Data Brief. 2025 Apr 22;60:111564. doi: 10.1016/j.dib.2025.111564. eCollection 2025 Jun.

ABSTRACT

In South Asian countries, agriculture is a crucial employment field, and a remarkable number of people depend on it for their livelihood. Crop diseases are a significant threat to sustainable development in the agriculture field. Automated efficient crop disease diagnosis techniques developed with comprehensive field image datasets can play a vital role in preventing diseases at an early stage. Betel leaf is widely consumed in South Asian countries for its nutritional benefits, but to the best of our knowledge, no extensive dataset of betel leaf is available that can play a crucial role in developing accurate disease diagnosis tools. Farmers face a significant economic loss due to betel leaf diseases, and due to the lack of efficient diagnosis tools, the farming of betel leaf has become very difficult day by day. Our motive is to develop a reliable and versatile image dataset of field images that will assist artificial intelligence-based pathology research on betel leaf diseases. This dataset contains healthy leaf images and two common disease images of betel leaf such as leaf rot and leaf spot [1]. Initially, 2,037 betel leaf images were captured in a natural daylight environment from several betel cultivation fields in Bangladesh. Afterward, 10,185 images were generated using image augmentation strategies including flipping, brightness factor, contrast factor, and rotation. This dataset is well-compatible with machine learning and deep learning-based pathology research, as it contains enough image samples for model training, validation, and testing. Moreover, a comparison study is conducted that ensures this dataset fulfills the gap of a reliable and extensive dataset of betel leaf. This comprehensive dataset serves as a crucial resource for researchers in developing efficient computational models for accurate betel leaf disease diagnosis.

PMID:40371167 | PMC:PMC12076791 | DOI:10.1016/j.dib.2025.111564

Front Neurol. 2025 Apr 30;16:1587347. doi: 10.3389/fneur.2025.1587347. eCollection 2025.

ABSTRACT

BACKGROUND: Acute ischemic stroke (AIS) is a major global health threat associated with high rates of disability and mortality, highlighting the need for early prognostic assessment to guide treatment. Currently, there are no reliable methods for the early prediction of poor prognosis in AIS, especially after mechanical thrombectomy. This study aimed to explore the value of radiomics and deep learning based on multimodal magnetic resonance imaging (MRI) in predicting poor prognosis in patients with AIS who underwent mechanical thrombectomy. This study aimed to provide a more accurate and comprehensive tool for stroke prognosis.

METHODS: This study retrospectively analyzed the clinical data and multimodal MRI images of patients with stroke at admission. Logistic regression was employed to identify the risk factors associated with poor prognosis and to construct a clinical model. Radiomics features of the stroke-affected regions were extracted from the patients' baseline multimodal MRI images, and the optimal radiomics features were selected using a least absolute shrinkage and selection operator regression model combined with five-fold cross-validation. The radiomics score was calculated based on the feature weights, and machine learning techniques were applied using a logistic regression classifier to develop the radiomics model. In addition, a deep learning model was devised using ResNet101 and transfer learning. The clinical, radiomics, and deep learning models were integrated to establish a comprehensive multifactorial logistic regression model, termed the CRD (Clinic-Radiomics-Deep Learning) model. The performance of each model in predicting poor prognosis was assessed using receiver operating characteristic (ROC) curve analysis, with the optimal model visualized as a nomogram. A calibration curve was plotted to evaluate the accuracy of nomogram predictions.

RESULTS: A total of 222 patients with AIS were enrolled in this study in a 7:3 ratio, with 155 patients in the training cohort and 67 in the validation cohort. Statistical analysis of clinical data from the training and validation cohorts identified two independent risk factors for poor prognosis: the National Institutes of Health Stroke Scale score at admission and the occurrence of intracerebral hemorrhage. Of the 1,197 radiomic features, 16 were selected to develop the radiomics model. Area under the ROC curve (AUC) analysis of specific indicators demonstrated varying performances across methods and cohorts. In the training cohort, the clinical, radiomics, deep learning, and integrated CRD models achieved AUC values of 0.762, 0.755, 0.689, and 0.834, respectively. In the validation cohort, the clinical model exhibited an AUC of 0.874, the radiomics model achieved an AUC of 0.805, the deep learning model attained an AUC of 0.757, and the CRD model outperformed all models, with an AUC of 0.908. Calibration curves indicated that the CRD model showed exceptional consistency and accuracy in predicting poor prognosis in patients with AIS. Decision curve analysis revealed that the CRD model offered the highest net benefit compared with the clinical, radiomics, and deep learning models.

CONCLUSION: The CRD model based on multimodal MRI demonstrated high diagnostic efficacy and reliability in predicting poor prognosis in patients with AIS who underwent mechanical thrombectomy. This model holds considerable potential for assisting clinicians with risk assessment and decision-making for patients experiencing ischemic stroke.

PMID:40371075 | PMC:PMC12074947 | DOI:10.3389/fneur.2025.1587347

Acute Med Surg. 2025 May 14;12(1):e70065. doi: 10.1002/ams2.70065. eCollection 2025 Jan-Dec.

NO ABSTRACT

PMID:40370970 | PMC:PMC12077104 | DOI:10.1002/ams2.70065

BJR Open. 2025 Apr 29;7(1):tzaf008. doi: 10.1093/bjro/tzaf008. eCollection 2025 Jan.

ABSTRACT

OBJECTIVES: Artificial intelligence (AI) deep learning algorithms trained on non-contrast CT scans effectively detect and quantify acute COVID-19 lung involvement. Our study explored whether radiological contrast affects the accuracy of AI-measured lung opacities, potentially impacting clinical decisions. We compared lung opacity measurements from AI software with visual assessments by radiologists using CT pulmonary angiography (CTPA) images of early-stage COVID-19 patients.

METHODS: This prospective single-centre study included 18 COVID-19 patients who underwent CTPA due to suspected pulmonary embolism. Patient demographics, clinical data, and 30-day and 90-day mortality were recorded. AI tool (Pulmonary Density Plug-in, AI-Rad Companion Chest CT, SyngoVia; Siemens Healthineers, Forchheim, Germany) was used to estimate the quantity of opacities. Visual quantitative assessments were performed independently by 2 radiologists.

RESULTS: There was a positive correlation between radiologist estimations (r 2 = 0.57) and between the AI data and the mean of the radiologists' estimations (r 2 = 0.70). Bland-Altman plot analysis showed a mean bias of +3.06% between radiologists and -1.32% between the mean radiologist vs AI, with no outliers outside 2×SD for respective comparison.

The AI protocol facilitated a quantitative assessment of lung opacities and showed a strong correlation with data obtained from 2 independent radiologists, demonstrating its potential as a complementary tool in clinical practice.

CONCLUSION: In assessing COVID-19 lung opacities in CTPA images, AI tools trained on non-contrast images, provide comparable results to visual assessments by radiologists.

ADVANCES IN KNOWLEDGE: The Pulmonary Density Plug-in enables quantitative analysis of lung opacities in COVID-19 patients using contrast-enhanced CT images, potentially streamlining clinical workflows and supporting timely decision-making.

PMID:40370862 | PMC:PMC12077292 | DOI:10.1093/bjro/tzaf008

Front Artif Intell. 2025 Apr 30;8:1529814. doi: 10.3389/frai.2025.1529814. eCollection 2025.

ABSTRACT

BACKGROUND: Wireless Capsule Endoscopy (WCE) enables non-invasive imaging of the gastrointestinal tract but generates vast video data, making real-time and accurate abnormality detection challenging. Traditional detection methods struggle with uncontrolled illumination, complex textures, and high-speed processing demands.

METHODS: This study presents a novel approach using Real-Time Detection Transformer (RT-DETR), a transformer-based object detection model, specifically optimized for WCE video analysis. The model captures contextual information between frames and handles variable image conditions. It was evaluated using the Kvasir-Capsule dataset, with performance assessed across three RT-DETR variants: Small (S), Medium (M), and X-Large (X).

RESULTS: RT-DETR-X achieved the highest detection precision. RT-DETR-M offered a practical trade-off between accuracy and speed, while RT-DETR-S processed frames at 270 FPS, enabling real-time performance. All three models demonstrated improved detection accuracy and computational efficiency compared to baseline methods.

DISCUSSION: The RT-DETR framework significantly enhances precision and real-time performance in gastrointestinal abnormality detection using WCE. Its clinical potential lies in supporting faster and more accurate diagnosis. Future work will focus on further optimization and deployment in endoscopic video analysis systems.

PMID:40370809 | PMC:PMC12075415 | DOI:10.3389/frai.2025.1529814

Front Genet. 2025 Apr 30;16:1583081. doi: 10.3389/fgene.2025.1583081. eCollection 2025.

ABSTRACT

BACKGROUND AND OBJECTIVE: Gene expression analysis plays a critical role in lung cancer research, offering molecular feature-based diagnostic insights that are particularly effective in distinguishing lung cancer subtypes. However, the high dimensionality and inherent imbalance of gene expression data create significant challenges for accurate diagnosis. This study aims to address these challenges by proposing an innovative deep learning-based method for predicting lung cancer subtypes.

METHODS: We propose a method called Exo-LCClassifier, which integrates feature selection, one-dimensional convolutional neural networks (1D CNN), and an improved Wasserstein Generative Adversarial Network (WGAN). First, differential gene expression analysis was performed using DESeq2 to identify significantly expressed genes from both normal and tumor tissues. Next, the enhanced WGAN was applied to augment the dataset, addressing the issue of sample imbalance and increasing the diversity of effective samples. Finally, a 1D CNN was used to classify the balanced dataset, thereby improving the model's diagnostic accuracy.

RESULTS: The proposed method was evaluated using five-fold cross-validation, achieving an average accuracy of 0.9766 ± 0.0070, precision of 0.9762 ± 0.0101, recall of 0.9827 ± 0.0050, and F1-score of 0.9793 ± 0.0068. On an external GEO lung cancer dataset, it also showed strong performance with an accuracy of 0.9588, precision of 0.9558, recall of 0.9678, and F1-score of 0.9616.

CONCLUSION: This study addresses the critical challenge of imbalanced learning in lung cancer gene expression analysis through an innovative computational framework. Our solution integrates three advanced techniques: (1) DESeq2 for differential expression analysis, (2) WGAN for data augmentation, and (3) 1D CNN for feature learning and classification. The source codes are publicly available at: https://github.com/lanlinxxs/Exo-classifier.

PMID:40370696 | PMC:PMC12075553 | DOI:10.3389/fgene.2025.1583081

Proc SPIE Int Soc Opt Eng. 2025 Feb;13405:134050L. doi: 10.1117/12.3047283. Epub 2025 Apr 8.

ABSTRACT

Ultra-high-resolution (UHR) photon-counting detector (PCD) CT offers superior spatial resolution compared to conventional CT, benefiting various clinical areas. However, the UHR resolution also significantly increases image noise, which can limit its clinical adoption in areas such as cardiac CT. In clinical practice, this image noise varies substantially across imaging conditions, such as different diagnostic tasks, patient characteristics (e.g., size), scan protocols, and image reconstruction settings. To address these challenges and provide the full potential of PCD-CT for optimal clinical performance, a convolutional neural network (CNN) denoising algorithm was developed, optimized, and tailored to each specific set of conditions. The algorithm's effectiveness in reducing noise and its impact on coronary artery stenosis quantification across different patient size categories (small: water equivalent diameter <300 mm, medium: 300-320 mm, and large: >320 mm) were objectively assessed. Reconstruction kernels at different sharpness, from Bv60 to Bv76, were investigated to determine optimal settings for each patient size regarding image quality and quantitative assessment of coronary stenosis (in terms of percent diameter stenosis). Our findings indicate that for patients with a water equivalent diameter less than 320 mm, CNN-denoised Bv72 images provide optimal image quality, less blooming artifact, and reduced percent diameter stenosis compared to routine images, while for patients with water equivalent diameter over 320 mm, CNN-denoised Bv60 images are preferable. Quantitatively, the CNN reduces noise-by 85% compared to the input images and 53% compared to commercial iterative reconstructions at strength 4 (QIR4)-while maintaining high spatial resolution and a natural noise texture. Moreover, it enhances stenosis quantification by reducing the percent diameter stenosis measurement by 52% relative to the input and 24% relative to QIR4. These improvements demonstrate the capability of CNN denoising in UHR PCD-CT to enhance image quality and quantitative assessment of coronary artery disease in a manner that is adaptive to patient characteristics and imaging conditions.

PMID:40370652 | PMC:PMC12076256 | DOI:10.1117/12.3047283

Alzheimers Dement. 2025 May;21(5):e70282. doi: 10.1002/alz.70282.

ABSTRACT

INTRODUCTION: Neurodegenerative diseases (NDDs) are chronic diseases caused by brain neuron degeneration, requiring systematic integration of risk factors to address their heterogeneity. Established in 2021, Knowledgebase of Risk Factors for Neurodegenerative Diseases (NDDRF) was the first knowledge base to consolidate NDD risk factors. NDDRF 2.0 expands focus to modifiable lifestyle-related factors, enhancing utility for NDD prevention.

METHODS: Data from the past 4 years were comprehensively updated, while lifestyle factors were manually collected and filtered from 1975 to 2024. Each factor was embedded with International Classification of Diseases codes and clinical stage annotations, and then re-standardized, classified, and annotated in accordance with the Unified Medical Language System Semantic Network.

RESULTS: NDDRF 2.0 encompasses 1971 risk factors classified under 151 subcategories across 20 NDDs, including 536 lifestyle-related factors covering six major categories and is freely accessible at http://sysbio.org.cn/NDDRF/.

DISCUSSION: As the first lifestyle-specific and holistic knowledge base for NDDs, NDDRF 2.0 offers structured and deep phenotype information, enabling personalized prevention strategies and clinical decision support.

HIGHLIGHTS: An enhanced lifestyle-specific and holistic knowledge base (Knowledgebase of Risk Factors for Neurodegenerative Diseases [NDDRF] 2.0) was built for neurodegenerative diseases (NDDs). NDDRF 2.0 provides detailed categorization and deep phenotypes to support targeted NDD prevention. NDDRF 2.0 provides a knowledge-driven resource that facilitates personalized risk assessment and proactive health management. NDDRF 2.0 provides clinicians, researchers, and at-risk populations with knowledge to develop and implement effective risk prevention strategies. NDDRF 2.0 can be used to build chatbots by enhancing large language models in the future.

PMID:40371632 | DOI:10.1002/alz.70282

J Am Heart Assoc. 2025 May 15:e039098. doi: 10.1161/JAHA.124.039098. Online ahead of print.

ABSTRACT

BACKGROUND: Most human disease definitions, except for rare and communicable diseases, are based on symptoms in specific organs, not on causal molecular mechanisms. This limits treatments to imprecise symptomatic approaches with high numbers needed to treat. Systems medicine, instead, has a holistic approach and defines diseases in an organ-agnostic manner on the basis of associated risk genes, their encoded proteins, and protein-protein interactions. Dysregulation of such disease modules is best corrected by multitarget, synergistic network pharmacology. Here we test this principle in acute ischemic stroke, a highly unmet medical indication without any approved neuroprotective drug so far.

METHODS: We extend 3 validated risk genes, neuronal nitric oxide synthase (NOS1), NADPH oxidase 5 (NOX5), and soluble guanylate cyclase (sGC), to a single disease module. For preclinical validation, we used C57/Bl6 mice and humanized NOX5-knock-in mice because NOX5 is not present in the mouse genome despite playing a key role in early stroke. Because up to 70% of patients with stroke have diabetes or prediabetes as an aggravating comorbidity, we also induced diabetes in these mice to model the increased clinical risk for hemorrhagic transformation.

RESULTS: We found that a triple-drug combination of a NOX inhibitor, a nitric oxide synthase inhibitor, and an sGC activator reduced infarct size and, in diabetic animals, also prevented hemorrhagic transformation. Reducing each individual compound dose to subthreshold levels still resulted in full protection when combined, typical for supra-additive network pharmacology. To examine clinical safety, 3 drugs, either marketed for sGC or repurposed for nitric oxide synthase and NADPH oxidase, were administered to healthy volunteers in a phase I trial.

CONCLUSIONS: Our data establish that a mechanism-based network pharmacology approach is effective and clinically safe, warranting a currently ongoing first-in-class neuroprotective phase II interventional trial.

REGISTRATION: URL: https://clinicaltrials.gov/study/NCT05762146?term=repo-stroke&rank=1; Unique Identifier: NCT05762146.

PMID:40371623 | DOI:10.1161/JAHA.124.039098

PNAS Nexus. 2025 May 2;4(5):pgaf139. doi: 10.1093/pnasnexus/pgaf139. eCollection 2025 May.

ABSTRACT

Topological signals are variables or features associated with both nodes and edges of a network. Recently, in the context of topological machine learning, great attention has been devoted to signal processing of such topological signals. Most of the previous topological signal processing algorithms treat node and edge signals separately and work under the hypothesis that the true signal is smooth and/or well approximated by a harmonic eigenvector of the higher-order Laplacian, which may be violated in practice. Here, we propose Dirac-equation signal processing, a framework for efficiently reconstructing true signals on nodes and edges, also if they are not smooth or harmonic, by processing them jointly. The proposed physics-inspired algorithm is based on the spectral properties of the topological Dirac operator. It leverages the mathematical structure of the topological Dirac equation to boost the performance of the signal processing algorithm. We discuss how the relativistic dispersion relation obeyed by the topological Dirac equation can be used to assess the quality of the signal reconstruction. Finally, we demonstrate the improved performance of the algorithm with respect to previous algorithms. Specifically, we show that Dirac-equation signal processing can also be used efficiently if the true signal is a nontrivial linear combination of more than one eigenstate of the Dirac equation, as it generally occurs for real signals.

PMID:40371396 | PMC:PMC12076202 | DOI:10.1093/pnasnexus/pgaf139

Plant Commun. 2025 May 13:101376. doi: 10.1016/j.xplc.2025.101376. Online ahead of print.

ABSTRACT

Cis-regulatory elements (CREs) are non-coding DNA sequences that modulate gene expression. Their identification is critical to study the transcriptional regulation of genes controlling key traits that govern plant growth and development. They are also crucial components for the delineation of gene regulatory networks, which represent regulatory interactions between transcription factors (TFs) and target genes. In maize, CREs have been profiled using different computational and experimental methods, but the extent to which these methods complement each other in identifying functional CREs is unclear. Here, we report the data-driven integration of different maize CRE profiling methods to optimize the capture of experimentally-confirmed TF binding sites, resulting in maps of integrated CREs (iCREs) showing increased levels of completeness and precision. We combined the iCREs with a wide diversity of gene expression data under drought conditions to perform motif enrichment and infer drought-specific GRNs. Mining these organ-specific GRNs revealed known and novel candidate regulators of maize drought response, and showed these networks significantly overlap with drought eQTL regulatory interactions. Furthermore, by studying the transposable elements (TEs) overlapping with iCREs, we identified few TE superfamilies displaying typical epigenetic features of regulatory DNA that are potentially involved in wiring specific TF-target gene regulatory interactions. Overall, our study showcases the integration of different omics data sources to generate a high-quality collection of CREs, together with their applicability to better characterize gene regulation in the complex maize genome.

PMID:40369872 | DOI:10.1016/j.xplc.2025.101376

Front Immunol. 2025 Apr 30;16:1576283. doi: 10.3389/fimmu.2025.1576283. eCollection 2025.

ABSTRACT

Gliomas, particularly glioblastoma (GBM), are among the most aggressive and challenging brain tumors to treat. Although current therapies such as chemotherapy, radiotherapy, and targeted treatments have extended patient survival to some extent, their efficacy remains limited and is often accompanied by severe side effects. In recent years, exercise therapy has gained increasing attention as an adjunctive treatment in clinical and research settings. Exercise not only improves patients' physical function and cognitive abilities but may also enhance the efficacy of conventional drug treatments by modulating the immune system, suppressing inflammatory responses, and improving blood-brain barrier permeability. This review summarizes the potential mechanisms of exercise in glioma treatment, including enhancing immune surveillance through activation of natural killer (NK) cells and T cells, and increasing drug penetration by improving blood-brain barrier function. Additionally, studies suggest that exercise can synergize with chemotherapy and immunotherapy, improving treatment outcomes while reducing drug-related side effects. Although the application of exercise therapy in glioma patients is still in the exploratory phase, existing evidence indicates its significant clinical value as an adjunctive approach, with the potential to become a new standard in glioma treatment in the future.

PMID:40370453 | PMC:PMC12075166 | DOI:10.3389/fimmu.2025.1576283

JAMA Netw Open. 2025 May 1;8(5):e2510298. doi: 10.1001/jamanetworkopen.2025.10298.

ABSTRACT

IMPORTANCE: Patients with dementia have considerable supportive care needs. Specialist palliative care may be beneficial, but it is unclear which patients are most appropriate for referral and when they should be referred.

OBJECTIVE: To identify a set of consensus referral criteria for specialist palliative care for patients with dementia.

DESIGN, SETTING, AND PARTICIPANTS: In this survey study using 3 rounds of Delphi surveys, an international, multidisciplinary panel of clinicians from 5 continents with expertise in the integration of dementia and palliative care were asked to rate 83 putative referral criteria (generated from a previous systematic review and steering committee discussion). Specialist palliative care was defined as an interdisciplinary team consisting of practitioners with advanced knowledge and skills in palliative medicine offering consultative services for specialist-level palliative care in (nonhospice) inpatient, outpatient, community, and home-based settings.

MAIN OUTCOMES AND MEASURES: Consensus was defined a priori as at least 70% agreement among experts. A criterion was coded as major if the experts advocated that meeting 1 criterion alone was satisfactory to justify a referral. Data were summarized using descriptive statistics.

RESULTS: Of the 63 invited and eligible panelists, the response rate was 58 (92.1%) in round 1, 58 (92.1%) in round 2, and 60 (95.2%) in round 3. Of the 58 panelists who provided demographic data in round 1, most were aged 40 to 49 years (28 of 58 [48.3%]), and 29 panelists (50%) each were men and women. Panelists achieved consensus on 15 major and 42 minor criteria for specialist palliative care referral. The 15 major criteria were grouped under 5 categories, including dementia type (eg, rapidly progressive dementia), symptom distress (eg, severe physical symptoms), psychosocial factors or decision-making (eg, request for hastened death, assisted suicide, or euthanasia), comorbidities or complications (eg, ≥2 episodes of aspiration pneumonia in the past 12 months); and hospital use (eg, ≥2 hospitalizations within the past 3 months).

CONCLUSIONS AND RELEVANCE: In this Delphi survey study, international experts reached consensus on a range of criteria for referral to specialist palliative care. With testing and validation, these criteria may be used to standardize specialist palliative care access for patients with dementia across various care settings.

PMID:40366652 | PMC:PMC12079294 | DOI:10.1001/jamanetworkopen.2025.10298

Nature. 2025 May 14. doi: 10.1038/s41586-025-09010-1. Online ahead of print.

ABSTRACT

The human cerebral cortex is composed of six layers and dozens of areas that are molecularly and structurally distinct1-4. Although single-cell transcriptomic studies have advanced the molecular characterization of human cortical development, a substantial gap exists owing to the loss of spatial context during cell dissociation5-8. Here we used multiplexed error-robust fluorescence in situ hybridization (MERFISH)9, augmented with deep-learning-based nucleus segmentation, to examine the molecular, cellular and cytoarchitectural development of the human fetal cortex with spatially resolved single-cell resolution. Our extensive spatial atlas, encompassing more than 18 million single cells, spans eight cortical areas across seven developmental time points. We uncovered the early establishment of the six-layer structure, identifiable by the laminar distribution of excitatory neuron subtypes, 3 months before the emergence of cytoarchitectural layers. Notably, we discovered two distinct modes of cortical areal specification during mid-gestation: (1) a continuous, gradual transition observed across most cortical areas along the anterior-posterior axis and (2) a discrete, abrupt boundary specifically identified between the primary (V1) and secondary (V2) visual cortices as early as gestational week 20. This sharp binary transition in V1-V2 neuronal subtypes challenges the notion that mid-gestation cortical arealization involves only gradient-like transitions6,10. Furthermore, integrating single-nucleus RNA sequencing with MERFISH revealed an early upregulation of synaptogenesis in V1-specific layer 4 neurons. Collectively, our findings underscore the crucial role of spatial relationships in determining the molecular specification of cortical layers and areas. This study establishes a spatially resolved single-cell analysis paradigm and paves the way for the construction of a comprehensive developmental atlas of the human brain.

PMID:40369074 | DOI:10.1038/s41586-025-09010-1

Sci Rep. 2025 May 15;15(1):16832. doi: 10.1038/s41598-025-01744-2.

ABSTRACT

PCOS (Poly-Cystic Ovary Syndrome) is a multifaceted disorder that often affects the ovarian morphology of women of their reproductive age, resulting in the development of numerous cysts on the ovaries. Ultrasound imaging typically diagnoses PCOS, which helps clinicians assess the size, shape, and existence of cysts in the ovaries. Nevertheless, manual ultrasound image analysis is often challenging and time-consuming, resulting in inter-observer variability. To effectively treat PCOS and prevent its long-term effects, prompt and accurate diagnosis is crucial. In such cases, a prediction model based on deep learning can help physicians by streamlining the diagnosis procedure, reducing time and potential errors. This article proposes a novel integrated approach, QEI-SAM (Quality Enhanced Image - Segment Anything Model), for enhancing image quality and ovarian cyst segmentation for accurate prediction. GAN (Generative Adversarial Networks) and CNN (Convolutional Neural Networks) are the most recent cutting-edge innovations that have supported the system in attaining the expected result. The proposed QEI-SAM model used Enhanced Super Resolution Generative Adversarial Networks (ESRGAN) for image enhancement to increase the resolution, sharpening the edges and restoring the finer structure of the ultrasound ovary images and achieved a better SSIM of 0.938, PSNR value of 38.60 and LPIPS value of 0.0859. Then, it incorporates the Segment Anything Model (SAM) to segment ovarian cysts and achieve the highest Dice coefficient of 0.9501 and IoU score of 0.9050. Furthermore, Convolutional Neural Network - ResNet 50, ResNet 101, VGG 16, VGG 19, AlexNet and Inception v3 have been implemented to diagnose PCOS promptly. Finally, VGG 19 has achieved the highest accuracy of 99.31%.

PMID:40369044 | DOI:10.1038/s41598-025-01744-2

Sci Rep. 2025 May 14;15(1):16804. doi: 10.1038/s41598-025-00890-x.

ABSTRACT

Deep learning, particularly convolutional neural networks (CNNs), has proven valuable for brain tumor classification, aiding diagnostic and therapeutic decisions in medical imaging. Despite their accuracy, these models are vulnerable to adversarial attacks, compromising their reliability in clinical settings. In this research, we utilized a VGG16-based CNN model to classify brain tumors, achieving 96% accuracy on clean magnetic resonance imaging (MRI) data. To assess robustness, we exposed the model to Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, which reduced accuracy to 32% and 13%, respectively. We then applied a multi-layered defense strategy, including adversarial training with FGSM and PGD examples and feature squeezing techniques such as bit-depth reduction and Gaussian blurring. This approach improved model resilience, achieving 54% accuracy on FGSM and 47% on PGD adversarial examples. Our results highlight the importance of proactive defense strategies for maintaining the reliability of AI in medical imaging under adversarial conditions.

PMID:40369011 | DOI:10.1038/s41598-025-00890-x

J Transl Med. 2025 May 14;23(1):543. doi: 10.1186/s12967-025-06491-6.

ABSTRACT

BACKGROUND: Genome-wide association studies (GWAS) and subsequent functional interpretation have been used to identify susceptible genes and potential drug-repositioning candidates. This study aimed to identify genes associated with colorectal cancer (CRC) and potential drug-repositioning candidates.

METHODS: Patients with CRC at Seoul National University Hospital (SNUH, discovery study) and Chonnam National University Hospital (CNUH, replication study) were included as case groups. The Korean Genome and Epidemiology Study (KoGES) participants were included as a control group. Single-nucleotide polymorphisms (SNPs) were extracted from blood-derived DNA (N = 409,063). A SNP-based logistic regression model was applied. Furthermore, post-GWAS analysis was conducted. Drug-repositioning candidates were identified using a pre-trained deep neural network and the druggability assessment tool.

RESULTS: In the discovery study, we conducted a 1:3 age- and sex-matched case-control study that included 500 CRC cases (mean age 63.0 ± 7.15 years) and 1,500 healthy controls (mean age 62.9 ± 7.07 years), each group comprising 50% males and 50% females. The replication study enrolled 4,860 patients with CRC and 46,384 healthy controls. The two-stage GWAS revealed statistically significant associations among MKLN1 (rs75170436, 7q32.3, beta (log odds ratio) = - 0.90, Pmeta = 5.90 × 10-13), MMP14 (rs3751489, 14q11.2, beta (log odds ratio) = - 1.91, Pmeta = 2.31 × 10-12). Post-GWAS functional analysis revealed strong associations on two genes highlighting deleterious effects and increased gene expression. Drug-repositioning analysis identified GW0742 (PPARβ/δ agonist) with the highest binding score and druggability score for MMP14 with a reference allele (12.06, 0.85).

CONCLUSIONS: Using GWAS, MKLN1 and MMP14 were found to be associated with CRC development and we identified GW0742 (PPARβ/δ agonist) as a potential drug-repositioning candidate for CRC based on MKLN1 and MMP14. These findings improve the understanding of CRC development and provide insights into novel therapeutic targets and candidates for CRC treatment.

PMID:40369569 | DOI:10.1186/s12967-025-06491-6