Field validation of deep learning based Point-of-Care device for early detection of oral malignant and potentially malignant disorders.

Early detection of oral cancer in low-resource settings necessitates a Point-of-Care screening tool that empowers Frontline-Health-Workers (FHW). This study was conducted to validate the accuracy of Convolutional-Neural-Network (CNN) enabled m(mobile)-Health device deployed with FHWs for delineation of suspicious oral lesions (malignant/potentially-malignant disorders). The effectiveness of the device was tested in tertiary-care hospitals and low-resource settings in India. The subjects were screened independently, either by FHWs alone or along with specialists. All the subjects were also remotely evaluated by oral cancer specialist/s. The program screened 5025 subjects (Images: 32,128) with 95% (n = 4728) having telediagnosis. Among the 16% (n = 752) assessed by onsite specialists, 20% (n = 102) underwent biopsy. Simple and complex CNN were integrated into the mobile phone and cloud respectively. The onsite specialist diagnosis showed a high sensitivity (94%), when compared to histology, while telediagnosis showed high accuracy in comparison with onsite specialists (sensitivity: 95%; specificity: 84%). FHWs, however, when compared with telediagnosis, identified suspicious lesions with less sensitivity (60%). Phone integrated, CNN (MobileNet) accurately delineated lesions (n = 1416; sensitivity: 82%) and Cloud-based CNN (VGG19) had higher accuracy (sensitivity: 87%) with tele-diagnosis as reference standard. The results of the study suggest that an automated mHealth-enabled, dual-image system is a useful triaging tool and empowers FHWs for oral cancer screening in low-resource settings.

Inter- and Intra-Observer Variability in Diagnosis of Oral Dysplasia

Background: Oral potentially malignant disorders (OPMDs) are lesions from which malignancy is more likely to develop that from other tissues. The potential for malignant transformation of OPMDs is estimated by determining the degree of dysplastic changes in the epithelium. Dysplasia grading has been criticized for lack of reproducibility and poor predictive value but is still considered the gold standard for diagnosing OPMDs. Since grading of dysplasia is based on architectural and cytological changes, there can be considerable inter- and intra-observer variability due to subjective impressions. This aim in this study was to assess the degree of agreement between two pathologists grading dysplasia in the same patients and review the existing grading system. Materials and Methods: In this hospital-based cross-sectional study, 100 patients with clinically diagnosed OPMDs were subjected to biopsy followed by histopathological examination. The slides were examined by two pathologists using WHO and binary systems of classification and both were blinded to the clinical and each other's histological diagnosis. For statistical analysis the Chi square test was applied. Results: Statistical analysis showed poor inter-observer variability with P values of 0.8 using the WHO classification and 0.3 using the binary classification. Conclusion: Our study provides evidence that the existing systems for grading dysplasia are not competent to rule out subjectivity. There is a need for a classification system that can overcome this drawback.