No abstract

Background and study aims Decisions concerning additional surgery after endoscopic resection of T1 colorectal cancer (CRC) are difficult because preoperative prediction of lymph node metastasis (LNM) is problematic. We investigated whether artificial intelligence can predict LNM presence, thus minimizing the need for additional surgery. Patients and methods Data on 690 consecutive patients with T1 CRCs that were surgically resected in 2001 – 2016 were retrospectively analyzed. We divided patients into two groups according to date: data from 590 patients were used for machine learning for the artificial intelligence model, and the remaining 100 patients were included for model validation. The artificial intelligence model analyzed 45 clinicopathological factors and then predicted positivity or negativity for LNM. Operative specimens were used as the gold standard for the presence of LNM. The artificial intelligence model was validated by calculating the sensitivity, specificity, and accuracy for predicting LNM, and comparing these data with those of the American, European, and Japanese guidelines. Results Sensitivity was 100 % (95 % confidence interval [CI] 72 % to 100 %) in all models. Specificity of the artificial intelligence model and the American, European, and Japanese guidelines was 66 % (95 %CI 56 % to 76 %), 44 % (95 %CI 34 % to 55 %), 0 % (95 %CI 0 % to 3 %), and 0 % (95 %CI 0 % to 3 %), respectively; and accuracy was 69 % (95 %CI 59 % to 78 %), 49 % (95 %CI 39 % to 59 %), 9 % (95 %CI 4 % to 16 %), and 9 % (95 %CI 4 % – 16 %), respectively. The rates of unnecessary additional surgery attributable to misdiagnosing LNM-negative patients as having LNM were: 77 % (95 %CI 62 % to 89 %) for the artificial intelligence model, and 85 % (95 %CI 73 % to 93 %; P < 0.001), 91 % (95 %CI 84 % to 96 %; P < 0.001), and 91 % (95 %CI 84 % to 96 %; P < 0.001) for the American, European, and Japanese guidelines, respectively. Conclusions Compared with current guidelines, artificial intelligence significantly reduced unnecessary additional surgery after endoscopic resection of T1 CRC without missing LNM positivity.

Invasive cancer carries the risk of metastasis, and therefore, the ability to distinguish between invasive cancerous lesions and less-aggressive lesions is important. We evaluated a computer-aided diagnosis system that uses ultra-high (approximately × 400) magnification endocytoscopy (EC-CAD). We generated an image database from a consecutive series of 5843 endocytoscopy images of 375 lesions. For construction of a diagnostic algorithm, 5543 endocytoscopy images from 238 lesions were randomly extracted from the database for machine learning. We applied the obtained algorithm to 200 endocytoscopy images and calculated test characteristics for the diagnosis of invasive cancer. We defined a high-confidence diagnosis as having a ≥ 90 % probability of being correct. Of the 200 test images, 188 (94.0 %) were assessable with the EC-CAD system. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were 89.4 %, 98.9 %, 94.1 %, 98.8 %, and 90.1 %, respectively. High-confidence diagnosis had a sensitivity, specificity, accuracy, PPV, and NPV of 98.1 %, 100 %, 99.3 %, 100 %, and 98.8 %, respectively. EC-CAD may be a useful tool in diagnosing invasive colorectal cancer.

Background and Aim: Recent advances in endoscopic technology have allowed many T1 colorectal carcinomas to be resected endoscopically with negative margins. However, the criteria for curative endoscopic resection remain unclear. We aimed to identify risk factors for nodal metastasis in T1 carcinoma patients and hence establish the indication for additional surgery with lymph node dissection. Methods: Initial or additional surgery with nodal dissection was performed in 653 T1 carcinoma cases. Clinicopathological factors were retrospectively analyzed with respect to nodal metastasis. The status of the muscularis mucosae (MM grade) was defined as grade 1 (maintenance) or grade 2 (fragmentation or disappearance). The lesions were then stratified based on the risk of nodal metastasis. Results: Muscularis mucosae grade was associated with nodal metastasis (P = 0.026), and no patients with MM grade 1 lesions had nodal metastasis. Significant risk factors for nodal metastasis in patients with MM grade 2 lesions were attribution of women (P = 0.006), lymphovascular infiltration (P < 0.001), tumor budding (P = 0.045), and poorly differentiated adenocarcinoma or mucinous carcinoma (P = 0.007). Nodal metastasis occurred in 1.06% of lesions without any of these pathological factors, but in 10.3% and 20.1% of lesions with at least one factor in male and female patients, respectively. There was good inter-observer agreement for MM grade evaluation, with a kappa value of 0.67. Conclusions: Stratification using MM grade, pathological factors, and patient sex provided more appropriate indication for additional surgery with lymph node dissection after endoscopic treatment for T1 colorectal carcinomas.

Laser-scanning confocal microscopy provides immediate images that correspond well with those of hematoxylin-eosin staining. An improved probe-type LCM endomicroscope is being developed which should provide better histological images of colorectal lesions in vivo.