Combiner and hypercombiner networks: Rules to combine multimodality MR images for prostate cancer localisation
One of the distinct characteristics of radiologists reading multiparametric prostate MR scans,
using reporting systems like PI-RADS v2. 1, is to score individual types of MR modalities …
using reporting systems like PI-RADS v2. 1, is to score individual types of MR modalities …
Competing for pixels: a self-play algorithm for weakly-supervised semantic segmentation
Weakly-supervised semantic segmentation (WSSS) methods, reliant on image-level labels
indicating object presence, lack explicit correspondence between labels and regions of …
indicating object presence, lack explicit correspondence between labels and regions of …
Boundary-RL: Reinforcement Learning for Weakly-Supervised Prostate Segmentation in TRUS Images
We propose Boundary-RL, a novel weakly supervised segmentation method that utilises
only patch-level labels for training. We envision segmentation as a boundary detection …
only patch-level labels for training. We envision segmentation as a boundary detection …
Competing for pixels: a self-play algorithm for weakly-supervised segmentation
Weakly-supervised segmentation (WSS) methods, reliant on image-level labels indicating
object presence, lack explicit correspondence between labels and regions of interest (ROIs) …
object presence, lack explicit correspondence between labels and regions of interest (ROIs) …
[HTML][HTML] Active learning using adaptable task-based prioritisation
Supervised machine learning-based medical image computing applications necessitate
expert label curation, while unlabelled image data might be relatively abundant. Active …
expert label curation, while unlabelled image data might be relatively abundant. Active …
Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images
In this paper we propose a reinforcement learning based weakly supervised system for
localisation. We train a controller function to localise regions of interest within an image by …
localisation. We train a controller function to localise regions of interest within an image by …
Segmentation by registration-enabled SAM prompt engineering using five reference images
Abstract The recently proposed Segment Anything Model (SAM) is a general tool for image
segmentation, but it requires additional adaptation and careful fine-tuning for medical image …
segmentation, but it requires additional adaptation and careful fine-tuning for medical image …
Segmentation by Registration-Enabled SAM Prompt Engineering Using Five
R Hargunani, J Huang¹, C Liu, Y Hu - Biomedical Image Registration … - books.google.com
The recently proposed Segment Anything Model (SAM) is a general tool for image
segmentation, but it requires additional adaptation and careful fine-tuning for medical image …
segmentation, but it requires additional adaptation and careful fine-tuning for medical image …