The Relationship between Post-colonoscopy Colorectal Cancer and Quality Indicators of Colonoscopy: The Latest Single-center Cohort Study with a Review of the Literature

AI support for colonoscopy quality control using CNN and transformer architectures

BACKGROUND

Construct deep learning models for colonoscopy quality control using different architectures and explore their decision-making mechanisms.

METHODS

A total of 4,189 colonoscopy images were collected from two medical centers, covering different levels of bowel cleanliness, the presence of polyps, and the cecum. Using these data, eight pre-trained models based on CNN and Transformer architectures underwent transfer learning and fine-tuning. The models' performance was evaluated using metrics such as AUC, Precision, and F1 score. Perceptual hash functions were employed to detect image changes, enabling real-time monitoring of colonoscopy withdrawal speed. Model interpretability was analyzed using techniques such as Grad-CAM and SHAP. Finally, the best-performing model was converted to ONNX format and deployed on device terminals.

RESULTS

The EfficientNetB2 model outperformed other architectures on the validation set, achieving an accuracy of 0.992. It surpassed models based on other CNN and Transformer architectures. The model's precision, recall, and F1 score were 0.991, 0.989, and 0.990, respectively. On the test set, the EfficientNetB2 model achieved an average AUC of 0.996, with a precision of 0.948 and a recall of 0.952. Interpretability analysis showed the specific image regions the model used for decision-making. The model was converted to ONNX format and deployed on device terminals, achieving an average inference speed of over 60 frames per second.

CONCLUSIONS

The AI-assisted quality system, based on the EfficientNetB2 model, integrates four key quality control indicators for colonoscopy. This integration enables medical institutions to comprehensively manage and enhance these indicators using a single model, showcasing promising potential for clinical applications.

Importance of preoperative total colonoscopy and endoscopic resection after self-expandable metallic stent placement for obstructive colorectal cancer as a bridge-to-surgery

BACKGROUND AND AIM

Colonic self-expandable metallic stent (SEMS) placement enables preoperative total colonoscopy (TCS) in patients with obstructive colorectal cancer. Following SEMS placement, it is possible to assess the presence or absence of synchronous proximal colon cancers and perform preoperative endoscopic resection (ER) for neoplastic lesions proximal to the primary lesion. The objective of this study was to determine the usefulness and safety of preoperative TCS and ER after SEMS placement in patients with obstructive colorectal cancer.

METHODS

From April 2016 to March 2022, we enrolled 100 patients with obstructive colorectal cancer who underwent SEMS placement, including 86 patients who underwent preoperative TCS after SEMS placement. Complications associated with preoperative TCS and ER after SEMS placement and the characteristics of the neoplastic lesions were assessed.

RESULTS

The success rate of SEMS placement as bridge-to-surgery was 98.0%; six patients had associated complications. Preoperative TCS was performed 8 (range: 1-30) days after SEMS placement. Four patients had synchronous advanced cancers. Nine non-advanced synchronous cancers, 116 adenomas, and 18 sessile-serrated lesions were treated by preoperative TCS and ER after SEMS placement. No procedure-related complications, namely stent migration, bleeding, and perforation were observed. Forty-five patients underwent follow-up TCS 1 year after surgery. Only one patient with submucosal invasive cancer required a second surgery.

CONCLUSIONS

Preoperative TCS and ER after SEMS placement was performed with no complications. This approach allows preoperative evaluation of the entire colon and the treatment of precancerous lesions. (240 words).

lncRNA pair as candidate diagnostic signature for colorectal cancer based on the within-sample relative expression levels

Background

Early diagnosis of colorectal cancer could significantly improve the prognosis and reduce mortality. However, indeterminate diagnosis is often met in pathology diagnosis in biopsy samples. Abnormal expression of long non-coding RNA (lncRNA) is associated with the initiation and progression of colorectal cancer. It is of great value and clinical significance to explore lncRNAs as candidate diagnostic biomarkers in colorectal cancer.

Methods

Based on the within-sample relative expression levels of lncRNA pairs, we identified a group of candidate diagnostic biomarkers for colorectal cancer. In addition, we validated it in independent datasets produced by different laboratories and different platforms. We also tested it in colorectal cancer tissue samples using quantitative real-time polymerase chain reaction (RT-qPCR).

Results

A biomarker consisting of six lncRNA pairs including nine lncRNAs was identified for the diagnosis of colorectal cancer. For a total of 950 cancer samples and 247 non-cancer samples, both of the sensitivity and specificity could achieve approximately 90%. For adenoma samples, the accuracy could achieve 73%. For normal tissues from inflammatory bowel disease patients, 93% (14/15) were correctly classified as non-cancer. Furthermore, the lncRNA pair biomarker showed excellent performance in all clinical stages; even in the early stage, the accuracy could achieve 87% and 82% in stage I and II. Meanwhile, the biomarker was also robust to the microsatellite instability status. More importantly, we measured the biomarker in 35 colorectal cancer and 30 cancer-adjacent tissue samples using quantitative real-time polymerase chain reaction (RT-qPCR). The accuracy could achieve 93.3% (70/75). Specially, even in early-stage tumors (I and II), the accuracy could also achieve 90.9% (30/33). The enrichment analysis revealed that these lncRNAs were involved in highly associated cancer pathways and immune-related pathways. Immune analysis showed that these marker lncRNAs were associated with multiple immune cells, implying that they might be involved in the regulation of immune cell functions in colorectal cancer. Most of the biomarker lncRNAs were also differentially expressed between the mutant group and wild-type group of colorectal cancer driver genes.

Conclusion

We identified and validated six lncRNA pairs including nine lncRNAs as a biomarker for assisting in the diagnosis of colorectal cancer.

Analysis of Post-Colonoscopy Colorectal Cancer and Its Subtypes in a Screening Programme

Using the algorithm of the World Endoscopy Organisation (WEO), we have studied retrospectively all colorectal cancers, both detected and non-detected by the Basque Country screening programme from 2009 to 2017. In the screening programme 61,335 colonoscopies were performed following a positive Faecal Immunochemical test (FIT) (≥20 µg Hb/g faeces) and the 128 cases of post-colonoscopy colorectal cancer (PCCRC) detected were analysed. Among them, 50 interval type PCCRCs were diagnosed (before the recommended surveillance), 0.8 cases per 1000 colonoscopies performed, and 78 non-interval type PCCRCs (in the surveillance carried out at the recommended time or delayed), 1.3 per 1000 colonoscopies. Among the non-interval type PCCRCs, 61 cases were detected in the surveillance carried out at the recommended time (type A) and 17 when the surveillance was delayed (type B), 1 case per 1000 colonoscopies performed and 0.28 cases per 1000 colonoscopies performed, respectively. Interval type PCCRC is less frequent than non-interval type PCCRC. In interval type PCCRCs, CRCs detected in advanced stages (stages III-IV) were significantly more frequent than those detected in early stages, compared to those of non-interval type PCCRCs (OR = 3.057; 95% CI, 1.410-6.625; p < 0.005). Non-interval type B PCCRCs are less frequent than non-interval type A PCCRCs, but the frequency of advanced stages is higher in interval type B PCCRCs.