Enhanced segmentation of gastrointestinal polyps from capsule endoscopy images with artifacts using ensemble learning

The application of the combination between artificial intelligence and endoscopy in gastrointestinal tumors

Gastrointestinal (GI) tumors have always been a major type of malignant tumor and a leading cause of tumor‐related deaths worldwide. The main principles of modern medicine for GI tumors are early prevention, early diagnosis, and early treatment, with early diagnosis being the most effective measure. Endoscopy, due to its ability to visualize lesions, has been one of the primary modalities for screening, diagnosing, and treating GI tumors. However, a qualified endoscopist often requires long training and extensive experience, which to some extent limits the wider use of endoscopy. With advances in data science, artificial intelligence (AI) has brought a new development direction for the endoscopy of GI tumors. AI can quickly process large quantities of data and images and improve diagnostic accuracy with some training, greatly reducing the workload of endoscopists and assisting them in early diagnosis. Therefore, this review focuses on the combined application of endoscopy and AI in GI tumors in recent years, describing the latest research progress on the main types of tumors and their performance in clinical trials, the application of multimodal AI in endoscopy, the development of endoscopy, and the potential applications of AI within it, with the aim of providing a reference for subsequent research.

Artificial intelligence in capsule endoscopy: development status and future expectations

In this review, we aim to illustrate the state-of-the-art artificial intelligence (AI) applications in the field of capsule endoscopy. AI has made significant strides in gastrointestinal imaging, particularly in capsule endoscopy - a non-invasive procedure for capturing gastrointestinal tract images. However, manual analysis of capsule endoscopy videos is labour-intensive and error-prone, prompting the development of automated computational algorithms and AI models. While currently serving as a supplementary observer, AI has the capacity to evolve into an autonomous, integrated reading system, potentially significantly reducing capsule reading time while surpassing human accuracy. We searched Embase, Pubmed, Medline, and Cochrane databases from inception to 06 Jul 2023 for studies investigating the use of AI for capsule endoscopy and screened retrieved records for eligibility. Quantitative and qualitative data were extracted and synthesised to identify current themes. In the search, 824 articles were collected, and 291 duplicates and 31 abstracts were deleted. After a double-screening process and full-text review, 106 publications were included in the review. Themes pertaining to AI for capsule endoscopy included active gastrointestinal bleeding, erosions and ulcers, vascular lesions and angiodysplasias, polyps and tumours, inflammatory bowel disease, coeliac disease, hookworms, bowel prep assessment, and multiple lesion detection. This review provides current insights into the impact of AI on capsule endoscopy as of 2023. AI holds the potential for faster and precise readings and the prospect of autonomous image analysis. However, careful consideration of diagnostic requirements and potential challenges is crucial. The untapped potential within vision transformer technology hints at further evolution and even greater patient benefit.

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

BACKGROUND

Deep learning provides an efficient automatic image recognition method for small bowel (SB) capsule endoscopy (CE) that can assist physicians in diagnosis. However, the existing deep learning models present some unresolved challenges.

AIM

To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks, and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.

METHODS

The proposed model represents a two-stage method that combined image classification with object detection. First, we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images, normal SB mucosa images, and invalid images. Then, the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding, and the location of the lesion was marked. We constructed training and testing sets and compared model-assisted reading with physician reading.

RESULTS

The accuracy of the model constructed in this study reached 98.96%, which was higher than the accuracy of other systems using only a single module. The sensitivity, specificity, and accuracy of the model-assisted reading detection of all images were 99.17%, 99.92%, and 99.86%, which were significantly higher than those of the endoscopists' diagnoses. The image processing time of the model was 48 ms/image, and the image processing time of the physicians was 0.40 ± 0.24 s/image (P < 0.001).

CONCLUSION

The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images, which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.