Search

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. [ABSTRACT FROM AUTHOR]

Objectives: Idiopathic granulomatous mastitis (IGM) is a rare inflammatory disease of the breast, which is benign but potentially morbid. Mammographic and sonographic findings have been well characterized, but magnetic resonance imaging (MRI) findings have been less thoroughly documented. The objective of this study was to demonstrate characteristic findings for IGM and its mimics via a retrospective review. Material and Methods: Breast MRI examinations performed at Sir Ganga Ram Hospital in New Delhi, India between 2014 and 2019 were retrospectively reviewed to identify cases in which a pattern suggestive of granulomatous mastitis was seen. Cases of known malignancy were excluded. Any available breast pathology results were then obtained, and cases with presumptive or definitive diagnoses were compiled for analysis. Results: Overall, cases identified with characteristic imaging findings and confirmed diagnosis included seven cases of IGM, four cases of invasive ductal carcinoma, two cases of tuberculous mastitis, one case of nontuberculous infectious mastitis, one case of foreign body mastitis, and one case of eosinophilc mastitis. One case of IGM with masses rather than of non-mass enhancement was also identified. Conclusion: In our review, cases with clustered ring enhancement were found to have inflammatory, idiopathic, infectious and malignant etiologies. While, these etiologies can only be reliably differentiated on pathology, familiarity with the pattern and an awareness of the differential may lead to decreased morbidity due to delays in diagnosis. [ABSTRACT FROM AUTHOR]

Aims: The aim of this study was to evaluate the role of MRI based diffusion-weighted imaging (DWI) and the apparent diffusion coefficient (ADC) for characterizing breast lesions in Indian patients. Materials and Methods: This prospective analysis was performed between October 2006 and June 2008. It includes 200 patients between the ages of 16 and 80 years with solid breast lesions greater than 1 cm in diameter. Of these 200 patients, 80 underwent breast MRI with contrast and DWI. One hundred and twenty patients had only DWI as they had come only for sonomammography. A total of 280 lesions were detected. ADC values were calculated for all the lesions and the highest and lowest values of ADC for benign and malignant lesions were identified. Finally, we compared our findings with those of previous studies. Results: Two hundred and eight lesions were categorized as benign and 72 lesions were categorized as malignant based on the ADC values. Based on previous data, lesions with ADC values from 1.3 to 1.5 mm²/s were considered benign where as lesions with ADC values ranging between 0.85 and1.1 mm²/s were considered malignant. Two lesions whose ADC values were in the benign range were proven to be malignant tumors after surgery. This method of using ADC values for the detection of malignant lesions showed a sensitivity of 97.22% and a specificity of 100%. The positive predictive value was 100%. Conclusion: DWI is a useful technique for characterizing breast tumors, especially for lesions that cannot be adequately characterized by ultrasonography and routine magnetic resonance imaging. [ABSTRACT FROM AUTHOR]