We focus on a novel loglet-SIFT descriptor for the parts representation in the Deformable Part Models (DPM).We manipulate the feature scales in the Fourier domain and decompose the image into multi-scale oriented gradient components for computing SIFT.The scale selection is controlled explicitly by tiling Log-wavelet functions (loglets) on the spectrum.Then oriented gradients are obtained by adding imaginary odd parts to the loglets, converting them into differential filters.Coherent feature scales and domain sizes are further generated by spectrum cropping.Our loglet gradient filters are shown to compare favourably against spatial differential operators, and have a straightforward and efficient implementation.We present experiments to validate the performance of the loglet-SIFT descriptor which show it to improve the DPM using a supervised descent method by a significant margin.
The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a `black-box' where the reasoning or criteria for a final decision is opaque to the user. To address this, some existing Explainable AI (XAI) approaches approximate model behaviour using perturbed data. However, such methods have been criticised for ignoring feature dependencies, with explanations being based on potentially unrealistic data. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations, which are faithful to the training data of the base model being explained. This is shown to improve both the soundness and accuracy of the explanations.
We used three-dimensional reconstructed magnetic resonance images for planning the operations of 16 patients with various cerebrovascular diseases. We studied the cases of these patients to determine the advantages and current limitations of our computer-assisted surgical planning system as it applies to the treatment of vascular lesions.Magnetic resonance angiograms or thin slice gradient echo magnetic resonance images were processed for three-dimensional reconstruction. The segmentation, based on the signal intensities and voxel connectivity, separated each anatomic structure of interest, such as the brain, vessels, and skin. A three-dimensional model was then reconstructed by surface rendering. This three-dimensional model could be colored, made translucent, and interactively rotated by a mouse-controlled cursor on a workstation display. In addition, a three-dimensional blood flow analysis was performed, if necessary. The three-dimensional model was used to assist in three stages of surgical planning, as follows: 1) to choose the best method of intervention, 2) to evaluate surgical risk, 3) to select a surgical approach, and 4) to localize lesions.The generation of three-dimensional models allows visualization of pathological anatomy and its relationship to adjacent normal structures, accurate lesion volume determination, and preoperative computer-assisted visualization of alternative surgical approaches.Computer-assisted surgical planning is useful for patients with cerebrovascular disease at various stages of treatment. Lesion identification, therapeutic and surgical option planning, and intraoperative localization are all enhanced with these techniques.
Recent advances in whole slide imaging (WSI) technology have led to the development of a myriad of computer vision and artificial intelligence (AI) based diagnostic, prognostic, and predictive algorithms. Computational Pathology (CPath) offers an integrated solution to utilize information embedded in pathology WSIs beyond what we obtain through visual assessment. For automated analysis of WSIs and validation of machine learning (ML) models, annotations at the slide, tissue and cellular levels are required. The annotation of important visual constructs in pathology images is an important component of CPath projects. Improper annotations can result in algorithms which are hard to interpret and can potentially produce inaccurate and inconsistent results. Despite the crucial role of annotations in CPath projects, there are no well-defined guidelines or best practices on how annotations should be carried out. In this paper, we address this shortcoming by presenting the experience and best practices acquired during the execution of a large-scale annotation exercise involving a multidisciplinary team of pathologists, ML experts and researchers as part of the Pathology image data Lake for Analytics, Knowledge and Education (PathLAKE) consortium. We present a real-world case study along with examples of different types of annotations, diagnostic algorithm, annotation data dictionary and annotation constructs. The analyses reported in this work highlight best practice recommendations that can be used as annotation guidelines over the lifecycle of a CPath project.
Anticipating lane change intentions of surrounding vehicles is crucial for efficient and safe driving decision making in an autonomous driving system. Previous works often adopt physical variables such as driving speed, acceleration and so forth for lane change classification. However, physical variables do not contain semantic information. Although 3D CNNs have been developing rapidly, the number of methods utilising action recognition models and appearance feature for lane change recognition is low, and they all require additional information to pre-process data. In this work, we propose an end-to-end framework including two action recognition methods for lane change recognition, using video data collected by cameras. Our method achieves the best lane change classification results using only the RGB video data of the PREVENTION dataset. Class activation maps demonstrate that action recognition models can efficiently extract lane change motions. A method to better extract motion clues is also proposed in this paper.
The increasing availability of multi-core and multiprocessor architectures provides new opportunities for improving the performance of many computer simulations. Markov chain Monte Carlo (MCMC) simulations are widely used for approximate counting problems, Bayesian inference and as a means for estimating very high-dimensional integrals. As such MCMC has found a wide variety of applications infields including computational biology and physics, financial econometrics, machine learning and image processing. This paper presents a new method for reducing the run-time of Markov chain Monte Carlo simulations by using SMP machines to speculatively perform iterations in parallel, reducing the runtime of MCMC programs whilst producing statistically identical results to conventional sequential implementations. We calculate the theoretical reduction in runtime that may be achieved using our technique under perfect conditions, and test and compare the method on a selection of multi-core and multi-processor architectures. Experiments are presented that show reductions in runtime of 35% using two cores and 55% using four cores.
A novel image-dependent representation, warplets, based on self-similarity of regions is introduced. The representation is well suited to the description and segmentation of images containing textures and oriented patterns, such as fingerprints. An affine model of an image as a collection of self-similar image blocks is developed and it is shown how textured regions can be represented by a single prototype block together with a set of transformation coefficients. Images regions are aligned to a set of dictionary blocks and their variability captured by PCA analysis. The block-to-block transformations are found by Gaussian mixture modelling of the block spectra and a least-squares estimation. Clustering in the April domain can be used to determine a April dictionary. Experimental results on a variety of images demonstrate the potential of the use of April for segmentation and coding.
Many natural textures comprise structural patterns and show strong self-similarity. We use affine symmetry to segment an image into self-similar regions; that is a patch of texture (blocks from a uniformly partitioned image) can be transformed to other similar patches by warping. If the texture image contains multiple regions, we then cluster patches into a number of classes such that the overall warping error is minimized. Discovering the optimal clusters is not trivial and known methods are computationally intensive due to the affine transformation. We demonstrate efficient segmentation of structural textures without affine computation. The algorithm uses Fourier Slice Analysis to obtain a spectral contour signature. Experimental evaluation on structural textures shows encouraging results and application on natural images demonstrates identification of texture objects.
The field of computational pathology presents many challenges for computer vision algorithms due to the sheer size of pathology images. Histopathology images are large and need to be split up into image tiles or patches so modern convolutional neural networks (CNNs) can process them. In this work, we present a method to generate an interpretable image representation of computational pathology images using quadtrees and a pipeline to use these representations for highly accurate downstream classification. To the best of our knowledge, this is the first attempt to use quadtrees for pathology image data. We show it is highly accurate, able to achieve as good results as the currently widely adopted tissue mask patch extraction methods all while using over 38% less data.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
