A diagonal masking self-attention-based multi-scale network for motor imagery classification.

Electroencephalography (EEG)-based motor imagery (MI) is a promising paradigm for brain-computer interface (BCI), but the non-stationarity and low signal-to-noise ratio of EEG signals make it a challenging task. To achieve high-precision motor imagery classification, we propose a Diagonal Masking Self-Attention-based Multi-Scale Network (DMSA-MSNet) to fully develop, extract, and emphasize features from different scales. First, for local features, a multi-scale temporal-spatial block is proposed to extract features from different receptive fields. Second, an adaptive branch fusion block is specifically designed to bridge the semantic gap between these coded features from different scales. Finally, in order to analyze global information over long ranges, adiagonal masking self-attentionblock is introduced, whichhighlightsthe most valuable features in the data. The proposed DMSA-MSNet outperforms state-of-the-art models on the BCI Competition IV 2a and the BCI Competition IV 2b datasets. Our study achieves rich information extraction from EEG signals and provides an effective solution for motor imagery classification. The code is available at https://github.com/HyperSystemAndImageProc/A-diagonal-masking-self-attention-based-Multi-Scale-Network-for-motor-imagery-classification. .

Dataset of weekly intra-treatment diffusion weighted imaging in head and neck cancer patients treated with MR-Linac.

Radiation therapy (RT) is a crucial treatment for head and neck squamous cell carcinoma (HNSCC); however, it can have adverse effects on patients' long-term function and quality of life. Biomarkers that can predict tumor response to RT are being explored to personalize treatment and improve outcomes. While tissue and blood biomarkers have limitations, imaging biomarkers derived from magnetic resonance imaging (MRI) offer detailed information. The integration of MRI and a linear accelerator in the MR-Linac system allows for MR-guided radiation therapy (MRgRT), offering precise visualization and treatment delivery. This data descriptor offers a valuable repository for weekly intra-treatment diffusion-weighted imaging (DWI) data obtained from head and neck cancer patients. By analyzing the sequential DWI changes and their correlation with treatment response, as well as oncological and survival outcomes, the study provides valuable insights into the clinical implications of DWI in HNSCC.

A Sinh-Cosh-Enhanced DBO Algorithm Applied to Global Optimization Problems.

The Dung beetle optimization (DBO) algorithm, devised by Jiankai Xue in 2022, is known for its strong optimization capabilities and fast convergence. However, it does have certain limitations, including insufficiently random population initialization, slow search speed, and inadequate global search capabilities. Drawing inspiration from the mathematical properties of the Sinh and Cosh functions, we proposed a new metaheuristic algorithm, Sinh-Cosh Dung Beetle Optimization (SCDBO). By leveraging the Sinh and Cosh functions to disrupt the initial distribution of DBO and balance the development of rollerball dung beetles, SCDBO enhances the search efficiency and global exploration capabilities of DBO through nonlinear enhancements. These improvements collectively enhance the performance of the dung beetle optimization algorithm, making it more adept at solving complex real-world problems. To evaluate the performance of the SCDBO algorithm, we compared it with seven typical algorithms using the CEC2017 test functions. Additionally, by successfully applying it to three engineering problems, robot arm design, pressure vessel problem, and unmanned aerial vehicle (UAV) path planning, we further demonstrate the superiority of the SCDBO algorithm.

A Novel Positive-Contrast Magnetic Resonance Imaging Line Marker for High-Dose-Rate (HDR) MRI-Assisted Radiosurgery (MARS).

Magnetic resonance imaging (MRI) can facilitate accurate organ delineation and optimal dose distributions in high-dose-rate (HDR) MRI-Assisted Radiosurgery (MARS). Its use for this purpose has been limited by the lack of positive-contrast MRI markers that can clearly delineate the lumen of the HDR applicator and precisely show the path of the HDR source on T1- and T2-weighted MRI sequences. We investigated a novel MRI positive-contrast HDR brachytherapy or interventional radiotherapy line marker, C4:S, consisting of C4 (visible on T1-weighted images) complexed with saline. Longitudinal relaxation time (T1) and transverse relaxation time (T2) for C4:S were measured on a 1.5 T MRI scanner. High-density polyethylene (HDPE) tubing filled with C4:S as an HDR brachytherapy line marker was tested for visibility on T1- and T2-weighted MRI sequences in a tissue-equivalent female ultrasound training pelvis phantom. Relaxivity measurements indicated that C4:S solution had good T1-weighted contrast (relative to oil [fat] signal intensity) and good T2-weighted contrast (relative to water signal intensity) at both room temperature (relaxivity ratio > 1; r2/r1 = 1.43) and body temperature (relaxivity ratio > 1; r2/r1 = 1.38). These measurements were verified by the positive visualization of the C4:S (C4/saline 50:50) HDPE tube HDR brachytherapy line marker on both T1- and T2-weighted MRI sequences. Orientation did not affect the relaxivity of the C4:S contrast solution. C4:S encapsulated in HDPE tubing can be visualized as a positive line marker on both T1- and T2-weighted MRI sequences. MRI-guided HDR planning may be possible with these novel line markers for HDR MARS for several types of cancer.

Disentangled Generation With Information Bottleneck for Enhanced Few-Shot Learning.

Few-shot learning (FSL) poses a significant challenge in classifying unseen classes with limited samples, primarily stemming from the scarcity of data. Although numerous generative approaches have been investigated for FSL, their generation process often results in entangled outputs, exacerbating the distribution shift inherent in FSL. Consequently, this considerably hampers the overall quality of the generated samples. Addressing this concern, we present a pioneering framework called DisGenIB, which leverages an Information Bottleneck (IB) approach for Disentangled Generation. Our framework ensures both discrimination and diversity in the generated samples, simultaneously. Specifically, we introduce a groundbreaking Information Theoretic objective that unifies disentangled representation learning and sample generation within a novel framework. In contrast to previous IB-based methods that struggle to leverage priors, our proposed DisGenIB effectively incorporates priors as invariant domain knowledge of sub-features, thereby enhancing disentanglement. This innovative approach enables us to exploit priors to their full potential and facilitates the overall disentanglement process. Moreover, we establish the theoretical foundation that reveals certain prior generative and disentanglement methods as special instances of our DisGenIB, underscoring the versatility of our proposed framework. To solidify our claims, we conduct comprehensive experiments on demanding FSL benchmarks, affirming the remarkable efficacy and superiority of DisGenIB. Furthermore, the validity of our theoretical analyses is substantiated by the experimental results. Our code is available at https://github.com/eric-hang/DisGenIB.

Biodegradation of atrazine and nicosulfuron by Streptomyces nigra LM01: Performance, degradative pathway, and possible genes involved.

Microbial herbicide degradation is an efficient bioremediation method. In this study, a strain of Streptomyces nigra, LM01, which efficiently degrades atrazine and nicosulfuron, was isolated from a corn field using a direct isolation method. The degradation effects of the identified strain on two herbicides were investigated and optimized using an artificial neural network. The maximum degradation rates of S. nigra LM01 were 58.09 % and 42.97 % for atrazine and nicosulfuron, respectively. The degradation rate of atrazine in the soil reached 67.94 % when the concentration was 108 CFU/g after 5 d and was less effective than that of nicosulfuron. Whole genome sequencing of strain LM01 helped elucidate the possible degradation pathways of atrazine and nicosulfuron. The protein sequences of strain LM01 were aligned with the sequences of the degraded proteins of the two herbicides by using the National Center for Biotechnology Information platform. The sequence (GE005358, GE001556, GE004212, GE005218, GE004846, GE002487) with the highest query cover was retained and docked with the small-molecule ligands of the herbicides. The results revealed a binding energy of - 6.23 kcal/mol between GE005358 and the atrazine ligand and - 6.66 kcal/mol between GE002487 and the nicosulfuron ligand.

Early Endonasal Dacryocystorhinostomy for Acute Dacryocystitis: A Systematic Review and Meta-Analysis.

OBJECTIVE: The aim of this meta-analysis is to compare the outcomes of early endonasal dacryocystorhinostomy (DCR) with delayed DCR in the treatment of acute dacryocystitis (AD). METHODS: A comprehensive electronic search of PubMed, Embase, Web of Science, and the Cochrane Library databases was conducted up to November 11, 2023. Data synthesis was performed using Review Manager 5.4, and forest plots were generated for each outcome measure. Potential publication bias was assessed using funnel plots and Egger's test. RESULTS: Six studies involving 288 patients were included in the meta-analysis. Overall, the success rate of early endonasal DCR was comparable to that in the delayed DCR group (odds ratio [OR] = 1.52, 95% confidence interval [CI]: 0.81-2.85, P = .19). Furthermore, in comparison with the delayed DCR group, early endonasal DCR significantly reduced the time for medial canthus swelling resolution (mean differences [MD] = -4.92, 95% CI: -5.46 to 4-.37, P < .00001) and complete resolution of symptoms (MD = -17.70, 95% CI: -23.88 to -11.52, P < .00001). CONCLUSION: Primary early endonasal DCR seems to be a promising and favorable approach for managing AD with comparable efficacy and faster relief of symptoms compared to conventional delayed DCR.

Multi-hop clustering routing protocol design based on simultaneous wireless information and power transfer technology and imperfect spectrum sensing for EH-CRSNs.

Existing clustering routing protocols for multi-hop energy harvesting-cognitive radio sensor networks (EH-CRSNs) generally assume perfect spectrum sensing, which is not aligned with the practical spectrum sensing capabilities of nodes in real networks. Additionally, the severe imbalance in residual energy among cluster heads (CHs) negatively affects the successful data delivery. To resolve these problems, this paper introduces a simultaneous wireless information and power transfer (SWIPT)- and imperfect spectrum sensing-based multi-hop clustering routing protocol (ES-ISSMCRP). ES-ISSMCRP makes full use of downlink EH and intra-cluster SWIPT technologies to replenish and equalize the remaining energy among nodes, further extending network lifespan while maintaining network surveillance capabilities. Specifically, to reduce the adverse impact of imperfect spectrum sensing on network performance and improve energy utilization, this paper proposes an EH-based energy level function and associated selection criteria for CHs and relays, facilitating distributed cluster formation and multi-hop routing selection between clusters. To equalize the residual energy among nodes within a cluster, ES-ISSMCRP protocol enables cluster members (CMs) to decide whether employ SWIPT technology with a power splitting (PS) receiver architecture to transmit energy to their CH while sending data. The actual energy value transmitted by CMs using SWIPT technology is deduced by calculating the PS ratio and the expected energy expenditure of nodes for data transmission. Simulation results show that ES-ISSMCRP protocol offers significant improvements over other comparative protocols in terms of extending network lifespan and enhancing network surveillance capabilities.

Inhibition of spinal BRD4 alleviates pyroptosis and M1 microglia polarization via STING-IRF3 pathway in morphine-tolerant rats.

BACKGROUND: Morphine tolerance has been a challenging medical issue. Neuroinflammation is considered as a critical mechanism for the development of morphine tolerance. Bromodomain-containing protein 4 (BRD4), a key regulator in cell damage and inflammation, participates in the development of chronic pain. However, whether BRD4 is involved in morphine tolerance and the underlying mechanisms remain unknown. METHODS: The morphine-tolerant rat model was established by intrathecal administration of morphine twice daily for 7 days. Behavior test was assessed by a tail-flick latency test. The roles of BRD4, pyroptosis, microglia polarization and related signaling pathways in morphine tolerance were elucidated by Western blot, real-time quantitative polymerase chain reaction, and immunofluorescence. RESULTS: Repeated morphine administration upregulated BRD4 level, induced pyroptosis, and promoted microglia M1-polarization in spinal cord, accompanied by the release of proinflammatory cytokines, such as TNF-α and IL-1ß. JQ-1, a BRD4 antagonist, alleviated the development of morphine tolerance, diminished pyroptosis and induced the switch of microglia from M1 to M2 phenotype. Mechanistically, stimulator of interferon gene (STING)- interferon regulatory factor 3 (IRF3) pathway was activated and the protective effect of JQ-1 against morphine tolerance was at least partially mediated by inhibition of STING-IRF3 pathway. CONCLUSION: This study demonstrated for the first time that spinal BRD4 contributes to pyroptosis and switch of microglia polarization via STING-IRF3 signaling pathway during the development of morphine tolerance, which extend the understanding of the neuroinflammation mechanism of morphine tolerance and provide an alternative strategy for the precaution against of this medical condition.

Enhanced chromium and nitrogen removal by constructing a biofilm reaction system based on denitrifying bacteria preferential colonization theory.

Understanding the developmental characteristics of microbial communities in biofilms is crucial for designing targeted functional microbial enhancements for the remediation of complex contamination scenarios. The strong prioritization effect of microorganisms confers the ability to colonize strains that arrive first dominantly. In this study, the auto-aggregating denitrifying bacterial Pseudomonas stutzeri strain YC-34, which has both nitrogen and chromium removal characteristics, was used as a biological material to form a stable biofilm system based on the principle of dominant colonization and biofortification. The effect of the biofilm system on nitrogen and chromium removal was characterized by measuring the changes in the quality of influent and effluent water. The pattern of biofilm changes was analyzed by measuring biofilm content and thickness and characterizing extracellular polymer substances (EPS). Further analysis of the biofilm microbiota characteristics and potential functions revealed the mechanism of strain YC-34 biofortified biofilm. The results revealed that the biofilm system formed could achieve 90.56% nitrate-nitrogen removal with an average initial nitrate-nitrogen concentration of 51.9 mg/L and 40% chromium removal with an average initial hexavalent chromium Cr(VI) concentration of 7.12 mg/L. The biofilm properties of the system were comparatively analyzed during the biofilm formation period, the fluctuation period of Cr(VI)-stressed water quality, and the stabilization period of Cr(VI)-stressed water quality. The biofilm system may be able to increase the structure of hydrogen bonds, the type of protein secondary structure, and the abundance of amino acid-like components in the EPS, which may confer biofilm tolerance to Cr(VI) stress and allow the system to maintain a stable biofilm structure. Furthermore, microbial characterization indicated an increase in microbial diversity in the face of chromium stress, with an increase in the abundance of nitrogen removal-associated functional microbiota and an increasing trend in the abundance of nitrogen transfer pathways. These results demonstrate that the biofilm system is stable in nitrogen and chromium removal. This bioaugmentation method may provide a new way for the remediation of heavy metal-polluted water bodies and also provides theoretical and application parameters for the popularization and application of biofilm systems.

Hyperspectral upgrade solution for biomicroscope combined with Transformer network to classify infectious bacteria.

Infectious diseases caused by bacterial pathogens pose a significant public health threat, emphasizing the need for swift and accurate bacterial species detection methods. Hyperspectral microscopic imaging (HMI) offers nondestructive, rapid, and data-rich advantages, making it a promising tool for microbial detection. In this research, we present a highly compatible and cost-effective approach to extend a standard biomicroscope system into a hyperspectral biomicroscope using a prism-grating-prism configuration. Using this prototype, we generate 600 hyperspectral data cubes for Listeria, Bacillus typhi, Bacillus pestis, and Bacillus anthracis. Additionally, we propose a Transformer-based classification network that achieves a 99.44% accuracy in classifying these infectious pathogens, outperforming traditional methods. Our results suggest that the successful combination of HMI and the optimized Transformer-based classification network highlights the potential for rapid and precise detection of infectious disease pathogens .

The effect of modifier and a water-soluble fertilizer on two forages grown in saline-alkaline soil.

Saline-alkali soil significantly impairs crop growth. This research employs the impacts of the modifier and water-soluble fertilizer, as well as their interaction, on the root systems of alfalfa and leymus chinensis in saline-alkali soil. The results exhibit that the hydrochar source modifier effectively enhances the root growth of both forage species. There are certain improvements in the root growth indicators of both crops at a dosage of 20 g/kg. Root enzyme activity and rhizosphere soil enzyme activity are enhanced in alfalfa, showing significant improvements in the first planting compared to the second planting. The application of water-soluble fertilizers also promotes root growth and root dehydrogenase activity. The root dehydrogenase activity of alfalfa and leymus chinensis are enhanced 62.18% and 10.15% in first planting than that of blank, respectively. Additionally, the two-factor variance analysis revealed a correlation between rhizosphere soil enzyme activity and changes in root traits. Higher rhizosphere soil enzyme activity is observed in conjunction with better root growth. The combined application of a modifier and water-soluble fertilizer has demonstrated a significant interaction effect on various aspects of the first planting of alfalfa and leymus chinensis. Moreover, the combined application of the modifier and water-soluble fertilizer has yielded superior results when compared to the individual application of either the modifier or the water-soluble fertilizer alone. This combined approach has proven effective in improving saline-alkali soil conditions and promoting crop growth in such challenging environments.

Enhanced humification via lignocellulosic pretreatment in remediation of agricultural solid waste.

Stover and manure are the main solid waste in agricultural industry. The generation of stover and manure could lead to serious environmental pollution if not handled properly. Composting is the potential greener solution to remediate and reduce agricultural solid waste, through which stover and manure could be remediated and converted into organic fertilizer, but the long composting period and low efficiency of humic substance production are the key constraints in such remediation approach. In this study, we explore the effect of lignocellulose selective removal on composting by performing chemical pretreatment on agricultural waste followed by utilization of biochar to assist in the remediation by co-composting treatment and reveal the impacts of different lignocellulose component on organic fertilizer production. Aiming to discover the key factors that influence humification during composting process and improve the composting quality as well as comprehensive utilization of agricultural solid waste. The results demonstrated that the removal of selective lignin or hemicellulose led to the shift of abundances lignocellulose-degrading bacteria, which in turn accelerated the degradation of lignocellulose by almost 51.2%. The process also facilitated the remediation of organic waste via humification and increased the humic acid level and HA/FA ratio in just 22 days. The richness of media relies on their lignocellulose content, which is negatively correlated with total nitrogen content, humic acid (HA) content, germination index (GI), and pH, but positively correlated with fulvic acid (FA) and total organic carbon (TOC). The work provides a potential cost effective and efficient framework for agricultural solid waste remediation and reduction.

Regulating Microstructure and Macroscopic Properties in Saturated Salt Solutions Containing Disordered Anions and Cations by Magnetic Field.

Saturated aqueous salt solutions have diverse applications in food production, mineral processing, pharmaceuticals, and environmental monitoring. However, the random and disordered arrangement of ions in these solutions poses limitations across different fields. In this study, we employ magnetic fields to regulate the disordered arrangement by a comprehensive methodology combining contact angle measurement, Raman spectroscopy, X-ray diffraction, and molecular dynamics simulations on saturated KCl solutions. Our findings reveal that weak magnetic fields impede the formation of K-Cl contact pairs and disrupt hydrogen bond networks, particularly DDAA and free OH types. However, they facilitate the interaction between water molecules and ions, leading to an increase in the number of K-O and Cl-H contact pairs, along with an expansion in ion hydration radius. These changes affect macroscopic properties, including the interaction with solid substrates and potential solubility increases. Our experimental and simulation results mutually validate each other, contributing to a theoretical framework for studying magnetic field-material interactions.

Comparative Analysis of Molecular Landscape in Mouse Models and Patients Reveals Conserved Inflammation Pathways in Age-Related Macular Degeneration.

Purpose: The purpose of this study was to identify key genes and their regulatory networks that are conserved in mouse models of age-related macular degeneration (AMD) and human AMD. Methods: Retinal RNA-Seq was performed in laser-induced choroidal neovascularization (CNV) mice at day 3 and day 7 after photocoagulation. Mass spectrometry-based proteomic analysis was performed with retinas collected at day 3. Retinal RNA-Seq data was further compared among mouse models of laser-induced CNV and NaIO3-induced retinal degeneration (RD) and a large AMD cohort. Results: Retinal RNA-Seq revealed upregulated genes and pathways related to innate immunity and inflammation in mice with CNV, with more profound changes at the early stage (day 3). Proteomic analysis further validated these differentially expressed genes and their networks in retinal inflammation during CNV. Notably, the most evident overlap in the retina of mice with laser-induced CNV and NaIO3-induced RD was the upregulation of inflammation-related genes, pointing to a common vital role of retinal inflammation in the early stage for both mouse AMD models. Further comparative transcriptomic analysis of the mouse AMD models and human AMD identified 48 conserved genes mainly involved in inflammation response. Among them, B2M, C3, and SERPING1 were upregulated in all stages of human AMD and the mouse AMD models compared to controls. Conclusions: Our study demonstrates conserved molecular changes related to retinal inflammation in mouse AMD models and human AMD and provides new insight into the translational application of these mouse models in studying AMD mechanisms and treatments.

Interleukin-18 in chronic pain: Focus on pathogenic mechanisms and potential therapeutic targets.

Chronic pain has been proven to be an independent disease, other than an accompanying symptom of certain diseases. Interleukin-18 (IL-18), a pro-inflammatory cytokine with pleiotropic biological effects, participates in immune modulation, inflammatory response, tumor growth, as well as the process of chronic pain. Compelling evidence suggests that IL-18 is upregulated in the occurrence of chronic pain. Antagonism or inhibition of IL-18 expression can alleviate the occurrence and development of chronic pain. And IL-18 is located in microglia, while IL-18R is mostly located in astrocytes in the spinal cord. This indicates that the interaction between microglia and astrocytes mediated by the IL-18/IL-18R axis is involved in the occurrence of chronic pain. In this review, we described the role and mechanism of IL-18 in different types of chronic pain. This review provides strong evidence that IL-18 is a potential therapeutic target in pain management.

A look-up-table development to facilitate CT simulation of MR-Linac treatment.

While current MR-Linac (MRL) treatment workflows utilize a large table overlay during CT simulation to convert indexing between the two machines, we developed a look-up-table (LUT) as an alternative approach. After populating the LUT, index conversion factors were verified at three separate table locations. The resultant root-mean-square isocenter shifts on the MRL were 0.04/0.08 cm, 0.08/0.07 cm, and 0.09/0.08 cm with/without using the table overlay during simulation in the lateral, longitudinal, and vertical directions, respectively, which is within registration tolerance. Clinical implementation of the LUT has resulted in a more efficient MRL treatment workflow while maintaining accurate patient setup.

H2H rehabilitation care promotes high quality recovery of patients with lung cancer comorbid with chronic obstructive pulmonary disease.

H2H is a patient and family-centered approach that integrates hospital and home care, emphasizing continuity, individualized rehabilitation training, and the active participation of patients and their families. However, it is still unclear whether H2H improves the efficacy for patients with COPD and lung cancer. This study investigated the efficacy of Hospital-to-Home (H2H) rehabilitation nursing for lung cancer patients with Chronic Obstructive Pulmonary Disease (COPD). We conducted a retrospective analysis to the clinical data of 95 patients treated in the Pingdingshan University Medical College from January 2018 to January 2020. We compared the effects of conventional nursing (control group, n=45) and H2H nursing (observation group, n=50) on the clinical efficacy for the patients. In this study, after nursing intervention, the quality of life and adverse emotions in the observation group were significantly improved compared to the control group (P<0.0001). Moreover, the lung function and blood oxygen saturation of patients in the H2H nursing model improved after the intervention (P<0.0001). In addition, there was no difference in the 3-year survival rate between the control group and the observation group (P=0.260). Multivariate COX regression analysis showed that the nursing scheme had no effect on the patients' 3-year survival, but the SAS score, SDS score, and CEA were independent prognostic factors affecting the 3-year survival rate (P<0.05). These results demonstrate that H2H rehabilitation care significantly improves the quality of life, emotional health, and lung function of patients with COPD and lung cancer, but does not affect the patients' 3-year survival rate.

Development and implementation of optimized endogenous contrast sequences for delineation in adaptive radiotherapy on a 1.5T MR-linear-accelerator: a prospective R-IDEAL stage 0-2a quantitative/qualitative evaluation of in vivo site-specific quality-assurance using a 3D T2 fat-suppressed platform for head and neck cancer.

Purpose: To improve segmentation accuracy in head and neck cancer (HNC) radiotherapy treatment planning for the 1.5T hybrid magnetic resonance imaging/linear accelerator (MR-Linac), three-dimensional (3D), T2-weighted, fat-suppressed magnetic resonance imaging sequences were developed and optimized. Approach: After initial testing, spectral attenuated inversion recovery (SPAIR) was chosen as the fat suppression technique. Five candidate SPAIR sequences and a nonsuppressed, T2-weighted sequence were acquired for five HNC patients using a 1.5T MR-Linac. MR physicists identified persistent artifacts in two of the SPAIR sequences, so the remaining three SPAIR sequences were further analyzed. The gross primary tumor volume, metastatic lymph nodes, parotid glands, and pterygoid muscles were delineated using five segmentors. A robust image quality analysis platform was developed to objectively score the SPAIR sequences on the basis of qualitative and quantitative metrics. Results: Sequences were analyzed for the signal-to-noise ratio and the contrast-to-noise ratio and compared with fat and muscle, conspicuity, pairwise distance metrics, and segmentor assessments. In this analysis, the nonsuppressed sequence was inferior to each of the SPAIR sequences for the primary tumor, lymph nodes, and parotid glands, but it was superior for the pterygoid muscles. The SPAIR sequence that received the highest combined score among the analysis categories was recommended to Unity MR-Linac users for HNC radiotherapy treatment planning. Conclusions: Our study led to two developments: an optimized, 3D, T2-weighted, fat-suppressed sequence that can be disseminated to Unity MR-Linac users and a robust image quality analysis pathway that can be used to objectively score SPAIR sequences and can be customized and generalized to any image quality optimization protocol. Improved segmentation accuracy with the proposed SPAIR sequence will potentially lead to improved treatment outcomes and reduced toxicity for patients by maximizing the target coverage and minimizing the radiation exposure of organs at risk.

MAUNext: a lightweight segmentation network for medical images.

Objective. The primary objective of this study is to enhance medical image segmentation techniques for clinical research by prioritizing accuracy and the number of parameters.Approach. To achieve this objective, a novel codec-based MAUNext approach is devised, focusing on lightweight backbone design and the integration of skip connections utilizing multiscale, attention mechanism, and other strategic components. The approach is composed of three core modules: a multi-scale attentional convolution module for improved accuracy and parameter reduction, a collaborative neighbourhood-attention MLP encoding module to enhance segmentation performance, and a tiny skip-connected cross-layer semantic fusion module to bridge the semantic gap between encoder and decoder.Main results. The study extensively evaluates the MAUNext approach alongside eight state-of-the-art methods on three renowned datasets: Kagglelung, ISIC, and Brain. The experimental outcomes robustly demonstrate that the proposed approach surpasses other methods in terms of both parameter numbers and accuracy. This achievement holds promise for effectively addressing medical image segmentation tasks.Significance. Automated medical image segmentation, particularly in organ and lesion identification, plays a pivotal role in clinical diagnosis and treatment. Manual segmentation is resource-intensive, thus automated methods are highly valuable. The study underscores the clinical significance of automated segmentation by providing an advanced solution through the innovative MAUNext approach. This approach offers substantial improvements in accuracy and efficiency, which can significantly aid clinical decision-making and patient treatment.