Investigation of vertical margin involvement in endoscopic resection for T1 colorectal cancer.

OBJECTIVES: The resection of vertical margin-negative submucosally invasive colorectal cancer (CRC) relies on the pathological risk assessment of lymph node metastasis. However, no large-scale study has clarified the endoscopic resection (ER) outcome for submucosally invasive CRC, focusing on the vertical margin status. This retrospective study aimed to examine vertical margin involvement in ER for submucosally invasive CRC and explore the treatment consequences associated with vertical margin status. METHODS: We analyzed 395 submucosally invasive CRC cases in 389 patients who underwent ER at our hospital between 2008 and 2020. The presence of residual tumors and simultaneous lymph node metastasis in patients who underwent additional surgery was assessed and compared between the vertical incomplete ER and the vertical margin-negative groups. RESULTS: Among the patients, 270 were men, with a median age of 69 years. The vertical incomplete ER rate was 21.5%, with positive vertical margins and unclear vertical margins identified in 12.2% and 9.3% of the cases, respectively. Among 154 patients who underwent additional surgery after ER, the vertical incomplete ER group had a significantly higher residual tumor rate than the vertical margin-negative group (P = 0.001). The vertical incomplete ER group had a significantly higher lymph node metastasis rate than the vertical margin-negative group (P = 0.029). CONCLUSION: This study clarified the substantial risk of vertical incomplete ER in submucosally invasive CRC and revealed the high risk of residual tumor and lymph node metastasis in vertical incomplete ER for submucosal CRC.

Detection of colorectal adenomas with texture and color enhancement imaging: Multicenter observational study.

OBJECTIVES: We aimed to evaluate the efficacy of texture and color enhancement imaging (TXI), which allows the acquisition of brighter images with enhanced color and surface structure in colorectal polyp detection compared to white light imaging. METHODS: Patients who underwent colonoscopy with repeated ascending colon observation using TXI and white light imaging between August 2020 and January 2021 were identified in three institutions. The outcomes included the mean number of adenomas detected per procedure (MAP), adenoma detection rate (ADR), and ascending colonic adenoma miss rate (Ac-AMR). Logistic regression was used to determine the effects of the variables on the outcomes. RESULTS: We included 1043 lesions from 470 patients in the analysis. The MAP, ADR, flat polyp detection rate, and Ac-AMR in TXI and white light imaging were 1.5% (95% confidence interval 1.3-1.6%) vs. 1.0% (0.9-1.1%), 58.2% (51.7-64.6%) vs. 46.8% (40.2-53.4%), 66.2% (59.8-72.2%) vs. 49.8% (43.2-56.4%), and 17.9% (12.1-25.2%) vs. 28.2% (20.0-37.6%), respectively. TXI, age, withdrawal time, and endoscopy type were identified as significant factors affecting the MAP and the ADR using multivariate regression analysis. CONCLUSIONS: Our study indicates that TXI improve the detection of colorectal neoplastic lesions. However, prospective randomized trials are required to confirm these findings.

Requirement of image standardization for AI-based macroscopic diagnosis for surgical specimens of gastric cancer.

PURPOSE: The pathological diagnosis of surgically resected gastric cancer involves both a macroscopic diagnosis by gross observation and a microscopic diagnosis by microscopy. Macroscopic diagnosis determines the location and stage of the disease and the involvement of other organs and surgical margin. Lesion recognition is, thus, an important diagnostic step that requires a skilled pathologist. Nonetheless, artificial intelligence (AI) technologies could allow even inexperienced doctors and laboratory technicians to examine surgically resected specimens without the need for pathologists. However, organ imaging conditions vary across hospitals, and an AI algorithm created in one setting may not work properly in another. Thus, we identified and standardized factors affecting the quality of pathological macroscopic images, which could further affect lesion identification using AI. METHODS: We examined necessary image standardization for developing cancer detection AI for surgically resected gastric cancer by changing the following imaging conditions: focus, resolution, brightness, and contrast. RESULTS: Regarding focus, brightness, and contrast, the farther away the test data were from the training macro-image, the less likely the inference was to be correct. Little change was observed for resolution, even with differing conditions for the training and test data. Regarding focus, brightness, and contrast, there were conditions appropriate for AI. Contrast, in particular, was far from the conditions appropriate for humans. CONCLUSION: Standardizing focus, brightness, and contrast is important in the development of AI methodologies for lesion detection in surgically resected gastric cancer. This standardization is essential for AI to be implemented across hospitals.

Hot snare polypectomy vs endoscopic mucosal resection using bipolar snare for intermediate size colorectal lesions: Propensity score matching.

BACKGROUND: Endoscopic resection (ER) with bipolar snare, in which the electric current only passes through the tissue between the device's two electrodes, is a prominent method used to prevent perforation due to electricity potentially. ER using bipolar snare with or without submucosal injection enabled safe resection of colorectal lesions measuring 10-15 mm in an ex vivo porcine model. ER with bipolar snare is expected to have good treatment outcomes in 10-15 mm colorectal lesions, with high safety even without submucosal injection. However, no clinical reports have compared treatment outcomes with and without submucosal injection. AIM: To compare the treatment outcomes of bipolar polypectomy with hot snare polypectomy (HSP) to those with endoscopic mucosal resection (EMR). METHODS: In this single-centre retrospective study, we enrolled 10-15 mm nonpedunculated colorectal lesions (565 Lesions in 463 patients) diagnosed as type 2A based on the Japan Narrow-band Imaging Expert Team classification, resected by either HSP or EMR between January 2018 and June 2021 at the National Cancer Center Hospital East. Lesions were divided into HSP and EMR groups, and propensity score matching was performed. In the matched cohort, en bloc and R0 resection rates and adverse events were compared between the two groups. RESULTS: Of the 565 lesions in 463 patients, 117 lesions each in the HSP and EMR groups were selected after propensity score matching. In the original cohort, there was a significant difference in antithrombotic drug use (P < 0.05), lesion size (P < 0.01), location (P < 0.01), and macroscopic type (P < 0.05) between the HSP and EMR groups. In the matched cohort, the en bloc resection rates were comparable between both groups [93.2% (109/117) vs 92.3% (108/117), P = 0.81], and there was no significant difference in the R0 resection rate [77.8% (91/117) vs 80.3% (94/117), P = 0.64]. The incidence of delayed bleeding was similar in both groups [1.7% (2/117)]. Perforation occurred in the EMR group [0.9% (1/117)] but not in the HSP group. CONCLUSION: Using bipolar snare, ER of nonpedunculated 10-15 mm colorectal lesions may be performed safely and effectively, even without submucosal injection.

Computer-aided demarcation of early gastric cancer: a pilot comparative study with endoscopists.

BACKGROUND: Precise area diagnosis of early gastric cancer (EGC) is critical for reliable endoscopic resection. Computer-aided diagnosis (CAD) shows strong potential for detecting EGC and reducing cancer-care disparities caused by differences in endoscopists' skills. To be used in clinical practice, CAD should enable both the detection and the demarcation of lesions. This study proposes a scheme for the detection and delineation of EGC under white-light endoscopy and validates its performance using 1-year consecutive cases. METHODS: Only 300 endoscopic images randomly selected from 68 consecutive cases were used for training a convolutional neural network. All cases were treated with endoscopic submucosal dissection, enabling the accumulation of a training dataset in which the extent of lesions was precisely determined. For validation, 462 cancer images and 396 normal images from 137 consecutive cases were used. From the validation results, 38 randomly selected images were compared with those delineated by six endoscopists. RESULTS: Successful detections of EGC in 387 cancer images (83.8%) and the absence of lesions in 307 normal images (77.5%) were achieved. Positive and negative predictive values were 81.3% and 80.4%, respectively. Successful detection was achieved in 130 cases (94.9%). We achieved precise demarcation of EGC with a mean intersection over union of 66.5%, showing the extent of lesions with a smooth boundary; the results were comparable to those achieved by specialists. CONCLUSIONS: Our scheme, validated using 1-year consecutive cases, shows potential for demarcating EGC. Its performance matched that of specialists; it might therefore be suitable for clinical use in the future.