Assessing risk factors for intracranial aneurysm (IA) development on images is crucial for early detection of high-risk cases. IAs often form at bifurcations within the circle of Willis (CoW), but manual assessment of these arteries is both time-consuming and susceptible to inconsistencies. Previous studies on imaging markers for IA development lack sufficient evidence for clinical implications, highlighting the need for automated methods to assess CoW morphology. No systematic approach currently exists to identify the best methodological strategies. To address this, we organized a scientific challenge to compare various techniques against a clinical reference standard. Participants were tasked with (1) automated classification of CoW anatomical variants and (2) automated prediction of CoW artery diameters and bifurcation angles. We provided 300 TOF-MRA scans for training and another 300 for testing, all manually annotated. Submissions were evaluated using balanced accuracy, mean absolute error, and Pearson correlation coefficient metrics. This paper provides a detailed analysis of the results from six participating teams. The findings show that various methods may be suitable for automated CoW assessment, but that these need further improvement to meet clinical standards. The challenge remains open for future submissions, offering a benchmark for new techniques.

Many cerebrovascular diseases are related to morphological variations in the Circle of Willis (CoW), an arterial network located at the base of the brain. Early detection of these structural abnormalities can result in effective treatments and helps to prevent the progression of the diseases to more advanced stages. This necessitates the need for developing a computer-aided model capable of automatically identifying anatomical variants of the CoW using a standardized classification framework, such as the Lippert and Pabst system. However, there are no reported studies that have applied the Lippert and Pabst classification in the context of computer-assisted analysis of CoW variants. Due to the small size and high class imbalance often present in medical datasets, it becomes challenging for standard CNNs to effectively capture CoW variants in classification tasks. To address this, we developed a novel graph-based method that incorporates spectral analysis with a hybrid Convolutional Neural Network and Graph Neural Network architecture to capture the complex morphological structures of the CoW. We conducted a detailed study comparing the performance of the proposed method in classifying anterior and posterior CoW variants across various configurations of VGG and ResNet networks. The proposed method attains a balanced accuracy of 0.69 for anterior and 0.71 for posterior CoW classification, indicating that the proposed framework significantly improved CoW classification performance across both anterior and posterior classes.

Revolutionary advances in DNA sequencing technologies fundamentally change the nature of genomics. Today's sequencing technologies have opened into an outburst in genomic data volume. These data can be used in various applications where long-term storage and analysis of genomic sequence data are required. Data-specific compression algorithms can effectively manage a large volume of data. In recent times, deep learning has achieved great success in many compression tools and is gradually being used in genomic sequence compression. Significantly, autoencoder has been applied in dimensionality reduction, compact representations of data, and generative model learning. It can use convolutional layers to learn essential features from input data, which is better for image and series data. Autoencoder reconstructs the input data with some loss of information. Since accuracy is critical in genomic data, compressed genomic data must be decompressed without any information loss. We introduce a new scheme to address the loss incurred in the decompressed data of the autoencoder. This paper proposes a novel algorithm called GenCoder for reference-free compression of genomic sequences using a convolutional autoencoder and regenerating the genomic sequences from a latent code produced by the autoencoder, and retrieving original data losslessly. Performance evaluation is conducted on various genomes and benchmarked datasets. The experimental results on the tested data demonstrate that the deep learning model used in the proposed compression algorithm generalizes well for genomic sequence data and achieves a compression gain of 27% over the best state-of-the-art method.

Resolution enhancement of Earth’s images from synthetic aperture radars (SARs), used for applications that require scene interpretations and detailed analysis, fails due to the presence of inherent speckle noise. An inexpensive alternative solution to the problem is to use super-resolution (SR) algorithms that deal with speckle. A novel approach to augment kernel regression into the Adaptive Importance Sampling Unscented Kalman Filter (AISUKF) framework for SAR image SR has been presented in this letter. We have experimented with three different nonlinear kernel regressions, namely, arc-cosine kernel, radial basis function kernel, and steering kernel (SK) regressions. Empirical results suggest that AISUKF with SK regression is more appropriate for the abovementioned SR problem resulting in a better denoised and more detail-preserved output.

Multi-View Stereo (MVS) methods tackle the ill-posed inverse problem of recovering an object's 3D structure from its multi-view calibrated images. High computational cost restricts most MVS methods from using global information for depth estimation. We present a depth map-based MVS method that uses global information to estimate the depths of all pixels in an image simultaneously. To this end, we transform the depth refinement problem into computing max-flow/min-cut on a 3D grid graph with offset vertices. The$s{-}t$min-cut of this graph corresponds to the minimization of an energy functional consisting of photo-consistency and smoothness terms. Experimental results on indoor and outdoor datasets validate the efficacy of our method, especially on models with low textured regions where global information is necessary to infer the correct depth.

Nuclear atypia scoring (NAS), forms a significant factor in determining individualized treatment plans and also for the prognosis of the disease. Automation of cancer grading using quantitative image-based analysis of histopathological images can circumvent the shortcomings of the prevailing manual grading and can assist the pathologists in cancer diagnosis. However, developing such a robust classifier model require sufficient amount of annotated data, while the labeled histopathological images are scarce and expensive to procure as annotation forms a time-consuming and laborious task. Hence, a semi-supervised learning framework combined with the deep neural network based generative adversarial training, that can improve the performance of the classification model with limited annotated data, is proposed in this paper. The proposed NAS-SGAN model consists of discriminator and generator models that are trained in an adversarial manner using both labeled and unlabeled samples. The discriminator model is designed as an unsupervised model stacked over the supervised model sharing the model parameters and learns the data distribution by extracting the discriminative features. The generator model is trained over a stable feature matching objective function following a composite GAN architecture, and its for the first time the semi-supervised GAN model is explored for the grading of breast cancer. Experimental analysis shows that the proposed model could better discriminate different cancer grades thereby improving the robustness and accuracy of the system, even with limited amount of labeled samples.

Recovering three-dimensional structure from images is a long-standing ill-posed inverse problem in computer vision. This paper presents a simple and highly scalable method to reconstruct dense 3D point cloud from multi-view images by estimating per-pixel depth using an evolutionary computation technique – CMA-ES. The proposed method uses ZNCCbased template matching to reconstruct fine details of textured regions and DAISY-based feature matching to reconstruct smooth surface of homogeneous regions. We handle the problem of reconstructing large homogeneous regions using distance transform-based adaptive median filtering. The proposed method is highly scalable since pixels are processed independently at all stages of reconstruction – depth map estimation, refinement, and fusion. This enables the proposed method to be parallelized at the pixel-level, unlike most existing methods that can only be parallelized at the image-level. Experimental results on Middlebury benchmark dataset demonstrate the robustness and efficacy of the proposed method in reconstructing textured as well as homogeneous regions.

Video summarization methods aim to generate a shortened representation of the original video. A novel method to extract key-frames based on Convolutional Neural Network and Random Forest Classifier is presented in this paper. The method processes videos on frame by frame basis. The redundant frames are first eliminated based on displacement vectors between the consecutive frames. The high-level feature vectors are extracted using CNN. The feature descriptors corresponding to frames are further classified into key-frames and non-keyframes using the Random Forest Classifier. The method is tested on two benchmark datasets: VSUMM and OVP. The proposed approach attains better results compared to other state-of-the-art video summarization techniques. The results show that the method is able to generate high quality summaries consistently for videos of all categories.

Breast cancer is found to be the most pervasive type of cancer among women. Computer aided detection and diagnosis of cancer at the initial stages can increase the chances of recovery and thus reduce the mortality rate through timely prognosis and adequate treatment planning. The nuclear atypia scoring or histopathological breast tumor grading remains to be a challenging problem due to the various artifacts and variabilities introduced during slide preparation and also because of the complexity in the structure of the underlying tissue patterns. Inspired by the success of symmetric positive definite (SPD) matrices in many of the challenging tasks in machine learning and computer vision, a sparse coding and dictionary learning on SPD matrices is proposed in this paper for the breast tumor grading. The proposed covariance-based SPD matrices form a Riemannian manifold and are represented as the sparse combination of Riemannian dictionary atoms. Non-linearity of the SPD manifold is tackled by embedding into the reproducing kernel Hilbert space using kernels derived from log-Euclidean metric, Jeffrey and Stein divergences and compared with the non-kernel-based affine invariant Riemannian metric. The novelty of the work lies in exploiting the kernel approach for the Hilbert space embedding of the Riemannian manifold, that can achieve a better discrimination of the breast cancer tissues, following a sparse representation over learned dictionaries and henceforth it outperforms many of the state-of-the-art algorithms in breast cancer grading in terms of quantitative and qualitative analysis.