Search Results for author: Matthew J. Clarkson

Found 28 papers, 12 papers with code

Competing for pixels: a self-play algorithm for weakly-supervised segmentation

1 code implementation26 May 2024 Shaheer U. Saeed, Shiqi Huang, João Ramalhinho, Iani J. M. B. Gayo, Nina Montaña-Brown, Ester Bonmati, Stephen P. Pereira, Brian Davidson, Dean C. Barratt, Matthew J. Clarkson, Yipeng Hu

Additionally, we propose a game termination condition that can be called by either side upon exhaustion of all ROI-containing patches, followed by the selection of a final patch from each.

Binary Classification Image Segmentation +5

PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery

1 code implementation22 May 2024 Runlong He, Mengya Xu, Adrito Das, Danyal Z. Khan, Sophia Bano, Hani J. Marcus, Danail Stoyanov, Matthew J. Clarkson, Mobarakol Islam

This paper introduces PitVQA, a novel dataset specifically designed for VQA in endonasal pituitary surgery and PitVQA-Net, an adaptation of the GPT2 with a novel image-grounded text embedding for surgical VQA.

Question Answering Visual Question Answering

Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery

1 code implementation22 Apr 2024 Yuyang Sheng, Sophia Bano, Matthew J. Clarkson, Mobarakol Islam

We utilise a commonly used detection architecture, DETR, and fine-tuned it to obtain bounding box prompt for the instruments.

Instance Segmentation Segmentation +1

Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images

no code implementations21 Feb 2024 Martynas Pocius, Wen Yan, Dean C. Barratt, Mark Emberton, Matthew J. Clarkson, Yipeng Hu, Shaheer U. Saeed

The object-presence classifier may then inform the controller of its localisation quality by quantifying the likelihood of the image containing an object.

Multiple Instance Learning Object

Semi-weakly-supervised neural network training for medical image registration

no code implementations16 Feb 2024 Yiwen Li, Yunguan Fu, Iani J. M. B. Gayo, Qianye Yang, Zhe Min, Shaheer U. Saeed, Wen Yan, Yipei Wang, J. Alison Noble, Mark Emberton, Matthew J. Clarkson, Dean C. Barratt, Victor A. Prisacariu, Yipeng Hu

For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective.

Image Registration Medical Image Registration

Long-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External Tracker

1 code implementation16 Oct 2023 Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, Yipeng Hu

Significance: The proposed new methodology with publicly available volunteer data and code for parametersing the long-term dependency, experimentally shown to be valid sources of performance improvement, which could potentially lead to better model development and practical optimisation of the reconstruction application.

3D Reconstruction

Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction

1 code implementation20 Aug 2023 Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, Yipeng Hu

Three-dimensional (3D) freehand ultrasound (US) reconstruction without using any additional external tracking device has seen recent advances with deep neural networks (DNNs).


Importance of Aligning Training Strategy with Evaluation for Diffusion Models in 3D Multiclass Segmentation

1 code implementation10 Mar 2023 Yunguan Fu, Yiwen Li, Shaheer U. Saeed, Matthew J. Clarkson, Yipeng Hu

Recently, denoising diffusion probabilistic models (DDPM) have been applied to image segmentation by generating segmentation masks conditioned on images, while the applications were mainly limited to 2D networks without exploiting potential benefits from the 3D formulation.

Denoising Image Segmentation +2

Bi-parametric prostate MR image synthesis using pathology and sequence-conditioned stable diffusion

no code implementations3 Mar 2023 Shaheer U. Saeed, Tom Syer, Wen Yan, Qianye Yang, Mark Emberton, Shonit Punwani, Matthew J. Clarkson, Dean C. Barratt, Yipeng Hu

For the first time, we evaluate the realism of the generated pathology by blind expert identification of the presence of suspected lesions, where we find that the clinician performs similarly for both real and synthesised images, with a 2. 9 percentage point difference in lesion identification accuracy between real and synthesised images, demonstrating the potentials in radiological training purposes.

Image Generation

Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration

1 code implementation12 Sep 2022 Yiwen Li, Yunguan Fu, Iani Gayo, Qianye Yang, Zhe Min, Shaheer Saeed, Wen Yan, Yipei Wang, J. Alison Noble, Mark Emberton, Matthew J. Clarkson, Henkjan Huisman, Dean Barratt, Victor Adrian Prisacariu, Yipeng Hu

The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training images and expert annotations.

Few-Shot Learning Segmentation

Cross-Modality Image Registration using a Training-Time Privileged Third Modality

1 code implementation26 Jul 2022 Qianye Yang, David Atkinson, Yunguan Fu, Tom Syer, Wen Yan, Shonit Punwani, Matthew J. Clarkson, Dean C. Barratt, Tom Vercauteren, Yipeng Hu

In this work, we consider the task of pairwise cross-modality image registration, which may benefit from exploiting additional images available only at training time from an additional modality that is different to those being registered.

Image Registration

Strategising template-guided needle placement for MR-targeted prostate biopsy

no code implementations21 Jul 2022 Iani JMB Gayo, Shaheer U. Saeed, Dean C. Barratt, Matthew J. Clarkson, Yipeng Hu

However, the diagnostic accuracy of the biopsy procedure is limited by the operator-dependent skills and experience in sampling the targets, a sequential decision making process that involves navigating an ultrasound probe and placing a series of sampling needles for potentially multiple targets.

Anatomy Decision Making +1

3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces

1 code implementation CVPR 2022 Simone Foti, Bongjin Koo, Danail Stoyanov, Matthew J. Clarkson

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem.


Voice-assisted Image Labelling for Endoscopic Ultrasound Classification using Neural Networks

no code implementations12 Oct 2021 Ester Bonmati, Yipeng Hu, Alexander Grimwood, Gavin J. Johnson, George Goodchild, Margaret G. Keane, Kurinchi Gurusamy, Brian Davidson, Matthew J. Clarkson, Stephen P. Pereira, Dean C. Barratt

In this work, we propose a multi-modal convolutional neural network (CNN) architecture that labels endoscopic ultrasound (EUS) images from raw verbal comments provided by a clinician during the procedure.

Anatomy Image Classification

Zero-shot super-resolution with a physically-motivated downsampling kernel for endomicroscopy

no code implementations25 Mar 2021 Agnieszka Barbara Szczotka, Dzhoshkun Ismail Shakir, Matthew J. Clarkson, Stephen P. Pereira, Tom Vercauteren

To address the need for non-reference image quality improvement, we designed a novel zero-shot super-resolution (ZSSR) approach that relies only on the endomicroscopy data to be processed in a self-supervised manner without the need for ground-truth HR images.

Image Quality Assessment Super-Resolution

Gesture Recognition in Robotic Surgery: a Review

no code implementations29 Jan 2021 Beatrice van Amsterdam, Matthew J. Clarkson, Danail Stoyanov

This paper reviews the state-of-the-art in methods for automatic recognition of fine-grained gestures in robotic surgery focusing on recent data-driven approaches and outlines the open questions and future research directions.

Activity Recognition Data Integration +4

Intraoperative Liver Surface Completion with Graph Convolutional VAE

no code implementations8 Sep 2020 Simone Foti, Bongjin Koo, Thomas Dowrick, Joao Ramalhinho, Moustafa Allam, Brian Davidson, Danail Stoyanov, Matthew J. Clarkson

In this work we propose a method based on geometric deep learning to predict the complete surface of the liver, given a partial point cloud of the organ obtained during the surgical laparoscopic procedure.

Data Augmentation

Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches

no code implementations29 Nov 2019 Agnieszka Barbara Szczotka, Dzhoshkun Ismail Shakir, DanieleRavi, Matthew J. Clarkson, Stephen P. Pereira, Tom Vercauteren

The main contributions of our study are a comparison of sparse and dense approach in pCLE image reconstruction, implementing trainable generalised NW kernel regression, and adaptation of synthetic data for training pCLE SR.

Image Quality Assessment Image Reconstruction +2

More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation

no code implementations20 Aug 2019 Yunguan Fu, Maria R. Robu, Bongjin Koo, Crispin Schneider, Stijn van Laarhoven, Danail Stoyanov, Brian Davidson, Matthew J. Clarkson, Yipeng Hu

Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications.

Image Segmentation Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.