Department Publications

Spatial transcriptomics is an emerging field that enables the identification of functional regions based on the spatial distribution of gene expression. Integrating this functional information present in transcriptomic data with structural data from histopathology images is an active research area with applications in identifying tumor substructures associated with cancer drug resistance. Current histopathology-spatial-transcriptomic region segmentation methods suffer due to either making spatial transcriptomics prominent by using histopathology features just to assist processing spatial transcriptomics data or using vanilla contrastive learning that make histopathology images prominent due to only promoting common features losing functional information. In both extremes, the model gets either lost in the noise of spatial transcriptomics or overly smoothed, losing essential information. Thus, we propose our novel …

Neonatal jaundice, caused by elevated bilirubin levels, requires timely diagnosis to prevent severe complications. Existing deep learning approaches primarily focus on binary classification of jaundice from visual data, but do not provide quantitative bilirubin estimation. A binary decision alone is insufficient for clinical management, where treatment thresholds depend on precise bilirubin levels. This paper presents a deep-learning-based contactless framework for neonatal jaundice assessment using image-based analysis. The proposed lightweight multi-stage pipeline integrates eye-region obfuscation, skin segmentation, and deep-learning-based image classification and bilirubin estimation. The system first performs jaundice classification; upon positive detection, a regression model is invoked to estimate bilirubin. Furthermore, image-based neonatal screening raises privacy concerns, as facial images of …

Diabetes is associated with progressive microvascular remodelling, commonly assessed using retinal imaging, yet alternative non-invasive vascular biomarkers remain underexplored. Conjunctival vessels are directly visible and may reflect systemic microvascular changes; however, reliable quantification is challenged by the need to preserve vascular topology during segmentation. In this work, we introduce a curated conjunctival imaging dataset with diameter-specific vessel annotations and demonstrate that topology-preserving vessel extraction is essential for robust tortuosity estimation. We develop a deep learning framework that prioritises vascular continuity and geometric fidelity while selectively segmenting clinically relevant vessel calibres, integrating multi-scale contextual modelling and attention-guided feature fusion to reduce fragmentation without post-processing. Compared with multiple state-of-the-art …

Machine-learning-assisted cancer subtyping is a promising avenue in digital pathology. Cancer subtyping models however require careful training using expert annotations, so that they can be inferred with a degree of known certainty (or uncertainty). To this end, we introduce the concept of uncertainty awareness into a self-supervised contrastive learning model. This is achieved by computing an evidence vector at every epoch, which assesses the model's confidence in its predictions. The derived uncertainty score is then utilized as a metric to selectively label the most crucial images that require further annotation, thus iteratively refining the training process. With just 1-10% of strategically selected annotations, we attain state-of-the-art performance in cancer subtyping on benchmark datasets. Our method not only strategically guides the annotation process to minimize the need for extensive labeled datasets, but …

3D reconstruction of the liver for volumetry is important for qualitative analysis and disease diagnosis. Liver volumetry using Ultrasound (US) scans, although advantageous due to less acquisition time and safety, is challenging due to the inherent noisiness in US scans, blurry boundaries, and partial liver visibility. We address these challenges by using the segmentation masks of a few incomplete sagittal-plane US scans of the liver in conjunction with a Statistical Shape Model (SSM) built using a set of CT scans of the liver. We compute the shape parameters needed to warp this canonical SSM to fit the US scans through a parametric regression network. The resulting 3D liver reconstruction is accurate and leads to automatic liver volume calculation. We evaluate the accuracy of the estimated liver volumes with respect to CT segmentation volumes using RMSE. Our volume computation is statistically much closer to the …

Neural networks can learn features from millions of histopathology images. However, curating high-quality annotations for training is laborious. In this work, we show how such models can be trained with only 1-10% of annotated data.

Minimally invasive liver cancer treatments are increasingly favoured for their reduced risks and improved patient outcomes. However, real-time guidance during liver ablation remains challenging due to limited resources and the reliance on ultrasound (US) imaging. This project introduces a deep learning-based approach for 2D US to 3D Computed Tomography (CT) image registration, eliminating the need for 3D tracking systems. By integrating self-supervised feature embeddings and matching point estimation methods, our approach enhances real-time visualization of the liver, improving surgical precision and cost-effectiveness. With around 0.99 Normalized Cross-Correlation (NCC) value and 25.48-pixel distance in US and CT image registration, this research promises significant advancements in liver tumor ablation procedures and holds potential for broader applications in other ablation therapies.

Deep neural network models can learn clinically relevant features from millions of histopathology images. However generating high-quality annotations to train such models for each hospital, each cancer type, and each diagnostic task is prohibitively laborious. On the other hand, terabytes of training data–while lacking reliable annotations–are readily available in the public domain in some cases. In this work, we explore how these large datasets can be consciously utilized to pre-train deep networks to encode informative representations. We then fine-tune our pre-trained models on a fraction of annotated training data to perform specific downstream tasks. We show that our approach can reach the current state-of-the-art (SOTA) for patch-level classification with only 1-10% randomly selected annotations compared to other SOTA approaches. Moreover, we propose an uncertainty-aware loss function, to quantify the model confidence during inference. Quantified uncertainty helps experts select the best instances to label for further training. Our uncertainty-aware labeling reaches the SOTA with significantly fewer annotations compared to random labeling. Last, we demonstrate how our pretrained encoders can surpass current SOTA for wholeslide image classification with weak supervision. Our work lays the foundation for data and task-agnostic pretrained deep networks with quantified uncertainty.