Many image processing applications rely on partitioning an image into disjoint regions whose pixels are ‘similar.’ The watershed and waterfall transforms are established mathematical morphology pixel clustering techniques. They are both relevant to modern applications where groups of pixels are to be decided upon in one go, or where adjacency information is relevant. We introduce three new parallel partitioning algorithms for GPUs. By repeatedly applying watershed algorithms, we produce waterfall results which form a hierarchy of partition regions over an input image. Our watershed algorithms attain competitive execution times in both 2D and 3D, processing an 800 megavoxel image in less than 1.4 sec. We also show how to use this fully deterministic image partitioning as a pre-processing step to machine-learning-based semantic segmentation. This replaces the role of superpixel algorithms, and results in comparable accuracy and faster training times. The code is publicly available at https://github.com/hamemm/PRUF-watershed.git .

Data government has played an instrumental role in securing the privacy-critical infrastructure in the medical domain and has led to an increased need of federated learning (FL). While decentralization can limit the effectiveness of standard supervised learning, the impact of decentralization on partially supervised learning remains unclear. Besides, due to data scarcity, each client may have access to only limited partially labeled data. As a remedy, this work formulates and discusses a new learning problem federated partially supervised learning (FPSL) for limited decentralized medical images with partial labels. We study the impact of decentralized partially labeled data on deep learning-based models via an exemplar of FPSL, namely, federated partially supervised learning multi-label classification. By dissecting FedAVG, a seminal FL framework, we formulate and analyze two major challenges of FPSL and propose a simple yet robust FPSL framework, FedPSL, which addresses these challenges. In particular, FedPSL contains two modules, task-dependent model aggregation and task-agnostic decoupling learning, where the first module addresses the weight assignment and the second module improves the generalization ability of the feature extractor. We provide a comprehensive empirical understanding of FSPL under data scarcity with simulated experiments. The empirical results not only indicate that FPSL is an under-explored problem with practical value but also show that the proposed FedPSL can achieve robust performance against baseline methods on data challenges such as data scarcity and domain shifts. The findings of this study also pose a new research direction towards label-efficient learning on medical images.

We propose an effective and easy-to-implement method for simultaneously performing landmark detection in images and obtaining an ingenious uncertainty measurement for each landmark. Uncertainty measurements for land-marks are particularly useful in medical imaging applications: rather than giving an erroneous reading, a landmark detection system is more useful when it flags its level of confidence in its prediction. When an automated system is unsure of its predictions, the accuracy of the results can be further improved manually by a human. In the medical domain, being able to review an automated system's level of certainty significantly improves a clinician's trust in it. This paper obtains landmark predictions with uncertainty measurements using a three stage method: 1) We train our network on one-hot heatmap images, 2) We calibrate the uncertainty of the network using temperature scaling, 3) We calculate a novel statistic called ‘Expected Radial Error’ to obtain uncertainty measurements. We find that this method not only achieves localization results on par with other state-of-the-art methods but also an uncertainty score which correlates with the true error for each landmark thereby bringing an overall step change in what a generic computer vision method for landmark detection should be capable of In addition we show that our uncertainty measurement can be used to classify, with good accuracy, what landmark predictions are likely to be inaccurate. Code available at: https://github.com/jfm15/ContourHuggingHeatmaps.git

The watershed transform is a common step in different image processing tasks. With the fast development of general-purpose computing on GPUs, a number of parallel watershed algorithms have been introduced for that setup. We propose two novel parallel watershed algorithms: one intended for relatively larger images and another for smaller images. Our algorithms are based on the combination of the parallel path reduction technique, introduced in our previous paper on the topic, and the parallel version of the Union–Find algorithm. We show through multiple experiments, both in 2D and 3D, that our algorithms achieve unmatched execution times. On a typical gaming GPU, our algorithm processes an 800 megavoxel image in around 2.5 seconds.

Ubiquitous accumulation of large volumes of data, and increased availability of annotated medical data in particular, has made it possible to show the many and varied benefits of deep learning to the semantic segmentation of medical images. Nevertheless, data access and annotation come at a high cost in clinician time. The power of Vision Transformer (ViT) is well-documented for generic computer vision tasks involving millions of images of every day objects, of which only relatively few have been annotated. Its translation to relatively more modest (i.e. thousands of images of) medical data is not immediately straightforward. This paper presents practical avenues for training a Computationally-Efficient Semi-Supervised Vision Transformer (CESS-ViT) for medical image segmentation task.We propose a self-attention-based image segmentation network which requires only limited computational resources. Additionally, we develop a dual pseudo-label supervision scheme for use with semi-supervision in a simple pure ViT.Our method has been evaluated on a publicly available cardiac MRI dataset with direct comparison against other semi-supervised methods. Our results illustrate the proposed ViT-based semi-supervised method outperforms the existing methods in the semantic segmentation of cardiac ventricles.

Although quantum neural networks (QNNs) have shown promising results in solving simple machine learning tasks recently, the behavior of QNNs in binary pattern classification is still underexplored. In this work, we find that QNNs have an Achilles’ heel in binary pattern classification. To illustrate this point, we provide a theoretical insight into the properties of QNNs by presenting and analyzing a new form of symmetry embedded in a family of QNNs with full entanglement , which we term negational symmetry . Due to negational symmetry, QNNs can not differentiate between a quantum binary signal and its negational counterpart. We empirically evaluate the negational symmetry of QNNs in binary pattern classification tasks using Google’s quantum computing framework. Both theoretical and experimental results suggest that negational symmetry is a fundamental property of QNNs, which is not shared by classical models. Our findings also imply that negational symmetry is a double-edged sword in practical quantum applications.

Segmentation algorithms for medical images are widely studied for various clinical and research purposes. In this paper, we propose a new and efficient method for medical image segmentation under noisy labels. The method operates under a deep learning paradigm, incorporating four novel contributions. Firstly, a residual interconnection is explored in different scale encoders to transfer gradient information efficiently. Secondly, four copy-and-crop connections are replaced by residual-block-based concatenation to alleviate the disparity between encoders and decoders. Thirdly, convolutional attention modules for feature refinement are studied on all scale decoders. Finally, an adaptive denoising learning strategy (ADL) is introduced into the training process to avoid too much influence from the noisy labels. Experimental results are illustrated on a publicly available benchmark database of spine CTs. Our proposed method achieves competitive performance against other state-of-the-art methods over a variety of different evaluation measures.

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.

The following topics are dealt with: learning (artificial intelligence); feature extraction; feedforward neural nets; image classification; object detection; computer vision; image representation; image segmentation; video signal processing; and image motion analysis.

Graph-based image segmentation is popular, because graphs can naturally represent image parts and the relationships between them. Whilst many single-scale approaches exist, significant interest has been shown in segmentation hierarchies, which represent image objects at different scales. However, segmenting arbitrary images automatically remains elusive: segmentation is under-specified, with different users expecting different outcomes. Hierarchical segmentation compounds this, since it is unclear where in the hierarchy objects should appear. Users can easily edit flat segmentations to influence the outcome, but editing hierarchical segmentations is harder: indeed, many existing interactive editing techniques make only small, local hierarchy changes. In this paper, we address this by introducing ‘zipping’ operations for segmentation hierarchies to facilitate user interaction. We use these operations to implement algorithms for non-sibling node merging and parent switching, and perform experiments on both 2D and 3D images to show that these latter algorithms can significantly reduce the interaction burden on the user.

This paper is about using interval computations in location, simplification, and root-finding for multivariate implicit functions that are used as shape primitives in a set-theoretic (that is, a CSG) geometric modeller. Three problems are discussed, and solutions to them presented: the location and simplification of the surfaces of semialgebraic sets (surfaces involving some transcendental functions are dealt with as well); the generalization of Newton-Raphson using intervals; and interval ray-tracing. Examples are presented for both conventional three-dimensional geometric models and for CSG models in higher dimensions representing configuration-space maps for moving and colliding three-dimensional objects.