Kaushalya Sivayogaraj, Sahan I. Guruge, Udari. A. Liyanage, Jeevani J. Udupihille, Gerard M. Jayasinghe, Saroj, Fernando, Ranga Rodrigo, Rukshani Liyanaarachchi
Conference
MICCAI International Conference on Medical Image Computing and Computer-Assisted Intervention , pp. 436-445 · 2024 · Cited by 3
Computer VisionMedical Image AnalysisBiomedical Imaging and Reconstruction
Abstract
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 …
Nirhoshan Sivaroopan, Hasindri Watawana, Chamuditha Jayanga, Chalani Ekanayake, Ranga Rodrigo, Chamira U. S. Edussooriya, Dushan N Wadduwage
Conference
Microscopy Histopathology and Analytics , pp. MM3A. 5 · 2024 · Cited by 2
Machine Learning and Pattern RecognitionMedical Image Analysis
Abstract
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.
Mokeeshan Vathanakumar, Poogitha Jegakumaran, Nifla Nasvi, Lakshika Sivakumar, Nuwan D Nanayakkara, Chinthaka Appuhamy, Rohan Siriwardena, Madhushanka Rukshani Liyanaarachchi
Conference
TENCON TENCON 2024-2024 IEEE Region 10 Conference (TENCON) , pp. 760-763 · 2024 · Cited by 0
Medical Image AnalysisBiomedical Imaging and Reconstruction
Abstract
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.
