Medical Image Analysis · Deep Learning · Computer Vision
I am an Assistant Professor in the School of Computer Science at UPES Dehradun. My research develops efficient, interpretable deep learning for medical image segmentation and classification — architectures such as EfficientU-Net and UMA-Net, and uncertainty-aware losses built on fuzzy rough set theory.
Citations per year
2023: 3 citations, 2024: 16 citations, 2025: 48 citations, 2026: 47 citations
Source: Google Scholar, updated weekly.
MSCT-Trans — a multi-scale CNN token transformer for interpretable ultrasound classification — published in Ultrasound in Medicine & Biology. Read the paper
Saliency-guided AttentionNet, our dual-branch model for breast ultrasound classification, published in Biomedical Signal Processing and Control. Read the paper
Awarded the PhD degree by the University of Hyderabad on 28 July 2026, for the thesis “Advances in Deep Learning for Medical Image Segmentation and Classification”. Read the summary
Shortlisted as Research Faculty at UPES Dehradun.
Our paper “Fuzzy Rough Set Loss for Deep Learning-Based Precise Medical Image Segmentation” was accepted in Computerized Medical Imaging and Graphics (SCI).
Joined the School of Computer Science, UPES Dehradun, as Assistant Professor.
Submitted my PhD thesis, “Advances in Deep Learning for Medical Image Segmentation and Classification”, to the University of Hyderabad.
UMA-Net — adaptive ensemble loss and multi-scale attention for breast ultrasound segmentation — published in Medical & Biological Engineering & Computing (Springer, SCIE).
Three papers submitted to Biomedical Signal Processing & Control and Ultrasound in Medicine & Biology.
Our work on genetic algorithm-based feature selection was published in Image and Vision Computing (Elsevier, SCIE).
Ultrasound in Medicine & Biology, 52(11), 2623–2638, 2026
Multi-scale convolutional features from a lightweight backbone become a unified token sequence for a transformer encoder, giving cross-scale global reasoning and interpretable predictions across breast, thyroid and fetal ultrasound.
Biomedical Signal Processing and Control, 127, 111194, 2026
Grad-CAM saliency splits each scan into lesion and context branches over a shared backbone, fused by an adaptive attention block — 90.51% accuracy across five public datasets and 78.46% on held-out data.
Computerized Medical Imaging and Graphics, 128, 102716, 2026
A loss built on fuzzy rough set theory that treats boundary ambiguity as a first-class signal, combining fuzzy similarity with lower and upper approximations to sharpen delineation across ultrasound, MRI and CT.
Medical & Biological Engineering & Computing, 63(6), 1697–1713, 2025
Residual connections, attention blocks and atrous convolutions trained under a dynamic ensemble loss that rebalances BCE, Dice, Hausdorff and Tversky terms during training — generalising across five breast ultrasound datasets.
Image and Vision Computing, 146, 105018, 2024
Deep features selected by a genetic algorithm and classified by a weighted-voting ensemble, gaining 4–9% accuracy on benchmark breast ultrasound data while curbing overfitting on small datasets.
Neural Processing Letters, 55(8), 10439–10462, 2023
EfficientNet-B7 and atrous convolution inside U-Net: a 13× parameter reduction over U-Net (1.31M vs 17.27M) with 97.9% classification accuracy on breast ultrasound.
01
Optimization frameworks that fold anatomical priors, imaging physics and clinical workflow constraints into the training pipeline, balancing accuracy, uncertainty and compute under limited medical data.
02
A dual-branch architecture that models lesion and peritumoral tissue separately through Grad-CAM saliency guidance — 90.51% accuracy across five public datasets, 78.46% on held-out data.
03
Fuzzy rough set losses that treat boundary ambiguity as a first-class signal, sharpening lesion delineation across ultrasound, MRI and CT at lower computational cost than conventional objectives.
04
Pixel-level uncertainty estimation paired with multi-modal explainability — detecting 92% of segmentation failures while sending only 15% of cases to manual review.