Tumor regression and safe distance of distal margin after neoadjuvant therapy for rectal cancer.

Neoadjuvant therapy has been widely employed in the treatment of rectal cancer, demonstrating its utility in reducing tumor volume, downstaging tumors, and improving patient prognosis. It has become the standard preoperative treatment modality for locally advanced rectal cancer. However, the efficacy of neoadjuvant therapy varies significantly among patients, with notable differences in tumor regression outcomes. In some cases, patients exhibit substantial tumor regression, even achieving pathological complete response. The assessment of tumor regression outcomes holds crucial significance for determining surgical approaches and establishing safe margins. Nonetheless, current research on tumor regression patterns remains limited, and there is considerable controversy surrounding the determination of a safe margin after neoadjuvant therapy. In light of these factors, this study aims to summarize the primary patterns of tumor regression observed following neoadjuvant therapy for rectal cancer, categorizing them into three types: tumor shrinkage, tumor fragmentation, and mucinous lake formation. Furthermore, a comparison will be made between gross and microscopic tumor regression, highlighting the asynchronous nature of regression in the two contexts. Additionally, this study will analyze the safety of non-surgical treatment in patients who achieve complete clinical response, elucidating the necessity of surgical intervention. Lastly, the study will investigate the optimal range for safe surgical resection margins and explore the concept of a safe margin distance post-neoadjuvant therapy.

Phasic/tonic glial GABA differentially transduce for olfactory adaptation and neuronal aging.

Phasic (fast) and tonic (sustained) inhibition of γ-aminobutyric acid (GABA) are fundamental for regulating day-to-day activities, neuronal excitability, and plasticity. However, the mechanisms and physiological functions of glial GABA transductions remain poorly understood. Here, we report that the AMsh glia in Caenorhabditis elegans exhibit both phasic and tonic GABAergic signaling, which distinctively regulate olfactory adaptation and neuronal aging. Through genetic screening, we find that GABA permeates through bestrophin-9/-13/-14 anion channels from AMsh glia, which primarily activate the metabolic GABAB receptor GBB-1 in the neighboring ASH sensory neurons. This tonic action of glial GABA regulates the age-associated changes of ASH neurons and olfactory responses via a conserved signaling pathway, inducing neuroprotection. In addition, the calcium-evoked, vesicular glial GABA release acts upon the ionotropic GABAA receptor LGC-38 in ASH neurons to regulate olfactory adaptation. These findings underscore the fundamental significance of glial GABA in maintaining healthy aging and neuronal stability.

Exploring the application and future outlook of Artificial intelligence in pancreatic cancer.

Pancreatic cancer, an exceptionally malignant tumor of the digestive system, presents a challenge due to its lack of typical early symptoms and highly invasive nature. The majority of pancreatic cancer patients are diagnosed when curative surgical resection is no longer possible, resulting in a poor overall prognosis. In recent years, the rapid progress of Artificial intelligence (AI) in the medical field has led to the extensive utilization of machine learning and deep learning as the prevailing approaches. Various models based on AI technology have been employed in the early screening, diagnosis, treatment, and prognostic prediction of pancreatic cancer patients. Furthermore, the development and application of three-dimensional visualization and augmented reality navigation techniques have also found their way into pancreatic cancer surgery. This article provides a concise summary of the current state of AI technology in pancreatic cancer and offers a promising outlook for its future applications.

High-performance presurgical differentiation of glioblastoma and metastasis by means of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics.

OBJECTIVES: To evaluate the performance of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics in distinguishing between glioblastoma (Gb) and solitary brain metastasis (SBM). MATERIALS AND METHODS: In this retrospective study, NODDI images were curated from 109 patients with Gb (n = 57) or SBM (n = 52). Automatically segmented multiple volumes of interest (VOIs) encompassed the main tumor regions, including necrosis, solid tumor, and peritumoral edema. Radiomics features were extracted for each main tumor region, using three NODDI parameter maps. Radiomics models were developed based on these three NODDI parameter maps and their amalgamation to differentiate between Gb and SBM. Additionally, radiomics models were constructed based on morphological magnetic resonance imaging (MRI) and diffusion imaging (diffusion-weighted imaging [DWI]; diffusion tensor imaging [DTI]) for performance comparison. RESULTS: The validation dataset results revealed that the performance of a single NODDI parameter map model was inferior to that of the combined NODDI model. In the necrotic regions, the combined NODDI radiomics model exhibited less than ideal discriminative capabilities (area under the receiver operating characteristic curve [AUC] = 0.701). For peritumoral edema regions, the combined NODDI radiomics model achieved a moderate level of discrimination (AUC = 0.820). Within the solid tumor regions, the combined NODDI radiomics model demonstrated superior performance (AUC = 0.904), surpassing the models of other VOIs. The comparison results demonstrated that the NODDI model was better than the DWI and DTI models, while those of the morphological MRI and NODDI models were similar. CONCLUSION: The NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM. CLINICAL RELEVANCE STATEMENT: The NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM, and radiomics features can be incorporated into the multidimensional phenotypic features that describe tumor heterogeneity. KEY POINTS: • The neurite orientation dispersion and density imaging (NODDI) radiomics model showed promising performance for preoperative discrimination between glioblastoma and solitary brain metastasis. • Compared with other tumor volumes of interest, the NODDI radiomics model based on solid tumor regions performed best in distinguishing the two types of tumors. • The performance of the single-parameter NODDI model was inferior to that of the combined-parameter NODDI model.

Efficient nitrate and Cr(VI) removal by denitrifier: The mechanism of S. oneidensis MR-1 promoting electron production, transportation and consumption.

When Cr(VI) and nitrate coexist, the efficiency of both bio-denitrification and Cr(VI) bio-reduction is poor because chromate hinders bacterial normal functions (i.e., electron production, transportation and consumption). Moreover, under anaerobic condition, the method about efficient nitrate and Cr(VI) removal remained unclear. In this paper, the addition of Shewanella oneidensis MR-1 to promote the electron production, transportation and consumption of denitrifier and cause an increase in the removal of nitrate and Cr(VI). The efficiency of nitrate and Cr(VI) removal accomplished by P. denitrificans as a used model denitrifier increased respectively from 51.3% to 96.1% and 34.3% to 99.8% after S. oneidensis MR-1 addition. The mechanism investigations revealed that P. denitrificans provided S. oneidensis MR-1 with lactate, which was utilized to secreted riboflavin and phenazine by S. oneidensis MR-1. The riboflavin served as coenzymes of cellular reductants (i.e., thioredoxin and glutathione) in P. denitrificans, which created favorable intracellular microenvironment conditions for electron generation. Meanwhile, phenazine promoted biofilm formation, which increased the adsorption of Cr(VI) on the cell surface and accelerated the Cr(VI) reduction by membrane bound chromate reductases thereby reducing damage to other enzymes respectively. Overall, this strategy reduced the negative effect of chromate, thus improved the generation, transportation, and consumption of electrons. SYNOPSIS: The presence of S. oneidensis MR-1 facilitated nitrate and Cr(VI) removal by P. denitrificans through decreasing the negative effect of chromate due to the metabolites' secretion.

Accelerated Dynamic Reconstruction in Metal-Organic Frameworks with Ligand Defects for Selective Electrooxidation of Amines to Azos Coupling with Hydrogen Production.

Electrosynthesis coupled hydrogen production (ESHP) mostly involves catalyst reconstruction in aqueous phase, but accurately identifying and controlling the process is still a challenge. Herein, we modulated the electronic structure and exposed unsaturated sites of metal-organic frameworks (MOFs) via ligand defect to promote the reconstruction of catalyst for azo electrosynthesis (ESA) coupled with hydrogen production overall reaction. The monolayer Ni-MOFs achieved 89.8 % Faraday efficiency and 90.8 % selectivity for the electrooxidation of 1-methyl-1H-pyrazol-3-amine (Pyr-NH2) to azo, and an 18.5-fold increase in H2 production compared to overall water splitting. Operando X-ray absorption fine spectroscopy (XAFS) and various in situ spectroscopy confirm that the ligand defect promotes the potential dependent dynamic reconstruction of Ni(OH)2 and NiOOH, and the reabsorption of ligand significantly lowers the energy barrier of rate-determining step (*Pyr-NH to *Pyr-N). This work provides theoretical guidance for modulation of electrocatalyst reconstruction to achieve highly selective ESHP.

Differential influences of rest tremor on brain fiber architecture in essential tremor and Parkinson's disease.

BACKGROUND: Rest tremor is a movement disorder commonly found in diseases like Parkinson's disease (PD) and essential tremor (ET). Rest tremor typically shows slower progression in PD, but more severe progression in ET. However, the underlying white matter organization of rest tremor behind PD and ET remains unclear. METHODS: This study included 57 ET patients (40 without rest tremor (ETWR), 17 with rest tremor (ETRT)), 68 PD patients (34 without rest tremor (PDWR), 34 with rest tremor (PDRT)), and 62 normal controls (NC). Fixel-based analysis was used to evaluate the structural changes of white matter in rest tremor in these different diseases. RESULTS: The fiber-bundle cross-section (FC) of the right non-decussating dentato-rubro-thalamic tract and several fibers outside the dentato-rubro-thalamic pathway in ETWR were significantly higher than that in NC. The fiber density and cross-section of the left nigro-pallidal in PDWR is significantly lower than that in NC, while the FC of bilateral nigro-pallidal in PDRT is significantly lower than that in NC. CONCLUSION: ET patients with pure action tremor showed over-activation of fiber tracts. However, when superimposed with rest tremor, ET patients no longer exhibited over-activation of fiber tracts, but rather showed a trend of fiber tract damage. Except for the nigro-pallidal degeneration in all PD, PDRT will not experience further deterioration in fiber organization. These results provide important insights into the unique effects of rest tremor on brain fiber architecture in ET and PD.

In vitro digestion and fecal fermentation of selenocompounds: impact on gut microbiota, antioxidant activity, and short-chain fatty acids.

Selenium bioavailability is critically influenced by gut microbiota, yet the interaction dynamics with selenocompounds remain unexplored. Our study found that L-Selenomethionine (SeMet) and Se-(Methyl)seleno-L-cysteine (MeSeCys) maintained stability during in vitro gastrointestinal digestion. In contrast, Selenite and L-Selenocystine (SeCys2) were degraded by approximately 13% and 35%. Intriguingly, gut microflora transformed MeSeCys, SeCys2, and Selenite into SeMet. Moreover, when SeCys2 and Selenite incubated with gut microbiota, they produced red selenium nanoparticles with diameters ranging between 100 and 400 nm and boosted glutathione peroxidase activity. These changes were positively associated with an increased relative abundance of unclassified_g__Blautia (Family Lachnospiraceae), Erysipelotrichaceae_UCG-003 (Family Erysipelatoclostridiaceae), and uncultured_bacterium_g__Subdoligranulum (Family Ruminococcaceae). Our findings implied that differential microbial sensitivities to selenocompounds, potentially attributable to their distinct mechanisms governing selenium uptake, storage, utilization, and excretion.

Identification of immune-associated genes in vascular dementia by integrated bioinformatics and inflammatory infiltrates.

Objective: Dysregulation of the immune system plays a vital role in the pathological process of vascular dementia, and this study aims to spot critical biomarkers and immune infiltrations in vascular dementia employing a bioinformatics approach. Methods: We acquired gene expression profiles from the Gene Expression Database. The gene expression data were analyzed using the bioinformatics method to identify candidate immune-related central genes for the diagnosis of vascular dementia. and the diagnostic value of nomograms and Receiver Operating Characteristic (ROC) curves were evaluated. We also examined the role of the VaD hub genes. Using the database and potential therapeutic drugs, we predicted the miRNA and lncRNA controlling the Hub genes. Immune cell infiltration was initiated to examine immune cell dysregulation in vascular dementia. Results: 1321 immune genes were included in the combined immune dataset, and 2816 DEGs were examined in GSE122063. Twenty potential genes were found using differential gene analysis and co-expression network analysis. PPI network design and functional enrichment analysis were also done using the immune system as the main subject. To create the nomogram for evaluating the diagnostic value, four potential core genes were chosen by machine learning. All four putative center genes and nomograms have a solid diagnostic value (AUC ranged from 0.81 to 0.92). Their high confidence level became unquestionable by validating each of the four biomarkers using a different dataset. According to GeneMANIA and GSEA enrichment investigations, the pathophysiology of VaD is strongly related to inflammatory responses, drug reactions, and central nervous system degeneration. The data and Hub genes were used to construct a ceRNA network that includes three miRNAs, 90 lncRNA, and potential VaD therapeutics. Immune cells with varying dysregulation were also found. Conclusion: Using bioinformatic techniques, our research identified four immune-related candidate core genes (HMOX1, EBI3, CYBB, and CCR5). Our study confirms the role of these Hub genes in the onset and progression of VaD at the level of immune infiltration. It predicts potential RNA regulatory pathways control VaD progression, which may provide ideas for treating clinical disease.

Tailoring the composition, antioxidant activity, and prebiotic potential of apple peel by Aspergillus oryzae fermentation.

Apple peel is a typical lignocellulosic food by-product rich in functional components. In this work, apple peel was solid-state fermented with Aspergillus oryzae with an aim to modulate its composition and bioactivity. The results showed that A. oryzae fermentation substantially tailored the composition, improved the antioxidant activity and prebiotic potential of apple peel. Upon the fermentation, 1) free phenolics increased and antioxidant activity improved; 2) the pectin substances degraded significantly, along with a decrease in soluble dietary fiber while an increase in insoluble dietary fiber; 3) the in vitro fermentability increased as indicated by the increase in total acid production. The gut microbiota was shaped with more health-promoting potentials, such as higher abundances of Lactobacillus, Bifidobacterium, Megamonas and Prevotella-9 as well as lower abundances of Enterobacter and Echerichia-Shigella. This work is conducive to the modification of apple peel as a potential ingredient in food formulations.

Early-onset familial essential tremor is associated with nucleotide expansions of spinocerebellar ataxia in China.

BACKGROUND: Essential tremor (ET) is a neurological disease characterized by action tremor in upper arms. Although its high heritability and prevalence worldwide, its etiology and association with other diseases are still unknown. METHOD: We investigated 10 common spinocerebellar ataxias (SCAs), including SCA1, SCA2, SCA3, SCA6, SCA7, SCA8, SCA12, SCA17, SCA36, dentatorubral-pallidoluysian atrophy (DRPLA) in 92 early-onset familial ET pedigrees in China collected from 2016 to 2022. RESULT: We found one SCA12 proband carried 51 CAG repeats within PPP2R2B gene and one SCA3 proband with intermediate CAG repeats (55) with ATXN3 gene. The other 90 ET probands all had normal repeat expansions. CONCLUSION: Tremor can be the initial phenotype of certain SCA. For early-onset, familial ET patients, careful physical examinations are needed before genetic SCA screening.

'Out of Africa' origin of the pantropical staghorn fern genus Platycerium (Polypodiaceae) supported by plastid phylogenomics and biogeographic analysis.

BACKGROUND AND AIMS: The staghorn fern genus Platycerium is one of the most commonly grown ornamental ferns, and it evolved to occupy a typical pantropical intercontinental disjunction. However, the species-level relationships in the genus have not been well-resolved, and the spatiotemporal evolutionary history of the genus also needs to be explored. METHODS: Plastomes of all the 18 Platycerium species were newly sequenced. Using plastome data, we reconstructed the phylogenetic relationships among Polypodiaceae members with the focus on Platycerium species, and further conducted molecular dating and biogeographic analyses of the genus. KEY RESULTS: The present analyses yielded a robustly supported phylogenetic hypothesis of Platycerium. Molecular dating result showed that Platycerium split from its sister genus Hovenkampia at ~35.2 million years ago (Ma) near the Eocene-Oligocene boundary and began to diverge at ~26.3 Ma during the late Oligocene, while multiple speciation events within Platycerium occurred during the middle to late Miocene. Biogeographic analysis suggested that Platycerium originated in tropical Africa and then dispersed eastward to southeast Asia-Australasia and westward to neotropical area. CONCLUSIONS: Our analyses using plastid phylogenomic approach improved understanding the species-level relationships within Platycerium. The global climate changes of both the Late-Oligocene Warming (LOW) and the cooling following the mid-Miocene Climate Optimum (MMCO) may have promoted the speciation of Platycerium, and the transoceanic long-distance dispersal (LLD) is the most plausible explanation for the genus attained its pantropical distribution. Our study to investigate the biogeographic history of Platycerium provides a case study not only for the formation of the pantropical intercontinental disjunction of fern genus but also the 'out of Africa' origin of plant lineages.

Matrix metalloproteinase-9 inhibition prevents aquaporin-4 depolarization-mediated glymphatic dysfunction in Parkinson's disease.

INTRODUCTION: The glymphatic system offers a perivascular pathway for the clearance of pathological proteins and metabolites to optimize neurological functions. Glymphatic dysfunction plays a pathogenic role in Parkinson's disease (PD); however, the molecular mechanism of glymphatic dysfunction in PD remains elusive. OBJECTIVE: To explore whether matrix metalloproteinase-9 (MMP-9)-mediated ß-dystroglycan (ß-DG) cleavage is involved in the regulation of aquaporin-4 (AQP4) polarity-mediated glymphatic system in PD. METHODS: 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP)-induced PD and A53T mice were used in this study. The glymphatic function was evaluated using ex vivo imaging. TGN-020, an AQP4 antagonist, was administered to investigate the role of AQP4 in glymphatic dysfunction in PD. GM6001, an MMP-9 antagonist, was administered to investigate the role of the MMP-9/ß-DG pathway in regulating AQP4. The expression and distribution of AQP4, MMP-9, and ß-DG were assessed using western blotting, immunofluorescence, and co-immunoprecipitation. The ultrastructure of basement membrane (BM)-astrocyte endfeet was detected using transmission electron microscopy. Rotarod and open-field tests were performed to evaluate motor behavior. RESULTS: Perivascular influx and efflux of cerebral spinal fluid tracers were reduced in MPTP-induced PD mice with impaired AQP4 polarization. AQP4 inhibition aggravated reactive astrogliosis, glymphatic drainage restriction, and dopaminergic neuronal loss in MPTP-induced PD mice. MMP-9 and cleaved ß-DG were upregulated in both MPTP-induced PD and A53T mice, with reduced polarized localization of ß-DG and AQP4 to astrocyte endfeet. MMP-9 inhibition restored BM-astrocyte endfeet-AQP4 integrity and attenuated MPTP-induced metabolic perturbations and dopaminergic neuronal loss. CONCLUSION: AQP4 depolarization contributes to glymphatic dysfunction and aggravates PD pathologies, and MMP-9-mediated ß-DG cleavage regulates glymphatic function through AQP4 polarization in PD, which may provide novel insights into the pathogenesis of PD.

A fast and non-invasive artificial intelligence olfactory-like system that aids diagnosis of Parkinson's disease.

BACKGROUND AND PURPOSE: Several previous studies have shown that skin sebum analysis can be used to diagnose Parkinson's disease (PD). The aim of this study was to develop a portable artificial intelligence olfactory-like (AIO) system based on gas chromatographic analysis of the volatile organic compounds (VOCs) in patient sebum and explore its application value in the diagnosis of PD. METHODS: The skin VOCs from 121 PD patients and 129 healthy controls were analyzed using the AIO system and three classic machine learning models were established, including the gradient boosting decision tree (GBDT), random forest and extreme gradient boosting, to assist the diagnosis of PD and predict its severity. RESULTS: A 20-s time series of AIO system data were collected from each participant. The VOC peaks at a large number of time points roughly concentrated around 5-12 s were significantly higher in PD subjects. The gradient boosting decision tree model showed the best ability to differentiate PD from healthy controls, yielding a sensitivity of 83.33% and a specificity of 84.00%. However, the system failed to predict PD progression scored by Hoehn-Yahr stage. CONCLUSIONS: This study provides a fast, low-cost and non-invasive method to distinguish PD patients from healthy controls. Furthermore, our study also indicates abnormal sebaceous gland secretion in PD patients, providing new evidence for exploring the pathogenesis of PD.

Characterization of a low-methoxyl pectin extracted from red radish (Raphanus sativus L.) pomace and its gelation induced by NaCl.

There is an increasing demand for obtaining pectin from new sources. Red radish (Raphanus sativus L.) pomace pectin extracted by alkali was low-methoxyl pectin with esterification degree of 10.17 %, galacturonic acid content of 69.71 % (wt), and average molar weight of 78.59 kDa. The pectin primarily consisted of rhamnogalacturonan I and homogalacturonan domains. The predominant monosaccharides of the pectin were galacturonic acid (46.32 mol%), arabinose (16.03 mol%), galactose (10.46 mol%), and rhamnose (10.28 mol%), respectively. The red radish pomace pectin solution exhibited a shear-thinning behavior. NaCl could induce gelation of red radish pomace pectin, and the gel properties of red radish pomace pectin were considerably affected by the NaCl concentration. As the NaCl concentration (0.25-0.50 mol/L) increased, the rate of gelation accelerated, and the time to gelation point appeared earlier. There was an optimal NaCl concentration (0.50 mol/L) for the pectin to form a gel with the greatest solid-like properties, gel hardness (33.84 g) and water-holding capacity (62.41 %). Gelation force analysis indicated gel formation mainly caused by electrostatic shielding effect of Na+ and hydrogen bonding. This research could facilitate the applications of the red radish pomace pectin in the realm of edible hydrocolloids.

Oscillatory rheometry for elucidating the influence of non-network biopolymer aggregation on pectin-gelatin composite gels.

Gel networks formed from biopolymers have intrigued rheological interest, especially in the food industry. Despite ubiquitous non-network biopolymer aggregation in real gel food systems, its fundamental rheological implications remain less understood. This study addresses this by preparing pectin-gelatin composite gels with dispersed or aggregated biopolymers and comparatively analyzing viscoelastic responses using rheometry. Subtle discrepancies in non-network biopolymer states were revealed through oscillatory shearing at different frequencies and amplitudes. Biopolymer aggregation in the network notably influenced loss tangent frequency dependency, particularly at high frequencies, elevating I3/I1 values and sensitizing the yield point. Non-network biopolymers weakened Payne effects and gel non-linearity. A combination of strain stiffening and shear thinning nonlinear responses characterized prepared gel systems. Aggregation of pectin and gelatin enhanced shear thinning, while strain stiffening was notable in highly aggregated pectin cases. This study enhances understanding of the link between non-network structural complexity and viscoelastic properties in oscillatory rheometry of food gels.

Unsupervised Joint Domain Adaptation for Decoding Brain Cognitive States From tfMRI Images.

Recent advances in large model and neuroscience have enabled exploration of the mechanism of brain activity by using neuroimaging data. Brain decoding is one of the most promising researches to further understand the human cognitive function. However, current methods excessively depends on high-quality labeled data, which brings enormous expense of collection and annotation of neural images by experts. Besides, the performance of cross-individual decoding suffers from inconsistency in data distribution caused by individual variation and different collection equipments. To address mentioned above issues, a Join Domain Adapative Decoding (JDAD) framework is proposed for unsupervised decoding specific brain cognitive state related to behavioral task. Based on the volumetric feature extraction from task-based functional Magnetic Resonance Imaging (tfMRI) data, a novel objective loss function is designed by the combination of joint distribution regularizer, which aims to restrict the distance of both the conditional and marginal probability distribution of labeled and unlabeled samples. Experimental results on the public Human Connectome Project (HCP) S1200 dataset show that JDAD achieves superior performance than other prevalent methods, especially for fine-grained task with 11.5%-21.6% improvements of decoding accuracy. The learned 3D features are visualized by Grad-CAM to build a combination with brain functional regions, which provides a novel path to learn the function of brain cortex regions related to specific cognitive task in group level.

Hoyaspectatissima (Gentianales, Apocynaceae), a new species from Yunnan, China.

Hoyaspectatissima, a new species from Yunnan Province, China, is described and illustrated. Hoyaspectatissima is morphologically similar to H.lyi, but can be easily distinguished from the latter by its succulent leaves that are 2‒4.5 cm long (vs. coriaceous leaves that are up to 9 cm long), corolla that is pink to pale pink (vs. yellowish-white) and corona lobes that are sub-rhombic in top view (vs. ovoid in top view).

AMSF: attention-based multi-view slice fusion for early diagnosis of Alzheimer's disease.

Alzheimer's disease (AD) is an irreversible neurodegenerative disease with a high prevalence in the elderly population over 65 years of age. Intervention in the early stages of AD is of great significance to alleviate the symptoms. Recent advances in deep learning have shown extreme advantages in computer-aided diagnosis of AD. However, most studies only focus on extracting features from slices in specific directions or whole brain images, ignoring the complementarity between features from different angles. To overcome the above problem, attention-based multi-view slice fusion (AMSF) is proposed for accurate early diagnosis of AD. It adopts the fusion of three-dimensional (3D) global features with multi-view 2D slice features by using an attention mechanism to guide the fusion of slice features for each view, to generate a comprehensive representation of the MRI images for classification. The experiments on the public dataset demonstrate that AMSF achieves 94.3% accuracy with 1.6-7.1% higher than other previous promising methods. It indicates that the better solution for AD early diagnosis depends not only on the large scale of the dataset but also on the organic combination of feature construction strategy and deep neural networks.

Multi-task Model for Glioma Segmentation and Isocitrate Dehydrogenase Status Prediction Using Global and Local Features.

According to the 2021 World Health Organization IDH status prediction scheme for gliomas, isocitrate dehydrogenase (IDH) is a particularly important basis for glioma diagnosis. In general, 3D multimodal brain MRI is an effective diagnostic tool. However, only using brain MRI data is difficult for experienced doctors to predict the IDH status. Surgery is necessary to be performed for confirming the IDH. Previous studies have shown that brain MRI images of glioma areas contain a lot of useful information for diagnosis. These studies usually need to mark the glioma area in advance to complete the prediction of IDH status, which takes a long time and has high computational cost. The tumor segmentation task model can automatically segment and locate the tumor region, which is exactly the information needed for the IDH prediction task. In this study, we proposed a multi-task deep learning model using 3D multimodal brain MRI images to achieve glioma segmentation and IDH status prediction simultaneously, which improved the accuracy of both tasks effectively. Firstly, we used a segmentation model to segment the tumor region. Also, the whole MRI image and the segmented glioma region features as the global and local features were used to predict IDH status. The effectiveness of the proposed method was validated via a public glioma dataset from the BraTS2020. Our experimental results show that our proposed method outperformed state-of-the-art methods with a prediction accuracy of 88.5% and average dice of 79.8%. The improvements in prediction and segmentation are 3% and 1% compared with the state-of-the-art method, respectively.