BACKGROUND/AIMS:The local excision of early colorectal cancer is limited by the presence of lymph node metastasis (LNM). Signet-ring cell carcinomas (SRC) and mucinous adenocarcinomas (MAC) are two relatively infrequent histological subtypes. However, little is known about the predictors of LNM and prognosis to support the feasibility of local excision in early-stage SRC and MAC. METHODS:The Surveillance Epidemiology and End Results Database were used to identify all patients with pT1 adenocarcinomas, including conventional adenocarcinoma (AC), MAC, and SRC. The prevalence of LNM was assessed, and the long-term survival rate in the above three types of colorectal cancer was calculated. RESULTS:SRC accounted for 0.3% and MAC accounted for 4.4% of the entire cohort of colorectal adenocarcinomas. Compared to AC, MRC and SRC were more often located in the proximal colon, and exhibited a higher grade. The incidence of LNM in AC, MAC, and SRC was 10.6%, 17.2%, and 33.3% for colon cancers and 14.8%, 25.9%, and 46.2% for rectal cancers, respectively. In patients with lymph nodes resected no less than 12, incidence of LNM in AC, MRC, and SRC was 12%, 21%, and 44% for colon tumors and 17%, 30%, and 14% for rectal tumors, respectively. Although, colon patients MAC showed an entirely worse survival rate than AC, rectum patients MAC showed a similar prognosis to AC. We found that in patients with rectal tumors, SRC had a worse 3 and 5-year prognosis than AC. However, for colon cancers, the prognosis of SRC was similar to that of AC. Histology was not found to be an independent prognostic factor in multivariate survival analysis. CONCLUSIONS:MAC and SRC are two distinct subtypes of colorectal cancer that require special attention despite their relatively rare prevalence. pT1 patients with SRC of the rectum and patients with MAC of the colon have higher incidences of LNM, and with these adverse outcomes, local excision is not recommended. AlthoughMAC of the rectum and SRC of colon have a high rate of LNM, the prognosis of these types are similar to that of AC.

Risk evaluation of lymph node metastasis (LNM) for endoscopically resected submucosal invasive (T1) colorectal cancers (CRC) is critical for determining therapeutic strategies, but interobserver variability for histologic evaluation remains a major problem. To address this issue, we developed a machine-learning model for predicting LNM of T1 CRC without histologic assessment. A total of 783 consecutive T1 CRC cases were randomly split into 548 training and 235 validation cases. First, we trained convolutional neural networks (CNN) to extract cancer tile images from whole-slide images, then re-labeled these cancer tiles with LNM status for re-training. Statistical parameters of the tile images based on the probability of primary endpoints were assembled to predict LNM in cases with a random forest algorithm, and defined its predictive value as random forest score. We evaluated the performance of case-based prediction models for both training and validation datasets with area under the receiver operating characteristic curves (AUC). The accuracy for classifying cancer tiles was 0.980. Among cancer tiles, the accuracy for classifying tiles that were LNM-positive or LNM-negative was 0.740. The AUCs of the prediction models in the training and validation sets were 0.971 and 0.760, respectively. CNN judged the LNM probability by considering histologic tumor grade.

BACKGROUND:Lymph node status and liver metastasis (LIM) are important in determining the prognosis of early colon carcinoma. We attempted to develop and validate nomograms to predict lymph node metastasis (LNM) and LIM in patients with early colon carcinoma. METHODS:A total of 32,819 patients who underwent surgery for pT1 or pT2 colon carcinoma were enrolled in the study based on their records in the SEER database. Risk factors for LNM and LIM were assessed based on univariate and multivariate binary logistic regression. The C-index and calibration plots were used to evaluate LNM and LIM model discrimination. The predictive accuracy and clinical values of the nomograms were measured by decision curve analysis. The predictive nomograms were further validated in the internal testing set. RESULTS:The LNM nomogram, consisting of seven features, achieved the same favorable prediction efficacy as the five-feature LIM nomogram. The calibration curves showed perfect agreement between nomogram predictions and actual observations. The decision curves indicated the clinical usefulness of the prediction nomograms. Receiver operating characteristic curves indicated good discrimination in the training set (area under the curve [AUC] = 0.667, 95% CI 0.661-0.673) and the testing set (AUC = 0.658, 95% CI 0.649-0.667) for the LNM nomogram and encouraging performance in the training set (AUC = 0.766, 95% CI 0.760-0.771) and the testing set (AUC = 0.825, 95% CI 0.818-0.832) for the LIM nomogram. CONCLUSION:Novel validated nomograms for patients with early colon carcinoma can effectively predict the individualized risk of LNM and LIM, and this predictive power may help doctors formulate suitable individual treatments.

OBJECTIVE:To identify clinical and histopathological risk factors of LNM in T1 CRC. SUMMARY OF BACKGROUND DATA:The requisite of additional surgery after locally resected T1 CRC is dependent on the risk of LNM. Depth of submucosal invasion is used as a key predictor of lymphatic metastases although data are conflicting on its actual impact. METHODS:Retrospective population-based cohort study on prospectively collected data on all patients with T1 CRC undergoing surgical resection in Sweden, 2009-2017 and Denmark 2016-2018. The Danish cohort was used for validation. Potential risk factors of LNM investigated were; age, sex, tumor location, submucosal invasion, grade of differentiation, mucinous subtype, lymphovascular, and perineural invasion. RESULTS:One hundred fifty out of the 1439 included patients (10%) had LNM. LVI (P < 0.001), perineural invasion (P < 0.001), mucinous subtype (P = 0.006), and age <60 years (P < 0.001) were identified as independent risk factors whereas deep submucosal invasion was only a dependent (P = 0.025) risk factor and not significant in multivariate analysis (P = 0.075). The incidence of LNM was 51/882 (6%) in absence of the independent risk factors. The Danish validation cohort, confirmed our findings regarding the role of submucosal invasion, LVI, and age. CONCLUSIONS:This is a large study on LNM in T1 CRC, including validation, showing that LVI and perineural invasion, mucinous subtype, and low age constitute independent risk factors, whereas depth of submucosal invasion is not an independent risk factor of LNM. Thus, our findings provide a useful basis for management of patients after local excision of early CRC.

OBJECTIVE:To investigate whether there is a differential impact of histopathological risk factors for lymph node metastases (LNM) in pedunculated and nonpedunculated pT1 colorectal cancers (CRC). BACKGROUND:Tumor budding, lymphovascular invasion (LVI), and venous invasion (VI) are recognized risk factors for LNM in pT1 CRC. Whether the importance of these factors varies according to tumor morphology is unknown. METHODS:Patients undergoing resection with lymphadenectomy for pT1 CRC in Denmark from January 2016 to January 2019 were identified in the Danish Colorectal Cancer Database and clinicopathological data was reviewed. Prognostic factors for LNM were investigated using multivariable analyses on the cohort as a whole as well as when stratifying according to tumor morphology (pedunculated vs. nonpedunculated). RESULTS:A total of 1167 eligible patients were identified, of whom 170 had LNM (14.6%). Independent prognostic factors for LNM included LVI [odds ratio (OR)=4.26, P <0.001], VI (OR=3.42, P <0.001), tumor budding (OR=2.12, P =0.002), high tumor grade (OR=2.76, P =0.020), and age per additional year (OR=0.96, P <0.001). On subgroup analyses, LVI and VI remained independently prognostic for LNM regardless of tumor morphology. However, tumor budding was only prognostic for LNM in pedunculated tumors (OR=4.19, P <0.001), whereas age was only prognostic in nonpedunculated tumors (OR=0.61, P =0.003). CONCLUSIONS:While LVI and LI were found to be prognostic of LNM in all pT1 CRC, the prognostic value of tumor budding differs between pedunculated and nonpedunculated tumors. Thus, tumor morphology should be taken into account when considering completion surgery in patients undergoing local excision.

The spread of early-stage (T1 and T2) adenocarcinomas to locoregional lymph nodes is a key event in disease progression of colorectal cancer (CRC). The cellular mechanisms behind this event are not completely understood and existing predictive biomarkers are imperfect. Here, we used an end-to-end deep learning algorithm to identify risk factors for lymph node metastasis (LNM) status in digitized histopathology slides of the primary CRC and its surrounding tissue. In two large population-based cohorts, we show that this system can predict the presence of more than one LNM in pT2 CRC patients with an area under the receiver operating curve (AUROC) of 0.733 (0.67-0.758) and patients with any LNM with an AUROC of 0.711 (0.597-0.797). Similarly, in pT1 CRC patients, the presence of more than one LNM or any LNM was predictable with an AUROC of 0.733 (0.644-0.778) and 0.567 (0.542-0.597), respectively. Based on these findings, we used the deep learning system to guide human pathology experts towards highly predictive regions for LNM in the whole slide images. This hybrid human observer and deep learning approach identified inflamed adipose tissue as the highest predictive feature for LNM presence. Our study is a first proof of concept that artificial intelligence (AI) systems may be able to discover potentially new biological mechanisms in cancer progression. Our deep learning algorithm is publicly available and can be used for biomarker discovery in any disease setting. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

OBJECTIVE:This study aimed to unravel the lymph node metastasis (LNM)-related methylated DNA (mDNA) landscape and develop a mDNA signature to identify LNM in patients with T1 colorectal cancers (T1 CRC). BACKGROUND:Considering the invasiveness of T1 CRC, current guidelines recommend endoscopic resection in patients with LNM-negative, and radical surgical resection only for high-risk LNM-positive patients. Unfortunately, the clinicopathological criteria for LNM risk stratification are imperfect, resulting in frequent misdiagnosis leading to unnecessary radical surgeries and postsurgical complications. METHODS:We conducted genome-wide methylation profiling of 39 T1 CRC specimens to identify differentially methylated CpGs between LNM-positive and LNM-negative, and performed quantitative pyrosequencing analysis in 235 specimens from 3 independent patient cohorts, including 195 resected tissues (training cohort: n=128, validation cohort: n=67) and 40 pretreatment biopsies. RESULTS:Using logistic regression analysis, we developed a 9-CpG signature to distinguish LNM-positive versus LNM-negative surgical specimens in the training cohort [area under the curve (AUC)=0.831, 95% confidence interval (CI)=0.755-0.892; P <0.0001], which was subsequently validated in additional surgical specimens (AUC=0.825; 95% CI=0.696-0.955; P =0.003) and pretreatment biopsies (AUC=0.836; 95% CI=0.640-1.000, P =0.0036). This diagnostic power was further improved by combining the signature with conventional clinicopathological features. CONCLUSIONS:We established a novel epigenetic signature that can robustly identify LNM in surgical specimens and even pretreatment biopsies from patients with T1 CRC. Our signature has strong translational potential to improve the selection of high-risk patients who require radical surgery while sparing others from its complications and expense.