Assessment of different U-Net backbones in segmenting colorectal adenocarcinoma from H&E histopathology.

Adenocarcinoma, the most prevalent type of colorectal cancer, makes up roughly 95 % of all cases and is associated with a notably high mortality rate. Owing to the various risk factors which might include personal choices and habits or genetic factors, the risk of developing the cancer for every individual might vary. However, given the statistics, the rate of acquiring the disease is pretty high.

Sequential recommendation via agent-based irrelevancy skipping.

Sequential Recommendation is based on modelling sequential dependencies in user interactions to produce subsequent recommendation results. However, due to the diversity of users' interests and the uncertainty of their behaviours, not all historical interactions in users' interaction sequences are relevant to their next-interaction intents, which hinders generating accurate sequential recommendations. To this end, a novel Sequential Recommendation method, Dynamic-Skip for Sequential Recommendation (DyS4Rec), is proposed in this study.

MGATAF: multi-channel graph attention network with adaptive fusion for cancer-drug response prediction.

Background: Drug response prediction is critical in precision medicine to determine the most effective and safe treatments for individual patients. Traditional prediction methods relying on demographic and genetic data often fall short in accuracy and robustness. Recent graph-based models, while promising, frequently neglect the critical role of atomic interactions and fail to integrate drug fingerprints with SMILES for comprehensive molecular graph construction.

Dietary carbohydrate intake and risk of type 2 diabetes: a 16-year prospective cohort study.

Despite considerable research underscoring the importance of carbohydrate intake in relation to the risk of type 2 diabetes (T2D), a comprehensive assessment of this relationship is currently lacking. We aimed to examine the associations of various types and food sources of dietary carbohydrate intake with the risk of T2D, to evaluate potential effect modification by other factors, including genetic susceptibility, and to explore the potential mediators for such associations. The present study included 161,872 participants of the UK Biobank who were free of prevalent cancer, cardiovascular disease, or diabetes, and had at least one validated 24-h dietary recall assessment.

Explainable deep learning and virtual evolution identifies antimicrobial peptides with activity against multidrug-resistant human pathogens.

Artificial intelligence (AI) is a promising approach to identify new antimicrobial compounds in diverse microbial species. Here we developed an AI-based, explainable deep learning model, EvoGradient, that predicts the potency of antimicrobial peptides (AMPs) and virtually modifies peptide sequences to produce more potent AMPs, akin to in silico directed evolution. We applied this model to peptides encoded in low-abundance human oral bacteria, resulting in the virtual evolution of 32 peptides into potent AMPs.

Efficient IP address retrieval using a novel octet based encoding technique for high speed lookup to improve network performance.

As the Internet becomes increasingly popular, the number of users connected to it grows significantly. Consequently, the packet processing speed of network systems, such as routers, must be enhanced. IP lookup is a critical task used to find the next hop address by searching for the longest prefix match in the forwarding information base (FIB).

FedKD-CPI: Combining the federated knowledge distillation technique to accomplish synergistic compound-protein interaction prediction.

Compound-protein interaction (CPI) prediction is critical in the early stages of drug discovery, narrowing the search space for CPIs and reducing the cost and time required for traditional high-throughput screening. However, CPI-related data are usually distributed across different institutions and their sharing is restricted because of data privacy and intellectual property rights. Constructing a scheme that enhances multi-institutional collaboration to improve prediction accuracy while protecting data privacy is essential.

TOM40 as a prognostic oncogene for oral squamous cell carcinoma prognosis.

Background: To investigate the role of the translocase of the outer mitochondrial membrane 40 (TOM40) in oral squamous cell carcinoma (OSCC) with the aim of identifying new biomarkers or potential therapeutic targets.

Methods: TOM40 expression level in OSCC was evaluated using datasets downloaded from The Cancer Genome Atlas (TCGA), as well as clinical data. The correlation between TOM40 expression level and the clinicopathological parameters and survival were analyzed in TCGA.

Efficient evidence selection for systematic reviews in traditional Chinese medicine.

Purpose: The process of searching for and selecting clinical evidence for systematic reviews (SRs) or clinical guidelines is essential for researchers in Traditional Chinese medicine (TCM). However, this process is often time-consuming and resource-intensive. In this study, we introduce a novel precision-preferred comprehensive information extraction and selection procedure to enhance both the efficiency and accuracy of evidence selection for TCM practitioners.

Massively parallel characterization of transcriptional regulatory elements.

The human genome contains millions of candidate cis-regulatory elements (cCREs) with cell-type-specific activities that shape both health and many disease states. However, we lack a functional understanding of the sequence features that control the activity and cell-type-specific features of these cCREs. Here we used lentivirus-based massively parallel reporter assays (lentiMPRAs) to test the regulatory activity of more than 680,000 sequences, representing an extensive set of annotated cCREs among three cell types (HepG2, K562 and WTC11), and found that 41.

Genetic algorithm optimized BP neural network for fast reconstruction of three-dimensional radiation field.

The three-dimensional radiation field is an important database reflecting the radioactivity distribution in a nuclear facility. It is of great significance to accurately and quickly grasp the radiation dose field distribution to implement radiation protection. Presently, majority of radiation field reconstruction algorithms concentrate on two-dimensional reconstruction and can only measure on a regular grid.

DECT sparse reconstruction based on hybrid spectrum data generative diffusion model.

Purpose: Dual-energy computed tomography (DECT) enables the differentiation of different materials. Additionally, DECT images consist of multiple scans of the same sample, revealing information similarity within the energy domain. To leverage this information similarity and address safety concerns related to excessive radiation exposure in DECT imaging, sparse view DECT imaging is proposed as a solution.

Metastatic Lung Lesion Changes in Follow-up Chest CT: The Advantage of Deep Learning Simultaneous Analysis of Prior and Current Scans With SimU-Net.

Purpose: Radiological follow-up of oncology patients requires the detection of metastatic lung lesions and the quantitative analysis of their changes in longitudinal imaging studies. Our aim was to evaluate SimU-Net, a novel deep learning method for the automatic analysis of metastatic lung lesions and their temporal changes in pairs of chest CT scans.

Materials And Methods: SimU-Net is a simultaneous multichannel 3D U-Net model trained on pairs of registered prior and current scans of a patient.

Correlation Between Dynamic Contrast-Enhanced CT Imaging Signs and Differentiation Grade and Microvascular Invasion of Hepatocellular Carcinoma.

Objective: This study aimed to investigate how dynamic contrast-enhanced CT imaging signs correlate with the differentiation grade and microvascular invasion (MVI) of hepatocellular carcinoma (HCC), and to assess their predictive value for MVI when combined with clinical characteristics.

Methods: We conducted a retrospective analysis of clinical data from 232 patients diagnosed with HCC at our hospital between 2021 and 2022. All patients underwent preoperative enhanced CT scans, laboratory tests, and postoperative pathological examinations.

An empirical study of LLaMA3 quantization: from LLMs to MLLMs.

The LLaMA family, a collection of foundation language models ranging from 7B to 65B parameters, has become one of the most powerful open-source large language models (LLMs) and the popular LLM backbone of multi-modal large language models (MLLMs), widely used in computer vision and natural language understanding tasks. In particular, LLaMA3 models have recently been released and have achieved impressive performance in various domains with super-large scale pre-training on over 15T tokens of data. Given the wide application of low-bit quantization for LLMs in resource-constrained scenarios, we explore LLaMA3's capabilities when quantized to low bit-width.

Feasibility of long-range telesurgical robotic radical gastrectomy in a live porcine model.

Background: Telesurgery has been made increasingly possible with the advancements in robotic surgical platforms and network connectivity. However, long-distance transnational complex robotic surgeries such as gastrectomy have yet to be attempted.

Methods: Multiple transnational network connections by Science Innovation Network (SINET), Japan Gigabit Network (JGN), and Arterial Research and Education Network in Asia-Pacific (ARENA-PAC) were established and tested by multiple surgeons in a dry box model.

Clinical Decision Support Using Speech Signal Analysis: Systematic Scoping Review of Neurological Disorders.

Background: Digital biomarkers are increasingly used in clinical decision support for various health conditions. Speech features as digital biomarkers can offer insights into underlying physiological processes due to the complexity of speech production. This process involves respiration, phonation, articulation, and resonance, all of which rely on specific motor systems for the preparation and execution of speech.

Deep Learning for Obstructive Sleep Apnea Detection and Severity Assessment: A Multimodal Signals Fusion Multiscale Transformer Model.

Purpose: To develop a deep learning (DL) model for obstructive sleep apnea (OSA) detection and severity assessment and provide a new approach for convenient, economical, and accurate disease detection.

Methods: Considering medical reliability and acquisition simplicity, we used electrocardiogram (ECG) and oxygen saturation (SpO) signals to develop a multimodal signal fusion multiscale Transformer model for OSA detection and severity assessment. The proposed model comprises signal preprocessing, feature extraction, cross-modal interaction, and classification modules.

Intelligent two-phase dual authentication framework for Internet of Medical Things.

The Internet of Medical Things (IoMT) has revolutionized healthcare by bringing real-time monitoring and data-driven treatments. Nevertheless, the security of communication between IoMT devices and servers remains a huge problem because of the inherent sensitivity of the health data and susceptibility to cyber threats. Current security solutions, including simple password-based authentication and standard Public Key Infrastructure (PKI) approaches, typically do not achieve an appropriate balance between security and low computational overhead, resulting in the possibility of performance bottlenecks and increased vulnerability to attacks.

RBBP6 anchors pre-mRNA 3' end processing to nuclear speckles for efficient gene expression.

Pre-mRNA 3' processing is an integral step in mRNA biogenesis. However, where this process occurs in the nucleus remains unknown. Here, we demonstrate that nuclear speckles (NSs), membraneless organelles enriched with splicing factors, are major sites for pre-mRNA 3' processing in human cells.

Semi-supervised medical image segmentation via weak-to-strong perturbation consistency and edge-aware contrastive representation.

Despite that supervised learning has demonstrated impressive accuracy in medical image segmentation, its reliance on large labeled datasets poses a challenge due to the effort and expertise required for data acquisition. Semi-supervised learning has emerged as a potential solution. However, it tends to yield satisfactory segmentation performance in the central region of the foreground, but struggles in the edge region.

A novel lightweight deep learning based approaches for the automatic diagnosis of gastrointestinal disease using image processing and knowledge distillation techniques.

Background: Gastrointestinal (GI) diseases pose significant challenges for healthcare systems, largely due to the complexities involved in their detection and treatment. Despite the advancements in deep neural networks, their high computational demands hinder their practical use in clinical environments.

Objective: This study aims to address the computational inefficiencies of deep neural networks by proposing a lightweight model that integrates model compression techniques, ConvLSTM layers, and ConvNext Blocks, all optimized through Knowledge Distillation (KD).

Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar.

Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this paper, we propose a multiscale residual weighted classification network with large-scale, medium-scale, and small-scale residual networks.

Retrieving and Identifying Remnants of Artefacts on Local Devices Using Sync.com Cloud.

Most current research in cloud forensics is focused on tackling the challenges encountered by forensic investigators in identifying and recovering artifacts from cloud devices. These challenges arise from the diverse array of cloud service providers as each has its distinct rules, guidelines, and requirements. This research proposes an investigation technique for identifying and locating data remnants in two main stages: artefact collection and evidence identification.