Exploring the interior of 3D endoluminal lesions in the air spaces by a novel electronic biopsy technique: A preliminary study of endoluminal colon lesions.

To explore the interior of a lesion in a 3D endoluminal view, this study investigates the application of an 'electronic biopsy' (EB) technique to computed tomographic colonography (CTC) for further differentiation and 2D image correlation of endoluminal lesions in the air spaces. A retrospective study of sixty-two various endoluminal lesions from thirty patients (13 males, 17 females; age range, 31 to 90 years) was approved by our institutional review board and evaluated. The endoluminal lesions were segmented using gray-level threshold and reconstructed into isosurfaces using a marching cube algorithm. EB allows users to interactively erode and apply grey-level mapping (GM) to the surface of the region of interest (ROI) in 3D CTC. Radiologists conducted the clinical evaluation, and the resulting data were analyzed. EB significantly improves 3D gray-level presentation for evaluating the surface and inside of endoluminal lesions over that of SR, GM or target GM (TGM) (P < 0.01) with preservation of the 3D spatial effect. Moreover, 3D to 2D image correlation were achieved in any layer of the lesion using EB as did GM/TGM on the surface. The specificity and diagnostic accuracy of EB are significantly greater than those of SR (P < 0.01). These performance can be better further with GM/TGM and reach the best with EB (specificity, 89.3-92.9%; accuracy, 95.2-96.8%). EB can be used in CTC to improve the differentiation of endoluminal lesions. EB increases 3D to 2D image correlations of the lesions on or beneath the lesion surface.

A Novel Convolutional Neural Network Model as an Alternative Approach to Bowel Preparation Evaluation Before Colonoscopy in the COVID-19 Era: A Multicenter, Single-Blinded, Randomized Study.

INTRODUCTION: Adequate bowel preparation is key to a successful colonoscopy, which is necessary for detecting adenomas and preventing colorectal cancer. We developed an artificial intelligence (AI) platform using a convolutional neural network (CNN) model (AI-CNN model) to evaluate the quality of bowel preparation before colonoscopy. METHODS: This was a colonoscopist-blinded, randomized study. Enrolled patients were randomized into an experimental group, in which our AI-CNN model was used to evaluate the quality of bowel preparation (AI-CNN group), or a control group, which performed self-evaluation per routine practice (control group). The primary outcome was the consistency (homogeneity) between the results of the 2 methods. The secondary outcomes included the quality of bowel preparation according to the Boston Bowel Preparation Scale (BBPS), polyp detection rate, and adenoma detection rate. RESULTS: A total of 1,434 patients were enrolled (AI-CNN, n = 730; control, n = 704). No significant difference was observed between the evaluation results ("pass" or "not pass") of the groups in the adequacy of bowel preparation as represented by BBPS scores. The mean BBPS scores, polyp detection rate, and adenoma detection rate were similar between the groups. These results indicated that the AI-CNN model and routine practice were generally consistent in the evaluation of bowel preparation quality. However, the mean BBPS score of patients with "pass" results were significantly higher in the AI-CNN group than in the control group, indicating that the AI-CNN model may further improve the quality of bowel preparation in patients exhibiting adequate bowel preparation. DISCUSSION: The novel AI-CNN model, which demonstrated comparable outcomes to the routine practice, may serve as an alternative approach for evaluating bowel preparation quality before colonoscopy.

Multiclassification of Endoscopic Colonoscopy Images Based on Deep Transfer Learning.

With the continuous improvement of human living standards, dietary habits are constantly changing, which brings various bowel problems. Among them, the morbidity and mortality rates of colorectal cancer have maintained a significant upward trend. In recent years, the application of deep learning in the medical field has become increasingly spread aboard and deep. In a colonoscopy, Artificial Intelligence based on deep learning is mainly used to assist in the detection of colorectal polyps and the classification of colorectal lesions. But when it comes to classification, it can lead to confusion between polyps and other diseases. In order to accurately diagnose various diseases in the intestines and improve the classification accuracy of polyps, this work proposes a multiclassification method for medical colonoscopy images based on deep learning, which mainly classifies the four conditions of polyps, inflammation, tumor, and normal. In view of the relatively small number of data sets, the network firstly trained by transfer learning on ImageNet was used as the pretraining model, and the prior knowledge learned from the source domain learning task was applied to the classification task about intestinal illnesses. Then, we fine-tune the model to make it more suitable for the task of intestinal classification by our data sets. Finally, the model is applied to the multiclassification of medical colonoscopy images. Experimental results show that the method in this work can significantly improve the recognition rate of polyps while ensuring the classification accuracy of other categories, so as to assist the doctor in the diagnosis of surgical resection.

Re-initiation of CT colonography services during the COVID-19 pandemic: Preliminary evaluation of safety.

OBJECTIVE: The COVID-19 pandemic has led to cancellation and deferral of many cancer investigations, including CT colonography (CTC). In May 2020, BSGAR and SCoR issued guidelines outlining steps for conduct of CTC in the early recovery phase. We evaluated the implementation of these in four English hospital trusts. METHODS: Ethical permission was not required for this multicentre service evaluation. We identified patients undergoing CTC over a 2-month period from May to July 2020 at four Trusts. We recorded demographics, scan indications, colonic findings, and incidental lung base changes compatible with COVID-19. A subset of patients were contacted via telephone to document new symptoms 2 weeks following their scan. Staff were contacted to determine if any acquired COVID-19 during the period. RESULTS: 224 patients (118 male, 52.7%) were scanned during the period. In 55 patients (24.6%), CTC showed a ≥6 mm polyp. 33 of 224 (14.7%) scans showed incidental lung base changes felt unrelated to COVID-19, and only one patient had changes indeterminate for COVID-19; no classic COVID-19 pulmonary changes were found. Of 169 patients with telephone follow-up, none reported any new symptoms of COVID-19 (cough, fever, anosmia, ageusia) within 14 days of CTC. None of the 86 staff contacted developed COVID-19. CONCLUSION: We found no cases of patients or staff acquiring COVID-19 infection following CTC; and no evidence of significant asymptomatic COVID-19 patients attending for CTC appointments based on lung base changes. ADVANCES IN KNOWLEDGE: Our findings suggest that current practice is unlikely to contribute significantly to spread of SARS-nCOV2. Cancer and significant polyp detection rates were high, underlining the importance of maintaining service provision.