Detail

Keywords

Artificial Intelligence; Computational Biology; Genomics; Image Processing, Computer-Assisted; Machine Learning

Research interests

I specialize in the fields of deep learning, medical image analysis, interpretable AI, and computational genomics. With expertise in developing deep learning frameworks to advance medical imaging and cancer diagnostics, I envision to contribute meaningfully to the field of healthcare by developing industry-aligned products with a collaborative spirit and interdisciplinary approach.

Techniques, methods & infrastructure

Machine/Deep Learning

• Experience ranging from vanilla feed-forward neural networks to the development of advanced frameworks integrating conv-nets, vision transformers, and generative models. Expertise in designing and implementing diverse attention mechanisms, along with profound knowledge of interpretable and explainable artificial intelligence.
• Extensive hands-on experience with state-of-the-art machine learning algorithms, including gradient boosting methods, support vector machines, and unsupervised learning techniques such as nearest neighbor–based methods.
• In-depth knowledge of pattern recognition tasks, including feature selection and feature extraction. Hands-on expertise with techniques ranging from iterative feature selection, SVM-RFE, mutual information, and ReliefF, to deep learning–based autoencoders and interpretability toolkits such as PyTorch Captum and SHAP.

Medical Image Analysis

• Hands-on experience with state-of-the-art models for medical imaging such as (U-Net, ViT, HoVerNet, Segment Anything, and CTransPath).
• Proficient in segmentation, classification and morphological attributions of nuclei and tissue in H&E, immunofluorescence, and tissue microarray images

Computational Biology & Bioinformatics

• Experience in omics/multiomics multimodal data-based biomarker discovery, survival analysis (PyCox, SurvPath, scikit-survival), protein-protein, gene-gene and gene-disease analyses, and AI-driven classification of various cancer subtypes.
• RNA-Seq and differential expression analysis via deseq2, edgeR, limma and HTSeq.
• Pathway and network analysis using STRING, CytoScape, DGIdb, KEGG, PANTHER, and Reactome.

Selected publications

1. Dwivedi, K. et al. (2023) ‘An explainable AI-driven biomarker discovery framework for Non-Small Cell Lung Cancer classification’, Computers in Biology and Medicine, 153, p. 106544. Available at: https://doi.org/10.1016/j.compbiomed.2023.106544.
2. Dwivedi, K. et al. (2024) ‘Enlightening the path to NSCLC biomarkers: Utilizing the power of XAI-guided deep learning’, Computer Methods and Programs in Biomedicine, 243, p. 107864. Available at: https://doi.org/10.1016/j.cmpb.2023.107864.
3. Dwivedi, K. et al. (2024) ‘Deep Learning-based NSCLC Classification from Whole-Slide Images: Leveraging Expectation-Maximization and InceptionV3’, Procedia Computer Science, 235, pp. 2422–2433. Available at: https://doi.org/10.1016/j.procs.2024.04.229.
4. Dwivedi, K. et al. (2025) ‘A multimodal cross-attention pathotranscriptome integration for enhanced survival prediction of oral squamous cell carcinoma’. Available at: https://doi.org/10.1101/2025.10.31.25339218.
5. Dwivedi, K. et al. (2024) ‘Deep Learning-based NSCLC Classification from Whole-Slide Images: Leveraging Expectation-Maximization and InceptionV3’, Procedia Computer Science, 235, pp. 2422–2433. Available at: https://doi.org/10.1016/j.procs.2024.04.229.