Resection Of T1 Colorectal Cancer Research Articles

Refining Risk Criteria May Substantially Reduce Unnecessary Additional Surgeries after Local Resection of T1 Colorectal Cancer.

The low positive predictive value for lymph node metastases (LNM) of common practice risk criteria (CPRC) in T1 colorectal carcinoma (CRC) leads to manyunnecessary additional surgeries following local resection. This study aimed to identify criteria that may improve on the CPRC. Logistic regression analysis was performed to determine the association of diverse variables with LNM or 'poor outcome' (LNM and/or distant metastases and/or recurrence) in a single center T1 CRC cohort. The diagnostic capacity of the set of variables obtained was compared with that of the CPRC. The study comprised 161 cases. Poorly differentiated clusters (PDC) and tumor budding grade > 1 (TB > 1) were the only independent variables associated with LNM. The area under the curve (AUC) for these criteria was 0.808 (CI 95% 0.717-0.880) compared to 0.582 (CI 95% 0.479-0.680) for CPRC. TB > 1 and lymphovascular invasion (LVI) were independently associated with 'poor outcome', with an AUC of 0.801 (CI 95% 0.731-0.859), while the AUC for CPRC was 0.691 (CI 95% 0.603-0.752). TB > 1, combined either with PDC or LVI, would reduce false positives between 41.5% and 45% without significantly increasing false negatives. Indicating additional surgery in T1 CRC only when either TB > 1, PDC, or LVI are present could reduce unnecessary surgeries significantly.

The Risk of Metastatic Recurrence after Non-Curative Endoscopic Resection with Negative Deep Margins for Early Colorectal Cancer: Two-Center Retrospective Cohort Study

Introduction: Non-curative endoscopic resection of T1 colorectal cancer (CRC) carries a substantial risk of recurrence. However, previous studies have reported a significant proportion of cases in which the deep margin of endoscopic resection was positive for cancer due to the technical difficulties of colorectal endoscopic submucosal dissection (ESD). With the advancement of endoscopic technology and techniques resulting in the reduction of positive resection margins, it is important to reassess the long-term prognosis and major risk factors for recurrence in cases of negative deep margins. Methods: We conducted a retrospective cohort study of consecutive patients with T1 CRC who underwent endoscopic resection between January 2006 and December 2021 with negative deep margins. The histological findings of the resected specimens were analyzed to determine the risk factors associated with the primary outcomes of this study, including recurrence and cancer-related deaths. Results: The median age of the 190 patients was 70 years, of which 63% were male, and endoscopic treatment was performed in 64% by endoscopic mucosal resection and 36% by ESD. Eighty-two patients were in the curative resection (CR) group and 108 were in the non-curative resection (NCR) group, wherein the latter comprised 79 patients who underwent additional surgery (AS) and 29 patients who did not receive AS. Five-year recurrence-free survival rates were 98.4% (95% CI: 89.3–99.8) for CR, 98.3% (95% CI: 88.8–99.8) for NCR with AS, and 73.7% (95% CI: 46.5–88.5) for NCR without AS. Lymphatic invasion and budding grade 2/3 were the major risk factors for recurrence, with hazard ratios of 40.7 (p p = 0.007), respectively. Of the patients in the NCR group without AS, the 5-year recurrence-free rate was 85.6% (95% CI: 52.5–96.3) if there were no major risk factors (i.e., no lymphatic invasion or budding grade 2/3) (n = 21), whereas the prognosis was poor in the presence of one or more of the major risk factors, with a median recurrence-free survival and disease-specific survival of 2.5 and 3.1 years, respectively (n = 8). Discussion: In endoscopically resected T1 CRC with negative deep margins, lymphatic invasion or budding grade 2/3 may indicate a higher risk of recurrence when followed up without AS.

Additional staining for lymphovascular invasion is associated with increased estimation of lymph node metastasis in patients with T1 colorectal cancer: Systematic review and meta-analysis.

Lymphovascular invasion (LVI) is a critical risk factor for lymph node metastasis (LNM), which requires additional surgery after endoscopic resection of T1 colorectal cancer (CRC). However, the impact of additional staining on estimating LNM is unclear. This systematic review aimed to evaluate the impact of additional staining on determining LNM in T1 CRC. We searched five electronic databases. Outcomes were diagnostic odds ratio (DOR), assessed using hierarchical summary receiver operating characteristic curves, and interobserver agreement among pathologists for positive LVI, assessed using Kappa coefficients (κ). We performed a subgroup analysis of studies that simultaneously included a multivariable analysis for other risk factors (deep submucosal invasion, poor differentiation, and tumor budding). Among the 64 studies (18,097 patients) identified, hematoxylin-eosin (HE) and additional staining for LVI had pooled sensitivities of 0.45 (95% confidence interval [CI] 0.32-0.58) and 0.68 (95% CI 0.44-0.86), specificities of 0.88 (95% CI 0.78-0.94) and 0.76 (95% CI 0.62-0.86), and DORs of 6.26 (95% CI 3.73-10.53) and 6.47 (95% CI 3.40-12.32) for determining LNM, respectively. In multivariable analysis, the DOR of additional staining for LNM (DOR 5.95; 95% CI 2.87-12.33) was higher than that of HE staining (DOR 1.89; 95% CI 1.13-3.16) (P = 0.01). Pooled κ values were 0.37 (95% CI 0.22-0.52) and 0.62 (95% CI 0.04-0.99) for HE and additional staining for LVI, respectively. Additional staining for LVI may increase the DOR for LNM and interobserver agreement for positive LVI among pathologists.

Impact of Lesion Location on Recurrence After Resection of T1 Colorectal Cancer: Post Hoc Analysis of a Nationwide Multicenter Cohort Study

Impact of Lesion Location on Recurrence After Resection of T1 Colorectal Cancer: Post Hoc Analysis of a Nationwide Multicenter Cohort Study

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

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. 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. 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). 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.

Endoscopic Treatment of T1 Colorectal Cancer.

Commonly accepted criteria for curative resection of T1 colorectal cancer include R0 resection with horizontal and vertical clear margins (R0), absence of lympho-vascular or vessel infiltration (L0, V0), a low to moderate histological grading (G1/2), low tumor cell budding, and limited (<1000 µm) infiltration into the submucosa. However, submucosal infiltration depth in the absence of other high-risk features has recently been questioned as a high-risk situation for lymph-node metastasis. Consequently, endoscopic resection techniques should focus on the acquisition of qualitatively and quantitively sufficient submucosal tissue. Here, we summarize the current literature on lymph-node metastasis risk after endoscopic resection of T1 colorectal cancer. Moreover, we discuss different endoscopic resection techniques with respect to the quality of the resected specimen.

A proposal for grading the risk of lymph node metastasis after endoscopic resection of T1 colorectal cancer.

At present, for patients with early colorectal cancer as long as having any one risk factor of lymph node metastasis (LNM) after endoscopic resection (ER), additional surgery will be considered, regardless of the degree of LNM risk; however, most patients are free of LNM. This study aimed to further grade these patients according to LNM risk. We assessed 271 patients with T1 colorectal cancers treated initially with ER to analyze the correlation between LNM-associated risk factors and LNM rate. Differences in this rate between groups were estimated using the χ2 test or Fisher's exact test. Poorly differentiated adenocarcinoma (Por) (3.4% vs. 40%, p < 0.001) and lymphovascular infiltration (LV) (1.6% vs. 29.0%, p < 0.001) were the only parameters correlated with LNM. When we divided the cases into LV-negative (LV(-)) and LV-positive (LV(+)) groups, we found a significantly higher LNM rate in the LV(+) group (29.0% vs. 1.6%, p < 0.001). Additionally, the rate of LNM in those positive for each parameter did not differ from the control rate in the same group, except in the Por subgroup. When the cases were divided into four groups based on the presence of LV infiltration and Por, the LNM rate in each group was 2/233 cases (0.8%) in the LV(-)Por(-) group, 2/7 cases (28.5%) in the LV(-)Por(+) group, 7/28 cases (25.0%) in the LV(+)Por(-) group, and 2/3 cases (66.6%) in the LV(+)Por(+) group. Based on LV and histological differentiation, patients were classified into three LNM risk grades: low (LNM, 0.8%), moderate (LNM, 25.0-28.5%), and high (LNM, 66.6%).

Tumor Location as a Prognostic Factor in T1 Colorectal Cancer.

The incidence of T1 colorectal cancer is expected to increase because of the prevalence of colorectal cancer screening and the progress of endoscopic treatment such as endoscopic submucosal dissection or endoscopic full-thickness resection. Currently, the requirement for additional surgery after endoscopic resection of T1 colorectal cancer is determined according to several treatment guidelines (in USA, Europe, and Japan) referring to the following pathological findings: lymphovascular invasion, tumor differentiation, depth of invasion, and tumor budding, all of which are reported to be risk factors for lymph node metastasis. In addition to these factors, in this review, we investigate whether tumor location, which is an objective factor, has an impact on the presence of lymph node metastasis and recurrence. From recent studies, left-sided location, especially the sigmoid colon in addition to rectum, could be a risk factor for lymph node metastasis and cancer recurrence. The treatment of T1 colorectal cancer should be managed considering these findings.

Current problems and perspectives of pathological risk factors for lymph node metastasis in T1 colorectal cancer: Systematic review.

With the prevalence of endoscopic submucosal dissection and endoscopic full thickness resection, which enable complete resection of T1 colorectal cancer with a negative margin, the treatment strategy following endoscopic resection has become more important. The necessity of secondary surgical resection is determined on the basis of the risk of lymph node metastasis according to the histopathological findings of resected specimens because ~10% of T1 colorectal cancer cases have lymph node metastasis. The current Japanese treatment guidelines state four risk factors for lymph node metastasis: lymphovascular invasion, histological differentiation, depth of submucosal invasion, and tumor budding. These guidelines have succeeded in stratifying the low-risk group for lymph node metastasis, in which endoscopic resection alone is acceptable for cure. On the other hand, there are some problems: there is variation in diagnosis methods and low interobserver agreement for each pathological factor and 90% of surgical resections are unnecessary, with lymph node metastasis negativity. To ensure patients with T1 colorectal cancer receive more appropriate treatment, these problems should be addressed. In this systematic review, we gave some suggestions to these practical issues of four pathological factors as predictors.

Risk Stratification of T1 Colorectal Cancer Metastasis to Lymph Nodes: Current Status and Perspective.

With the widely spreading population-based screening programs for colorectal cancer and recent improvements in endoscopic diagnosis, the number of endoscopic resections in subjects with T1 colorectal cancer has been increasing. Some reports suggest that endoscopic resection prior to surgical resection of T1 colorectal cancer has no adverse effect on prognosis and contributes to this tendency. The decision on the need for surgical resection as an additional treatment after endoscopic resection of T1 colorectal cancer should be made according to the metastasis risk to lymph nodes based on histopathological findings. Because lymph node metastasis occurs in approximately 10% of patients with T1 colorectal cancer according to current international guidelines, the remaining 90% of patients may be at an increased risk of surgical resection and associated postoperative mortality, with no clinical benefit derived from unnecessary surgical resection. Although a more accurate prediction system for lymph node metastasis is needed to solve this problem, risk stratification for lymph node metastasis remains controversial. In this review, we focus on the current status of risk stratification of T1 colorectal cancer metastasis to lymph nodes and outline future perspectives.

Histopathological risk factors for lymph node metastases in T1 colorectal cancer: meta-analysis

National screening programmes increase the proportion of T1 colorectal cancers. Local excision may be possible, but the risk of lymph node metastases (LNMs) could jeopardize long-term outcomes. The aim of the present study was to review the association between histopathological findings and LNMs in T1 colorectal cancer. A systematic literature search was conducted using PubMed,Embase, and Cochrane online databases. Studies investigating the association between one or more histopathological factors and LNMs in patients who underwent resection for T1 colorectal cancer were included. Sixteen observational studies were included in the meta-analysis, including a total of 10 181 patients, of whom 1 307 had LNMs. Lymphovascular invasion (odds ratio (OR) 7.42; P < 0.001), tumour budding (OR 4.00; P < 0.001), depth of submucosal invasion, whether measured as at least 1000 µm (OR 3.53; P < 0.001) or Sm2-3 (OR 2.12; P = 0.020), high tumour grade (OR 3.75; P < 0.001), polypoid growth pattern (OR 1.59; P = 0.040), and rectal location of tumour (OR 1.36; P = 0.003) were associated with LNMs. Distinct histopathological factors associated with nodal metastases in T1 colorectal cancer can aid selection of patients for local excision or major excisional surgery.

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

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

Risk and Time Pattern of Recurrences After Local Endoscopic Resection of T1 Colorectal Cancer: A Meta-analysis

Growing numbers of patients with T1 CRC are being treated with local endoscopic resection only and as a result, the need for optimization of surveillance strategies for these patients also increases. We aimed to estimate the cumulative incidence and time pattern of CRC recurrences for endoscopically treated patients with T1 CRC. Using a systematic literature search in PubMed, EMBASE, Web of Science and Cochrane Library (from inception till 15 May 2020), we identified and extracted data from studies describing the cumulative incidence of local or distant CRC recurrence for patients with T1 CRC treated with local endoscopic resection only. Pooled estimates were calculated using mixed-effect logistic regression models. Seventy-one studies with 5167 unique, endoscopically treated patients with T1 CRC were included. The pooled cumulative incidence of any CRC recurrence was 3.3% (209 events; 95% CI, 2.6%-4.3%; I2= 54.9%), with local and distant recurrences being found at comparable rates (pooled incidences 1.9% and 1.6%, respectively). CRC-related mortality was observed in 42 out of 2519 patients (35 studies; pooled incidence 1.7%, 95% CI, 1.2%-2.2%; I2= 0%), and the CRC-related mortality rate among patients with recurrence was 40.8% (42/103 patients). The vast majority of recurrences (95.6%) occurred within 72 months of follow-up. Pooled incidences of any CRC recurrence were 7.0% for high-risk T1 CRCs (28 studies; 95% CI, 4.9%-9.9%; I2= 48.1%) and 0.7% (36 studies; 95% CI, 0.4%-1.2%; I2= 0%) for low-risk T1 CRCs. Our meta-analysis provides quantitative outcome measures which are relevant to guidelines on surveillance after local endoscopic resection of T1 CRC.

Mo1638 ENDOSCOPIC RESECTION FOLLOWED BY SURGERY IN T1 COLORECTAL CANCER WITH HIGH RISK HISTOLOGICAL FEATURES DOES NOT AFFECT CANCER-RELATED LONG-TERM OUTCOMES

We aimed to identify if endoscopic resection of T1 colorectal cancer (CRC) before surgical resection (secondary surgery) unfavorably affects cancer-related long-term outcomes compared to surgery without prior endoscopic resection (primary surgery). We included patients who underwent surgery for T1 CRC with at least one high-risk histological features (poor differentiation, deep submucosal invasion, lympho-vascular invasion, and/or positive/indeterminate resection margins) at our institution between 2011-2016. Medical records, histology reports and results of endoscopic and radiologic examinations were reviewed retrospectively. Radical abdominal surgery was performed in 852 patients (388 primary and 464 secondary surgeries). Surgical trans-anal excision was performed in 21 patients (9 primary and 12 secondary surgeries). During follow-up periods of 51.4±18.3 months, cancer recurrence occurred in 20 patients. Five-year survival rates did not differ between primary and secondary abdominal surgery groups (97.3% vs. 98.5%, p = 0.294). Analyses stratified by nodal stages and number of high-risk histological features did not show any difference in cumulative survival rates. However, patients with secondary abdominal surgery showed higher 5-year survival rates compared to secondary trans-anal surgery (98.6% vs. 90.9%, p < 0.001). In multivariable Cox regression analysis, preoperative serum CEA level was an independent risk factor for cancer recurrence. Prior endoscopic resection was not an independent risk factor for cancer recurrence. Endoscopic resection of T1 CRC with high-risk histological features did not affect cancer-related long-term outcomes. Therefore, endoscopic resection of suspected T1 CRC can be performed without fear for worsening the oncological prognosis.View Large Image Figure ViewerDownload Hi-res image Download (PPT)

Nomogram Development and External Validation for Predicting the Risk of Lymph Node Metastasis in T1 Colorectal Cancer.

PurposePredicting lymph node metastasis (LNM) risk is crucial in determining further treatment strategies following endoscopic resection of T1 colorectal cancer (CRC). This study aimed to establish a new prediction model for the risk of LNM in T1 CRC patients.Materials and MethodsThe development set included 833 patients with T1 CRC who had undergone endoscopic (n=154) or surgical (n=679) resection at the National Cancer Center. The validation set included 722 T1 CRC patients who had undergone endoscopic (n=249) or surgical (n=473) resection at Daehang Hospital. A logistic regression model was used to construct the prediction model. To assess the performance of prediction model, discrimination was evaluated using the receiver operating characteristic (ROC) curves with area under the ROC curve (AUC), and calibration was assessed using the Hosmer-Lemeshow (HL) goodness-of-fit test.ResultsFive independent risk factors were determined in the multivariable model, including vascular invasion, high-grade histology, submucosal invasion, budding, and background adenoma. In final prediction model, the performance of the model was good that the AUC was 0.812 (95% confidence interval [CI], 0.770 to 0.855) and the HL chi-squared test statistic was 1.266 (p=0.737). In external validation, the performance was still good that the AUC was 0.771 (95% CI, 0.708 to 0.834) and the p-value of the HL chi-squared test was 0.040. We constructed the nomogram with the final prediction model.ConclusionWe presented an externally validated new prediction model for LNM risk in T1 CRC patients, guiding decision making in determining whether additional surgery is required after endoscopic resection of T1 CRC.

Endoscopic full-thickness resection for early colorectal cancer

Current international guidelines recommend endoscopic resection for T1 colorectal cancer (CRC) with low-risk histology features and oncologic resection for those at high risk of lymphatic metastasis. Exact risk stratification is therefore crucial to avoid under-treatment as well as over-treatment. Endoscopic full-thickness resection (EFTR) has shown to be effective for treatment of non-lifting benign lesions. In this multicenter, retrospective study we aimed to evaluate efficacy, safety, and clinical value of EFTR for early CRC. Records of 1234 patients undergoing EFTR for various indications at 96 centers were screened for eligibility. A total of 156 patients with histologic evidence of adenocarcinoma were identified. This cohort included 64 cases undergoing EFTR after incomplete resection of a malignant polyp (group 1) and 92 non-lifting lesions (group 2). Endpoints of the study were: technical success, R0-resection, adverse events, and successful discrimination of high-risk versus low-risk tumors. Technical success was achieved in 144 out of 156 (92.3%). Mean procedural time was 42 minutes. R0 resection was achieved in 112 of 156 (71.8%). Subgroup analysis showed a R0 resection rate of 87.5% in Group 1 and 60.9% in Group 2 (P < .001). Severe procedure-related adverse events were recorded in 3.9% of patients. Discrimination between high-risk versus low-risk tumor was successful in 155 of 156 cases (99.3%). In Group 1, 84.1% were identified as low-risk lesions, whereas 16.3% in group 2 had low-risk features. In total, 53 patients (34%) underwent oncologic resection due to high-risk features whereas 98 patients (62%) were followed endoscopically. In early colorectal cancer, EFTR is technically feasible and safe. It allows exact histological risk stratification and can avoid surgery for low-risk lesions. Prospective studies are required to further define indications for EFTR in malignant colorectal lesions and to evaluate long-term outcome.

Endoscopic Submucosal Dissection Decreases Additional Colorectal Resection for T1 Colorectal Cancer.

BackgroundThere are 3 methods of treating T1 colorectal cancer (T1 CRC), which include endoscopic resection, endoscopic resection followed by additional colorectal resection, and surgical resection. In this retrospective study, changes in the management of T1 CRC after introduction of endoscopic submucosal dissection (ESD) were investigated by comparison with the 10-year period before introduction of ESD.Material/MethodsDuring a 20-year period from 1996 to 2015, 835 patients with T1 CRC were treated, including 331 patients before introduction of ESD (Group A) and 504 patients after introduction of ESD (Group B). Clinicopathological findings and treatment methods were compared between these 2 groups.ResultsAs the initial treatment, endoscopic treatment was performed in 185 patients (55.9%) in Group A and 288 (57.1%) in Group B. In Group B, ESD was performed in 161 patients (55.9%), accounting for more than half of the T1 CRC patients receiving endoscopic treatment. In Groups A and B, observation after endoscopic resection was selected for 54.2% and 67.3% of T1a patients, respectively (p=0.04). A similar trend was noted for T1b patients, and there was no significant difference of the treatment approach. Among all T1 CRC patients, the percentage undergoing observation after endoscopic resection was significantly higher in Group B than in Group A (34.3% vs. 26.9%, p=0.02), and the percentage of patients undergoing additional colorectal resection was significantly lower in Group B (22.8% vs. 29.0%, p=0.04).ConclusionsAfter introduction of ESD, it was performed in more than half of all patients with T1 CRC undergoing endoscopic treatment. The percentage of patients undergoing observation following endoscopic resection of T1 CRC increased after introduction of ESD.

French comment on article Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer

Ce papier par Ichimasa et al. est le premier à décrire l’apport de l’intelligence artificielle pour prédire la nécessité de chirurgie complémentaire dans les cancers superficiels (T1) colo-rectaux. La pertinence clinique est majeure puisque le risque d’envahissement ganglionnaire et de métastases à distance concerne environ 10 % de ces patients en cas de résection endoscopique incomplète ou de présence de facteurs pronostiques péjoratifs sur le spécimen de résection. A l’heure actuelle, les guidelines recommandent donc un traitement chirurgical complémentaire dans cette situation, mais seules 8 à 16 % des chirurgies sont réellement nécessaires, les autres pièces opératoires étant indemnes de lésions carcinomateuses. De plus, la chirurgie colorectale complémentaire comporte un risque non nul de morbi-mortalité. Dans ce contexte, il est nécessaire de développer des aides à la décision cliniques de chirurgie complémentaire ou d’abstention, et l’avènement de l’intelligence artificielle et des “big datas” représente une opportunité majeure.

Correction: Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer.

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 P P Conclusions Compared with current guidelines, artificial intelligence significantly reduced unnecessary additional surgery after endoscopic resection of T1 CRC without missing LNM positivity.

633 Long-Term Local Recurrence After Macroscopic Complete Endoscopic Resection of T1 Colorectal Cancer: Rationale for Follow-Up

633 Long-Term Local Recurrence After Macroscopic Complete Endoscopic Resection of T1 Colorectal Cancer: Rationale for Follow-Up