arXiv subjects

Bernhard Kainz

Publications and source records attributed to Bernhard Kainz.

At least 127 records · Page 7Linked to original sources

arXiv2021

PRETUS: A plug-in based platform for real-time ultrasound imaging research

We present PRETUS -a Plugin-based Real Time UltraSound software platform for live ultrasound image analysis and operator support. The software is lightweight; functionality is brought in via independent plug-ins that can be arranged in sequence. The software allows to capture the real-time stream of ultrasound images from virtually any ultrasound machine, applies computational methods and visualises the results on-the-fly. Plug-ins can run concurrently without blocking each other. They can be implemented in C ++ and Python. A graphical user interface can be implemented for each plug-in, and presented to the user in a compact way. The software is free and open source, and allows for rapid prototyping and testing of real-time ultrasound imaging methods in a manufacturer-agnostic fashion. The software is provided with input, output and processing plug-ins, as well as with tutorials to illustrate how to develop new plug-ins for PRETUS.

physics.med-ph↗

arXiv2021

Learning normal appearance for fetal anomaly screening: Application to the unsupervised detection of Hypoplastic Left Heart Syndrome

Congenital heart disease is considered as one the most common groups of congenital malformations which affects $6-11$ per $1000$ newborns. In this work, an automated framework for detection of cardiac anomalies during ultrasound screening is proposed and evaluated on the example of Hypoplastic Left Heart Syndrome (HLHS), a sub-category of congenital heart disease. We propose an unsupervised approach that learns healthy anatomy exclusively from clinically confirmed normal control patients. We evaluate a number of known anomaly detection frameworks together with a model architecture based on the $α$-GAN network and find evidence that the proposed model performs significantly better than the state-of-the-art in image-based anomaly detection, yielding average $0.81$ AUC \emph{and} a better robustness towards initialisation compared to previous works.

eess.IV↗

arXiv2021

PialNN: A Fast Deep Learning Framework for Cortical Pial Surface Reconstruction

Traditional cortical surface reconstruction is time consuming and limited by the resolution of brain Magnetic Resonance Imaging (MRI). In this work, we introduce Pial Neural Network (PialNN), a 3D deep learning framework for pial surface reconstruction. PialNN is trained end-to-end to deform an initial white matter surface to a target pial surface by a sequence of learned deformation blocks. A local convolutional operation is incorporated in each block to capture the multi-scale MRI information of each vertex and its neighborhood. This is fast and memory-efficient, which allows reconstructing a pial surface mesh with 150k vertices in one second. The performance is evaluated on the Human Connectome Project (HCP) dataset including T1-weighted MRI scans of 300 subjects. The experimental results demonstrate that PialNN reduces the geometric error of the predicted pial surface by 30% compared to state-of-the-art deep learning approaches.

eess.IV↗

arXiv2021

Contrastive Learning for View Classification of Echocardiograms

Analysis of cardiac ultrasound images is commonly performed in routine clinical practice for quantification of cardiac function. Its increasing automation frequently employs deep learning networks that are trained to predict disease or detect image features. However, such models are extremely data-hungry and training requires labelling of many thousands of images by experienced clinicians. Here we propose the use of contrastive learning to mitigate the labelling bottleneck. We train view classification models for imbalanced cardiac ultrasound datasets and show improved performance for views/classes for which minimal labelled data is available. Compared to a naive baseline model, we achieve an improvement in F1 score of up to 26% in those views while maintaining state-of-the-art performance for the views with sufficiently many labelled training observations.

cs.CV↗

arXiv2021

Can non-specialists provide high quality gold standard labels in challenging modalities?

Probably yes. -- Supervised Deep Learning dominates performance scores for many computer vision tasks and defines the state-of-the-art. However, medical image analysis lags behind natural image applications. One of the many reasons is the lack of well annotated medical image data available to researchers. One of the first things researchers are told is that we require significant expertise to reliably and accurately interpret and label such data. We see significant inter- and intra-observer variability between expert annotations of medical images. Still, it is a widely held assumption that novice annotators are unable to provide useful annotations for use by clinical Deep Learning models. In this work we challenge this assumption and examine the implications of using a minimally trained novice labelling workforce to acquire annotations for a complex medical image dataset. We study the time and cost implications of using novice annotators, the raw performance of novice annotators compared to gold-standard expert annotators, and the downstream effects on a trained Deep Learning segmentation model's performance for detecting a specific congenital heart disease (hypoplastic left heart syndrome) in fetal ultrasound imaging.

cs.CV↗

arXiv2021

Detecting Outliers with Poisson Image Interpolation

Supervised learning of every possible pathology is unrealistic for many primary care applications like health screening. Image anomaly detection methods that learn normal appearance from only healthy data have shown promising results recently. We propose an alternative to image reconstruction-based and image embedding-based methods and propose a new self-supervised method to tackle pathological anomaly detection. Our approach originates in the foreign patch interpolation (FPI) strategy that has shown superior performance on brain MRI and abdominal CT data. We propose to use a better patch interpolation strategy, Poisson image interpolation (PII), which makes our method suitable for applications in challenging data regimes. PII outperforms state-of-the-art methods by a good margin when tested on surrogate tasks like identifying common lung anomalies in chest X-rays or hypo-plastic left heart syndrome in prenatal, fetal cardiac ultrasound images. Code available at https://github.com/jemtan/PII.

cs.CV↗

arXiv2021

Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-specific Atlas Maps

Fetal ultrasound screening during pregnancy plays a vital role in the early detection of fetal malformations which have potential long-term health impacts. The level of skill required to diagnose such malformations from live ultrasound during examination is high and resources for screening are often limited. We present an interpretable, atlas-learning segmentation method for automatic diagnosis of Hypo-plastic Left Heart Syndrome (HLHS) from a single `4 Chamber Heart' view image. We propose to extend the recently introduced Image-and-Spatial Transformer Networks (Atlas-ISTN) into a framework that enables sensitising atlas generation to disease. In this framework we can jointly learn image segmentation, registration, atlas construction and disease prediction while providing a maximum level of clinical interpretability compared to direct image classification methods. As a result our segmentation allows diagnoses competitive with expert-derived manual diagnosis and yields an AUC-ROC of 0.978 (1043 cases for training, 260 for validation and 325 for testing).

eess.IV↗

arXiv2021

Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation

Cardiac ultrasound imaging is used to diagnose various heart diseases. Common analysis pipelines involve manual processing of the video frames by expert clinicians. This suffers from intra- and inter-observer variability. We propose a novel approach to ultrasound video analysis using a transformer architecture based on a Residual Auto-Encoder Network and a BERT model adapted for token classification. This enables videos of any length to be processed. We apply our model to the task of End-Systolic (ES) and End-Diastolic (ED) frame detection and the automated computation of the left ventricular ejection fraction. We achieve an average frame distance of 3.36 frames for the ES and 7.17 frames for the ED on videos of arbitrary length. Our end-to-end learnable approach can estimate the ejection fraction with a MAE of 5.95 and $R^2$ of 0.52 in 0.15s per video, showing that segmentation is not the only way to predict ejection fraction. Code and models are available at https://github.com/HReynaud/UVT.

cs.CV↗

arXiv2021

Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net

Intelligent video summarization algorithms allow to quickly convey the most relevant information in videos through the identification of the most essential and explanatory content while removing redundant video frames. In this paper, we introduce the 3DST-UNet-RL framework for video summarization. A 3D spatio-temporal U-Net is used to efficiently encode spatio-temporal information of the input videos for downstream reinforcement learning (RL). An RL agent learns from spatio-temporal latent scores and predicts actions for keeping or rejecting a video frame in a video summary. We investigate if real/inflated 3D spatio-temporal CNN features are better suited to learn representations from videos than commonly used 2D image features. Our framework can operate in both, a fully unsupervised mode and a supervised training mode. We analyse the impact of prescribed summary lengths and show experimental evidence for the effectiveness of 3DST-UNet-RL on two commonly used general video summarization benchmarks. We also applied our method on a medical video summarization task. The proposed video summarization method has the potential to save storage costs of ultrasound screening videos as well as to increase efficiency when browsing patient video data during retrospective analysis or audit without loosing essential information

cs.CV↗

arXiv2021

Unsupervised Human Pose Estimation through Transforming Shape Templates

Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking. In the medical context, the latter may be an important biomarker for neurological impairments in infants. Whilst many methods exist, their application has been limited by the need for well annotated large datasets and the inability to generalize to humans of different shapes and body compositions, e.g. children and infants. In this paper we present a novel method for learning pose estimators for human adults and infants in an unsupervised fashion. We approach this as a learnable template matching problem facilitated by deep feature extractors. Human-interpretable landmarks are estimated by transforming a template consisting of predefined body parts that are characterized by 2D Gaussian distributions. Enforcing a connectivity prior guides our model to meaningful human shape representations. We demonstrate the effectiveness of our approach on two different datasets including adults and infants.

cs.CV↗

arXiv2021

A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis

Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinically useful information for computer-aided detection, diagnosis, treatment planning, intervention and therapy. However, the unique challenges posed by medical image analysis suggest that retaining a human end user in any deep learning enabled system will be beneficial. In this review we investigate the role that humans might play in the development and deployment of deep learning enabled diagnostic applications and focus on techniques that will retain a significant input from a human end user. Human-in-the-Loop computing is an area that we see as increasingly important in future research due to the safety-critical nature of working in the medical domain. We evaluate four key areas that we consider vital for deep learning in the clinical practice: (1) Active Learning to choose the best data to annotate for optimal model performance; (2) Interaction with model outputs - using iterative feedback to steer models to optima for a given prediction and offering meaningful ways to interpret and respond to predictions; (3) Practical considerations - developing full scale applications and the key considerations that need to be made before deployment; (4) Future Prospective and Unanswered Questions - knowledge gaps and related research fields that will benefit human-in-the-loop computing as they evolve. We offer our opinions on the most promising directions of research and how various aspects of each area might be unified towards common goals.

cs.LG↗

arXiv2021

Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging

Deep neural networks exhibit limited generalizability across images with different entangled domain features and categorical features. Learning generalizable features that can form universal categorical decision boundaries across domains is an interesting and difficult challenge. This problem occurs frequently in medical imaging applications when attempts are made to deploy and improve deep learning models across different image acquisition devices, across acquisition parameters or if some classes are unavailable in new training databases. To address this problem, we propose Mutual Information-based Disentangled Neural Networks (MIDNet), which extract generalizable categorical features to transfer knowledge to unseen categories in a target domain. The proposed MIDNet adopts a semi-supervised learning paradigm to alleviate the dependency on labeled data. This is important for real-world applications where data annotation is time-consuming, costly and requires training and expertise. We extensively evaluate the proposed method on fetal ultrasound datasets for two different image classification tasks where domain features are respectively defined by shadow artifacts and image acquisition devices. Experimental results show that the proposed method outperforms the state-of-the-art on the classification of unseen categories in a target domain with sparsely labeled training data.

cs.CV↗

arXiv2020

Surface Agnostic Metrics for Cortical Volume Segmentation and Regression

The cerebral cortex performs higher-order brain functions and is thus implicated in a range of cognitive disorders. Current analysis of cortical variation is typically performed by fitting surface mesh models to inner and outer cortical boundaries and investigating metrics such as surface area and cortical curvature or thickness. These, however, take a long time to run, and are sensitive to motion and image and surface resolution, which can prohibit their use in clinical settings. In this paper, we instead propose a machine learning solution, training a novel architecture to predict cortical thickness and curvature metrics from T2 MRI images, while additionally returning metrics of prediction uncertainty. Our proposed model is tested on a clinical cohort (Down Syndrome) for which surface-based modelling often fails. Results suggest that deep convolutional neural networks are a viable option to predict cortical metrics across a range of brain development stages and pathologies.

eess.IV↗

arXiv2020

Causal Future Prediction in a Minkowski Space-Time

Estimating future events is a difficult task. Unlike humans, machine learning approaches are not regularized by a natural understanding of physics. In the wild, a plausible succession of events is governed by the rules of causality, which cannot easily be derived from a finite training set. In this paper we propose a novel theoretical framework to perform causal future prediction by embedding spatiotemporal information on a Minkowski space-time. We utilize the concept of a light cone from special relativity to restrict and traverse the latent space of an arbitrary model. We demonstrate successful applications in causal image synthesis and future video frame prediction on a dataset of images. Our framework is architecture- and task-independent and comes with strong theoretical guarantees of causal capabilities.

cs.CV↗

arXiv2020

Projective Latent Interventions for Understanding and Fine-tuning Classifiers

High-dimensional latent representations learned by neural network classifiers are notoriously hard to interpret. Especially in medical applications, model developers and domain experts desire a better understanding of how these latent representations relate to the resulting classification performance. We present Projective Latent Interventions (PLIs), a technique for retraining classifiers by back-propagating manual changes made to low-dimensional embeddings of the latent space. The back-propagation is based on parametric approximations of t-distributed stochastic neighbourhood embeddings. PLIs allow domain experts to control the latent decision space in an intuitive way in order to better match their expectations. For instance, the performance for specific pairs of classes can be enhanced by manually separating the class clusters in the embedding. We evaluate our technique on a real-world scenario in fetal ultrasound imaging.

cs.LG↗

arXiv2020

Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment

Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain without using any labels in the target domain. Contemporary techniques focus on extracting domain-invariant features using domain adversarial training. However, these techniques neglect to learn discriminative class boundaries in the latent representation space on a target domain and yield limited adaptation performance. To address this problem, we propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. The proposed MetFA method explicitly and directly learns the latent representation without using domain adversarial training. Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain. We evaluate the proposed method on fetal ultrasound datasets for cross-device image classification. Experimental results demonstrate that the proposed method outperforms the state-of-the-art and enables model generalization.

cs.LG↗

arXiv2020

Automated Detection of Congenital Heart Disease in Fetal Ultrasound Screening

Prenatal screening with ultrasound can lower neonatal mortality significantly for selected cardiac abnormalities. However, the need for human expertise, coupled with the high volume of screening cases, limits the practically achievable detection rates. In this paper we discuss the potential for deep learning techniques to aid in the detection of congenital heart disease (CHD) in fetal ultrasound. We propose a pipeline for automated data curation and classification. During both training and inference, we exploit an auxiliary view classification task to bias features toward relevant cardiac structures. This bias helps to improve in F1-scores from 0.72 and 0.77 to 0.87 and 0.85 for healthy and CHD classes respectively.

eess.IV↗

arXiv2020

Deep Radiance Caching: Convolutional Autoencoders Deeper in Ray Tracing

Rendering realistic images with global illumination is a computationally demanding task and often requires dedicated hardware for feasible runtime. Recent research uses Deep Neural Networks to predict indirect lighting on image level, but such methods are commonly limited to diffuse materials and require training on each scene.We present Deep Radiance Caching (DRC), an efficient variant of Radiance Caching utilizing Convolutional Autoencoders for rendering global illumination. DRC employs a denoising neural network with Radiance Caching to support a wide range of material types, without the requirement of offline pre-computation or training for each scene.This offers high performance CPU rendering for maximum accessibility. Our method has been evaluated on interior scenes, and is able to produce high-quality images within 180 seconds on a single CPU.

cs.GR↗