Search Results for author:
Found 96 papers, 52 papers with code
Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentation
In this work, we propose an adaptive multi-scale online likelihood network (MONet) that adaptively learns in a data-efficient online setting from both an initial automatic segmentation and user interactions providing corrections.
Hyperspectral Image Segmentation: A Preliminary Study on the Oral and Dental Spectral Image Database (ODSI-DB)
Visual discrimination of clinical tissue types remains challenging, with traditional RGB imaging providing limited contrast for such tasks.
Spatial gradient consistency for unsupervised learning of hyperspectral demosaicking: Application to surgical imaging
However, a demosaicking algorithm is required to fully recover the spatial and spectral information of the snapshot images.
VideoSum: A Python Library for Surgical Video Summarization
It is thus unsurprising that substantial research efforts are made to develop methods aiming at mitigating the scarcity of annotated SDS data.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Trackerless freehand ultrasound with sequence modelling and auxiliary transformation over past and future frames
Little benefit was observed by adding frames more than one second away from the predicted transformation, with or without LSTM-based RNNs.
MONAI: An open-source framework for deep learning in healthcare
For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e. g. geometry, physiology, physics) of medical data being processed.
Rapid and robust endoscopic content area estimation: A lean GPU-based pipeline and curated benchmark dataset
The estimation of the content area is a common task in endoscopic image processing and computer vision pipelines.
ROS-PyBullet Interface: A Framework for Reliable Contact Simulation and Human-Robot Interaction
However, there is a lack of software connecting reliable contact simulation with the larger robotics ecosystem (i. e. ROS, Orocos), for a more seamless application of novel approaches, found in the literature, to existing robotic hardware.
Can segmentation models be trained with fully synthetically generated data?
Data augmentation is often used to artificially increase the variability in the data distribution and improve model generalisability.
Boundary Distance Loss for Intra-/Extra-meatal Segmentation of Vestibular Schwannoma
It can be separated into two regions, intrameatal and extrameatal respectively corresponding to being inside or outside the inner ear canal.
Driving Points Prediction For Abdominal Probabilistic Registration
Among the various registration methods proposed for this task, probabilistic displacement registration models estimate displacement distribution for a subset of points by comparing feature vectors of points from the two images.
FastGeodis: Fast Generalised Geodesic Distance Transform
The FastGeodis package provides an efficient implementation for computing Geodesic and Euclidean distance transforms (or a mixture of both), targeting efficient utilisation of CPU and GPU hardware.
Cross-Modality Image Registration using a Training-Time Privileged Third Modality
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.
Spatiotemporal singular value decomposition for denoising in photoacoustic imaging with low-energy excitation light source
However, PA signals generated with these light sources are readily degraded by noise due to the low optical fluence, leading to decreased signal-to-noise ratio (SNR) in PA images.
blob loss: instance imbalance aware loss functions for semantic segmentation
Blob loss is designed for semantic segmentation problems in which the instances are the connected components within a class.
Deep Quality Estimation: Creating Surrogate Models for Human Quality Ratings
To approximate human quality ratings on scarce expert data, we train surrogate quality estimation models.
Fetal Brain Tissue Annotation and Segmentation Challenge Results
Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context.
A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
Our method automatically discards the voxel-level labeling predicted by the backbone AI that violate expert knowledge and relies on a fallback for those voxels.
MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images
It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user-interface.
A multi-organ point cloud registration algorithm for abdominal CT registration
Registering CT images of the chest is a crucial step for several tasks such as disease progression tracking or surgical planning.
Motion Correction and Volumetric Reconstruction for Fetal Functional Magnetic Resonance Imaging Data
Here, we propose a novel framework, which estimates a high-resolution reference volume by using outlier-robust motion correction, and by utilizing Huber L2 regularization for intra-stack volumetric reconstruction of the motion-corrected fetal brain fMRI.
ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentation
Automatic segmentation of lung lesions associated with COVID-19 in CT images requires large amount of annotated volumes.
CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137).
Generalized Wasserstein Dice Loss, Test-time Augmentation, and Transformers for the BraTS 2021 challenge
Importantly, we explore the inclusion of a transformer in the bottleneck of the U-Net architecture.
Improving needle visibility in LED-based photoacoustic imaging using deep learning with semi-synthetic datasets
Photoacoustic imaging has shown great potential for guiding minimally invasive procedures by accurate identification of critical tissue targets and invasive medical devices (such as metallic needles).
Partial supervision for the FeTA challenge 2021
Label-set loss functions allow to train deep neural networks with partially segmented images, i. e. segmentations in which some classes may be grouped into super-classes.
Homography-based Visual Servoing with Remote Center of Motion for Semi-autonomous Robotic Endoscope Manipulation
Our approach allows a surgeon to build a graph of desired views, from which, once built, views can be manually selected and automatically servoed to irrespective of robot-patient frame transformation changes.
Interactive Segmentation via Deep Learning and B-Spline Explicit Active Surfaces
The interactive element of the framework allows the user to precisely edit the contour in real-time, and by utilising BEAS it ensures the final contour is smooth and anatomically plausible.
Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction
We perform an extensive evaluation of state-of-the-art (SOTA) Deep Neural Networks (DNNs) across multiple compute regimes, finding our method transfers from our camera motion free da Vinci surgery dataset to videos of laparoscopic interventions, outperforming classical homography estimation approaches in both, precision by 41%, and runtime on a CPU by 43%.
Deep Learning Approach for Hyperspectral Image Demosaicking, Spectral Correction and High-resolution RGB Reconstruction
Hyperspectral imaging is one of the most promising techniques for intraoperative tissue characterisation.
Distributionally Robust Segmentation of Abnormal Fetal Brain 3D MRI
The performance of deep neural networks typically increases with the number of training images.
Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation
Deep neural networks have increased the accuracy of automatic segmentation, however, their accuracy depends on the availability of a large number of fully segmented images.
Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation
We introduce $\textit{InExtremIS}$, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest.
A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections
We fine-tuned our model on three small annotated datasets from different institutions and on the annotated images in EPISURG, comprising 20, 33, 19 and 133 subjects.
Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas
The model relies on a spanning tree of latent transforms connecting all the sections and slices of the reference volume, and assumes that the registration between any pair of images can be see as a noisy version of the composition of (possibly inverted) latent transforms connecting the two images.
MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
To solve these problems, we propose a novel deep learning-based interactive segmentation method that not only has high efficiency due to only requiring clicks as user inputs but also generalizes well to a range of previously unseen objects.
Zero-shot super-resolution with a physically-motivated downsampling kernel for endomicroscopy
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.
MONAIfbs: MONAI-based fetal brain MRI deep learning segmentation
In this work, we aim at improving the fetal brain segmentation for SRR in Spina Bifida.
Intrapapillary Capillary Loop Classification in Magnification Endoscopy: Open Dataset and Baseline Methodology
A future work path of high clinical relevance is the extension of the classification to ESCN types.
Image Compositing for Segmentation of Surgical Tools without Manual Annotations
Background data is captured by collecting videos that do not contain instruments.
Morphological Change Forecasting for Prostate Glands using Feature-based Registration and Kernel Density Extrapolation
Organ morphology is a key indicator for prostate disease diagnosis and prognosis.
Scale factor point spread function matching: Beyond aliasing in image resampling
Imaging devices exploit the Nyquist-Shannon sampling theorem to avoid both aliasing and redundant oversampling by design.
Active Annotation of Informative Overlapping Frames in Video Mosaicking Applications
In addition to the efficient construction of a mosaic, our framework provides, as a by-product, ground truth landmark correspondences which can be used for evaluation or learning purposes.
Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging
Our motivating application is a real-world problem: COVID-19 classification from CT imaging, for which we present an explainable Deep Learning approach based on a semi-supervised classification pipeline that employs variational autoencoders to extract efficient feature embedding.
DeepReg: a deep learning toolkit for medical image registration
DeepReg (https://github. com/DeepRegNet/DeepReg) is a community-supported open-source toolkit for research and education in medical image registration using deep learning.
Generalized Wasserstein Dice Score, Distributionally Robust Deep Learning, and Ranger for brain tumor segmentation: BraTS 2020 challenge
We stuck to a generic and state-of-the-art 3D U-Net architecture and experimented with a non-standard per-sample loss function, the generalized Wasserstein Dice loss, a non-standard population loss function, corresponding to distributionally robust optimization, and a non-standard optimizer, Ranger.
High-throughput molecular imaging via deep learning enabled Raman spectroscopy
Here, we present a comprehensive framework for higher-throughput molecular imaging via deep learning enabled Raman spectroscopy, termed DeepeR, trained on a large dataset of hyperspectral Raman images, with over 1. 5 million spectra (400 hours of acquisition) in total.
CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation
Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object.
Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
However, few existing approaches allow for the joint segmentation of normal tissue and brain lesions.
Real-Time Segmentation of Non-Rigid Surgical Tools based on Deep Learning and Tracking
The latter, a combination of deep learning with optical flow tracking, yields an average balanced accuracy of 78. 2% across all the validated datasets.
Longitudinal Image Registration with Temporal-order and Subject-specificity Discrimination
Morphological analysis of longitudinal MR images plays a key role in monitoring disease progression for prostate cancer patients, who are placed under an active surveillance program.
Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients
There is an increasing number of studies that propose to use deep learning to provide fast and accurate quantification of COVID-19 using chest CT scans.
Deep Placental Vessel Segmentation for Fetoscopic Mosaicking
We propose a solution utilising the U-Net architecture for performing placental vessel segmentation in fetoscopic videos.
Scribble-based Domain Adaptation via Co-segmentation
Instead of requiring detailed but time-consuming annotations, scribbles on the target domain are used to perform domain adaptation.
Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slices
Experimental results show that: (1) our proposed CNN obtains uncertainty estimation in real time which correlates well with mis-segmentations, (2) the proposed interactive level set is effective and efficient for refinement, (3) UGIR obtains accurate refinement results with around 30% improvement of efficiency by using uncertainty to guide user interactions.
Distributionally Robust Deep Learning using Hardness Weighted Sampling
In order to improve the robustness of machine learning systems, Distributionally Robust Optimization (DRO) has been proposed as a generalization of Empirical Risk Minimization (ERM).
Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches
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.
CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions
Data-driven computational approaches have evolved to enable extraction of information from medical images with a reliability, accuracy and speed which is already transforming their interpretation and exploitation in clinical practice.
SGD with Hardness Weighted Sampling for Distributionally Robust Deep Learning
Similar to a hard example mining strategy in essence and in practice, the proposed algorithm is straightforward to implement and computationally as efficient as SGD-based optimizers used for deep learning.
Improved MR to CT synthesis for PET/MR attenuation correction using Imitation Learning
Quantitative results show that the network generates pCTs that seem less accurate when evaluating the Mean Absolute Error on the pCT (69. 68HU) compared to a baseline CNN (66. 25HU), but lead to significant improvement in the PET reconstruction - 115a. u.
Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation
We propose a new deep learning method for tumour segmentation when dealing with missing imaging modalities.
Deep Sequential Mosaicking of Fetoscopic Videos
Mosaicking can align multiple overlapping images to generate an image with increased FoV, however, existing techniques apply poorly to fetoscopy due to the low visual quality, texture paucity, and hence fail in longer sequences due to the drift accumulated over time.
Learning joint lesion and tissue segmentation from task-specific hetero-modal datasets
Developing a DNN for such joint task is currently hampered by the fact that annotated datasets typically address only one specific task and rely on a task-specific hetero-modal imaging protocol.
Permutohedral Attention Module for Efficient Non-Local Neural Networks
Medical image processing tasks such as segmentation often require capturing non-local information.
Conditional Segmentation in Lieu of Image Registration
Classical pairwise image registration methods search for a spatial transformation that optimises a numerical measure that indicates how well a pair of moving and fixed images are aligned.
Automatic Segmentation of Vestibular Schwannoma from T2-Weighted MRI by Deep Spatial Attention with Hardness-Weighted Loss
Automatic segmentation of vestibular schwannoma (VS) tumors from magnetic resonance imaging (MRI) would facilitate efficient and accurate volume measurement to guide patient management and improve clinical workflow.
Medical Imaging with Deep Learning: MIDL 2019 -- Extended Abstract Track
This compendium gathers all the accepted extended abstracts from the Second International Conference on Medical Imaging with Deep Learning (MIDL 2019), held in London, UK, 8-10 July 2019.
Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy
Our framework can exploit HR images, regardless of the domain where they are coming from, to transfer the quality of the HR images to the initial LR images.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
Automatic brain tumor segmentation plays an important role for diagnosis, surgical planning and treatment assessment of brain tumors.
Image computing for fibre-bundle endomicroscopy: A review
Endomicroscopy is an emerging imaging modality, that facilitates the acquisition of in vivo, in situ optical biopsies, assisting diagnostic and potentially therapeutic interventions.
Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks.
Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration
A median target registration error of 3. 6 mm on landmark centroids and a median Dice of 0. 87 on prostate glands are achieved from cross-validation experiments, in which 108 pairs of multimodal images from 76 patients were tested with high-quality anatomical labels.
Adversarial Deformation Regularization for Training Image Registration Neural Networks
During training, the registration network simultaneously aims to maximize similarity between anatomical labels that drives image alignment and to minimize an adversarial generator loss that measures divergence between the predicted- and simulated deformation.
Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery
The paper presents a comparative validation study of different vision-based methods for instrument segmentation and tracking in the context of robotic as well as conventional laparoscopic surgery.
Interpretable Fully Convolutional Classification of Intrapapillary Capillary Loops for Real-Time Detection of Early Squamous Neoplasia
We present a new approach to visualise attention that aims to give some insights on those areas of the oesophageal tissue that lead a network to conclude that the images belong to a particular class and compare them with those visual features employed by clinicians to produce a clinical diagnosis.
Effective deep learning training for single-image super-resolution in endomicroscopy exploiting video-registration-based reconstruction
Purpose: Probe-based Confocal Laser Endomicroscopy (pCLE) is a recent imaging modality that allows performing in vivo optical biopsies.
Retrieval and Registration of Long-Range Overlapping Frames for Scalable Mosaicking of In Vivo Fetoscopy
Robustness to visual challenges during registration and long-range temporal consistency are proposed, offering first positive results on in vivo data for which standard mosaicking techniques are not applicable.
A Log-Euclidean and Total Variation based Variational Framework for Computational Sonography
We propose a spatial compounding technique and variational framework to improve 3D ultrasound image quality by compositing multiple ultrasound volumes acquired from different probe orientations.
Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections
Here, we overcome this limitation with a probabilistic method that simultaneously solves for registration and synthesis directly on the target images, without any training data.
Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalising neural network
Results show a median Dice similarity coefficient of 0. 90 with an interquartile range of 0. 08, with equivalent performance to the three operators (with a Williams' index of 1. 03), and outperforming a U-Net architecture without the need for batch normalisation.
Label-driven weakly-supervised learning for multimodal deformable image registration
Spatially aligning medical images from different modalities remains a challenging task, especially for intraoperative applications that require fast and robust algorithms.
Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
Experimental results show that 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine-tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.
Refractive Structure-From-Motion Through a Flat Refractive Interface
By explicitly considering a refractive interface, we develop a succinct derivation of the refractive fundamental matrix in the form of the generalised epipolar constraint for an axial camera.
NiftyNet: a deep-learning platform for medical imaging
NiftyNet provides a modular deep-learning pipeline for a range of medical imaging applications including segmentation, regression, image generation and representation learning applications.
Intraoperative Organ Motion Models with an Ensemble of Conditional Generative Adversarial Networks
In this paper, we describe how a patient-specific, ultrasound-probe-induced prostate motion model can be directly generated from a single preoperative MR image.
Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networks
A cascade of fully convolutional neural networks is proposed to segment multi-modal Magnetic Resonance (MR) images with brain tumor into background and three hierarchical regions: whole tumor, tumor core and enhancing tumor core.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2014
Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks
Sonography synthesis has a wide range of applications, including medical procedure simulation, clinical training and multimodality image registration.
Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images.
On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task
To illustrate its efficiency of learning 3D representation from large-scale image data, the proposed network is validated with the challenging task of parcellating 155 neuroanatomical structures from brain MR images.
DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy.
Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks
3) We show that the joint use of holistic CNNs and generalised Wasserstein Dice scores achieves segmentations that are more semantically meaningful for brain tumour segmentation.
Scalable multimodal convolutional networks for brain tumour segmentation
Brain tumour segmentation plays a key role in computer-assisted surgery.
ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools
We propose the use of parametric rectified linear units for semantic labeling in these small architectures to increase the regularization ability of the design and maintain the segmentation accuracy without overfitting the training sets.
Counting sub-multisets of fixed cardinality
This report presents an expression for the number of a multiset's sub-multisets of a given cardinality as a function of the multiplicity of its elements.
Combinatorics 05A19
