A smart tele-cytology point-of-care platform for oral cancer screening

Abstract

Early detection of oral cancer necessitates a minimally invasive, tissue-specific diagnostic tool that facilitates screening/surveillance. Brush biopsy, though minimally invasive, demands skilled cyto-pathologist expertise. In this study, we explored the clinical utility/efficacy of a tele-cytology system in combination with Artificial Neural Network (ANN) based risk-stratification model for early detection of oral potentially malignant (OPML)/malignant lesion. A portable, automated tablet-based tele-cytology platform capable of digitization of cytology slides was evaluated for its efficacy in the detection of OPML/malignant lesions (n = 82) in comparison with conventional cytology and histology. Then, an image pre-processing algorithm was established to segregate cells, ANN was trained with images (n = 11,981) and a risk-stratification model developed. The specificity, sensitivity and accuracy of platform/ stratification model were computed, and agreement was examined using Kappa statistics. The tele-cytology platform, Cellscope, showed an overall accuracy of 84–86% with no difference between tele-cytology and conventional cytology in detection of oral lesions (kappa, 0.67–0.72). However, OPML could be detected with low sensitivity (18%) in accordance with the limitations of conventional cytology. The integration of image processing and development of an ANN-based risk stratification model improved the detection sensitivity of malignant lesions (93%) and high grade OPML (73%), thereby increasing the overall accuracy by 30%. Tele-cytology integrated with the risk stratification model, a novel strategy established in this study, can be an invaluable Point-of-Care (PoC) tool for early detection/screening in oral cancer. This study hence establishes the applicability of tele-cytology for accurate, remote diagnosis and use of automated ANN-based analysis in improving its efficacy.

Diagnostic accuracy of cytology for the detection of endometrial cancer in urine and vaginal samples

“…Cytology is an established technology for the detection of cancers and their precursors, for example of the bladder 31 , lung 32 and cervix 33 . Recent years have witnessed innovative solutions to the detection of Barrett’s oesophagus 34 and oral cancer 35 using cytology, offering hope for early detection strategies 36 . Here we hijack the natural shed of endometrial tumours via PMB to similarly develop a novel approach to endometrial cancer detection.…”

Teledentistry during COVID-19 pandemic

“…While the use of smartphones for detection of dental caries is well advocated [15,16]; it has also served as a reliable adjunct for screening of oral potentially malignant lesions [17]. An addition to telediagnosis is telecytology, a system for early detection of oral potentially malignant or malignant lesions [18]. Haron et al developed Mobile Mouth Screening Anywhere (MeMoSA®) to facilitate early detection of oral cancer and found it to be beneficial for patients with limited access to specialists [19].…”

Application of Artificial Intelligence in Dentistry

“…A risk stratification model based on brush biopsy and cytology was also constructed with ML algorithms such as SVM and RF. Utilizing CNN to score the malignancy of cytology images derived from a telemedicine platform, this model showed high sensitivity in detecting oral malignant (93%) and high-grade potential malignant (73%) lesions (Sunny et al 2019). Despite these excellent results, contemporary AI models for oral and maxillofacial surgery diagnosis focus on only 1 type of data, such as radiographic results or cytopathologic images.…”

“…Extracting information from constantly updating medical and dental databases for the application of AI requires continuous upgrading of processing power. Because the computational power of classical computers has been largely saturated (Solenov et al 2018), the insufficient computational resources in data processing have become one of the obstacles that constrain the efficacy of AI (Sunny et al 2019). Quantum computing processes data by using quantum bits (qubits), in accordance with the laws and restrictions of quantum mechanics.…”