Search

BackgroundAccurate response evaluation is necessary to select complete responders (CRs) for a watch-and-wait approach. Deep learning may aid in this process, but so far has never been evaluated for this purpose. The aim was to evaluate the accuracy to assess response with deep learning methods based on endoscopic images in rectal cancer patients after neoadjuvant therapy.MethodsRectal cancer patients diagnosed between January 2012 and December 2015 and treated with neoadjuvant (chemo)radiotherapy were retrospectively selected from a single institute. All patients underwent flexible endoscopy for response evaluation. Diagnostic performance (accuracy, area under the receiver operator characteristics curve (AUC), positive- and negative predictive values, sensitivities and specificities) of different open accessible deep learning networks was calculated. Reference standard was histology after surgery, or long-term outcome (>2 years of follow-up) in a watch-and-wait policy.Results226 patients were included for the study (117(52%) were non-CRs; 109(48%) were CRs). The accuracy, AUC, positive- and negative predictive values, sensitivity and specificity of the different models varied from 0.67–0.75%, 0.76–0.83%, 67–74%, 70–78%, 68–79% to 66–75%, respectively. Overall, EfficientNet-B2 was the most successful model with the highest diagnostic performance.ConclusionsThis pilot study shows that deep learning has a modest accuracy (AUCs 0.76-0.83). This is not accurate enough for clinical decision making, and lower than what is generally reported by experienced endoscopists. Deep learning models can however be further improved and may become useful to assist endoscopists in evaluating the response. More well-designed prospective studies are required.

Aim Computed tomography (CT) is currently the diagnostic tool most often used to detect anastomotic leakage (AL) after colorectal surgery. The aim of this study was to investigate the value of rectal contrast. Method All patients who underwent colorectal surgery with a primary anastomosis between 2009 and 2018 were identified from a prospectively maintained database. Patients who underwent postoperative CT scanning in suspicion of AL were included. The clinical and radiological outcomes of patients with and without rectal contrast were compared. Results A total of 1183 patient records were reviewed; 225 patients underwent CT‐abdomen in suspicion of AL. Of these patients, 175 (77.8%) received rectal contrast. Sensitivity and specificity in this group were 78% and 94%, respectively. The positive predictive value (PPV) was 0.78 and the negative predictive value (NPV) was 0.94. In the group without rectal contrast (n = 50), sensitivity was 47%, specificity 88%, PPV 0.66 and NPV 0.76. In patients who received rectal contrast, contrast reached the anastomosis in 81.7% compared with 26.0% in patients who were given only oral contrast (p

Introduction: The aim was assess the oncological and functional outcome of the watch-and-wait (W&W) approach in older patients with a clinical (near)complete response after neoadjuvant treatment for rectal cancer.Material and methods: Patients were included in a W&W-approach (2004-2019) when digital rectal examination, endoscopy and MRI showed a (near)clinical complete response. Patients underwent endoscopy and MRI every 3 months during the first year, and 6-monthly thereafter. Patients aged >= 75 and >= 2 years of follow-up (FU) were selected. Oncological outcomes were assessed with Kaplan-Meier curves. Functional outcome was assessed with colostomy-free rate, Vaizey incontinence score, low anterior resection syndrome-score and International Prostate Syndrome Score.Results: 43/304 (14%) of patients in a W&W-approach met the inclusion criteria. Median FU was 37 (24-109) months. 5/43(12%) developed a local regrowth. All were treated surgically, with one patient experiencing a pelvic failure. Distant metastases occurred in 3/43 patients and 4 patients died, 3 of whom not related to rectal cancer. The 3-year local regrowth-free rate was 88%, 3-year non-regrowth disease-free survival 91%, overall survival 97% and 3-year colostomy-free rate 93%. Overall, the bowel- and urinary dysfunction scores at 3, 12 and 24 months indicated good continence, no or minor LARS and moderate urinary problems.Conclusion: W&W for older patients with a clinical (near) complete response appears to be a safe alternative to a total mesorectal excision (TME), with a very high pelvic control rate, and few rectal cancer related deaths. Most patients can avoid major surgery and a definitive colostomy, and have a reasonable anorectal and urinary function. (C) 2020 Elsevier Ltd, BASO similar to The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights reserved.

Background: The purpose of this study was to investigate the prevalence of ypN+ status according to ypT category in patients with locally advanced rectal cancer treated with chemoradiotherapy and total mesorectal excision, and to assess the impact of ypN+ on disease recurrence and survival by pooled analysis of individual-patient data.Methods: Individual-patient data from 10 studies of chemoradiotherapy for rectal cancer were included. Pooled rates of ypN+ disease were calculated with 95 per cent confidence interval for each ypT category. Kaplan-Meier and Cox regression analyses were undertaken to assess influence of ypN status on 5-year disease-free survival (DFS) and overall survival (OS).Results: Data on 1898 patients were included in the study. Median follow-up was 50 (range 0-219)months. The pooled rate of ypN+ disease was 7 per cent for ypT0, 12 per cent for ypT1, 17 per cent for ypT2, 40 per cent for ypT3, and 46 per cent for ypT4 tumours. Patients with ypN+ disease had lower 5-year DFS and OS (46.2 and 63.4 per cent respectively) than patients with ypN0 tumours (74.5 and 83.2 per cent) (P

The aim of this study was to evaluate whether magnetic resonance imaging (MRI) can accurately identify poor responders after chemoradiotherapy (CRT) who will need to go straight to surgery, and to evaluate whether results are reproducible among radiologists with different levels of expertise.Seven independent readers with different levels of expertise retrospectively evaluated the restaging MRIs (T2-weighted + diffusion-weighted imaging [T2W + DWI]) of 62 patients and categorized them as (1) poor responders - highly suspicious of tumor; (2) intermediate responders - tumor most likely; and (3) good - potential (near) complete responders. The reference standard was histopathology after surgery (or long-term follow-up in the case of a watch-and-wait program).Fourteen patients were complete responders and 48 had residual tumor. The median percentage of patients categorized by the seven readers as 'poor', 'intermediate', and 'good' responders was 21% (range 11-37%), 50% (range 23-58%), and 29% (range 23-42%), respectively. The vast majority of poor responders had histopathologically confirmed residual tumor (73% ypT3-4), with a low rate (0-5%) of 'missed complete responders'. Of the 14 confirmed complete responders, a median percentage of 71% were categorized in the MR-good response group and 29% were categorized in the MR-intermediate response group.Radiologists of varying experience levels should be able to use MRI to identify the ± 20% subgroup of poor responders who will definitely require surgical resection after CRT. This may facilitate more selective use of endoscopy, particularly in general settings or in centers with limited access to endoscopy.