in inflammatory bowel disease (IBD) endoscopy is not clearly defined. We aimed at systematically reviewing the role of AI in IBD endoscopy and identifying future research areas.

METHODS

We searched the PubMed and Embase database using keywords ("artificial intelligence" OR "machine learning" OR "computer-aided" OR "convolutional neural network") AND ("inflammatory bowel disease" OR "ulcerative colitis" OR "Crohn's") AND ("endoscopy" or "colonoscopy" or "capsule endoscopy" or "device assisted enteroscopy") between 1975 and September 2023 and identified 62 original articles for detailed review. Review articles, consensus guidelines, case reports/series, editorials, letter to the editor, non-peer-reviewed pre-prints and conference abstracts were excluded. The quality of the included studies was assessed using the MI-CLAIM checklist.

RESULTS

The accuracy of AI models (25 studies) to assess ulcerative colitis (UC) endoscopic activity ranged between 86.54% and 94.5%. AI-assisted capsule endoscopy reading (12 studies) substantially reduced analyzable images and reading time with excellent accuracy (90.5% to 99.9%). AI-assisted analysis of colonoscopic images can help differentiate IBD from non-IBD, UC from non-UC and UC from Crohn's disease (CD) (three studies) with 72.1%, 98.3% and > 90% accuracy, respectively. AI models based on non-invasive clinical and radiologic parameters could predict endoscopic activity (three studies). AI-assisted virtual chromoendoscopy (four studies) could predict histologic remission and long-term outcomes. Computer-assisted detection (CADe) of dysplasia (two studies) is feasible along with AI-based differentiation of high from low-grade IBD neoplasia (79% accuracy). AI is effective in linking electronic medical record data (two studies) with colonoscopic videos to facilitate widespread machine learning.

CONCLUSION

AI-assisted IBD endoscopy has the potential to impact clinical management by automated detection and characterization of endoscopic lesions. Large, multi-center, prospective studies and commercially available IBD-specific endoscopic AI algorithms are warranted.

Uncertainty-aware network for fine-grained and imbalanced reflux esophagitis grading

Computer-aided diagnosis (CAD) assists endoscopists in analyzing endoscopic images, reducing misdiagnosis rates and enabling timely treatment. A few studies have focused on CAD for gastroesophageal reflux disease, but CAD studies on reflux esophagitis (RE) are still inadequate. This paper presents a CAD study on RE using a dataset collected from hospital, comprising over 3000 images. We propose an uncertainty-aware network with handcrafted features, utilizing representation and classifier decoupling with metric learning to address class imbalance and achieve fine-grained RE classification. To enhance interpretability, the network estimates uncertainty through test time augmentation. The experimental results demonstrate that the proposed network surpasses previous methods, achieving an accuracy of 90.2% and an F1 score of 90.1%.

A systematic review and meta-analysis of artificial intelligence-diagnosed endoscopic remission in ulcerative colitis

Endoscopic remission is an important therapeutic goal in ulcerative colitis (UC). The Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Mayo Endoscopic Score (MES) are the commonly used endoscopic scoring criteria. This systematic review and meta-analysis aimed to evaluate the accuracy of artificial intelligence (AI) in diagnosing endoscopic remission in UC. We also performed a meta-analysis of each of the four endoscopic remission criteria (UCEIS = 0, MES = 0, UCEIS = <1, MES = <1). Eighteen studies involving 13,687 patients were included. The combined sensitivity and specificity of AI for diagnosing endoscopic remission in UC was 87% (95% confidence interval [CI]:81-92%) and 92% (95% CI: 89-94%), respectively. The area under the curve (AUC) was 0.96 (95% CI: 0.94-0.97). The results showed that the AI model performed well regardless of which criteria were used to define endoscopic remission of UC.

Using a Deep Learning Model to Address Interobserver Variability in the Evaluation of Ulcerative Colitis (UC) Severity

The use of endoscopic images for the accurate assessment of ulcerative colitis (UC) severity is crucial to determining appropriate treatment. However, experts may interpret these images differently, leading to inconsistent diagnoses. This study aims to address the issue by introducing a standardization method based on deep learning. We collected 254 rectal endoscopic images from 115 patients with UC, and five experts in endoscopic image interpretation assigned classification labels based on the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) scoring system. Interobserver variance analysis of the five experts yielded an intraclass correlation coefficient of 0.8431 for UCEIS scores and a kappa coefficient of 0.4916 when the UCEIS scores were transformed into UC severity measures. To establish a consensus, we created a model that considered only the images and labels on which more than half of the experts agreed. This consensus model achieved an accuracy of 0.94 when tested with 50 images. Compared with models trained from individual expert labels, the consensus model demonstrated the most reliable prediction results.

PKDN: Prior Knowledge Distillation Network for bronchoscopy diagnosis

Bronchoscopy plays a crucial role in diagnosing and treating lung diseases. The deep learning-based diagnostic system for bronchoscopic images can assist physicians in accurately and efficiently diagnosing lung diseases, enabling patients to undergo timely pathological examinations and receive appropriate treatment. However, the existing diagnostic methods overlook the utilization of prior knowledge of medical images, and the limited feature extraction capability hinders precise focus on lesion regions, consequently affecting the overall diagnostic effectiveness. To address these challenges, this paper proposes a prior knowledge distillation network (PKDN) for identifying lung diseases through bronchoscopic images. The proposed method extracts color and edge features from lesion images using the prior knowledge guidance module, and subsequently enhances spatial and channel features by employing the dynamic spatial attention module and gated channel attention module, respectively. Finally, the extracted features undergo refinement and self-regulation through feature distillation. Furthermore, decoupled distillation is implemented to balance the importance of target and non-target class distillation, thereby enhancing the diagnostic performance of the network. The effectiveness of the proposed method is validated on the bronchoscopic dataset provided by Harbin Medical University Cancer Hospital, which consists of 2,029 bronchoscopic images from 200 patients. Experimental results demonstrate that the proposed method achieves an accuracy of 94.78% and an AUC of 98.17%, outperforming other methods significantly in diagnostic performance. These results indicate that the computer-aided diagnostic system based on PKDN provides satisfactory accuracy in diagnosing lung diseases during bronchoscopy.

Improving the Computer-Aided Estimation of Ulcerative Colitis Severity According to Mayo Endoscopic Score by Using Regression-Based Deep Learning

BACKGROUND

Assessment of endoscopic activity in ulcerative colitis (UC) is important for treatment decisions and monitoring disease progress. However, substantial inter- and intraobserver variability in grading impairs the assessment. Our aim was to develop a computer-aided diagnosis system using deep learning to reduce subjectivity and improve the reliability of the assessment.

METHODS

The cohort comprises 11 276 images from 564 patients who underwent colonoscopy for UC. We propose a regression-based deep learning approach for the endoscopic evaluation of UC according to the Mayo endoscopic score (MES). Five state-of-the-art convolutional neural network (CNN) architectures were used for the performance measurements and comparisons. Ten-fold cross-validation was used to train the models and objectively benchmark them. Model performances were assessed using quadratic weighted kappa and macro F1 scores for full Mayo score classification and kappa statistics and F1 score for remission classification.

RESULTS

Five classification-based CNNs used in the study were in excellent agreement with the expert annotations for all Mayo subscores and remission classification according to the kappa statistics. When the proposed regression-based approach was used, (1) the performance of most of the models statistically significantly increased and (2) the same model trained on different cross-validation folds produced more robust results on the test set in terms of deviation between different folds.

CONCLUSIONS

Comprehensive experimental evaluations show that commonly used classification-based CNN architectures have successful performance in evaluating endoscopic disease activity of UC. Integration of domain knowledge into these architectures further increases performance and robustness, accelerating their translation into clinical use.

Recent Advances of Artificial Intelligence Applications in Interstitial Lung Diseases

Interstitial lung diseases (ILDs) comprise a rather heterogeneous group of diseases varying in pathophysiology, presentation, epidemiology, diagnosis, treatment and prognosis. Even though they have been recognized for several years, there are still areas of research debate. In the majority of ILDs, imaging modalities and especially high-resolution Computed Tomography (CT) scans have been the cornerstone in patient diagnostic approach and follow-up. The intricate nature of ILDs and the accompanying data have led to an increasing adoption of artificial intelligence (AI) techniques, primarily on imaging data but also in genetic data, spirometry and lung diffusion, among others. In this literature review, we describe the most prominent applications of AI in ILDs presented approximately within the last five years. We roughly stratify these studies in three categories, namely: (i) screening, (ii) diagnosis and classification, (iii) prognosis.

Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis

Background

The ulcerative colitis (UC) Mayo endoscopy score is a useful tool for evaluating the severity of UC in patients in clinical practice.

Objectives

We aimed to develop and validate a deep learning-based approach to automatically predict the Mayo endoscopic score using UC endoscopic images.

Design

A multicenter, diagnostic retrospective study.

Methods

We collected 15120 colonoscopy images of 768 UC patients from two hospitals in China and developed a deep model based on a vision transformer named the UC-former. The performance of the UC-former was compared with that of six endoscopists on the internal test set. Furthermore, multicenter validation from three hospitals was also carried out to evaluate UC-former's generalization performance.

Results

On the internal test set, the areas under the curve of Mayo 0, Mayo 1, Mayo 2, and Mayo 3 achieved by the UC-former were 0.998, 0.984, 0.973, and 0.990, respectively. The accuracy (ACC) achieved by the UC-former was 90.8%, which is higher than that achieved by the best senior endoscopist. For three multicenter external validations, the ACC was 82.4%, 85.0%, and 83.6%, respectively.

Conclusions

The developed UC-former could achieve high ACC, fidelity, and stability to evaluate the severity of UC, which may provide potential application in clinical practice.

Registration

This clinical trial was registered at the ClinicalTrials.gov (trial registration number: NCT05336773).

PHF3 Technique: A Pyramid Hybrid Feature Fusion Framework for Severity Classification of Ulcerative Colitis Using Endoscopic Images

Evaluating the severity of ulcerative colitis (UC) through the Mayo endoscopic subscore (MES) is crucial for understanding patient conditions and providing effective treatment. However, UC lesions present different characteristics in endoscopic images, exacerbating interclass similarities and intraclass differences in MES classification. In addition, inexperience and review fatigue in endoscopists introduces nontrivial challenges to the reliability and repeatability of MES evaluations. In this paper, we propose a pyramid hybrid feature fusion framework (PHF3) as an auxiliary diagnostic tool for clinical UC severity classification. Specifically, the PHF3 model has a dual-branch hybrid architecture with ResNet50 and a pyramid vision Transformer (PvT), where the local features extracted by ResNet50 represent the relationship between the intestinal wall at the near-shot point and its depth, and the global representations modeled by the PvT capture similar information in the cross-section of the intestinal cavity. Furthermore, a feature fusion module (FFM) is designed to combine local features with global representations, while second-order pooling (SOP) is applied to enhance discriminative information in the classification process. The experimental results show that, compared with existing methods, the proposed PHF3 model has competitive performance. The area under the receiver operating characteristic curve (AUC) of MES 0, MES 1, MES 2, and MES 3 reached 0.996, 0.972, 0.967, and 0.990, respectively, and the overall accuracy reached 88.91%. Thus, our proposed method is valuable for developing an auxiliary assessment system for UC severity.

A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images

The first step in the diagnosis of gastric abnormalities is the detection of various abnormalities in the human gastrointestinal tract. Manual examination of endoscopy images relies on a medical practitioner's expertise to identify inflammatory regions on the inner surface of the gastrointestinal tract. The length of the alimentary canal and the large volume of images obtained from endoscopic procedures make traditional detection methods time consuming and laborious. Recently, deep learning architectures have achieved better results in the classification of endoscopy images. However, visual similarities between different portions of the gastrointestinal tract pose a challenge for effective disease detection. This work proposes a novel system for the classification of endoscopy images by focusing on feature mining through convolutional neural networks (CNN). The model presented is built by combining a state-of-the-art architecture (i.e., EfficientNet B0) with a custom-built CNN architecture named Effimix. The proposed Effimix model employs a combination of squeeze and excitation layers and self-normalising activation layers for precise classification of gastrointestinal diseases. Experimental observations on the HyperKvasir dataset confirm the effectiveness of the proposed architecture for the classification of endoscopy images. The proposed model yields an accuracy of 97.99%, with an F1 score, precision, and recall of 97%, 97%, and 98%, respectively, which is significantly higher compared to the existing works.

CodnNet: A lightweight CNN architecture for detection of COVID-19 infection

The application of Convolutional Neural Network (CNN) on the detection of COVID-19 infection has yielded favorable results. However, with excessive model parameters, the CNN detection of COVID-19 is low in recall, highly complex in computation. In this paper, a novel lightweight CNN model, CodnNet is proposed for quick detection of COVID-19 infection. CodnNet builds a more effective dense connections based on DenseNet network to make features highly reusable and enhances interactivity of local and global features. It also uses depthwise separable convolution with large convolution kernels instead of traditional convolution to improve the range of receptive field and enhances classification performance while reducing model complexity. The 5-Fold cross validation results on Kaggle’s COVID-19 Dataset showed that CodnNet has an average precision of 97.9%, recall of 97.4%, F1score of 97.7%, accuracy of 98.5%, mAP of 99.3%, and mAUC of 99.7%. Compared to the typical CNNs, CodnNet with fewer parameters and lower computational complexity has achieved better classification accuracy and generalization performance. Therefore, the CodnNet model provides a good reference for quick detection of COVID-19 infection.

Intestinal Elastography in the Diagnostics of Ulcerative Colitis: A Narrative Review

Ulcerative colitis (UC) is an inflammatory bowel disease (IBD) that mainly affects developed countries, but the number of cases in developing countries is increasing. We conducted a narrative review on the potential application of ultrasound elastography in the diagnosis and monitoring of UC, as this newly emerging method has promising results in other gut diseases. This review fulfilled the PRISMA Statement criteria with a time cut-off of June 2022. At the end of the review, of the 1334 identified studies, only five fulfilled all the inclusion criteria. Due to the small number of studies in this field, a reliable assessment of the usefulness of ultrasound elastography is difficult. We can only conclude that the transabdominal elastography examination did not significantly differ from the standard gastrointestinal ultrasonography examination and that measurements of the frontal intestinal wall should be made in the longitudinal section. The reports suggest that it is impossible to estimate the clinical scales used in disease assessment solely on the basis of elastographic measurements. Due to the different inclusion criteria, measurement methodologies, and elastographic techniques used in the analysed studies, a reliable comparative evaluation was impossible. Further work is required to assess the validity of expanding gastrointestinal ultrasonography with elastography in the diagnosis and monitoring of UC.

Artificial Intelligence for Colonoscopy: Past, Present, and Future

During the past decades, many automated image analysis methods have been developed for colonoscopy. Real-time implementation of the most promising methods during colonoscopy has been tested in clinical trials, including several recent multi-center studies. All trials have shown results that may contribute to prevention of colorectal cancer. We summarize the past and present development of colonoscopy video analysis methods, focusing on two categories of artificial intelligence (AI) technologies used in clinical trials. These are (1) analysis and feedback for improving colonoscopy quality and (2) detection of abnormalities. Our survey includes methods that use traditional machine learning algorithms on carefully designed hand-crafted features as well as recent deep-learning methods. Lastly, we present the gap between current state-of-the-art technology and desirable clinical features and conclude with future directions of endoscopic AI technology development that will bridge the current gap.