Search

Objective: Improving prognostication to direct personalised therapy remains an unmet need. This study prospectively investigated promising CT, genetic, and immunohistochemical markers to improve the prediction of colorectal cancer recurrence., Material and Methods: This multicentre trial (ISRCTN 95037515) recruited patients with primary colorectal cancer undergoing CT staging from 13 hospitals. Follow-up identified cancer recurrence and death. A baseline model for cancer recurrence at 3 years was developed from pre-specified clinicopathological variables (age, sex, tumour-node stage, tumour size, location, extramural venous invasion, and treatment). Then, CT perfusion (blood flow, blood volume, transit time and permeability), genetic (RAS, RAF, and DNA mismatch repair), and immunohistochemical markers of angiogenesis and hypoxia (CD105, vascular endothelial growth factor, glucose transporter protein, and hypoxia-inducible factor) were added to assess whether prediction improved over tumour-node staging alone as the main outcome measure., Results: Three hundred twenty-six of 448 participants formed the final cohort (226 male; mean 66 ± 10 years. 227 (70%) had ≥ T3 stage cancers; 151 (46%) were node-positive; 81 (25%) developed subsequent recurrence. The sensitivity and specificity of staging alone for recurrence were 0.56 [95% CI: 0.44, 0.67] and 0.58 [0.51, 0.64], respectively. The baseline clinicopathologic model improved specificity (0.74 [0.68, 0.79], with equivalent sensitivity of 0.57 [0.45, 0.68] for high vs medium/low-risk participants. The addition of prespecified CT perfusion, genetic, and immunohistochemical markers did not improve prediction over and above the clinicopathologic model (sensitivity, 0.58-0.68; specificity, 0.75-0.76)., Conclusion: A multivariable clinicopathological model outperformed staging in identifying patients at high risk of recurrence. Promising CT, genetic, and immunohistochemical markers investigated did not further improve prognostication in rigorous prospective evaluation., Clinical Relevance Statement: A prognostic model based on clinicopathological variables including age, sex, tumour-node stage, size, location, and extramural venous invasion better identifies colorectal cancer patients at high risk of recurrence for neoadjuvant/adjuvant therapy than stage alone., Key Points: Identification of colorectal cancer patients at high risk of recurrence is an unmet need for treatment personalisation. This model for recurrence, incorporating many patient variables, had higher specificity than staging alone. Continued optimisation of risk stratification schema will help individualise treatment plans and follow-up schedules., (© 2024. The Author(s).)

Objectives: Small bowel obstruction is a common surgical emergency which can lead to bowel necrosis, perforation and death. Plain abdominal X-rays are frequently used as a first-line test but the availability of immediate expert radiological review is variable. The aim was to investigate the feasibility of using a deep learning model for automated identification of small bowel obstruction., Methods: A total of 990 plain abdominal radiographs were collected, 445 with normal findings and 445 demonstrating small bowel obstruction. The images were labelled using the radiology reports, subsequent CT scans, surgical operation notes and enhanced radiological review. The data were used to develop a predictive model comprising an ensemble of five convolutional neural networks trained using transfer learning., Results: The performance of the model was excellent with an area under the receiver operator curve (AUC) of 0.961, corresponding to sensitivity and specificity of 91 and 93% respectively., Conclusion: Deep learning can be used to identify small bowel obstruction on plain radiographs with a high degree of accuracy. A system such as this could be used to alert clinicians to the presence of urgent findings with the potential for expedited clinical review and improved patient outcomes., Advances in Knowledge: This paper describes a novel labelling method using composite clinical follow-up and demonstrates that ensemble models can be used effectively in medical imaging tasks. It also provides evidence that deep learning methods can be used to identify small bowel obstruction with high accuracy.

Aim: To determine if patients can localise dysphagia level determined endoscopically or radiologically and association of gender, age, level and pathology., Methods: Retrospective review of consecutive patients presenting to dysphagia hotline between March 2004 and March 2015 was carried out. Demographics, clinical history and investigation findings were recorded including patient perception of obstruction level (pharyngeal, mid sternal or low sternal) was documented and the actual level of obstruction found on endoscopic or radiological examination (if any) was noted. All patients with evidence of obstruction including oesophageal carcinoma, peptic stricture, Schatzki ring, oesophageal pouch and cricopharyngeal hypertrophy were included in the study who had given a perceived level of dysphagia. The upper GI endoscopy reports (barium study where upper GI endoscopy was not performed) were reviewed to confirm the distance of obstructing lesion from central incisors. A previously described anatomical classification of oesophagus was used to define the level of obstruction to be upper, middle or lower oesophagus and this was compared with patient perceived level., Results: Three thousand six hundred and sixty-eight patients were included, 42.0% of who were female, mean age 70.7 ± 12.8 years old. Of those with obstructing lesions, 726 gave a perceived level of dysphagia: 37.2% had oesophageal cancer, 36.0% peptic stricture, 13.1% pharyngeal pouches, 10.3% Schatzki rings and 3.3% achalasia. Twenty-seven point five percent of patients reported pharyngeal level (upper) dysphagia, 36.9% mid sternal dysphagia and 25.9% lower sternal dysphagia (9.5% reported multiple levels). The level of obstructing lesion seen on diagnostic testing was upper (17.2%), mid (19.4%) or lower (62.9%) or combined (0.3%). When patients localised their level of dysphagia to a single level, the kappa statistic was 0.245 ( P < 0.001), indicating fair agreement. 48% of patients reporting a single level of dysphagia were accurate in localising the obstructing pathology. With respect to pathology, patients with pharyngeal pouches were most accurate localising their level of dysphagia ( P < 0.001). With respect to level of dysphagia, those with pharyngeal level lesions were best able to identify the level of dysphagia accurately ( P < 0.001). No association ( P > 0.05) was found between gender, patient age or clinical symptoms with their ability to detect the level of dysphagia., Conclusion: Patient perceived level of dysphagia is unreliable in determining actual level of obstructing pathology and should not be used to tailor investigations., Competing Interests: Conflict-of-interest statement: Dalton HR has received travel and accommodation costs and consultancy fees from GlaxoSmithKline, Wantai and Roche, travel accommodation and lecture fees from Merck, Gilead and GFE Blut and travel and accommodation fees from the Falk and Gates Foundations. None of the other authors has any conflict of interest to disclose.

We describe a case of superior vena cava (SVC) obstruction caused by extension of tumour thrombus from a vertebral body metastasis through the azygos system to the SVC. The primary tumour was a renal cell carcinoma.