No abstract

No standardised, comprehensive approach to rapid on‐site evaluation (ROSE) of cytology samples currently exists. Recent meta‐analysis indicates variation in the effectiveness of ROSE, however, reviews commonly omit the details of how ROSE is conducted. This review demonstrates the clinical effectiveness of single slide assessment (SSA) for ROSE of cytology samples, providing a highly effective, standardised methodology, maximising cell yield and the diagnostic potential of samples obtained via endobronchial or endoscopic ultrasound. Advances in molecular testing and immunotherapy now allow patients to access sophisticated, targeted cancer treatments and, consequently, obtaining diagnostic material alone is no longer sufficient. SSA uses specific criteria, based on the morphological presentation, to ensure sufficient material is obtained through one procedure, allowing for all the molecular profiling and tumour expression testing required to provide the patient and clinicians with the optimal treatment options. In total, 450 endobronchial or endoscopic ultrasound procedures were conducted with ROSE SSA performed by a biomedical scientist between 2010 and 2017. In 97% of cases, ROSE SSA matched the final report (inadequate vs adequate—benign material vs malignancy). ROSE SSA provided sufficient material for immunocytochemistry in 200/208 cases (96%) and for additional molecular testing/tumour profiling in 92% (85/92) of cases. The median number of needle passes was three. ROSE SSA streamlines diagnostic pathways; minimising risk of complications to patients, reducing cost and delays to treatment associated with repeat or more invasive procedures. Using SSA, sufficient material for a comprehensive diagnosis can be obtained in one procedure.

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.

No abstract