Intracranial aneurysms bring substantial health risks due to their potential to rupture, which may lead to severe morbidity and mortality. Accurate prediction of rupture risk is essential for guiding clinical decision-making and formulating effective treatment strategies. In this study, we introduce GN-Net, a novel deep learning model designed to predict the rupture risk of intracranial aneurysms by integrating geometric and neighborhood features extracted from 3D Computed Tomography Angiography (CTA) images. GN-Net comprises two distinct branches: a geometric branch that utilizes geometric deep learning to capture the local geometric structures of aneurysms and their parent arteries, and a neighborhood-aware branch that employs 3D Convolutional Neural Networks (CNNs) and Transformer encoders to model the surrounding anatomical context. We evaluated GN-Net on an internal dataset and an external dataset. This study collected 423 valid intracranial aneurysm patients from a hospital for model training and testing. Experimental results demonstrated that our method achieved the highest prediction accuracy (91.46 https://github.com/YouWillLikeIt/GN-Net .

Finding known homologs of newly predicted proteins is essential for understanding their functions and mechanisms. It is a highly complex task because proteins undergo various changes during evolution. Traditional methods based on sequence or structure alignment either have low accuracy or take a long time. Recent deep learning-based methods primarily focus on structural information, yet they can’t fully exploiting protein information. To solve this problem, in this paper, we propose a novel general-purpose protein embedding model that can be used for homology search. It first employs a protein language pre-trained model to extract protein sequence embeddings, capturing intricate biological patterns. Subsequently, a Transformer integrating protein structural information generates the high-level representations. By combining protein sequence and structural features, the model can effectively exploit the rich contextual and spatial information inherent in proteins. We applied the model to the SCOP dataset for protein superfamily classification, achieving a classification accuracy of 86.97%, outperforming state-of-the-art method by 7.91%. The source code has been published on GitHub (https://github.com/CMACH508/PEST).

Protein binding site prediction is an important prerequisite for the discovery of new drugs. Usually, natural 3D U-Net is adopted as the standard site prediction framework to do per-voxel binary mask classification. However, this scheme only performs feature extraction for single-scale samples, which may bring the loss of global or local information, resulting in incomplete, artifacted or even missed predictions. To tackle this issue, we propose a network called GLPocket, which is based on the Lmser (Least mean square error reconstruction) network and utilizes multi-scale representation to predict binding sites. Firstly, GLPocket uses Target Cropping Block (TCB) for targeted prediction. TCB selects the local interested feature from the global representations to perform concentrated prediction, and reduces the volume of feature maps to be calculated by 82% without adding additional parameters. It integrates global distribution information into local regions, making prediction more concentrated on decoding stage. Secondly, GLPocket establishes long-range relationship of patches within the local region with Transformer Block (TB), to enrich local context semantic information. Experiments show that GLPocket improves by 0.5%-4% on DCA Top-n prediction compared with previous state-of-the-art methods on four datasets. Our code has been released in https://github.com/CMACH508/GLPocket.

It is critical to accurately predict the rupture risk of an intracranial aneurysm (IA) for timely and appropriate treatment because the fatality rate after rupture is 50 % . Existing methods relying on morphological features (e.g., height-width ratio) measured manually by neuroradiologists are labor intensive and have limited use for risk assessment. Therefore, we propose an end-to-end deep-learning method, called TransIAR net, to automatically learn the morphological features from 3D computed tomography angiography (CTA) data and accurately predict the status of IA rupture. We devise a multiscale 3D convolutional neural network (CNN) to extract the structural patterns of the IA and its neighborhood with a dual branch of shared network structures. Moreover, we learn the spatial dependence within the IA neighborhood with a transformer encoder. Our experiments demonstrated that the features learned by TransIAR are more effective and robust than handcrafted features, resulting in a 10 % - 15 % improvement in the accuracy of rupture status prediction.

Protein binding site prediction is an important prerequisite task of drug discovery and design. While binding sites are very small, irregular and varied in shape, making the prediction very challenging. Standard 3D U-Net has been adopted to predict binding sites but got stuck with unsatisfactory prediction results, incomplete, out-of-bounds, or even failed. The reason is that this scheme is less capable of extracting the chemical interactions of the entire region and hardly takes into account the difficulty of segmenting complex shapes. In this paper, we propose a refined U-Net architecture, called RefinePocket, consisting of an attention-enhanced encoder and a mask-guided decoder. During encoding, taking binding site proposal as input, we employ Dual Attention Block (DAB) hierarchically to capture rich global information, exploring residue relationship and chemical correlations in spatial and channel dimensions respectively. Then, based on the enhanced representation extracted by the encoder, we devise Refine Block (RB) in the decoder to enable self-guided refinement of uncertain regions gradually, resulting in more precise segmentation. Experiments show that DAB and RB complement and promote each other, making RefinePocket has an average improvement of 10.02% on DCC and 4.26% on DVO compared with the state-of-the-art method on four test sets.

It is an essential step to locate the binding sites or pockets of drug molecules on protein structure in drug design. This is challenging because the 3D protein structures are usually in complicated, irregular shape and the pockets are relatively small. Existing deep learning methods for this task are U-Net models, and they have forward skip connections to efficiently transfer features of different levels of 3D structure from encoder to decoder for improving pocket prediction. However, there is still room to improve prediction accuracy. In this paper, we propose RecurPocket, a recurrent Lmser (Least mean square error reconstruction) network for pocket detection. A gated recurrent refinement is devised in RecurPocket to enhance the representation learning on the 3D protein structures. This is fulfilled by feedback connections in RecurPocket network from decoder to encoder, recurrently and progressively improving the feature embedding for accurate prediction. Moreover, a 3D gate mechanism filters out irrelevant information through the feedback links that interfere with detection, making the prediction more precise and clear. Experiments show that RecurPocket improves by 3%-9% on top-n prediction compared with previous state-of-the-art on five benchmark data sets. The source code and trained model are available at https://github.con CMACH508/RecurPocket.

Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e.g., by video surveillance. Existing methods are featured by learning data uncertainty to avoid overfitting the noise, or by adding margins to the angle or cosine space of the normalized softmax loss to penalize the target logit, which enforces intra-class compactness and inter-class discrepancy. In this paper, we propose a deep Rival Penalized Competitive Learning (RPCL) for deep face recognition in low-resolution (LR) images. Inspired by the idea of the RPCL, our method further enforces regulation on the rival logit, which is defined as the largest non-target logit for an input image. Different from existing methods that only consider penalization on the target logit, our method not only strengthens the learning towards the target label, but also enforces a reverse direction, i.e., becoming de-learning, away from the rival label. Comprehensive experiments demonstrate that our method improves the existing state-of-the-art methods to be very robust for LR face recognition.

Developing an efficient system for automated detection and segmentation of intracranial aneurysms (IAs) became an active research topic recently. However, existing methods are poor in detecting small IA with high false positives. In this paper, we present a feature enrichment (FE) based deep learning method for robust IA detection and segmentation. The FE technique is featured by reconstructing a 3D model from all computed tomography angiography (CTA) images and then projecting 3D information into the so-called projection images of different slicing levels along various directions. The appearances of aneurysms in the projection images are enhanced in morphology and 3D neighborhood features, and thus are easy to be detected and segmented by the widely-used faster RCNN and V-Net. To evaluate our method, we collect CTA images from 145 patients (including 148 IAs) for training and testing. The proposed method achieves 96.0 % sensitivity for all aneurysms, and 80.0% sensitivity for aneurysms smaller than 4mm, better than the state-of-the-art methods. Also, the segmentation performance is improved on the detected IAs.

Existing single image super-resolution (SISR) methods usually focus on Low-Resolution (LR) images which are artificially generated from High-Resolution (HR) images by a down-sampling process, but are not robust for unmatched training set and testing set. This paper proposes a GAN Flexible Lmser (GFLmser) network that bidirectionally learns the High-to-Low (H2L) process that degrades HR images to LR images and the Low-to-High (L2H) process that recovers the LR images back to HR images. The two directions share the same architecture, added with the gated skip connections from the H2L-net to the L2H-net in order to enhance information transferring for super-resolution. In comparison with several related state-of-the-art methods, experiments demonstrate that not only GFLmser is the most robust method on images of unmatched training set and testing set, but also its performance on real-world face LR images is best in PSNR and reasonably good in FID.