Search

Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent criss-cross-attention module aims to approximate global self-attention while remaining memory and time efficient by separating horizontal and vertical self-similarity computations. However, capturing attention from all non-local locations can adversely impact the accuracy of semantic segmentation networks. We propose a new Dynamic Deformable Attention Network (DDANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on a deformable criss-cross attention block that learns both attention coefficients and attention offsets in a continuous way. A deep U-Net (Schlemper et al., 2019) segmentation network that employs this attention mechanism is able to capture attention from pertinent non-local locations and also improves the performance on semantic segmentation tasks compared to criss-cross attention within a U-Net on a challenging COVID-19 lesion segmentation task. Our validation experiments show that the performance gain of the recursively applied dynamic deformable attention blocks comes from their ability to capture dynamic and precise attention context. Our DDANet achieves Dice scores of 73.4% and 61.3% for Ground-glass opacity and consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.9% points compared to a baseline U-Net and 24.4% points compared to current state of art methods (Fan et al., 2020). [ABSTRACT FROM AUTHOR]

Flow estimation on 3D point clouds is a challenging problem in the field of computer vision, which has great significance in many areas, such as autonomous driving and human interaction applications. Within the last years, the field of motion analysis has made great progress. The evaluation of the existing approaches mostly focuses on scenarios where objects are affected by rigid transformations. However, in many application areas such as gesture recognition or pose tracking, the detection of shape changes is essential and breaking them down to local rigid transformations is accompanied by loss of information. One component of our contributions is that we specifically prepared existing datasets for scene flow estimation on deformable objects. Additionally, we benchmark existing methods and analyze their behavior on various subtasks. The results show that already close to 80% of correct correspondences can be found on synthetic hand data, while only around 50% are found on real hand data. Our experimental validation and analysis help to build an understanding of new possibilities in broader areas. Furthermore, they should help to inspire possible further research directions. • Real human data challenges existing scene flow estimation methods. • Learning cost volumes reduces the runtime for calculating correspondences. • Occlusions of body parts pose different problems to scene flow estimation methods. • Generalization abilities of scene flow methods on human data are limited. [ABSTRACT FROM AUTHOR]

3D human pose estimation is a key component of clinical monitoring systems. The clinical applicability of deep pose estimation models, however, is limited by their poor generalization under domain shifts along with their need for sufficient labeled training data. As a remedy, we present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method comprises two complementary adaptation strategies based on prior knowledge about human anatomy. First, we guide the learning process in the target domain by constraining predictions to the space of anatomically plausible poses. To this end, we embed the prior knowledge into an anatomical loss function that penalizes asymmetric limb lengths, implausible bone lengths, and implausible joint angles. Second, we propose to filter pseudo labels for self-training according to their anatomical plausibility and incorporate the concept into the Mean Teacher paradigm. We unify both strategies in a point cloud-based framework applicable to unsupervised and source-free domain adaptation. Evaluation is performed for in-bed pose estimation under two adaptation scenarios, using the public SLP dataset and a newly created dataset. Our method consistently outperforms various state-of-the-art domain adaptation methods, surpasses the baseline model by 31%/66%, and reduces the domain gap by 65%/82%. Source code is available at https://github.com/multimodallearning/da-3dhpe-anatomy. [Display omitted] • Novel domain adaptation method for point cloud-based in-bed 3D human pose estimation. • Anatomy-constrained optimization to supervise the learning on unlabeled target data. • Anatomy-guided filtering of pseudo labels for self-training with the Mean Teacher. • Flexible applicability to unsupervised and source-free domain adaptation. • State-of-the-art results against 11 competitors under two different domain shifts. [ABSTRACT FROM AUTHOR]

Diffusion MRI is an exquisitely sensitive probe of tissue microstructure, and is currently the only non-invasive measure of the brain's fibre architecture. As this technique becomes more sophisticated and microstructurally informative, there is increasing value in comparing diffusion MRI with microscopic imaging in the same tissue samples. This study compared estimates of fibre orientation dispersion in white matter derived from diffusion MRI to reference measures of dispersion obtained from polarized light imaging and histology. Three post-mortem brain specimens were scanned with diffusion MRI and analyzed with a two-compartment dispersion model. The specimens were then sectioned for microscopy, including polarized light imaging estimates of fibre orientation and histological quantitative estimates of myelin and astrocytes. Dispersion estimates were correlated on region – and voxel-wise levels in the corpus callosum, the centrum semiovale and the corticospinal tract. The region-wise analysis yielded correlation coefficients of r = 0.79 for the diffusion MRI and histology comparison, while r = 0.60 was reported for the comparison with polarized light imaging. In the corpus callosum, we observed a pattern of higher dispersion at the midline compared to its lateral aspects. This pattern was present in all modalities and the dispersion profiles from microscopy and diffusion MRI were highly correlated. The astrocytes appeared to have minor contribution to dispersion observed with diffusion MRI. These results demonstrate that fibre orientation dispersion estimates from diffusion MRI represents the tissue architecture well. Dispersion models might be improved by more faithfully incorporating an informed mapping based on microscopy data. [ABSTRACT FROM AUTHOR]

Domain Adaptation (DA) has recently been of strong interest in the medical imaging community. While a large variety of DA techniques have been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. The goal of the challenge is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are commonly performed using contrast-enhanced T1 (ceT 1) MR imaging. However, there is growing interest in using non-contrast imaging sequences such as high-resolution T2 (hrT 2) imaging. For this reason, we established an unsupervised cross-modality segmentation benchmark. The training dataset provides annotated ceT 1 scans (N=105) and unpaired non-annotated hrT 2 scans (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT 2 scans as provided in the testing set (N=137). This problem is particularly challenging given the large intensity distribution gap across the modalities and the small volume of the structures. A total of 55 teams from 16 countries submitted predictions to the validation leaderboard. Among them, 16 teams from 9 different countries submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice score — VS: 88.4%; Cochleas: 85.7%) and close to full supervision (median Dice score — VS: 92.5%; Cochleas: 87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image. [Display omitted] • The first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. • Segmentation of two structures for the follow-up and treatment planning of vestibular schwannoma. • Large domain gap between the source (post-contrast T1) and target (T2) domains. • An extensive comparison of the techniques proposed by 16 teams from 9 countries. • Top-performing teams used image-to-image translation to bridge the domain gap. [ABSTRACT FROM AUTHOR]

Registration of medical image data requires methods that can align anatomical structures precisely while applying smooth and plausible transformations. Ideally, these methods should furthermore operate quickly and apply to a wide variety of tasks. Deep learning-based image registration methods usually entail an elaborate learning procedure with the need for extensive training data. However, they often struggle with versatility when aiming to apply the same approach across various anatomical regions and different imaging modalities. In this work, we present a method that extracts semantic or hand-crafted image features and uses a coupled convex optimisation followed by Adam-based instance optimisation for multitask medical image registration. We make use of pre-trained semantic feature extraction models for the individual datasets and combine them with our fast dual optimisation procedure for deformation field computation. Furthermore, we propose a very fast automatic hyperparameter selection procedure that explores many settings and ranks them on validation data to provide a self-configuring image registration framework. With our approach, we can align image data for various tasks with little learning. We conduct experiments on all available Learn2Reg challenge datasets and obtain results that are to be positioned in the upper ranks of the challenge leaderboards. github.com/multimodallearning/convexAdam.

Deep learning-based image segmentation models rely strongly on capturing sufficient spatial context without requiring complex models that are hard to train with limited labeled data. For COVID-19 infection segmentation on CT images, training data are currently scarce. Attention models, in particular the most recent self-attention methods, have shown to help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent attention-augmented convolution model aims to capture long range interactions by concatenating self-attention and convolution feature maps. This work proposes a novel attention-augmented convolution U-Net (AA-U-Net) that enables a more accurate spatial aggregation of contextual information by integrating attention-augmented convolution in the bottleneck of an encoder-decoder segmentation architecture. A deep segmentation network (U-Net) with this attention mechanism significantly improves the performance of semantic segmentation tasks on challenging COVID-19 lesion segmentation. The validation experiments show that the performance gain of the attention-augmented U-Net comes from their ability to capture dynamic and precise (wider) attention context. The AA-U-Net achieves Dice scores of 72.3% and 61.4% for ground-glass opacity and consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.2% points against a baseline U-Net and 3.09% points compared to a baseline U-Net with matched parameters., Supplementary Information: The online version contains supplementary material available at 10.1007/s11760-022-02302-3., (© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022.)

Purpose: Body weight is a crucial parameter for patient-specific treatments, particularly in the context of proper drug dosage. Contactless weight estimation from visual sensor data constitutes a promising approach to overcome challenges arising in emergency situations. Machine learning-based methods have recently been shown to perform accurate weight estimation from point cloud data. The proposed methods, however, are designed for controlled conditions in terms of visibility and position of the patient, which limits their practical applicability. In this work, we aim to decouple accurate weight estimation from such specific conditions by predicting the weight of covered patients from voxelized point cloud data., Methods: We propose a novel deep learning framework, which comprises two 3D CNN modules solving the given task in two separate steps. First, we train a 3D U-Net to virtually uncover the patient, i.e. to predict the patient's volumetric surface without a cover. Second, the patient's weight is predicted from this 3D volume by means of a 3D CNN architecture, which we optimized for weight regression., Results: We evaluate our approach on a lying pose dataset (SLP) under two different cover conditions. The proposed framework considerably improves on the baseline model by up to [Formula: see text] and reduces the gap between the accuracy of weight estimates for covered and uncovered patients by up to [Formula: see text]., Conclusion: We present a novel pipeline to estimate the weight of patients, which are covered by a blanket. Our approach relaxes the specific conditions that were required for accurate weight estimates by previous contactless methods and thus constitutes an important step towards fully automatic weight estimation in clinical practice., (© 2021. The Author(s).)

Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to have a DVT, resulting in long referral waiting times for patients and a large clinical burden for specialists. Thus, diagnosis at the point of care by non-specialists is desired. We collect images in a pre-clinical study and investigate a deep learning approach for the automatic interpretation of compression ultrasound images. Our method provides guidance for free-hand ultrasound and aids non-specialists in detecting DVT. We train a deep learning algorithm on ultrasound videos from 255 volunteers and evaluate on a sample size of 53 prospectively enrolled patients from an NHS DVT diagnostic clinic and 30 prospectively enrolled patients from a German DVT clinic. Algorithmic DVT diagnosis performance results in a sensitivity within a 95% CI range of (0.82, 0.94), specificity of (0.70, 0.82), a positive predictive value of (0.65, 0.89), and a negative predictive value of (0.99, 1.00) when compared to the clinical gold standard. To assess the potential benefits of this technology in healthcare we evaluate the entire clinical DVT decision algorithm and provide cost analysis when integrating our approach into diagnostic pathways for DVT. Our approach is estimated to generate a positive net monetary benefit at costs up to £72 to £175 per software-supported examination, assuming a willingness to pay of £20,000/QALY., (© 2021. The Author(s).)

A major goal of lung cancer screening is to identify individuals with particular phenotypes that are associated with high risk of cancer. Identifying relevant phenotypes is complicated by the variation in body position and body composition. In the brain, standardized coordinate systems (e.g., atlases) have enabled separate consideration of local features from gross/global structure. To date, no analogous standard atlas has been presented to enable spatial mapping and harmonization in chest computational tomography (CT). In this paper, we propose a thoracic atlas built upon a large low dose CT (LDCT) database of lung cancer screening program. The study cohort includes 466 male and 387 female subjects with no screening detected malignancy (age 46-79 years, mean 64.9 years). To provide spatial mapping, we optimize a multi-stage inter-subject non-rigid registration pipeline for the entire thoracic space. Briefly, with 50 scans of 50 randomly selected female subjects as fine tuning dataset, we search for the optimal configuration of the non-rigid registration module in a range of adjustable parameters including: registration searching radius, degree of keypoint dispersion, regularization coefficient and similarity patch size, to minimize the registration failure rate approximated by the number of samples with low Dice similarity score (DSC) for lung and body segmentation. We evaluate the optimized pipeline on a separate cohort (100 scans of 50 female and 50 male subjects) relative to two baselines with alternative non-rigid registration module: the same software with default parameters and an alternative software. We achieve a significant improvement in terms of registration success rate based on manual QA. For the entire study cohort, the optimized pipeline achieves a registration success rate of 91.7%. The application validity of the developed atlas is evaluated in terms of discriminative capability for different anatomic phenotypes, including body mass index (BMI), chronic obstructive pulmonary disease (COPD), and coronary artery calcification (CAC).