'Cytology-on-a-chip' based sensors for monitoring of potentially malignant oral lesions. (September 2016)

• Record Type: Journal Article
• Authors: Abram, Timothy J.; Floriano, Pierre N.; Christodoulides, Nicolaos; James, Robert; Kerr, A. Ross; Thornhill, Martin H.; Redding, Spencer W.; Vigneswaran, Nadarajah; Speight, Paul M.; Vick, Julie; Murdoch, Craig; Freeman, Christine; Hegarty, Anne M.; D'Apice, Katy; Phelan, Joan A.; Corby, Patricia M.; Khouly, Ismael; Bouquot, Jerry; Demian, Nagi M.; Weinstock, Y. Etan; Rowan, Stephanie; Yeh, Chih-Ko; McGuff, H. Stan; Miller, Frank R.; Gaur, Surabhi; Karthikeyan, Kailash; Taylor, Leander; Le, Cathy; Nguyen, Michael; Talavera, Humberto; Raja, Rameez; Wong, Jorge; McDevitt, John T.;
• Is Part Of: Oral oncology. Volume 60(2016:Sep.)
• Page Start: 103
• Page End: 111
• Publication Date: 2016-09
• Subjects: PMOL potentially malignant oral lesion(s) -- OED oral epithelial dysplasia -- OSCC oral squamous cell carcinoma -- HCA high content analysis -- AUC area under the (receiver-operator characteristic) curve -- NC ratio nuclear-cytoplasmic area ratio; Cytology -- Oral cancer -- Oral epithelial dysplasia -- Microfluidic -- High content analysis -- Machine learning -- Random forest -- LASSO; Mouth -- Cancer -- Periodicals; Mouth -- Tumors -- Periodicals; Mouth Diseases -- Periodicals; Mouth Neoplasms -- Periodicals; Bouche -- Cancer -- Périodiques; Bouche -- Tumeurs -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9943105
• DOI: 10.1016/j.oraloncology.2016.07.002
• Languages: English
• ISSNs: 1368-8375

Abstract

Highlights: Cytology-on-chip approach permits rapid molecular and morphometric analysis. Stable, robust predictive models created from single-cell data. Prognostic cytology features identified including cell circularity, Ki67 expression. Unique combination of parameters required for different diagnostic splits. Abstract: Despite significant advances in surgical procedures and treatment, long-term prognosis for patients with oral cancer remains poor, with survival rates among the lowest of major cancers. Better methods are desperately needed to identify potential malignancies early when treatments are more effective. Objective: To develop robust classification models from cytology-on-a-chip measurements that mirror diagnostic performance of gold standard approach involving tissue biopsy. Materials and methods: Measurements were recorded from 714 prospectively recruited patients with suspicious lesions across 6 diagnostic categories (each confirmed by tissue biopsy -histopathology) using a powerful new 'cytology-on-a-chip' approach capable of executing high content analysis at a single cell level. Over 200 cellular features related to biomarker expression, nuclear parameters and cellular morphology were recorded per cell. By cataloging an average of 2000 cells per patient, these efforts resulted in nearly 13 million indexed objects. Results: Binary "low-risk"/"high-risk" models yielded AUC values of 0.88 and 0.84 for training and validation models, respectively, with an accompanying difference in sensitivity + specificity of 6.2%. In terms of accuracy, this model accurately predicted the correct diagnosis approximately 70% of the time, compared to the 69% initial agreement rate of the pool of expert pathologists. Key parameters identified in these models included cell circularity, Ki67 and EGFR expression, nuclear-cytoplasmic ratio, nuclear area, and cell area. Conclusions: This chip-based approach yields objective data that can be leveraged for diagnosis and management of patients with PMOL as well as uncovering new molecular-level insights behind cytological differences across the OED spectrum.