CURRENT RESEARCH THEMES- Omics Data Integration ( Single cell Data Analysis, Transcriptomics, Genomics)- Radiomics (Medical imaging)- Pathomics (Histopathology images) - Antimicrobial resistance (AMR) surveillance (Metagenomics, Resistome, Mobilome, Pipeline development, Monitoring Dashboard )SUMMARYAn experienced digital health expert in AI, machine learning, and bioinformatics, particularly in medical imaging and disease detection. A proven track record in leading research initiatives, developing deep learning models, and integrating multi-omics data. Adept at promoting industry-university partnerships and leading innovative projects with experience in AI ethical practices, policy development, and regulatory standards.SUMMARY OF AI AND MACHINE LEARNING EXPERTISE - Disease Detection in Spine Radiographs: Developed a convolutional neural network (ConvNet) to detect diseases in lumbosacral spine radiographs, showcasing proficiency in deep learning applications for medical imaging.- Breast Cancer Treatment Prediction: Implemented predictive modeling using dynamic contrast-enhanced MRI (DCE-MRI) images to forecast breast cancer response to neoadjuvant chemotherapy, leveraging tumor habitat analysis for personalized treatment planning.- Malignant Breast Lesions Detection: Combined bioinspired texture descriptors with deep learning features to enhance the detection accuracy of malignant breast lesions in histopathological images.- Tumor Segmentation in Breast MRI: Utilized deep learning methods for precisely segmenting tumors in breast DCE-MRI slices, improving the accuracy and reliability of cancer diagnostics.- COVID-19 Lesion Segmentation: Developed an automated deep-learning method for segmenting COVID-19 lesions in CT images, contributing to pandemic-related diagnostic tools.- Classification of Pulmonary Nodules: Evaluated data balancing techniques in 3D convolutional neural networks (3D CNNs) to classify pulmonary nodules in CT images, enhancing lung cancer detection capabilities.- Automated Glaucoma Diagnosis: Applied 3D convolutional neural networks for the automatic diagnosis of glaucoma, demonstrating expertise in ophthalmology-related AI applications.- Glaucoma Identification with Capsule Networks: Implemented capsule networks to identify glaucoma in retinal images, showcasing advanced neural network architectures for medical image analysis.