Early detection of esophageal squamous cell carcinoma with the Cytosponge coupled with molecular biomarkers and machine learning
Background: Esophageal squamous cell carcinoma (ESCC) carries significant mortality and remains the predominant type of esophageal cancer worldwide. Since a potential screening regime for ESCC would have to rely on endoscopy, this creates substantial challenges regarding its cost-effectiveness and applicability. Therefore, we hypothesize that a non-endoscopic Cytosponge cell collection device could provide a novel approach to ESCC screening.
Aims: The primary aim is to evaluate the diagnostic yield of Cytosponge combined with tissue biomarkers (p53-immunohistochemistry [p53-IHC]) and molecular biomarkers for detecting ESCC and its precursor lesions. As secondary aims, we plan to assess the utility of machine learning-based approaches to assist pathological assessment of the Cytosponge samples. Lastly, we aim to investigate the use of Cytosponge in sampling the esophageal microbiota and its potential role in identifying at-risk individuals for ESCC utilizing microbial biomarkers.
Methods: In this multicenter study, we plan to recruit patients within three risk groups for ESCC: 1. healthy controls, 2. high-risk individuals (previous head-and-neck cancer/ ESCC), and 3. patients with known early ESCC. Each patient will undergo high-definition endoscopy and a Cytosponge examination. The biomarker assay, including p53-IHC and shallow whole genome sequencing, will be tested within the Cytosponge samples and compared with the final endoscopic diagnosis. Machine learning algorithms will be applied to digitalized cytology to detect atypical cells and regions of p53-IHC overexpression. Lastly, we will extract microbial DNA from Cytosponge samples to assess any taxonomic diversity within three risk groups for ESCC.
Potential impact: We hope to develop a novel, effective, and affordable diagnostic assay that, coupled with a minimally-invasive Cytosponge device, could be implemented in a clinical setting, improving the early detection of ESCC and, eventually, patient outcomes.
Subscribe to our Newsletter You can unsubscribe at any moment by clicking on the subscription preferences link at the bottom of a received newsletter.
This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No. 964264.