Importance of histological evaluation in endoscopic resection of early colorectal cancer

Emerging Technologies in Endoscopy for Gastrointestinal Neoplasms: A Comprehensive Overview

Gastrointestinal neoplasms are a growing global health concern, requiring prompt identification and treatment. Endoscopic procedures have revolutionized the detection and treatment of gastrointestinal tumors by providing accurate, minimally invasive methods. Early-stage malignancies can be treated with endoscopic excision, leading to improved outcomes and increased survival rates. Precancerous lesions, like adenomatous polyps, can be prevented by removing them, reducing cancer occurrence and death rates. Advanced techniques like chromoendoscopy, narrow-band imaging, and confocal laser endomicroscopy improve the ability to see the mucosa surface and diagnose conditions. Artificial Intelligence (AI) applications in endoscopy can enhance diagnostic accuracy and predict histology outcomes. However, challenges remain in accurately defining lesions and ensuring precise diagnosis and treatment selection. Molecular imaging approaches and therapeutic modalities like photodynamic therapy and endoscopic ultrasonography-guided therapies hold potential but require further study and clinical confirmation. This study examines the future prospects and obstacles in endoscopic procedures for the timely identification and treatment of gastrointestinal cancers. The focus is on developing technology, limits, and prospective effects on clinical practice.

Application of artificial intelligence in endoscopic gastrointestinal tumors

With an increasing number of patients with gastrointestinal cancer, effective and accurate early diagnostic clinical tools are required provide better health care for patients with gastrointestinal cancer. Recent studies have shown that artificial intelligence (AI) plays an important role in the diagnosis and treatment of patients with gastrointestinal tumors, which not only improves the efficiency of early tumor screening, but also significantly improves the survival rate of patients after treatment. With the aid of efficient learning and judgment abilities of AI, endoscopists can improve the accuracy of diagnosis and treatment through endoscopy and avoid incorrect descriptions or judgments of gastrointestinal lesions. The present article provides an overview of the application status of various artificial intelligence in gastric and colorectal cancers in recent years, and the direction of future research and clinical practice is clarified from a clinical perspective to provide a comprehensive theoretical basis for AI as a promising diagnostic and therapeutic tool for gastrointestinal cancer.

Artificial intelligence-enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth

BACKGROUND AND AIMS

Endoscopic submucosal dissection (ESD) and EMR are applied in treating superficial colorectal neoplasms but are contraindicated by deeply invasive colorectal cancer (CRC). The invasion depth of neoplasms can be examined by an automated artificial intelligence (AI) system to determine the applicability of ESD and EMR.

METHODS

A deep convolutional neural network with a tumor localization branch to guide invasion depth classification was constructed on the GoogLeNet architecture. The model was trained using 7734 nonmagnified white-light colonoscopy (WLC) images supplemented by image augmentation from 657 lesions labeled with histopathologic analysis of invasion depth. An independent testing dataset consisting of 1634 WLC images from 156 lesions was used to validate the model.

RESULTS

For predicting noninvasive and superficially invasive neoplasms, the model achieved an overall accuracy of 91.1% (95% confidence interval [CI], 89.6%-92.4%), with 91.2% sensitivity (95% CI, 88.8%-93.3%) and 91.0% specificity (95% CI, 89.0%-92.7%) at an optimal cutoff of .41 and the area under the receiver operating characteristic (AUROC) curve of .970 (95% CI, .962-.978). Inclusion of the advanced CRC data significantly increased the sensitivity in differentiating superficial neoplasms from deeply invasive early CRC to 65.3% (95% CI, 61.9%-68.8%) with an AUROC curve of .729 (95% CI, .699-.759), similar to experienced endoscopists (.691; 95% CI, .624-.758).

CONCLUSIONS

We have developed an AI-enhanced attention-guided WLC system that differentiates noninvasive or superficially submucosal invasive neoplasms from deeply invasive CRC with high accuracy, sensitivity, and specificity.

The effectiveness of Video-feedback Intervention to promote Positive Parenting for Foster Care (VIPP-FC): study protocol for a randomized controlled trial

Background

Foster children are at higher risk of the development of behavior and emotional problems, which can contribute to the development of insecure attachment bonds with their foster parents and (subsequently) to placement breakdown. Sensitive parenting might minimize the adverse effects of the behavior and emotional problems. Video-feedback Intervention to promote Positive Parenting and Sensitive Discipline in Foster Care (VIPP-FC) is an adaptation of the evidence-based Video-feedback Intervention to promote Positive Parenting and Sensitive Discipline (VIPP-SD) and aims at increasing sensitive parenting and the use of sensitive discipline strategies of foster parents. The current study is the first to examine the effectiveness of VIPP-FC.

Methods

A randomized controlled trial is used with 60 foster parent-child dyads (intervention group n = 30, control group n = 30). The primary outcomes are parental sensitivity, parental disciplining, and parental attitudes towards parenting. Data about attachment (in)security, behavioral and emotional problems, neurobiological parameters, and possible confounders is additionally collected.

Discussion

Examining the effectiveness of VIPP-FC contributes to the knowledge of evidence-based prevention and intervention programs needed in foster care practice.

Trial registration

NTR3899.

Can positron emission tomography detect colorectal adenomas and cancers?

BACKGROUND AND AIM

Fluorine-18 2-fluoro-2-deoxy-d-glucose positron emission tomography (PET) is effective and less invasive than other modalities used to diagnose tumors, including colorectal cancer (CRC). However, the detectability of adenomas and CRCs, especially in the early stages, is unclear.

METHODS

We evaluated the records of 2323 consecutive eligible patients who underwent both a total colonoscopy (TCS) and PET between October 2002 and September 2012 at a tertiary cancer center. The PET findings were verified by TCS performed independently within 1 year. Target lesions were defined as CRCs and adenomas that were 6 mm or larger in size.

RESULTS

Total colonoscopy detected 532 target lesions ≥ 6 mm in size: 56 T2-T4 CRCs, 39 T1 CRCs, 223 advanced adenomas, and 214 low-grade adenomas. Of the 532 lesions, 216 (40.6%) were PET positive. Of the 369 cases with positive uptakes, PET detected target lesions in the matched segments for 58.5% (216/369). Sensitivity of PET to T2-T4 CRCs, T1 CRCs, advanced adenomas, and low-grade adenomas was 92.9%, 79.5%, 50.7%, and 9.3%, respectively. PET could detect 76.5% (13/17) of T1 CRCs whose size is 10 to 19 mm and 85.0% (17/20) of T1 CRCs equal or larger than 20 mm. The multivariate analysis excluding T2-T4 CRCs showed malignant histology, larger size, protruded lesions, villous histology, and lesions in distal colon were significant factors.

CONCLUSIONS

Sensitivity of PET for detecting T2-T4 and even T1 cancers are promising. However, sensitivity of PET to adenomas, even advanced adenomas, is limited.

Factors predicting clinical outcomes of endoscopic submucosal dissection in the rectum and sigmoid colon during the learning curve

BACKGROUND AND STUDY AIMS

Colorectal endoscopic submucosal dissection (ESD) is associated with significant technical difficulty, long procedure time, and increased risk of complications, especially perforation. This study aimed to determine the factors associated with clinical results of ESD during the learning curve.

PATIENTS AND METHODS

In total, 44 patients with sessile and flat rectal and sigmoid colon lesions underwent ESD from November 2009 to September 2013. The procedure time, resection method, tumor size, location, gross morphology, presence of fibrosis, histologic findings, rates of en bloc and piecemeal resections and perforation were analyzed. The ESD procedure was classified as technically difficult in the case of procedure time > 120 minutes and/or piecemeal resection. The whole study time was divided into two periods: first period: resections 1 - 22, second period: resections 23 - 44.

RESULTS

En bloc and R0 resection have been achieved in 84.1 % of lesions. The mean procedure time was 119.95 ± 11.22 minutes (range 25 - 360 minutes). Perforation was seen in five cases (11.4 %). A larger tumor size was a risk factor for difficult ESD (P = 0.0001). A finding of fibrosis was a risk factor for piecemeal ESD (P = 0.0074), and perforation (P = 0.0012). There was a high direct positive correlation between tumor size and operation time (r = 0.83, P < 0.0001, 0.95 and 0.99 confidence interval for rho 0.71 - 0.904). There was no significant difference between the first and second period in terms of mean procedure time, en bloc resection or complication rate.

CONCLUSION

A larger tumor size was associated with technically difficult ESD. Severe submucosal fibrosis was a risk factor for both piecemeal resection and perforation.

Training methods and models for colonoscopic insertion, endoscopic mucosal resection, and endoscopic submucosal dissection

Colonoscopic examination is considered an effective examination for the detection of colorectal cancers. Additionally, early colorectal cancers can be resected using endoscopic techniques such as endoscopic mucosal resection and endoscopic submucosal dissection. However, those examinations and treatments need special techniques. Various training methods are practiced to acquire such endoscopic techniques throughout the world. In clinical cases, magnetic positioning devices help endoscopic insertion by less experienced endoscopists. There is a physical model made by polyvinyl chloride and a virtual simulator for training of colonoscopic insertion. Various techniques including a method to apply pressure to the abdomen and consideration for patient's pain can be trained using these models. In view of extensive training of endoscopic mucosal resection and endoscopic submucosal dissection, animal models are useful and actually used. Live animal models of minipig, which entails blood flow, are ideal and used frequently, but are cumbersome to prepare. On the other hand, ex vivo animal models using intestine of porcine and bovine are convenient for preparation and less expensive. Unique ex vivo animal models with blood flow have been developed recently and techniques for hemostasis can be practiced. With respect to a method of training for colorectal endoscopic submucosal dissection, a stepwise system has been adopted throughout the world. Thus, first they observe the expert's technique, then practice training of animal models, and finally, they perform clinical rectal cases. The system is useful for a safe and definite procedure. In this review, we reveal various training methods for colonoscopic examinations and treatments.

Ability of a novel blue laser imaging system for the diagnosis of colorectal polyps

BACKGROUND

A new endoscope system with a laser light source, blue laser imaging (BLI), has been developed by Fujifilm that allows for narrow-band light observation. The aim of the present study was to evaluate the utility of BLI for the diagnosis of colorectal polyps.

METHODS

We retrospectively analyzed 314 colorectal polyps that were examined with BLI observation at Kyoto Prefectural University of Medicine between September 2011 and January 2013. The surface and vascular patterns of polyps detected by published narrow-band imaging magnification: Hiroshima classification were used. Correlations were determined between the classifications and the histopathological diagnoses. Additionally, the ability of BLI without magnification to differentiate between neoplastic or non-neoplastic polyps was analyzed.

RESULTS

A total of 41 hyperplastic polyps, 168 adenomas, 80 intramucosal cancer, 11 shallowly invaded submucosal cancer, and 14 deeply invaded submucosal cancer were analyzed.Hyperplastic polyp was observed in 100% of Type A lesions (39 lesions), adenoma was observed in 89.3% of Type B lesions (159 lesions), intramucosal cancer and shallowly invaded submucosal cancer was observed in 69.6% of Type C1 (92 lesions) and in 84.6% of Type C2 (13 lesions), and deeply invaded submucosal cancer was observed in 81.8% of Type C3 lesions (11 lesions). The overall diagnostic accuracy of BLI with magnification was 84.3%. Additionally, the diagnostic accuracy of BLI without magnification for differentiating between neoplastic and non-neoplastic polyps <10 mm in diameter was 95.2%, which was greater than that of white light (83.2%).

CONCLUSION

BLI was useful for the diagnosis of colorectal polyps.

Multicenter study of endoscopic mucosal resection using 0.13% hyaluronic acid solution of colorectal polyps less than 20 mm in size

PURPOSE

Endoscopic mucosal resection (EMR) of colorectal polyps should be curative and safe. This study aimed to determine the efficacy and safety of colorectal EMR using 0.13% hyaluronic acid (HA) solution.

METHODS

This was a single-armed multicenter prospective open trial conducted at 11 Japanese institutions. Lesion characteristics and various measures of clinical outcome, including en bloc resection, histopathologically complete resection, and postoperative bleeding were analyzed for 624 consecutive patients who underwent EMR of colorectal polyps at ≤20 mm in size from August 2010 to September 2011.

RESULTS

En bloc and complete resection were achieved in 93.3 and 78.3% of 624 lesions. The median EMR procedure time was 2.1 ± 1.5 min. The rates of postoperative bleeding and perforation were 1.1 and 0%. The rate of en bloc resection was higher for polyps at 5-10 mm than for polyps at 11-20 mm (95.1 vs. 85.1%; P < 0.001) and was higher for protruding polyps than for superficial polyps (94.5 vs. 87.1%; P < 0.05). The rate of en bloc resection was also higher for polyps in the left-side colon than for those in the right-side colon or rectum (96.7 vs. 91.6 vs. 90.8%; P < 0.05). Multivariate analysis showed that polyp at 11-20 mm in size and location not on the left-side colon was significantly independent risk factors for failure of en bloc resection.

CONCLUSION

EMR using 0.13% HA of colorectal polyps less than 20 mm in size had high rates of en bloc and complete resection and few complications.

Possibility of ex vivo animal training model for colorectal endoscopic submucosal dissection

PURPOSE

Colorectal endoscopic submucosal dissection (ESD) has not been standardized due to technical difficulties and requires extensive training for reliability. Ex vivo animal model is convenient, but has no blood flow. The objective of this study is to evaluate the characteristics of various ex vivo animal models including a blood flow model for colorectal ESD training and the usefulness of practicing endoscopic hemostasis and closure using an animal model.

METHODS

Harvested porcine cecum, rectum, and stomach and bovine cecum and rectum were analyzed regarding ease of mucosal injection, degree of submucosal elevation, and status of the proper muscle layer. Ex vivo animal model with blood flow was made using the bovine cecum. The vessel around the cecum was detached, and red ink was injected. Endoscopic hemostasis for perioperative hemorrhage and endoscopic closure for perforation were performed in this model.

RESULTS

Mucosal injection was easily performed in the bovine cecum and rectum. Submucosal elevation was low in the bovine cecum, while the proper muscle layer was not tight in the porcine rectum and bovine cecum. Endoscopic hemostasis were accomplished in six (60 %) out of ten procedures of the ex vivo blood flow model. In two non-experts, the completion rates of endoscopic closure were 40 and 60 % in the first five procedures. These rates became 100 % in the last five procedures.

CONCLUSIONS

We have evaluated the characteristics of various ex vivo animal models and shown the possibility of training for endoscopic hemostasis and endoscopic closure in the ex vivo animal model.