Estimation of Invasion Depth: The First Key to Successful Colorectal ESD

Survival machine learning model of T1 colorectal postoperative recurrence after endoscopic resection and surgical operation: a retrospective cohort study

OBJECTIVE

To construct a postoperative recurrence prediction model for patients with T1 colorectal cancer after endoscopic resection and surgical operation via survival machine learning algorithms.

METHODS

Based on two tertiary-level affiliated hospitals, case data of 580 patients with T1 colorectal cancer treated by endoscopic resection and surgery were obtained, and patients' personal information, treatment modalities, and pathology-related information were extracted. After Boruta's algorithmic feature selection, predictors with significant contributions were identified. The patients were divided into a train set and a test set at a ratio of 7:3, and five survival machine learning models were subsequently built, namely, Randomized Survival Forest (RSF), Gradient Boosting (GB), Survival Tree (ST), CoxPH and Coxnet. Interpretability analysis of the model is based on the SHAP algorithm.

RESULTS

Patients at high risk of lymph node metastasis have a poor prognosis, but different treatment modalities do not significantly affect the prognosis of patients with recurrence. The Random Survival Forest model shows better performance, with a C-index and Integrated Brier Score of 0.848 and 0.098 in the test set, respectively, and its time-dependent AUC is 0.918. The interpretability analysis of the model revealed that submucosal invasion depth < 1000 μm, tumor budding grade of BD1, lymphovascular invasion and perineural invasion are absent, well differentiated cancer cells, and tumor size < 20 mm have positive effects on the model, lts negative gain characteristics are a contributing factor to patient relapse.

CONCLUSIONS

The prognostic model constructed via survival machine learning for patients with T1 colorectal cancer has good performance, and can provide accurate individualized predictions.

Deep Learning in Endoscopic Ultrasound: A Breakthrough in Detecting Distal Cholangiocarcinoma

INTRODUCTION

Cholangiocarcinoma (CCA) is a highly lethal malignancy originating in the bile ducts, often diagnosed late with poor prognosis. Differentiating benign from malignant biliary tumors remains challenging, necessitating advanced diagnostic techniques.

OBJECTIVE

This study aims to enhance the diagnostic accuracy of endoscopic ultrasound (EUS) for distal cholangiocarcinoma (dCCA) using advanced convolutional neural networks (CCNs) for the classification and segmentation of EUS images, specifically targeting dCCAs, the pancreas, and the bile duct.

MATERIALS AND METHODS

In this retrospective study, EUS images from patients diagnosed with dCCA via biopsy and an EUS-identified bile duct tumor were evaluated. A custom CNN was developed for classification, trained on 156 EUS images. To enhance the model's robustness, image augmentation techniques were applied, generating a total of 1248 images. For tumor and organ segmentation, the DeepLabv3+ network with ResNet50 architecture was utilized, employing Tversky loss to manage unbalanced classes. Performance evaluation included metrics such as accuracy, sensitivity, specificity, and Intersection over Union (IoU). These methods were implemented in collaboration with the ADAPTED Research Group at the Technical University of Cluj-Napoca.

RESULTS

The classification model achieved a high accuracy of 97.82%, with precision and specificity both at 100% and sensitivity at 94.44%. The segmentation models for the pancreas and bile duct demonstrated global accuracies of 84% and 90%, respectively, with robust IoU scores indicating good overlap between predicted and actual contours. The application performed better than the UNet model, particularly in generalization and boundary delineation.

CONCLUSIONS

This study demonstrates the significant potential of AI in EUS imaging for dCCA, presenting a robust tool that enhances diagnostic accuracy and efficiency. The developed MATLAB application serves as a valuable aid for medical professionals, facilitating informed decision-making and improving patient outcomes in the diagnosis of cholangiocarcinoma and related pathologies.

Comparison of two pathological processing methods for large endoscopic submucosal dissection (ESD) specimens

AIMS

Accurate histopathological evaluation of the endoscopic submucosal dissection (ESD) specimens is essential for clinicians to guide further triage and management. This study aimed to report a novel processing technique for large ESD (≥4 cm) specimens.

METHODS

92 patients with colorectal neoplasms who had undergone ESD were included. 46 ESD specimens were treated with conventional handling process, while the rest 46 cases were given the optimised method. Macrobiocassettes and L-shaped embedding moulds were applied in the optimised method. We evaluated the efficacy of this improved procedure in terms of the number of paraffin blocks, storage space and time consumption of pathological assessment.

RESULTS

The average diameter of ESD specimens was 4.5±0.4 cm and 4.7±0.5 cm in the control and test group (p=0.023), respectively. In control group, 398 paraffin blocks of 46 cases were obtained. With the same cases number and larger lesion size, only 276 blocks were achieved in test group (p<0.001). As for the storage space, the total volume of paraffin blocks and slides (4554.0 cm3 and 1207.5 cm3) of optimised method was significantly reduced compared with the control group (6208.8 cm3 and 1741.3 cm3) (p=0.001, p<0.001). In addition, the optimised method was superior to the conventional one in shortening time consumption of pathological assessment (164.5 min and 269.0 min, p<0.001).

CONCLUSIONS

The optimised technique not only reduced the workload and storage space, but also facilitated accurate pathological assessment.

Detecting colorectal lesions with image-enhanced endoscopy: an updated review from clinical trials

Colonoscopy plays an important role in reducing the incidence and mortality of colorectal cancer by detecting adenomas and other precancerous lesions. Image-enhanced endoscopy (IEE) increases lesion visibility by enhancing the microstructure, blood vessels, and mucosal surface color, resulting in the detection of colorectal lesions. In recent years, various IEE techniques have been used in clinical practice, each with its unique characteristics. Numerous studies have reported the effectiveness of IEE in the detection of colorectal lesions. IEEs can be divided into two broad categories according to the nature of the image: images constructed using narrowband wavelength light, such as narrowband imaging and blue laser imaging/blue light imaging, or color images based on white light, such as linked color imaging, texture and color enhancement imaging, and i-scan. Conversely, artificial intelligence (AI) systems, such as computer-aided diagnosis systems, have recently been developed to assist endoscopists in detecting colorectal lesions during colonoscopy. To better understand the features of each IEE, this review presents the effectiveness of each type of IEE and their combination with AI for colorectal lesion detection by referencing the latest research data.

Endoscopic management of patients with high-risk colorectal colitis-associated neoplasia: a Delphi study

BACKGROUND AND AIMS

Current guidelines recommend endoscopic resection of visible and endoscopically resectable colorectal colitis-associated neoplasia (CAN) in patients with inflammatory bowel disease (IBD). However, patients with high-risk CAN (HR-CAN) are often not amenable to conventional resection techniques, and a consensus approach for the endoscopic management of these lesions is presently lacking. This Delphi study aims to reach consensus among experts on the endoscopic management of these lesions.

METHODS

A 3-round modified Delphi process was conducted to reach consensus among worldwide IBD and/or endoscopy experts (n = 18) from 3 continents. Consensus was considered if ≥75% agreed or disagreed. Quality of evidence was assessed by the criteria of the Cochrane Collaboration group.

RESULTS

Consensus was reached on all statements (n = 14). Experts agreed on a definition for CAN and HR-CAN. Consensus was reached on the examination of the colon with enhanced endoscopic imaging before resection, the endoscopic resectability of an HR-CAN lesion, and endoscopic assessment and standard report of CAN lesions. In addition, experts agreed on type of resections of HR-CAN (< 20 mm, >20 mm, with or without good lifting), endoscopic success (technical success and outcomes), histologic assessment, and follow-up in HR-CAN.

CONCLUSIONS

This is the first step in developing international consensus-based recommendations for endoscopic management of CAN and HR-CAN. Although the quality of available evidence was considered low, consensus was reached on several aspects of the management of CAN and HR-CAN. The present work and proposed standardization might benefit future studies.

Endoscopic submucosal dissection for colorectal polyps: outcome determining factors

BACKGROUND

Endoscopic submucosal dissection (ESD) has gained increasing popularity in the management of complicated colorectal polyps. However, clinical outcomes for ESD have remained highly inconsistent worldwide. This study investigated and analysed factors that significantly affect ESD outcomes.

METHODS

We conducted a single-centred retrospective study on 220 colorectal polyps removed by ESD from 1st January 2016 to 31st December 2020. Data were collected and retrieved from clinical records. Variables studied included patient demographics, ESD technicalities and polyp characteristics. The primary outcome was completeness of resection based on en bloc and R0 resection rates. The secondary outcomes were recurrence, complications and hospital stay. Further analysis was performed for significant outcome determining factors.

RESULTS

The en bloc resection and R0 resection rates were 97.3% and 65% respectively. Intraprocedural and delayed perforation rates were 3.2% and 0.5% respectively. Intraprocedural and delayed bleeding rates were both 1.8%. Post-polypectomy syndrome rate was 2.7%. The median hospital stay was 4 days. Submucosal fibrosis was a significant determining factor for lower en bloc resection (p = 0.004), lower R0 resection (p = 0.002), intraprocedural perforation (p = 0.001), intraprocedural bleeding (p = 0.025) and post-polypectomy syndrome (p = 0.039). Hybrid snaring was associated with lower en bloc resection (p < 0.001), while longer ESD time was associated with lower R0 resection (p = 0.003) and post-polypectomy syndrome (p = 0.025). Other significant factors for post-polypectomy syndrome included young age (p = 0.021) and large polyp size (p = 0.018). Secondary analysis showed that submucosal fibrosis was significantly associated with non-granular lesions (p < 0.001) and prior biopsy (p = 0.003).

CONCLUSION

Submucosal fibrosis, hybrid snaring, ESD time, age and polyp size were significant outcome determining factors for ESD. By identifying these factors, strategies may be formulated to improve ESD outcomes.

Development of artificial intelligence technology in diagnosis, treatment, and prognosis of colorectal cancer

Artificial intelligence (AI) technology has made leaps and bounds since its invention. AI technology can be subdivided into many technologies such as machine learning and deep learning. The application scope and prospect of different technologies are also totally different. Currently, AI technologies play a pivotal role in the highly complex and wide-ranging medical field, such as medical image recognition, biotechnology, auxiliary diagnosis, drug research and development, and nutrition. Colorectal cancer (CRC) is a common gastrointestinal cancer that has a high mortality, posing a serious threat to human health. Many CRCs are caused by the malignant transformation of colorectal polyps. Therefore, early diagnosis and treatment are crucial to CRC prognosis. The methods of diagnosing CRC are divided into imaging diagnosis, endoscopy, and pathology diagnosis. Treatment methods are divided into endoscopic treatment, surgical treatment, and drug treatment. AI technology is in the weak era and does not have communication capabilities. Therefore, the current AI technology is mainly used for image recognition and auxiliary analysis without in-depth communication with patients. This article reviews the application of AI in the diagnosis, treatment, and prognosis of CRC and provides the prospects for the broader application of AI in CRC.

Editors' Choice of Noteworthy Clinical Endoscopy Publications in the First Decade

This is a special review to celebrate the 10^th anniversary of Clinical Endoscopy. Each deputy editor has selected articles from one’s subspecialty that are significant in terms of the number of downloads, citations, and clinical importance. The articles included original articles, review articles, systematic reviews, and meta-analyses.

Comparison of long-term recurrence-free survival between primary surgery and endoscopic resection followed by secondary surgery in T1 colorectal cancer

BACKGROUND AND AIMS

We aimed to investigate whether endoscopic resection of T1 colorectal cancer (CRC) before surgery (secondary surgery) unfavorably affects long-term recurrence-free survival (RFS) compared with surgery without prior endoscopic resection (primary surgery).

METHODS

We reviewed the medical records of patients who underwent radical surgery for T1 CRC with high-risk histologic features at a tertiary referral hospital in Korea between 2011 and 2016. The primary outcome was RFS. We performed 2 types of propensity score (PS) analyses to control for confounders.

RESULTS

Of 852 patients, 388 underwent primary surgery and 464 secondary surgery. During the median follow-up period of 57.0 months (range, 41.0-63.0), cancer recurred in 18 patients (2.1%). The 5-year RFS rates did not differ between the primary and secondary surgery groups (97.0 vs 98.5%, P = .194). Further analyses of RFS rates according to nodal stages and number of high-risk histologic features showed no difference between groups. Moreover, RFS rates were not different between the groups after PS matching. In multivariable Cox proportional regression analysis, baseline serum carcinoembryonic antigen level was an independent risk factor for cancer recurrence (hazard ratio, 1.464; 95% confidence interval, 1.242-1.725; P < .001) but prior endoscopic resection of T1 CRC was not (P = .201). Both PS analyses consistently showed no increase in cancer recurrence risk in the secondary surgery group.

CONCLUSIONS

Our data showed no additional cancer recurrence risk by endoscopic resection before surgery of T1 CRC with high-risk histologic features.

RNA-sequencing identification and validation of genes differentially expressed in high-risk adenoma, advanced colorectal cancer, and normal controls

Distinct gene expression patterns that occur during the adenoma-carcinoma sequence need to be determined to analyze the underlying mechanism in each step of colorectal cancer progression. Elucidation of biomarkers for colorectal polyps that harbor malignancy potential is important for prevention of colorectal cancer. Here, we use RNA sequencing to determine gene expression profile in patients with high-risk adenoma treated with endoscopic submucosal dissection by comparing with gene expression in patients with advanced colorectal cancer and normal controls. We collected 70 samples, which consisted of 27 colorectal polyps, 24 cancer tissues, and 19 normal colorectal mucosa. RNA sequencing was performed on an Illumina platform to select differentially expressed genes (DEGs) between colorectal polyps and cancer, polyps and controls, and cancer and normal controls. The Kyoto Gene and Genome Encyclopedia (KEGG) and gene ontology (GO) analysis, gene-concept network, GSEA, and a decision tree were used to evaluate the DEGs. We selected the most highly expressed genes in high-risk polyps and validated their expression using real-time PCR and immunohistochemistry. Compared to patients with colorectal cancer, 82 upregulated and 24 downregulated genes were detected in high-risk adenoma. In comparison with normal controls, 33 upregulated and 79 downregulated genes were found in high-risk adenoma. In total, six genes were retrieved as the highest and second highest expressed in advanced polyps and cancers among the three groups. Among the six genes, ANAX3 and CD44 expression in real-time PCR for validation was in good accordance with RNA sequencing. We identified differential expression of mRNAs among high-risk adenoma, advanced colorectal cancer, and normal controls, including that of CD44 and ANXA3, suggesting that this cluster of genes as a marker of high-risk colorectal adenoma.

Role of Artificial Intelligence in Video Capsule Endoscopy

Capsule endoscopy (CE) has been increasingly utilised in recent years as a minimally invasive tool to investigate the whole gastrointestinal (GI) tract and a range of capsules are currently available for evaluation of upper GI, small bowel, and lower GI pathology. Although CE is undoubtedly an invaluable test for the investigation of small bowel pathology, it presents considerable challenges and limitations, such as long and laborious reading times, risk of missing lesions, lack of bowel cleansing score and lack of locomotion. Artificial intelligence (AI) seems to be a promising tool that may help improve the performance metrics of CE, and consequently translate to better patient care. In the last decade, significant progress has been made to apply AI in the field of endoscopy, including CE. Although it is certain that AI will find soon its place in day-to-day endoscopy clinical practice, there are still some open questions and barriers limiting its widespread application. In this review, we provide some general information about AI, and outline recent advances in AI and CE, issues around implementation of AI in medical practice and potential future applications of AI-aided CE.

The impact of transanal local excision of early rectal cancer on completion rectal resection without neoadjuvant chemoradiotherapy: a systematic review

BACKGROUND

The impact of transanal local excision (TAE) of early rectal cancer (ERC) on subsequent completion rectal resection (CRR) for unfavorable histology or margin involvement is unclear. The aim of this study was to provide a comprehensive review of the literature on the impact of TAE on CRR in patients without neoadjuvant chemoradiotherapy (CRT).

METHODS

We performed a systematic review of the literature up to March 2020. Medline and Cochrane libraries were searched for studies reporting outcomes of CRR after TAE for ERC. We excluded patients who had neoadjuvant CRT and endoscopic local excision. Surgical, functional, pathological and oncological outcomes were assessed. The Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines were followed.

RESULTS

Sixteen studies involving 353 patients were included. Pathology following TAE was as follows T0 = 2 (0.5%); T1 = 154 (44.7%); T2 = 142 (41.2%); T3 = 43 (12.5%); Tx = 3 (0.8%); T not reported = 9. Fifty-three percent were > T1. Abdominoperineal resection (APR) was performed in 80 (23.2%) patients. Postoperative major morbidity and mortality occurred in 22 (11.4%) and 3 (1.1%), patients, respectively. An incomplete mesorectal fascia resulting in defects of the mesorectum was reported in 30 (24.6%) cases. Thirteen (12%) patients developed recurrence: 8 (3.1%) local, 19 (7.3%) distant, 4 (1.5%) local and distant. The 5-year cancer-specific survival was 92%. Only 1 study assessed anal function reporting no continence disorders in 11 patients. In the meta-analysis, CRR after TAE showed an increased APR rate (OR 5.25; 95% CI 1.27-21.8; p 0.020) and incomplete mesorectum rate (OR 3.48; 95% CI 1.32-9.19; p 0.010) compared to primary total mesorectal excision (TME). Two case matched studies reported no difference in recurrence rate and disease free survival respectively.

CONCLUSIONS

The data are incomplete and of low quality. There was a tendency towards an increased risk of APR and poor specimen quality. It is necessary to improve the accuracy of preoperative staging of malignant rectal tumors in patients scheduled for TAE.

Controversies in EUS: Do we need miniprobes?

This is the fifth in a series of papers entitled "Controversies in EUS." In the current paper, we deal with high-resolution catheter probes, otherwise known as EUS miniprobes (EUS-MPs). The application of miniprobes for early carcinomas in the entire intestinal tract, for subepithelial lesions, and for findings in the bile duct and pancreatic duct as well as endobronchial use is critically discussed. Submucous lesions, especially in the colon, but also early carcinomas in special cases are considered the most important indications. The argument is illustrated by numerous examples.

The Role of Artificial Intelligence in Endoscopic Ultrasound for Pancreatic Disorders

The use of artificial intelligence (AI) in various medical imaging applications has expanded remarkably, and several reports have focused on endoscopic ultrasound (EUS) images of the pancreas. This review briefly summarizes each report in order to help endoscopists better understand and utilize the potential of this rapidly developing AI, after a description of the fundamentals of the AI involved, as is necessary for understanding each study. At first, conventional computer-aided diagnosis (CAD) was used, which extracts and selects features from imaging data using various methods and introduces them into machine learning algorithms as inputs. Deep learning-based CAD utilizing convolutional neural networks has been used; in these approaches, the images themselves are used as inputs, and more information can be analyzed in less time and with higher accuracy. In the field of EUS imaging, although AI is still in its infancy, further research and development of AI applications is expected to contribute to the role of optical biopsy as an alternative to EUS-guided tissue sampling while also improving diagnostic accuracy through double reading with humans and contributing to EUS education.

Artificial intelligence in gastrointestinal endoscopy: general overview

Artificial intelligence (AI) is now a trendy subject in clinical medicine and especially in gastrointestinal (GI) endoscopy. AI has the potential to improve the quality of GI endoscopy at all levels. It will compensate for humans' errors and limited capabilities by bringing more accuracy, consistency, and higher speed, making endoscopic procedures more efficient and of higher quality. AI showed great results in diagnostic and therapeutic endoscopy in all parts of the GI tract. More studies are still needed before the introduction of this new technology in our daily practice and clinical guidelines. Furthermore, ethical clearance and new legislations might be needed. In conclusion, the introduction of AI will be a big breakthrough in the field of GI endoscopy in the upcoming years. It has the potential to bring major improvements to GI endoscopy at all levels.

Use of artificial intelligence in improving adenoma detection rate during colonoscopy: Might both endoscopists and pathologists be further helped

Colonoscopy remains the standard strategy for screening for colorectal cancer around the world due to its efficacy in both detecting adenomatous or pre-cancerous lesions and the capacity to remove them intra-procedurally. Computer-aided detection and diagnosis (CAD), thanks to the brand new developed innovations of artificial intelligence, and especially deep-learning techniques, leads to a promising solution to human biases in performance by guarantying decision support during colonoscopy. The application of CAD on real-time colonoscopy helps increasing the adenoma detection rate, and therefore contributes to reduce the incidence of interval cancers improving the effectiveness of colonoscopy screening on critical outcome such as colorectal cancer related mortality. Furthermore, a significant reduction in costs is also expected. In addition, the assistance of the machine will lead to a reduction of the examination time and therefore an optimization of the endoscopic schedule. The aim of this opinion review is to analyze the clinical applications of CAD and artificial intelligence in colonoscopy, as it is reported in literature, addressing evidence, limitations, and future prospects.

Deep learning analysis for the detection of pancreatic cancer on endosonographic images: a pilot study

BACKGROUND/PURPOSE

The application of artificial intelligence to clinical diagnostics using deep learning has been developed in recent years. In this study, we developed an original computer-assisted diagnosis (CAD) system using deep learning analysis of EUS images (EUS-CAD), and assessed its ability to detect pancreatic ductal carcinoma (PDAC), using control images from patients with chronic pancreatitis (CP) and those with a normal pancreas (NP).

METHODS

A total of 920 endosonographic images were used for the training and 10-fold cross-validation, and another 470 images were independently tested. The detection abilities in both the validation and test setting were assessed, and independent factors associated with misdetection were identified among participants' characteristics and endosonographic image features.

RESULTS

Regarding the detection ability of EUS-CAD, the areas under the receiver operating characteristic curve were found to be 0.924 and 0.940 in the validation and test setting, respectively. In the analysis of misdetection, no factors were identified on univariate analysis in PDAC cases. On multivariate analysis of non-PDAC cases, only mass formation was associated with overdiagnosis of tumors.

CONCLUSIONS

Our pilot study demonstrated the efficacy of EUS-CAD for the detection of PDAC.

Curriculum for optical diagnosis training in Europe: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

This manuscript represents an official Position Statement of the European Society of Gastrointestinal Endoscopy (ESGE) aiming to guide general gastroenterologists to develop and maintain skills in optical diagnosis during endoscopy. In general, this requires additional training beyond the core curriculum currently provided in each country. In this context, ESGE have developed a European core curriculum for optical diagnosis practice across Europe for high quality optical diagnosis training. 1:  ESGE suggests that every endoscopist should have achieved general competence in upper and/or lower gastrointestinal (UGI/LGI) endoscopy before commencing training in optical diagnosis of the UGI/LGI tract, meaning personal experience of at least 300 UGI and/or 300 LGI endoscopies and meeting the ESGE quality measures for UGI/LGI endoscopy. ESGE suggests that every endoscopist should be able and competent to perform UGI/LGI endoscopy with high definition white light combined with virtual and/or dye-based chromoendoscopy before commencing training in optical diagnosis. 2:  ESGE suggests competency in optical diagnosis can be learned by attending a validated optical diagnosis training course based on a validated classification, and self-learning with a minimum number of lesions. If no validated training course is available, optical diagnosis can only be learned by attending a non-validated onsite training course and self-learning with a minimum number of lesions. 3:  ESGE suggests endoscopists are competent in optical diagnosis after meeting the pre-adoption and learning criteria, and meeting competence thresholds by assessing a minimum number of lesions prospectively during real-time endoscopy. ESGE suggests ongoing in vivo practice by endoscopists to maintain competence in optical diagnosis. If a competent endoscopist does not perform in vivo optical diagnosis on a regular basis, ESGE suggests repeating the learning and competence phases to maintain competence.Key areas of interest were optical diagnosis training in Barrett's esophagus, esophageal squamous cell carcinoma, early gastric cancer, diminutive colorectal lesions, early colorectal cancer, and neoplasia in inflammatory bowel disease. Condition-specific recommendations are provided in the main document.

Linear-array EUS improves the accuracy of predicting deep submucosal invasion in non-pedunculated rectal polyps compared with radial EUS: a prospective observational study

BACKGROUND

Radial endoscopic ultrasound (EUS) is typically used to estimate the depth of rectal polyp invasion, however, there are no data on linear EUS in this setting and its relative accuracy compared to radial EUS.

METHODS

In this prospective cohort study, 89 patients with non-pedunculated rectal polyp who underwent linear EUS or radial EUS were prospectively enrolled. The invasion depth was measured for each polyp and categorized as mucosal to shallow submucosal(SM_s) or deep submucosal(SM_d) invasion. Invasion measurements were compared with the final diagnosis on histopathology.

RESULTS

A total of 58 patients underwent radial EUS and 31 patients underwent linear EUS examination. There were 38 lesions correctly diagnosed in the radial EUS group and 29 correctly diagnosed lesions in the linear EUS group. The diagnostic accuracy of SM_d invasion for linear EUS was significantly higher than radial EUS (0.936 vs. 0.655, p = 0.003). A significant difference was also noted for specificity between the two groups (0.963 vs. 0.659, p = 0.003). Univariate analysis showed radial EUS type (OR 0.131, 95% CI 0.028-0.606, p = 0.009) to be an independent predictor for incorrect diagnosis. The area under the receiver operating curve (ROC) was 0.856 and 0.651 for linear EUS and radial EUS, respectively. It was noted that four patients underwent unnecessary surgery for radial EUS while there were no such patients in the linear EUS group.

CONCLUSIONS

Linear EUS was more accurate for determining SM_d invasion and contributed to the selection of appropriate treatment modalities in patients with non-pedunculated rectal polyp.

Endoscopic imaging techniques for detecting early colorectal cancer

PURPOSE OF REVIEW

The detection of early colorectal cancer has improved notably since the introduction of bowel cancer screening programmes. This has created new challenges from endoscopic, histological and therapeutic perspectives. Here, we outline the limitations of current clinical practice and ways of implementing optical diagnosis to overcome these limitations.

RECENT FINDINGS

Virtual chromoendoscopy without magnification for predicting or ruling out deep submucosal invasion is useful in real clinical practice for most lesions. However, magnifying virtual chromoendoscopy is needed to make an accurate diagnosis in nonulcerated narrow-band imaging international colorectal endoscopic (NICE) type 3 lesions or NICE type 2 lesions with depressed areas or of nodular mixed type. Finally, dye-based magnifying chromoendoscopy is needed in Japanese NBI Expert Team 2B lesions assessed with magnifying virtual chromoendoscopy.

SUMMARY

A four-step strategy is proposed, combining white-light assessment, virtual chromoendoscopy without magnification, virtual chromoendoscopy with magnification and dye-based chromoendoscopy with magnification.