Early rectal cancer: The diagnostic performance of MRI supplemented with a rectal micro-enema and a modified staging system to identify tumors eligible for local excision.

Background: In staging early rectal cancers (ERC), submucosal tumor depth is one of the most important features determining the possibility of local excision (LE). The micro-enema (Bisacodyl) induces submucosal edema and may hypothetically improve the visualization of tumor depth. Purpose: To test the diagnostic performance of MRI to identify ERC suitable for LE when adding a pre-procedural micro-enema and concurrent use of a modified classification system. Material and Methods: In this prospective study, we consecutively included 73 patients with newly diagnosed rectal tumors. Two experienced radiologists independently interpreted the MRI examinations, and diagnostic performance was calculated for local tumors eligible for LE (Tis-T1sm2, n = 43) and non-local tumors too advanced for LE (T1sm3-T3b, n = 30). Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were registered for each reader. Inter- and intra-reader agreements were assessed by kappa statistics. Lymph node status was derived from the clinical MRI reports. Results: Reader1/reader2 achieved sensitivities of 93%/86%, specificities of 90%/83%, PPV of 93%/88%, and NPV of 90%/81%, respectively, for identifying tumors eligible for LE. Rates of overstaging of local tumors were 7% and 14% for the two readers, and kappa values for the inter- and intra-reader agreement were 0.69 and 0.80, respectively. For tumors ≤T2, all metastatic lymph nodes were smaller than 3 mm on histopathology. Conclusion: MRI after a rectal micro-enema and concurrent use of a modified staging system achieved good diagnostic performance to identify tumors suitable for LE. The rate of overstaging of local tumors was comparable to results reported in previous endorectal ultrasound (ERUS) studies.

Deep learning for prediction of colorectal cancer outcome: a discovery and validation study.

BACKGROUND: Improved markers of prognosis are needed to stratify patients with early-stage colorectal cancer to refine selection of adjuvant therapy. The aim of the present study was to develop a biomarker of patient outcome after primary colorectal cancer resection by directly analysing scanned conventional haematoxylin and eosin stained sections using deep learning. METHODS: More than 12 000 000 image tiles from patients with a distinctly good or poor disease outcome from four cohorts were used to train a total of ten convolutional neural networks, purpose-built for classifying supersized heterogeneous images. A prognostic biomarker integrating the ten networks was determined using patients with a non-distinct outcome. The marker was tested on 920 patients with slides prepared in the UK, and then independently validated according to a predefined protocol in 1122 patients treated with single-agent capecitabine using slides prepared in Norway. All cohorts included only patients with resectable tumours, and a formalin-fixed, paraffin-embedded tumour tissue block available for analysis. The primary outcome was cancer-specific survival. FINDINGS: 828 patients from four cohorts had a distinct outcome and were used as a training cohort to obtain clear ground truth. 1645 patients had a non-distinct outcome and were used for tuning. The biomarker provided a hazard ratio for poor versus good prognosis of 3·84 (95% CI 2·72-5·43; p<0·0001) in the primary analysis of the validation cohort, and 3·04 (2·07-4·47; p<0·0001) after adjusting for established prognostic markers significant in univariable analyses of the same cohort, which were pN stage, pT stage, lymphatic invasion, and venous vascular invasion. INTERPRETATION: A clinically useful prognostic marker was developed using deep learning allied to digital scanning of conventional haematoxylin and eosin stained tumour tissue sections. The assay has been extensively evaluated in large, independent patient populations, correlates with and outperforms established molecular and morphological prognostic markers, and gives consistent results across tumour and nodal stage. The biomarker stratified stage II and III patients into sufficiently distinct prognostic groups that potentially could be used to guide selection of adjuvant treatment by avoiding therapy in very low risk groups and identifying patients who would benefit from more intensive treatment regimes. FUNDING: The Research Council of Norway.

Prognostic significance of S100A4 expression in stage II and III colorectal cancer: results from a population-based series and a randomized phase III study on adjuvant chemotherapy.

Current clinical algorithms are unable to precisely predict which colorectal cancer patients would benefit from adjuvant chemotherapy, and there is a need for novel biomarkers to improve the selection of patients. The metastasis-promoting protein S100A4 predicts poor outcome in colorectal cancer, but whether it could be used to guide clinical decision making remains to be resolved. S100A4 expression was analyzed by immunohistochemistry in primary colorectal carcinomas from a consecutively collected, population-representative cohort and a randomized phase III study on adjuvant 5-fluorouracil/levamisole. Sensitivity to treatment with 5-fluorouracil in S100A4 knockdown cells was investigated using 2D and 3D cell culture assays. Strong nuclear expression of S100A4 was detected in 19% and 23% of the tumors in the two study cohorts, respectively. In both cohorts, nuclear immunoreactivity was associated with reduced relapse-free (P < 0.001 and P = 0.010) and overall survival (P = 0.046 and P = 0.006) in univariate analysis. In multivariate analysis, nuclear S100A4 was a predictor of poor relapse-free survival in the consecutive series (P = 0.002; HR 1.9), but not in the randomized study. Sensitivity to treatment with 5-fluorouracil was not affected by S100A4 expression in in vitro cell culture assays, and there was no indication from subgroup analyses in the randomized study that S100A4 expression was associated with increased benefit of adjuvant treatment with 5-fluorouracil/levamisole. The present study confirms that nuclear S100A4 expression is a negative prognostic biomarker in colorectal cancer, but the clinical utility in selection of patients for adjuvant fluoropyrimidine-based chemotherapy is limited.

Anticipating the clinical use of prognostic gene expression-based tests for colon cancer stage II and III: is Godot finally arriving?

PURPOSE: According to current recommendations for adjuvant treatment, patients with colon cancer stage II are not routinely offered chemotherapy, unless considered to have a high risk of relapse based on specific clinicopathological parameters. Following these criteria, it is challenging to identify the subgroup of patients that will benefit the most from adjuvant treatment. Contrarily, patients with colon cancer stage III are routinely offered chemotherapy, but due to expected adverse effects and frailty, elderly patients are often excluded from standard protocols. Colon cancer is a disease of the elderly and accordingly, there is a large subgroup of patients for which guidelines for adjuvant treatment remain less clear. In these two clinical settings, improved risk stratification has great potential impact on patient care, anticipating that high-risk patients will benefit from chemotherapy. However, microsatellite instability is the only molecular prognostic marker recommended for clinical use. EXPERIMENTAL DESIGN: In this perspective, we provide an updated view on the status and clinical potential of the many proposed prognostic gene expression-based tests for colon cancer stage II and III. RESULTS: The main limitation for clinical implementation is lack of prospective validation. For patients with stage II, highly promising tests have been identified and clinical trials are ongoing. For elderly patients with stage III, the value of such tests has received less focus, but promising early results have been shown. CONCLUSION: Although awaiting results from prospective trials, improved risk assessment for patients with stage II and III is likely to be achieved in the foreseeable future.