Early-stage breast cancer is often asymptomatic, highlighting the critical role of computer-aided diagnostic(CAD) systems in mammography screening. While radiologists often refer to bilateral symmetry to identify abnormalities, most existing CAD methods analyze unilateral views or require image registration, which limits their ability to model structural heterogeneity and often introduces distortion. To address this, we propose a registration-free, structure-aware diagnostic framework that integrates bilateral mammography with soft spatial prompting via Vision Transformers (ViT). By directly concatenating bilateral images and introducing a soft attention mask generated from a lightweight segmentation network, our approach enables end-to-end modeling of cross-breast structural differences without the need for region-of-interest extraction. Extensive evaluations on both public and clinical datasets demonstrate that our method consistently outperforms CNN and lightweight Transformer baselines, achieving up to 0.930 accuracy and 0.972 AUC. To our knowledge, this is the first framework to combine bilateral structural modeling and soft guidance in a unified, interpretable, and scalable ViT-based pipeline for breast cancer diagnosis.

Although some pyroptosis-related (PR) prognostic models for cancers have been reported, pyroptosis-based features have not been fully discovered at the single-cell level in hepatocellular carcinoma (HCC). In this study, by deeply integrating single-cell and bulk transcriptome data, we systematically investigated significance of the shared pyroptotic signature at both single-cell and bulk levels in HCC prognosis. Based on the pyroptotic signature, a robust PR risk system was constructed to quantify the prognostic risk of individual patient. To further verify capacity of the pyroptotic signature on predicting patients' prognosis, an attention mechanism-based deep neural network classification model was constructed. The mechanisms of prognostic difference in the patients with distinct PR risk were dissected on tumor stemness, cancer pathways, transcriptional regulation, immune infiltration and cell communications. A nomogram model combining PR risk with clinicopathologic data was constructed to evaluate the prognosis of individual patients in clinic. The PR risk could also evaluate therapeutic response to neoadjuvant therapies in HCC patients. In conclusion, the constructed PR risk system enables a comprehensive assessment of tumor microenvironment characteristics, accurate prognosis prediction and rational therapeutic options in HCC.

Presents corrections to the article "A Sub-Pixel Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis".

Recent advances in deep reinforcement learning (DRL) have made it possible to train various powerful agents to perform complex tasks in real-time environments. With the next-generation communication technologies, making cloud-edge collaborative artificial intelligence service with evolved DRL agents can be a significant scenario. However, agents with different algorithms and architectures in the same DRL scenario may not be compatible, and training them is either time-consuming or resource-demanding. In this paper, we design a novel cloud-edge collaborative DRL training framework, named Offline-Transfer-Online, which is a new approach that can speed up the convergence of online DRL agents at the edge by interacting with offline agents in the cloud, with the minimum data interchanged and without relying on high-quality offline datasets. Therein, we propose a novel algorithm-independent knowledge distillation algorithm for online RL agents, by leveraging pre-trained models and the interface between agents and the environment to transfer distilled knowledge among multiple heterogeneous agents efficiently. Extensive experiments show that our algorithm can accelerate the convergence of various online agents in a double to decuple speed, with comparable reward achieved in different environments.

Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of best utilizing the limited edge resources flexibly for ML task performance optimization. This paper proposes TapFinger, a distributed scheduler that minimizes the total completion time of ML tasks in a multi-cluster edge network, through co-optimizing task placement and fine-grained multi-resource allocation. To learn the tasks' uncertain resource sensitivity and enable distributed online scheduling, we adopt multi-agent reinforcement learning (MARL), and propose several techniques to make it efficient for our ML-task resource allocation. First, TapFinger uses a heterogeneous graph attention network as the MARL backbone to abstract inter-related state features into more learnable environmental patterns. Second, the actor network is augmented through a tailored task selection phase, which decomposes the actions and encodes the optimization constraints. Third, to mitigate decision conflicts among agents, we novelly combine Bayes' theorem and masking schemes to facilitate our MARL model training. Extensive experiments using synthetic and test-bed ML task traces show that TapFinger can achieve up to 28.6% reduction in the average task completion time and improve resource efficiency as compared to state-of-the- art resource schedulers.

Deep reinforcement learning (DRL) has been a successful paradigm in machine learning that enables solving complex control problems at the human level. However, the sampling and training efficiency of state-of-the-art DRL frameworks can not satisfy the stringent latency and throughput requirements of today’s mobile environments. Existing distributed and offline reinforcement learning algorithms along with the libraries for training acceleration are inherently designed for DRL tasks performed in the cloud rather than on distributed mobile devices, on which the computing resources are highly constrained, heterogeneous, and possibly dynamically changing. With the rise of edge computing and intelligence services, this paper presents RLink, a novel distributed training library to accelerate on-device deep reinforcement learning with inference knowledge at the edge. We leverage knowledge distillation to realize lightweight interaction between our on-device training task and the remote models that can provide inference knowledge. In this way, RLink is designed to be event-driven and agnostic to heterogeneous deep reinforcement learning algorithms and libraries. To tackle the communication bottleneck, a novel asynchronous sampling algorithm is proposed to facilitate real-time training in RLink. Tuned for unstable-connected mobile devices, RLink is robust and efficient by using a semantic-aware communication pipeline for lossless data compression. Extensive experimental results show that, compared with state-of-the-art algorithms and libraries, RLink can accelerate deep reinforcement learning at the edge with up to decuple speedups in convergence and ideal computational performance.

Rheumatoid arthritis (RA) is a chronic autoimmune disease that primarily affects peripheral synovial joints, like fingers, wrists and feet. Radiology plays a critical role in the diagnosis and monitoring of RA. Limited by the current spatial resolution of radiographic imaging, joint space narrowing (JSN) progression of RA for the same reason above can be less than one pixel per year with universal spatial resolution. Insensitive monitoring of JSN can hinder the radiologist/rheumatologist from making a proper and timely clinical judgment. In this paper, we propose a novel and sensitive method that we call partial image phase-only correlation which aims to automatically quantify JSN progression in the early RA. The majority of the current literature utilizes the mean error, root-mean-square deviation and standard deviation to report the accuracy at pixel level. Our work measures JSN progression between a baseline and its follow-up finger joint images by using the phase spectrum in the frequency domain. Using this study, the mean error can be reduced to 0.0130 mm when applied to phantom radiographs with ground truth, and 0.0519 mm standard deviation for clinical radiography. With the sub-pixel accuracy far beyond usual manual measurements, we are optimistic that the proposed work is a promising scheme for automatically quantifying JSN progression.

Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of best utilizing the limited edge resources for ML tasks. This paper proposesTapFinger, a distributed scheduler for edge clusters that minimizes the total completion time of ML tasks through co-optimizing task placement and fine-grained multi-resource allocation. To learn the tasks’ uncertain resource sensitivity and enable distributed scheduling, we adopt multi-agent reinforcement learning (MARL) and propose several techniques to make it efficient, including a heterogeneous graph attention network as the MARL backbone, a tailored task selection phase in the actor network, and the integration of Bayes’ theorem and masking schemes. We first implement asingle-task schedulingversion, which schedules at most one task each time. Then we generalize to themulti-task schedulingcase, in which a sequence of tasks is scheduled simultaneously. Our design can mitigate the expanded decision space and yield fast convergence to optimal scheduling solutions. Extensive experiments using synthetic and test-bed ML task traces show thatTapFingercan achieve up to 54.9% reduction in the average task completion time and improve resource efficiency as compared to state-of-the-art schedulers.