Mask-Guided Vision Transformer for Few-Shot Learning.

Learning with little data is challenging but often inevitable in various application scenarios where the labeled data are limited and costly. Recently, few-shot learning (FSL) gained increasing attention because of its generalizability of prior knowledge to new tasks that contain only a few samples. However, for data-intensive models such as vision transformer (ViT), current fine-tuning-based FSL approaches are inefficient in knowledge generalization and, thus, degenerate the downstream task performances. In this article, we propose a novel mask-guided ViT (MG-ViT) to achieve an effective and efficient FSL on the ViT model. The key idea is to apply a mask on image patches to screen out the task-irrelevant ones and to guide the ViT focusing on task-relevant and discriminative patches during FSL. Particularly, MG-ViT only introduces an additional mask operation and a residual connection, enabling the inheritance of parameters from pretrained ViT without any other cost. To optimally select representative few-shot samples, we also include an active learning-based sample selection method to further improve the generalizability of MG-ViT-based FSL. We evaluate the proposed MG-ViT on classification, object detection, and segmentation tasks using gradient-weighted class activation mapping (Grad-CAM) to generate masks. The experimental results show that the MG-ViT model significantly improves the performance and efficiency compared with general fine-tuning-based ViT and ResNet models, providing novel insights and a concrete approach toward generalizing data-intensive and large-scale deep learning models for FSL.

Helicobacter pylori CagA Promotes the Formation of Gallstones by Increasing the Permeability of Gallbladder Epithelial Cells.

BACKGROUND: The formation of gallstones is often accompanied by chronic inflammation, and the mechanisms underlying inflammation and stone formation are not fully understood. Our aim is to utilize single-cell transcriptomics, bulk transcriptomics, and microbiome data to explore key pathogenic bacteria that may contribute to chronic inflammation and gallstone formation, as well as their associated mechanisms. METHODS: scRNA-seq data from a gallstone mouse model were extracted from the Gene Expression Omnibus (GEO) database and analyzed using the FindCluster() package for cell clustering analysis. Bulk transcriptomics data from patients with gallstone were also extracted from the GEO database, and intergroup functional differences were assessed using GO and KEGG enrichment analysis. Additionally, 16S rRNA sequencing was performed on gallbladder mucosal samples from asymptomatic patients with gallstone (n = 6) and liver transplant donor gallbladder mucosal samples (n = 6) to identify key bacteria associated with stone formation and chronic inflammation. Animal models were constructed to investigate the mechanisms by which these key pathogenic bacterial genera promote gallstone formation. RESULTS: Analysis of scRNA-seq data from the gallstone mouse model (GSE179524) revealed seven distinct cell clusters, with a significant increase in neutrophil numbers in the gallstone group. Analysis of bulk transcriptomics data from patients with gallstone (GSE202479) identified chronic inflammation in the gallbladder, potentially associated with dysbiosis of the gallbladder microbiota. 16S rRNA sequencing identified Helicobacter pylori as a key bacterium associated with gallbladder chronic inflammation and stone formation. CONCLUSIONS: Dysbiosis of the gallbladder mucosal microbiota is implicated in gallstone disease and leads to chronic inflammation. This study identified H. pylori as a potential key mucosal resident bacterium contributing to gallstone formation and discovered its key pathogenic factor CagA, which causes damage to the gallbladder mucosal barrier. These findings provide important clues for the prevention and treatment of gallstones.

A Histopathologic Correlation Study Evaluating Glymphatic Function in Brain Tumors by Multi-Parametric MRI.

PURPOSE: This study aimed to elucidate the impact of brain tumors on cerebral edema and glymphatic drainage, leveraging advanced imaging techniques to explore the relationship between tumor characteristics, glymphatic function, and aquaporin 4 (AQP4) expression. EXPERIMENTAL DESIGN: In a prospective cohort from March 2022 to April 2023, patients with glioblastoma, brain metastases, and aggressive meningiomas, alongside age- and sex-matched healthy controls, underwent 3.0T MRI, including Diffusion Tensor Imaging Analysis Along the Perivascular Space (DTI-ALPS) index and Multiparametric MRI (MTP) for quantitative brain mapping. Tumor and peri-tumor tissues were analyzed for AQP4 expression via immunofluorescence. Correlations between imaging parameters, glymphatic function (DTI-ALPS index), and AQP4 expression were statistically assessed. RESULTS: Among 84 patients (mean age: 55 ± 12 years; 38 males) and 59 controls (mean age: 54 ± 8 years; 23 males), brain tumor patients exhibited significantly reduced glymphatic function (DTI-ALPS index: 2.315 vs. 2.879; p = 0.001) and increased cerebrospinal fluid (CSF) volume (201.376 cm³ vs. 115.957 cm³; p = 0.001). A negative correlation was observed between tumor volume and the DTI-ALPS index (r: -0.715, p < 0.001), while AQP4 expression correlated positively with peritumoral brain edema (PTBE) volume (r: 0.989; p < 0.001) and negatively with PD in PTBE areas (ρ: -0.506; p < 0.001). CONCLUSIONS: Our findings highlight the interplay between tumor-induced compression, glymphatic dysfunction, and altered fluid dynamics, showing the utility of DTI-ALPS and MTP in understanding the pathophysiology of tumor-related cerebral edema. These insights provide a radiological foundation for further neuro-oncological investigations into the glymphatic system.

PhraseAug: An Augmented Medical Report Generation Model with Phrasebook.

Medical report generation is a valuable and challenging task, which automatically generates accurate and fluent diagnostic reports for medical images, reducing workload of radiologists and improving efficiency of disease diagnosis. Fine-grained alignment of medical images and reports facilitates the exploration of close correlations between images and texts, which is crucial for cross-modal generation. However, visual and linguistic biases caused by radiologists' writing styles make cross-modal image-text alignment difficult. To alleviate visual-linguistic bias, this paper discretizes medical reports and introduces an intermediate modality, i.e. phrasebook, consisting of key noun phrases. As discretized representation of medical reports, phrasebook contains both disease-related medical terms, and synonymous phrases representing different writing styles which can identify synonymous sentences, thereby promoting fine-grained alignment between images and reports. In this paper, an augmented two-stage medical report generation model with phrasebook (PhraseAug) is developed, which combines medical images, clinical histories and writing styles to generate diagnostic reports. In the first stage, phrasebook is used to extract semantically relevant important features and predict key phrases contained in the report. In the second stage, medical reports are generated according to the predicted key phrases which contain synonymous phrases, promoting our model to adapt to different writing styles and generating diverse medical reports. Experimental results on two public datasets, IU-Xray and MIMIC-CXR, demonstrate that our proposed PhraseAug outperforms state-of-the-art baselines.

Advancing microbial production through artificial intelligence-aided biology.

Microbial cell factories (MCFs) have been leveraged to construct sustainable platforms for value-added compound production. To optimize metabolism and reach optimal productivity, synthetic biology has developed various genetic devices to engineer microbial systems by gene editing, high-throughput protein engineering, and dynamic regulation. However, current synthetic biology methodologies still rely heavily on manual design, laborious testing, and exhaustive analysis. The emerging interdisciplinary field of artificial intelligence (AI) and biology has become pivotal in addressing the remaining challenges. AI-aided microbial production harnesses the power of processing, learning, and predicting vast amounts of biological data within seconds, providing outputs with high probability. With well-trained AI models, the conventional Design-Build-Test (DBT) cycle has been transformed into a multidimensional Design-Build-Test-Learn-Predict (DBTLP) workflow, leading to significantly improved operational efficiency and reduced labor consumption. Here, we comprehensively review the main components and recent advances in AI-aided microbial production, focusing on genome annotation, AI-aided protein engineering, artificial functional protein design, and AI-enabled pathway prediction. Finally, we discuss the challenges of integrating novel AI techniques into biology and propose the potential of large language models (LLMs) in advancing microbial production.

Mask-aware transformer with structure invariant loss for CT translation.

Multi-phase enhanced computed tomography (MPECT) translation from plain CT can help doctors to detect the liver lesion and prevent patients from the allergy during MPECT examination. Existing CT translation methods directly learn an end-to-end mapping from plain CT to MPECT, ignoring the crucial clinical domain knowledge. As clinicians subtract the plain CT from MPECT images as subtraction image to highlight the contrast-enhanced regions and further to facilitate liver disease diagnosis in the clinical diagnosis, we aim to exploit this domain knowledge for automatic CT translation. To this end, we propose a Mask-Aware Transformer (MAFormer) with structure invariant loss for CT translation, which presents the first effort to exploit this domain knowledge for CT translation. Specifically, the proposed MAFormer introduces a mask estimator to predict the subtraction image from the plain CT image. To integrate the subtraction image into the network, the MAFormer devises a Mask-Aware Transformer based Normalization (MATNorm) as normalization layer to highlight the contrast-enhanced regions and capture the long-range dependencies among these regions. Moreover, aiming to preserve the biological structure of CT slices, a structure invariant loss is designed to extract the structural information and minimize the structural similarity between the plain and synthetic CT images to ensure the structure invariant. Extensive experiments have proven the effectiveness of the proposed method and its superiority to the state-of-the-art CT translation methods. Source code is to be released.

CE-GAN: Community Evolutionary Generative Adversarial Network for Alzheimer's Disease Risk Prediction.

In the studies of neurodegenerative diseases such as Alzheimer's Disease (AD), researchers often focus on the associations among multi-omics pathogeny based on imaging genetics data. However, current studies overlook the communities in brain networks, leading to inaccurate models of disease development. This paper explores the developmental patterns of AD from the perspective of community evolution. We first establish a mathematical model to describe functional degeneration in the brain as the community evolution driven by entropy information propagation. Next, we propose an interpretable Community Evolutionary Generative Adversarial Network (CE-GAN) to predict disease risk. In the generator of CE-GAN, community evolutionary convolutions are designed to capture the evolutionary patterns of AD. The experiments are conducted using functional magnetic resonance imaging (fMRI) data and single nucleotide polymorphism (SNP) data. CE-GAN achieves 91.67% accuracy and 91.83% area under curve (AUC) in AD risk prediction tasks, surpassing advanced methods on the same dataset. In addition, we validated the effectiveness of CE-GAN for pathogeny extraction. The source code of this work is available at https://github.com/fmri123456/CE-GAN.

Species -shared and -unique gyral peaks on human and macaque brains.

Cortical folding is an important feature of primate brains that plays a crucial role in various cognitive and behavioral processes. Extensive research has revealed both similarities and differences in folding morphology and brain function among primates including macaque and human. The folding morphology is the basis of brain function, making cross-species studies on folding morphology important for understanding brain function and species evolution. However, prior studies on cross-species folding morphology mainly focused on partial regions of the cortex instead of the entire brain. Previously, our research defined a whole-brain landmark based on folding morphology: the gyral peak. It was found to exist stably across individuals and ages in both human and macaque brains. Shared and unique gyral peaks in human and macaque are identified in this study, and their similarities and differences in spatial distribution, anatomical morphology, and functional connectivity were also dicussed.

Task sub-type states decoding via group deep bidirectional recurrent neural network.

Decoding brain states under different cognitive tasks from functional magnetic resonance imaging (fMRI) data has attracted great attention in the neuroimaging filed. However, the well-known temporal dependency in fMRI sequences has not been fully exploited in existing studies, due to the limited temporal-modeling capacity of the backbone machine learning algorithms and rigid training sample organization strategies upon which the brain decoding methods are built. To address these limitations, we propose a novel method for fine-grain brain state decoding, namely, group deep bidirectional recurrent neural network (Group-DBRNN) model. We first propose a training sample organization strategy that consists of a group-task sample generation module and a multiple-scale random fragment strategy (MRFS) module to collect training samples that contain rich task-relevant brain activity contrast (i.e., the comparison of neural activity patterns between different tasks) and maintain the temporal dependency. We then develop a novel decoding model by replacing the unidirectional RNNs that are widely used in existing brain state decoding studies with bidirectional stacked RNNs to better capture the temporal dependency, and by introducing a multi-task interaction layer (MTIL) module to effectively model the task-relevant brain activity contrast. Our experimental results on the Human Connectome Project task fMRI dataset (7 tasks consisting of 23 task sub-type states) show that the proposed model achieves an average decoding accuracy of 94.7% over the 23 fine-grain sub-type states. Meanwhile, our extensive interpretations of the intermediate features learned in the proposed model via visualizations and quantitative assessments of their discriminability and inter-subject alignment evidence that the proposed model can effectively capture the temporal dependency and task-relevant contrast.

Hierarchical functional differences between gyri and sulci at different scales.

Gyri and sulci are 2 fundamental cortical folding patterns of the human brain. Recent studies have suggested that gyri and sulci may play different functional roles given their structural and functional heterogeneity. However, our understanding of the functional differences between gyri and sulci remains limited due to several factors. Firstly, previous studies have typically focused on either the spatial or temporal domain, neglecting the inherently spatiotemporal nature of brain functions. Secondly, analyses have often been restricted to either local or global scales, leaving the question of hierarchical functional differences unresolved. Lastly, there has been a lack of appropriate analytical tools for interpreting the hierarchical spatiotemporal features that could provide insights into these differences. To overcome these limitations, in this paper, we proposed a novel hierarchical interpretable autoencoder (HIAE) to explore the hierarchical functional difference between gyri and sulci. Central to our approach is its capability to extract hierarchical features via a deep convolutional autoencoder and then to map these features into an embedding vector using a carefully designed feature interpreter. This process transforms the features into interpretable spatiotemporal patterns, which are pivotal in investigating the functional disparities between gyri and sulci. We evaluate the proposed framework on Human Connectome Project task functional magnetic resonance imaging dataset. The experiments demonstrate that the HIAE model can effectively extract and interpret hierarchical spatiotemporal features that are neuroscientifically meaningful. The analyses based on the interpreted features suggest that gyri are more globally activated, whereas sulci are more locally activated, demonstrating a distinct transition in activation patterns as the scale shifts from local to global. Overall, our study provides novel insights into the brain's anatomy-function relationship.

Exploring Alzheimer's disease: a comprehensive brain connectome-based survey.

Dementia is an escalating global health challenge, with Alzheimer's disease (AD) at its forefront. Substantial evidence highlights the accumulation of AD-related pathological proteins in specific brain regions and their subsequent dissemination throughout the broader area along the brain network, leading to disruptions in both individual brain regions and their interconnections. Although a comprehensive understanding of the neurodegeneration-brain network link is lacking, it is undeniable that brain networks play a pivotal role in the development and progression of AD. To thoroughly elucidate the intricate network of elements and connections constituting the human brain, the concept of the brain connectome was introduced. Research based on the connectome holds immense potential for revealing the mechanisms underlying disease development, and it has become a prominent topic that has attracted the attention of numerous researchers. In this review, we aim to systematically summarize studies on brain networks within the context of AD, critically analyze the strengths and weaknesses of existing methodologies, and offer novel perspectives and insights, intending to serve as inspiration for future research.

Mapping dynamic spatial patterns of brain function with spatial-wise attention.

Objective: Using functional magnetic resonance imaging (fMRI) and deep learning to discover the spatial pattern of brain function, or functional brain networks (FBNs) has been attracted many reseachers. Most existing works focus on static FBNs or dynamic functional connectivity among fixed spatial network nodes, but ignore the potential dynamic/time-varying characteristics of the spatial networks themselves. And most of works based on the assumption of linearity and independence, that oversimplify the relationship between blood-oxygen level dependence signal changes and the heterogeneity of neuronal activity within voxels.Approach: To overcome these problems, we proposed a novel spatial-wise attention (SA) based method called Spatial and Channel-wise Attention Autoencoder (SCAAE) to discover the dynamic FBNs without the assumptions of linearity or independence. The core idea of SCAAE is to apply the SA to generate FBNs directly, relying solely on the spatial information present in fMRI volumes. Specifically, we trained the SCAAE in a self-supervised manner, using the autoencoder to guide the SA to focus on the activation regions. Experimental results show that the SA can generate multiple meaningful FBNs at each fMRI time point, which spatial similarity are close to the FBNs derived by known classical methods, such as independent component analysis.Main results: To validate the generalization of the method, we evaluate the approach on HCP-rest, HCP-task and ADHD-200 dataset. The results demonstrate that SA mechanism can be used to discover time-varying FBNs, and the identified dynamic FBNs over time clearly show the process of time-varying spatial patterns fading in and out.Significance: Thus we provide a novel method to understand human brain better. Code is available athttps://github.com/WhatAboutMyStar/SCAAE.

Technical note: Generalizable and promptable artificial intelligence model to augment clinical delineation in radiation oncology.

BACKGROUND: Efficient and accurate delineation of organs at risk (OARs) is a critical procedure for treatment planning and dose evaluation. Deep learning-based auto-segmentation of OARs has shown promising results and is increasingly being used in radiation therapy. However, existing deep learning-based auto-segmentation approaches face two challenges in clinical practice: generalizability and human-AI interaction. A generalizable and promptable auto-segmentation model, which segments OARs of multiple disease sites simultaneously and supports on-the-fly human-AI interaction, can significantly enhance the efficiency of radiation therapy treatment planning. PURPOSE: Meta's segment anything model (SAM) was proposed as a generalizable and promptable model for next-generation natural image segmentation. We further evaluated the performance of SAM in radiotherapy segmentation. METHODS: Computed tomography (CT) images of clinical cases from four disease sites at our institute were collected: prostate, lung, gastrointestinal, and head & neck. For each case, we selected the OARs important in radiotherapy treatment planning. We then compared both the Dice coefficients and Jaccard indices derived from three distinct methods: manual delineation (ground truth), automatic segmentation using SAM's 'segment anything' mode, and automatic segmentation using SAM's 'box prompt' mode that implements manual interaction via live prompts during segmentation. RESULTS: Our results indicate that SAM's segment anything mode can achieve clinically acceptable segmentation results in most OARs with Dice scores higher than 0.7. SAM's box prompt mode further improves Dice scores by 0.1∼0.5. Similar results were observed for Jaccard indices. The results show that SAM performs better for prostate and lung, but worse for gastrointestinal and head & neck. When considering the size of organs and the distinctiveness of their boundaries, SAM shows better performance for large organs with distinct boundaries, such as lung and liver, and worse for smaller organs with less distinct boundaries, like parotid and cochlea. CONCLUSIONS: Our results demonstrate SAM's robust generalizability with consistent accuracy in automatic segmentation for radiotherapy. Furthermore, the advanced box-prompt method enables the users to augment auto-segmentation interactively and dynamically, leading to patient-specific auto-segmentation in radiation therapy. SAM's generalizability across different disease sites and different modalities makes it feasible to develop a generic auto-segmentation model in radiotherapy.

The concentration of dissolved organic matter impacts the neurobehavior in female zebrafish exposed to cyclophosphamide.

Cyclophosphamide (CP) is a broad-spectrum anticancer drug for various cancers and frequently detected in aquatic environments, reaching concentrations up to 22 µg/L. However, there is limited understanding of the toxicities of CP with the presence of dissolved organic matter, a ubiquitous component in aquatic environments, in fish. In this study, we investigated the behaviors, morphological alterations of retina, and related gene transcripts in zebrafish exposed to CP (0 and 50 µg/L) and Humic acid (HA, a main component of DOM) at concentrations of 0, 3, 10, and 30 mg-C/L for 30 days. The results showed that, relative to the zebrafish in CP treatment, HA at 30 mg-C/L increased the locomotion (12.1 % in the light and 7.2 % in the dark) and startle response (9.7 %), while inhibiting the anxiety (12.5 %) and cognition of female zebrafish (24.6 %). The levels of transcripts of neurotransmitter- (tph1b and ache), neuroinflammation-(il-6 and tnfα) and antioxidant-(gpx) related genes in the brain of female adult were also altered by CP with the presence of HA. In addition, HA promoted the transgenerational effects of CP on the neurobehaviors. Therefore, HA can enhance potential neurotoxicity of CP in female fish through alteration neurotransmission related genes. Our findings provide new insights into the toxicity and underlying mechanisms of CP with the presence of dissolved organic matter, thereby contribute to a deeper understanding of the risks posed by CP in aquatic ecosystems.

RBCK1 overexpression is associated with immune cell infiltration and poor prognosis in hepatocellular carcinoma.

RBCK1 is an important E3 ubiquitin ligase, which plays an important role in many major diseases. However, the function and mechanism of RBCK1 in pan-cancer and its association with immune cell infiltration have not been reported. The purpose of this study is to find out the expression of RBCK1 in cancer, and to explore the relationship between RBCK1 and the prognosis of patients. Our results show that the expression of RBCK1 is up-regulated in a variety of malignant tumors, and is closely related to the prognosis of patients. Further studies have shown that RBCK1 regulates protein expression in the nucleus and plays an important role in ribosome and valine, leucine, and isoleucine degradation. Genetic variation analysis showed that RBCK1 was mainly involved in missense mutations in multiple tumors, and mutated patients showed poor prognoses. Further studies showed that RBCK1 may be interacted with proteins such as RNRPB, MCRS1, TRIB3, MKKS and ARPC3. Through protein interaction analysis, we found 43 proteins interacting with RBCK1 in liver cancer. We also analyzed immune cell infiltration and found that RBCK1 expression was positively correlated with T cells and macrophages, while it was negatively correlated with neutrophils, NK cells, and DCs in liver cancer. Finally, we confirmed experimentally that RBCK1 can significantly inhibit the apoptosis and invasion of HCC. Therefore, we speculate that RBCK1 plays an important regulatory role in the occurrence and development of HCC.

Brain Structural Connectivity Guided Vision Transformers for Identification of Functional Connectivity Characteristics in Preterm Neonates.

Preterm birth is the leading cause of death in children under five years old, and is associated with a wide sequence of complications in both short and long term. In view of rapid neurodevelopment during the neonatal period, preterm neonates may exhibit considerable functional alterations compared to term ones. However, the identified functional alterations in previous studies merely achieve moderate classification performance, while more accurate functional characteristics with satisfying discrimination ability for better diagnosis and therapeutic treatment is underexplored. To address this problem, we propose a novel brain structural connectivity (SC) guided Vision Transformer (SCG-ViT) to identify functional connectivity (FC) differences among three neonatal groups: preterm, preterm with early postnatal experience, and term. Particularly, inspired by the neuroscience-derived information, a novel patch token of SC/FC matrix is defined, and the SC matrix is then adopted as an effective mask into the ViT model to screen out input FC patch embeddings with weaker SC, and to focus on stronger ones for better classification and identification of FC differences among the three groups. The experimental results on multi-modal MRI data of 437 neonatal brains from publicly released Developing Human Connectome Project (dHCP) demonstrate that SCG-ViT achieves superior classification ability compared to baseline models, and successfully identifies holistically different FC patterns among the three groups. Moreover, these different FCs are significantly correlated with the differential gene expressions of the three groups. In summary, SCG-ViT provides a powerfully brain-guided pipeline of adopting large-scale and data-intensive deep learning models for medical imaging-based diagnosis.

A Unified and Biologically Plausible Relational Graph Representation of Vision Transformers.

Vision transformer (ViT) and its variants have achieved remarkable success in various tasks. The key characteristic of these ViT models is to adopt different aggregation strategies of spatial patch information within the artificial neural networks (ANNs). However, there is still a key lack of unified representation of different ViT architectures for systematic understanding and assessment of model representation performance. Moreover, how those well-performing ViT ANNs are similar to real biological neural networks (BNNs) is largely unexplored. To answer these fundamental questions, we, for the first time, propose a unified and biologically plausible relational graph representation of ViT models. Specifically, the proposed relational graph representation consists of two key subgraphs: an aggregation graph and an affine graph. The former considers ViT tokens as nodes and describes their spatial interaction, while the latter regards network channels as nodes and reflects the information communication between channels. Using this unified relational graph representation, we found that: 1) model performance was closely related to graph measures; 2) the proposed relational graph representation of ViT has high similarity with real BNNs; and 3) there was a further improvement in model performance when training with a superior model to constrain the aggregation graph.

Frequency-specific functional difference between gyri and sulci in naturalistic paradigm fMRI.

Disentangling functional difference between cortical folding patterns of gyri and sulci provides novel insights into the relationship between brain structure and function. Previous studies using resting-state functional magnetic resonance imaging (rsfMRI) have revealed that sulcal signals exhibit stronger high-frequency but weaker low-frequency components compared to gyral ones, suggesting that gyri may serve as functional integration centers while sulci are segregated local processing units. In this study, we utilize naturalistic paradigm fMRI (nfMRI) to explore the functional difference between gyri and sulci as it has proven to record stronger functional integrations compared to rsfMRI. We adopt a convolutional neural network (CNN) to classify gyral and sulcal fMRI signals in the whole brain (the global model) and within functional brain networks (the local models). The frequency-specific difference between gyri and sulci is then inferred from the power spectral density (PSD) profiles of the learned filters in the CNN model. Our experimental results show that nfMRI shows higher gyral-sulcal PSD contrast effect sizes in the global model compared to rsfMRI. In the local models, the effect sizes are either increased or decreased depending on frequency bands and functional complexity of the FBNs. This study highlights the advantages of nfMRI in depicting the functional difference between gyri and sulci, and provides novel insights into unraveling the relationship between brain structure and function.

Spatial-temporal convolutional attention for discovering and characterizing functional brain networks in task fMRI.

Functional brain networks (FBNs) are spatial patterns of brain function that play a critical role in understanding human brain function. There are many proposed methods for mapping the spatial patterns of brain function, however they oversimplify the underlying assumptions of brain function and have various limitations such as linearity and independence. Additionally, current methods fail to account for the dynamic nature of FBNs, which limits their effectiveness in accurately characterizing these networks. To address these limitations, we present a novel deep learning and spatial-wise attention based model called Spatial-Temporal Convolutional Attention (STCA) to accurately model dynamic FBNs. Specifically, we train STCA in a self-supervised manner by utilizing a Convolutional Autoencoder to guide the STCA module in assigning higher attention weights to regions of functional activity. To validate the reliability of the results, we evaluate our approach on the HCP-task motor behavior dataset, the experimental results demonstrate that the STCA derived FBNs have higher spatial similarity with the templates and that the spatial similarity between the templates and the FBNs derived by STCA fluctuates with the task design over time, suggesting that STCA can reflect the dynamic changes of brain function, providing a powerful tool to better understand human brain function. Code is available at https://github.com/SNNUBIAI/STCAE.

Beam mask and sliding window-facilitated deep learning-based accurate and efficient dose prediction for pencil beam scanning proton therapy.

BACKGROUND: Accurate and efficient dose calculation is essential for on-line adaptive planning in proton therapy. Deep learning (DL) has shown promising dose prediction results in photon therapy. However, there is a scarcity of DL-based dose prediction methods specifically designed for proton therapy. Successful dose prediction method for proton therapy should account for more challenging dose prediction problems in pencil beam scanning proton therapy (PBSPT) due to its sensitivity to heterogeneities. PURPOSE: To develop a DL-based PBSPT dose prediction workflow with high accuracy and balanced complexity to support on-line adaptive proton therapy clinical decision and subsequent replanning. METHODS: PBSPT plans of 103 prostate cancer patients (93 for training and the other 10 for independent testing) and 83 lung cancer patients (73 for training and the other 10 for independent testing) previously treated at our institution were included in the study, each with computed tomography scans (CTs), structure sets, and plan doses calculated by the in-house developed Monte-Carlo dose engine (considered as the ground truth in the model training and testing). For the ablation study, we designed three experiments corresponding to the following three methods: (1) Experiment 1, the conventional region of interest (ROI) (composed of targets and organs-at-risk [OARs]) method. (2) Experiment 2, the beam mask (generated by raytracing of proton beams) method to improve proton dose prediction. (3) Experiment 3, the sliding window method for the model to focus on local details to further improve proton dose prediction. A fully connected 3D-Unet was adopted as the backbone. Dose volume histogram (DVH) indices, 3D Gamma passing rates with a criterion of 3%/3 mm/10%, and dice coefficients for the structures enclosed by the iso-dose lines between the predicted and the ground truth doses were used as the evaluation metrics. The calculation time for each proton dose prediction was recorded to evaluate the method's efficiency. RESULTS: Compared to the conventional ROI method, the beam mask method improved the agreement of DVH indices for both targets and OARs and the sliding window method further improved the agreement of the DVH indices (for lung cancer, CTV D98 absolute deviation: 0.74 ± 0.18 vs. 0.57 ± 0.21 vs. 0.54 ± 0.15 Gy[RBE], ROI vs. beam mask vs. sliding window methods, respectively). For the 3D Gamma passing rates in the target, OARs, and BODY (outside target and OARs), the beam mask method improved the passing rates in these regions and the sliding window method further improved them (for prostate cancer, targets: 96.93% ± 0.53% vs. 98.88% ± 0.49% vs. 99.97% ± 0.07%, BODY: 86.88% ± 0.74% vs. 93.21% ± 0.56% vs. 95.17% ± 0.59%). A similar trend was also observed for the dice coefficients. This trend was especially remarkable for relatively low prescription isodose lines (for lung cancer, 10% isodose line dice: 0.871 ± 0.027 vs. 0.911 ± 0.023 vs. 0.927 ± 0.017). The dose predictions for all the testing cases were completed within 0.25 s. CONCLUSIONS: An accurate and efficient deep learning-augmented proton dose prediction framework has been developed for PBSPT, which can predict accurate dose distributions not only inside but also outside ROI efficiently. The framework can potentially further reduce the initial planning and adaptive replanning workload in PBSPT.