Abstract
SummaryBackgroundNon-endoscopic cell collection devices combined with biomarkers can detect Barrett's intestinal metaplasia and early oesophageal cancer. However, assays performed on multi-cellular samples lose information about the cell source of the biomarker signal. This cross-sectional study examines whether a bespoke artificial intelligence-based computational pathology tool could ascertain the cellular origin of microRNA biomarkers, to inform interpretation of the disease pathology, and confirm biomarker validity.MethodsThe microRNA expression profiles of 110 targets were assessed with a custom multiplexed panel in a cohort of 117 individuals with reflux that took a Cytosponge test. A computational pathology tool quantified the amount of columnar epithelium present in pathology slides, and results were correlated with microRNA signals. An independent cohort of 139 Cytosponges, each from an individual patient, was used to validate the findings via qPCR.FindingsSeventeen microRNAs are upregulated in BE compared to healthy squamous epithelia, of which 13 remain upregulated in dysplasia. A pathway enrichment analysis confirmed association to neoplastic and cell cycle regulation processes. Ten microRNAs positively correlated with columnar epithelium content, with miRNA-192–5p and -194–5p accurately detecting the presence of gastric cells (AUC 0.97 and 0.95). In contrast, miR-196a-5p is confirmed as a specific BE marker.InterpretationComputational pathology tools aid accurate cellular attribution of molecular signals. This innovative design with multiplex microRNA coupled with artificial intelligence has led to discovery of a quality control metric suitable for large scale application of the Cytosponge. Similar approaches could aid optimal interpretation of biomarkers for clinical use.FundingFunded by the NIHR Cambridge Biomedical Research Centre, the Medical Research Council, the Rosetrees and Stoneygate Trusts, and CRUK core grants.
Highlights
Biomarkers are critical for early detection of cancer that cannot otherwise be and reliably detected from morphological analysis of fluid, biopsy or cytology samples
Non-endoscopic cell collection tools coupled with novel biomarkers have been developed as an alternative to endoscopy for the early detection of oesophageal cancer.[1-6]
There was a bias towards male sex, abdominal fat and older age in Barrett’s patients, and these factors were statistically significantly higher in Barrett’s oesophagus (BE) compared to normal squamous epithelium (NE) groups in our two study cohorts (Table 1 and Supplementary figures S1 and S2)
Summary
Biomarkers are critical for early detection of cancer that cannot otherwise be and reliably detected from morphological analysis of fluid, biopsy or cytology samples. To facilitate high data throughput, bulk assays are often performed on entire cell samples, yielding no spatial or cellular tissue information. New methods such as single cell sequencing are improving experimental resolution, but they are not feasible for large-scale clinical application and spatial features are not retained from single cell analysis. Non-endoscopic cell collection tools coupled with novel biomarkers have been developed as an alternative to endoscopy for the early detection of oesophageal cancer.[1-6] These tools are promising to identify patients with risk factors such as heartburn symptoms who have the premalignant condition Barrett’s oesophagus (BE) who warrant endoscopy. Our group has developed a the Cytopsonge-TFF3 test, which is a non-endoscopic, panoesophageal collection device that is coupled with www.thelancet.com Vol 76 Month February, 2022
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
