bioRxiv [Preprint]. 2025 Mar 8:2025.03.03.641186. doi: 10.1101/2025.03.03.641186.

ABSTRACT

Amyotrophic lateral sclerosis (ALS), frontotemporal dementia (FTD), and Alzheimer's disease (AD) are common neurodegenerative disorders for which the mechanisms driving neuronal death remain unclear. Single-cell whole-genome sequencing of 429 neurons from three C9ORF72 ALS, six C9ORF72 FTD, seven AD, and twenty-three neurotypical control brains revealed significantly increased burdens in somatic single nucleotide variant (sSNV) and insertion/deletion (sIndel) in all three disease conditions. Mutational signature analysis identified a disease-associated sSNV signature suggestive of oxidative damage and an sIndel process, affecting 28% of ALS, 79% of FTD, and 65% of AD neurons but only 5% of control neurons (diseased vs. control: OR=31.20, p = 2.35×10-10). Disease-associated sIndels were primarily two-basepair deletions resembling signature ID4, which was previously linked to topoisomerase 1 (TOP1)-mediated mutagenesis. Duplex sequencing confirmed the presence of sIndels and identified similar single-strand events as potential precursor lesions. TOP1-associated sIndel mutagenesis and resulting genome instability may thus represent a common mechanism of neurodegeneration.

PMID:40093130 | PMC:PMC11908196 | DOI:10.1101/2025.03.03.641186

bioRxiv [Preprint]. 2025 Mar 4:2025.03.03.641217. doi: 10.1101/2025.03.03.641217.

ABSTRACT

Chronic traumatic encephalopathy (CTE) is a neurodegenerative disease that is linked to exposure to repetitive head impacts (RHI), yet little is known about its pathogenesis. Applying two single-cell whole-genome sequencing methods to hundreds of neurons from prefrontal cortex of 15 individuals with CTE, and 4 with RHI without CTE, revealed increased somatic single-nucleotide variants in CTE, resembling a pattern previously reported in Alzheimer's disease (AD). Furthermore, we discovered remarkably high burdens of somatic small insertions and deletions in a subset of CTE individuals, resembling a known pattern, ID4, also found in AD. Our results suggest that neurons in CTE experience stereotyped mutational processes shared with AD; the absence of similar changes in RHI neurons without CTE suggests that CTE involves mechanisms beyond RHI alone.

PMID:40093089 | PMC:PMC11908173 | DOI:10.1101/2025.03.03.641217

bioRxiv [Preprint]. 2025 Mar 6:2025.03.05.641682. doi: 10.1101/2025.03.05.641682.

ABSTRACT

A mechanistic understanding of neurodevelopment requires us to follow the multiscale processes that connect molecular genetic processes to macroscopic cerebral cortical formations and thence to neurological function. Using magnetic resonance imaging of the brain of the ferret, a model organism for studying cortical morphogenesis, we create in vitro physical gel models and in silico numerical simulations of normal brain gyrification. Using observations of genetically manipulated animal models, we identify cerebral cortical thickness and cortical expansion rate as the primary drivers of dysmorphogenesis and demonstrate that in silico models allow us to examine the causes of aberrations in morphology and developmental processes at various stages of cortical ontogenesis. Finally, we explain analogous cortical malformations in human brains, with comparisons with human phenotypes induced by the same genetic defects, providing a unified perspective on brain morphogenesis that is driven proximally by genetic causes and affected mechanically via variations in the geometry of the brain and differential growth of the cortex.

PMID:40093050 | PMC:PMC11908256 | DOI:10.1101/2025.03.05.641682

Tunis Med. 2025 Feb 5;103(2):212-216. doi: 10.62438/tunismed.v103i2.5261.

ABSTRACT

INTRODUCTION: Lipoid pneumonia is a rare disease affecting adults' which frequency increases with age. Exogenous lipoid pneumonia results from the penetration, usually by inhalation, of oily substances into the pulmonary parenchyma.

AIM: To study the clinical and radiological features of exogenous lipoid pneumonia and to define therapeutic strategies.

METHODS: We performed a monocentric, retrospective study of patients followed in the Pneumology Department of the Hedi Chaker Hospital in Sfax between 2004 and 2023. The diagnosis of exogenous lipoid pneumonia was confirmed by bronchoalveolar lavage with positive Oil Red O staining or by biopsy with anatomopathological examination showing lipid-laden foamy histiocytes.

RESULTS: During this period, we collected nine patients with an average age of 46. Dyspnea and cough were the most frequent symptoms. Chest computed tomography revealed ground-glass opacity in five cases, parenchymal condensations in three cases and crazy paving in three cases. The frequent risk factors were occupational exposure to a lipid in five cases and consumption of a lipid product in four cases. In terms of treatment, four patients underwent occupational reclassification and a declaration of occupational disease. Systemic corticotherapy was indicated in six patients.

CONCLUSION: Exogenous lipoid pneumonia is a rare entity. This study highlights the difficulty of making a diagnosis, due to misleading clinico-radiological presentation in the absence of exposure.

PMID:40096721 | DOI:10.62438/tunismed.v103i2.5261

JAMA Netw Open. 2025 Mar 3;8(3):e250908. doi: 10.1001/jamanetworkopen.2025.0908.

ABSTRACT

IMPORTANCE: Black pregnant patients are significantly more likely than their White counterparts to undergo peripartum urine drug screening (UDS) and subsequent reporting to child protective services (CPS).

OBJECTIVE: To evaluate the association of removing isolated cannabis use and limited prenatal care as order indications, combined with clinician-facing clinical decision support, with racial parity in peripartum UDS and CPS reporting.

DESIGN, SETTING, AND PARTICIPANTS: This quality improvement study assessed 9396 pregnant patients at a single tertiary care center in a Midwestern US urban metropolitan region who delivered before (June 1, 2021, to September 31, 2022) and after (October 1, 2022, to January 31, 2024) the intervention.

EXPOSURE: Updated UDS indications combined with clinical decision support.

MAIN OUTCOMES AND MEASURES: Primary outcomes included UDS and CPS report rate by race before vs after the intervention. The secondary outcome was the rate of nonprescribed, noncannabis substance-positive UDS. Neonatal outcomes were included as balancing measures.

RESULTS: Of 9396 female patients (median [IQR] age, 29 [24-33] years; 4305 [45.8%] Black, 4277 [45.5%] White, and 814 [8.7%] other race) included in the analysis, 4639 and 4757 delivered in the preintervention and postintervention periods, respectively. There was a small but statistically significant decrease in the number of Black patients before vs after the intervention (2210 [47.6%] vs 2095 [44.0%], P = .005); there were no significant differences in other race groups, median age, or multiparity. Before the intervention, 513 (23.2%) and 228 (11.1%) Black and White patients, respectively, had UDS (P < .001) compared with 95 (4.5%) and 79 (3.6%) Black and White patients, respectively, after the intervention (P = .40). Before the intervention, an association between Black race and CPS report was observed (249 [11.3%] Black and 119 [5.8%] White patients, P < .001); there was no association between race and CPS report after the intervention (87 [4.2%] Black and 78 [3.5%] White patients, P = .67). There was no association between the intervention and the percentage of UDS results that were positive for nonprescribed, noncannabis substances (107 [2.5%] preintervention vs 88 [2.0%] postintervention; P = .14). There was no significant association between the intervention and any measured neonatal outcomes.

CONCLUSIONS AND RELEVANCE: In this quality improvement study, removal of isolated cannabis use and limited prenatal care as UDS indications, coupled with clinical decision support, was associated with improved racial equity in UDS testing and CPS reporting. The intervention was not associated with a significant change in UDS positivity for nonprescribed, noncannabis substances. These findings suggest that this intervention improved equity in UDS practices without decreasing identification of clinically relevant substance use.

PMID:40094663 | PMC:PMC11915058 | DOI:10.1001/jamanetworkopen.2025.0908

J Mol Cell Biol. 2025 Mar 17:mjaf009. doi: 10.1093/jmcb/mjaf009. Online ahead of print.

ABSTRACT

Calciphylaxis is a rare, progressive disorder characterized by subcutaneous adipose and dermal microvascular calcifications, microthrombi, and endothelial damage. It mainly affects patients with chronic kidney disease (CKD), which is also known as calcific uremic arteriolopathy. Skin biopsy is the gold standard for diagnosis, but it is an invasive procedure. Calciphylaxis frequently results in ischemic and nonhealing ulcerations with a high mortality rate. A multidisciplinary targeted approach is the primary treatment method. Vascular calcification, which is a common complication in patients with CKD, cannot completely explain the rapid progression of calciphylaxis. This article reviews the advances in the epidemiological characteristics, risk factors, and diagnosis, including non-uraemic calciphylaxis (NUC) and visceral calciphylaxis, pathogenesis, associated animal models, and treatment of calciphylaxis. The scarcity of animal models that mimic the clinical presentation of calciphylaxis hampers the understanding of its pathogenesis. The acute effects on progressive vascular injury, including the induction of severe ischemia and inflammatory responses, have been emphasized. Actively listening to the voices of patients and their families and building a multidimensional research system with artificial intelligence technologies based on the specific molecular makeup of calciphylaxis patients will help tailor regenerative treatment strategies. Mesenchymal stem cells (MSCs) may be proposed as a novel therapy for calciphylaxis because of their regenerative effects, inhibition of vascular calcification, anti-infection and immunomodulation properties, and improvement of hypercoagulability. Safe, effective, accessible, and economical MSC strategies guided by biomarkers deserve consideration for the treatment of this devastating disease.

PMID:40097288 | DOI:10.1093/jmcb/mjaf009

Bioinformatics. 2025 Mar 17:btaf117. doi: 10.1093/bioinformatics/btaf117. Online ahead of print.

ABSTRACT

MOTIVATION: Identifying drug target interactions is a crucial step in drug repurposing and drug discovery. The significant increase in demand and the expensive nature for experimentally identifying drug target interactions necessitate computational tools for automated prediction and comprehension of drug target interactions. Despite recent advancements, current methods fail to fully leverage the hierarchical information in drug target interactions.

RESULTS: Here we introduce H2GnnDTI, a novel two-level hierarchical heterogeneous graph learning model to predict drug target interactions, by integrating the structures of drugs and proteins via a low-level view GNN (LGNN) and a high-level view GNN (HGNN). The hierarchical graph consists of high-level heterogeneous nodes representing drugs and proteins, connected by edges representing known DTIs. Each drug or protein node is further detailed in a low-level graph, where nodes represent molecules within each drug or amino acids within each protein, accompanied by their respective chemical descriptors. Two distinct low-level graph neural networks are first deployed to capture structural and chemical features specific to drugs and proteins from these low-level graphs. Subsequently, a high-level graph encoder is employed to comprehensively capture and merge interactive features pertaining to drugs and proteins from the high-level graph. The high-level encoder incorporates a structure and attribute information fusion module designed to explicitly integrate representations acquired from both a feature encoder and a graph encoder, facilitating consensus representation learning. Extensive experiments conducted on three benchmark datasets have shown that our proposed H2GnnDTI model consistently outperforms state-of-the-art deep learning methods.

AVAILABILITY AND IMPLEMENTATION: The codes are freely available at https://github.com/LiminLi-xjtu/H2GnnDTI.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:40097269 | DOI:10.1093/bioinformatics/btaf117

Brain Res. 2025 Mar 15:149571. doi: 10.1016/j.brainres.2025.149571. Online ahead of print.

ABSTRACT

Dravet Syndrome is a severe childhood drug-resistant epilepsy. The predominant etiology of this condition is related to de novo mutations within the SCN1A gene, which codes for the alpha subunit of the NaV1.1 sodium channels. This dysfunction leads to hypoexcitability of GABAergic interneurons. In turn, the loss of electrical excitability in GABAergic interneurons leads to an imbalance of excitation over inhibition in many neural circuits. Notably, exacerbation of symptoms is observed when non-selective sodium channel blockers are administered to patients with Dravet. Recent studies in animal models of Dravet have highlighted the potential of highly specific sodium channel blockers capable of blocking other sodium channel subtypes without inhibiting NaV1.1 current and selective activators of NaV1.1 as viable therapeutic strategies for alleviating Dravet Syndrome symptoms. Here, we describe the development and validation of ligand-based machine learning models to identify ligands with inhibitory effects on sodium channel isoforms NaV1.1 and NaV1.2. These models were built based on in-house open-source routines and Mordred molecular descriptors. First, linear classifiers were inferred using a combination of feature-bagging and Forward Stepwise selection. Secondly, ensemble learning was applied to build meta-classifiers with improved predictive ability, whose performance was tested in retrospective screening experiments. After in silico validation, the models were applied to screen for drug repurposing opportunities in the DrugBank and Drug Repurposing Hub databases, to identify selective blocking agents of NaV1.2 devoid of NaV1.1 blocking activity as potential compounds for the treatment of Dravet Syndrome. Forty in silico hits were later identified in a prospective screening experiment. Four of them were acquired and submitted to experimental confirmation via patch clamp: three of these candidates, Eltrombopag, Sufugolix, and Glesatinib, showed blocking effects on NaV1.2 currents, although no subtype selectivity was observed. The different predictive abilities of the NaV1.1 and NaV1.2 models may be attributed to the different sizes of the datasets used to train and validate the respective models.

PMID:40096941 | DOI:10.1016/j.brainres.2025.149571

Biophys Chem. 2025 Mar 10;322:107434. doi: 10.1016/j.bpc.2025.107434. Online ahead of print.

ABSTRACT

Emergence of viruses cause unprecedented challenges and thus leading to wide-ranging consequences today. The world has faced massive disruptions like COVID-19 and continues to suffer in terms of public health and world economy. Fighting with this emergence of viruses and its reemergence plays a critical role in the health care industry. Identification of novel virus-drug associations is a vital step in drug discovery. Prediction and prioritization of novel virus-drug associations through computational approaches is an alternative and best choice considering the cost and risk of biological experiments. This study proposes a method, KR-AEVDA that relies on k-nearest neighbor based reliable negative sample selection and autoencoder based feature extraction to explore promising virus-drug associations for further experimental validation. The method analyzes complex relationships among drugs and viruses by investigating similarity and association data between drugs and viruses. It generates feature vectors from the similarity data, and reliable negative samples are extracted through an effective distance-based algorithm from the unlabeled samples in the dataset. Then high level features are extracted via an autoencoder and is fed to an ensemble classifier for inferring novel associations. Experimental results on three different datasets showed that KR-AEVDA reliably attained better performance than other state-of-the-art methods. Molecular docking is carried out between the top-predicted drugs and the crystal structure of the SARS-CoV-2's main protease to further validate the predictions. Case studies for SARS-CoV-2 illustrate the effectiveness of KR-AEVDA in identifying potential virus-drug associations.

PMID:40096790 | DOI:10.1016/j.bpc.2025.107434

Pancreatology. 2025 Feb 28:S1424-3903(25)00043-2. doi: 10.1016/j.pan.2025.02.015. Online ahead of print.

ABSTRACT

BACKGROUND: Pancreatic exocrine insufficiency (PEI) is defined as a reduction in pancreatic exocrine secretion below a level that allows normal digestion of nutrients. Pancreatic disease and pancreatic surgery are the main causes of PEI, but other conditions can affect the digestive function of the pancreas.

METHODS: In collaboration with European Digestive Surgery (EDS), European Society for Pediatric Gastroenterology, Hepatology and Nutrition (ESPGHAN), European Society for Clinical Nutrition and Metabolism (ESPEN), European Society of Digestive Oncology (ESDO), and European Society of Primary Care Gastroenterology (ESPCG) the working group developed European guidelines for the diagnosis and therapy of PEI. United European Gastroenterology (UEG) provided both endorsement and financial support for the development of the guidelines.

RESULTS: Recommendations covered topics related to the clinical management of PEI: concept, pathogenesis, clinical relevance, general diagnostic approach, general therapeutic approach, PEI secondary to chronic pancreatitis, PEI after acute pancreatitis, PEI associated with pancreatic cancer, PEI secondary to cystic fibrosis, PEI after pancreatic surgery, PEI after esophageal, gastric, and bariatric surgery, PEI in patients with type 1 and type 2 diabetes, and PEI in other conditions.

CONCLUSIONS: The European guidelines for the diagnosis and therapy of PEI provide evidence-based recommendations concerning key aspects of the etiology, diagnosis, therapy, and follow-up, based on current available evidence. These recommendations should serve as a reference standard for existing management of PEI and as a guide for future clinical research. This article summarizes the recommendations and statements.

PMID:40097316 | DOI:10.1016/j.pan.2025.02.015

Sci Total Environ. 2025 Mar 15;972:179010. doi: 10.1016/j.scitotenv.2025.179010. Online ahead of print.

ABSTRACT

Sewage contamination of freshwater occurs in the form of raw waste or as effluent from wastewater treatment plants (WWTP's). While raw waste (animal and human) and under-functioning WWTP's can introduce live enteric bacteria to freshwater systems, most WWTP's, even when operating correctly, do not remove bacterial genetic material from treated waste, resulting in the addition of bacterial DNA, including antibiotic resistance genes, into water columns and sediment of freshwater systems. In freshwater systems with both raw and treated waste inputs, then, there will be increased interaction between live sewage-associated bacteria (untreated sewage) and DNA contamination (from both untreated and treated wastewater effluent). To evaluate this understudied interaction between DNA and bacterial contamination in the freshwater environment, we conducted a three-month field-based study of sewage-associated bacteria and genetic material in water and sediment in a freshwater tributary of the Hudson River (NY, USA) that supplies drinking water and receives treated and untreated wastewater discharges from several municipalities. Using both DNA and culture-based bacterial analyses, we found that both treated and untreated sewage influences water and sediment bacterial communities in this tributary, and water-sediment exchanges of enteric bacteria and genetic material. Our results also indicated that the treated sewage effluent on this waterway serves as a concentrated source of intI1 (antibiotic resistance) genes, which appear to collect in the sediments below the outfall along with fecal indicator bacteria. Our work also captured the environmental impact of a large rain event that perturbed bacterial populations in sediment and water matrices, independently from the outflow. This study suggests that large precipitation events are an important cause of bacterial and DNA contamination for freshwater tributaries, with runoff from the surrounding environment being an important factor.

PMID:40096758 | DOI:10.1016/j.scitotenv.2025.179010

Bioinformatics. 2025 Mar 17:btaf113. doi: 10.1093/bioinformatics/btaf113. Online ahead of print.

ABSTRACT

SUMMARY: The lit-OTAR framework, developed through a collaboration between Europe PMC and Open Targets, leverages deep learning to revolutionise drug discovery by extracting evidence from scientific literature for drug target identification and validation. This novel framework combines Named Entity Recognition (NER) for identifying gene/protein (target), disease, organism, and chemical/drug within scientific texts, and entity normalisation to map these entities to databases like Ensembl, Experimental Factor Ontology (EFO), and ChEMBL. Continuously operational, it has processed over 39 million abstracts and 4.5 million full-text articles and preprints to date, identifying more than 48.5 million unique associations that significantly help accelerate the drug discovery process and scientific research >29.9 m distinct target-disease, 11.8 m distinct target-drug, and 8.3 m distinct disease-drug relationships).

AVAILABILITY AND IMPLEMENTATION: The results are accessible through Europe PMC's SciLite web app (https://europepmc.org/) and its annotations API (https://europepmc.org/annotationsapi), as well as via the Open Targets Platform (https://platform.opentargets.org/). The daily pipeline is available at https://github.com/ML4LitS/otar-maintenance, and the Open Targets ETL processes are available at https://github.com/opentargets.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:40097274 | DOI:10.1093/bioinformatics/btaf113

Bioinformatics. 2025 Mar 17:btaf117. doi: 10.1093/bioinformatics/btaf117. Online ahead of print.

ABSTRACT

MOTIVATION: Identifying drug target interactions is a crucial step in drug repurposing and drug discovery. The significant increase in demand and the expensive nature for experimentally identifying drug target interactions necessitate computational tools for automated prediction and comprehension of drug target interactions. Despite recent advancements, current methods fail to fully leverage the hierarchical information in drug target interactions.

RESULTS: Here we introduce H2GnnDTI, a novel two-level hierarchical heterogeneous graph learning model to predict drug target interactions, by integrating the structures of drugs and proteins via a low-level view GNN (LGNN) and a high-level view GNN (HGNN). The hierarchical graph consists of high-level heterogeneous nodes representing drugs and proteins, connected by edges representing known DTIs. Each drug or protein node is further detailed in a low-level graph, where nodes represent molecules within each drug or amino acids within each protein, accompanied by their respective chemical descriptors. Two distinct low-level graph neural networks are first deployed to capture structural and chemical features specific to drugs and proteins from these low-level graphs. Subsequently, a high-level graph encoder is employed to comprehensively capture and merge interactive features pertaining to drugs and proteins from the high-level graph. The high-level encoder incorporates a structure and attribute information fusion module designed to explicitly integrate representations acquired from both a feature encoder and a graph encoder, facilitating consensus representation learning. Extensive experiments conducted on three benchmark datasets have shown that our proposed H2GnnDTI model consistently outperforms state-of-the-art deep learning methods.

AVAILABILITY AND IMPLEMENTATION: The codes are freely available at https://github.com/LiminLi-xjtu/H2GnnDTI.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:40097269 | DOI:10.1093/bioinformatics/btaf117

Zhongguo Zhen Jiu. 2025 Mar 12;45(3):391-396. doi: 10.13703/j.0255-2930.20240207-0003. Epub 2024 Oct 28.

ABSTRACT

This study aims to develop an abdominal acupoint localization system based on computer vision and convolutional neural networks (CNNs). To address the challenge of abdominal acupoint localization, a multi-task CNNs architecture was constructed and trained to locate the Shenque (CV8) and human body boundaries. Based on the identified Shenque (CV8), the system further deduces key characteristics of four acupoints: Shangwan (CV13), Qugu (CV2), and bilateral Daheng (SP15). An affine transformation matrix is applied to accurately map image coordinates to an acupoint template space, achieving precise localization of abdominal acupoints. Testing has verified that this system can accurately identify and locate abdominal acupoints in images. The development of this localization system provides technical support for TCM remote education, diagnostic assistance, and advanced TCM equipment, such as intelligent acupuncture robots, facilitating the standardization and intelligent advancement of acupuncture.

PMID:40097227 | DOI:10.13703/j.0255-2930.20240207-0003

BMJ Health Care Inform. 2025 Mar 17;32(1):e101192. doi: 10.1136/bmjhci-2024-101192.

ABSTRACT

BACKGROUND: Chronic kidney disease (CKD) is a global health concern characterised by irreversible renal damage that is often assessed using invasive renal biopsy. Accurate evaluation of interstitial fibrosis and tubular atrophy (IFTA) is crucial for CKD management. This study aimed to leverage machine learning (ML) models to predict IFTA using a combination of ultrasonography (US) images and patient biomarkers.

METHODS: We retrospectively collected US images and biomarkers from 632 patients with CKD across three hospitals. The data were subjected to pre-processing, exclusion of sub-optimal images, and feature extraction using a dual-path convolutional neural network. Various ML models, including XGBoost, random forest and logistic regression, were trained and validated using fivefold cross-validation.

RESULTS: The dataset was divided into training and test datasets. For image-level IFTA classification, the best performance was achieved by combining US image features and patient biomarkers, with logistic regression yielding an area under the receiver operating characteristic curve (AUROC) of 99%. At the patient level, logistic regression combining US image features and biomarkers provided an AUROC of 96%. Models trained solely on US image features or biomarkers also exhibited high performance, with AUROC exceeding 80%.

CONCLUSION: Our artificial intelligence-based approach to IFTA classification demonstrated high accuracy and AUROC across various ML models. By leveraging patient biomarkers alone, this method offers a non-invasive and robust tool for early CKD assessment, demonstrating that biomarkers alone may suffice for accurate predictions without the added complexity of image-derived features.

PMID:40097202 | DOI:10.1136/bmjhci-2024-101192

Am J Vet Res. 2025 Mar 17:1-8. doi: 10.2460/ajvr.24.08.0248. Online ahead of print.

ABSTRACT

OBJECTIVE: The purpose of this research was to examine the feasibility of utilizing generative adversarial networks (GANs) to generate accurate pseudo-CT images for dogs.

METHODS: This study used head standard CT images and T1-weighted transverse with contrast 3-D fast spoiled gradient echo head MRI images from 45 nonbrachycephalic dogs that received treatment between 2014 and 2023. Two conditional GANs (CGANs), one with a U-Net generator and a PatchGAN discriminator and another with a residual neural network (ResNet) U-Net generator and ResNet discriminator were used to generate the pseudo-CT images.

RESULTS: The CGAN with a ResNet U-Net generator and ResNet discriminator had an average mean absolute error of 109.5 ± 153.7 HU, average peak signal-to-noise ratio of 21.2 ± 4.31 dB, normalized mutual information of 0.89 ± 0.05, and dice similarity coefficient of 0.91 ± 0.12. The dice similarity coefficient for the bone was 0.71 ± 0.17. Qualitative results indicated that the most common ranking was "slightly similar" for both models. The CGAN with a ResNet U-Net generator and ResNet discriminator produced more accurate pseudo-CT images than the CGAN with a U-Net generator and PatchGAN discriminator.

CONCLUSIONS: The study concludes that CGAN can generate relatively accurate pseudo-CT images but suggests exploring alternative GAN extensions.

CLINICAL RELEVANCE: Implementing generative learning into veterinary radiation therapy planning demonstrates the potential to reduce imaging costs and time.

PMID:40096825 | DOI:10.2460/ajvr.24.08.0248

Psychiatry Res Neuroimaging. 2025 Mar 14;349:111970. doi: 10.1016/j.pscychresns.2025.111970. Online ahead of print.

ABSTRACT

Autism spectrum disorder (ASD) is a neurodevelopmental condition that affects a child's cognitive and social skills, often diagnosed only after symptoms appear around age 2. Leveraging MRI for early ASD detection can improve intervention outcomes. This study proposes a framework for autism detection and region localization using an optimized deep learning approach with attention mechanisms. The pipeline includes MRI image collection, pre-processing (bias field correction, histogram equalization, artifact removal, and non-local mean filtering), and autism classification with a Symmetric Structured MobileNet with Attention Mechanism (SSM-AM). Enhanced by Refreshing Awareness-aided Election-Based Optimization (RA-EBO), SSM-AM achieves robust classification. Abnormality region localization utilizes a Multiscale Dilated Attention-based Adaptive U-Net (MDA-AUnet) further optimized by RA-EBO. Experimental results demonstrate that our proposed model outperforms existing methods, achieving an accuracy of 97.29%, sensitivity of 97.27%, specificity of 97.36%, and precision of 98.98%, significantly improving classification and localization performance. These results highlight the potential of our approach for early ASD diagnosis and targeted interventions. The datasets utilized for this work are publicly available at https://fcon_1000.projects.nitrc.org/indi/abide/.

PMID:40096789 | DOI:10.1016/j.pscychresns.2025.111970

Psychiatry Res Neuroimaging. 2025 Mar 13;349:111969. doi: 10.1016/j.pscychresns.2025.111969. Online ahead of print.

ABSTRACT

Schizophrenia (SZ) is a complex mental disorder characterized by a profound disruption in cognition and emotion, often resulting in a distorted perception of reality. Magnetic resonance imaging (MRI) is an essential tool for diagnosing SZ which helps to understand the organization of the brain. Functional MRI (fMRI) is a specialized imaging technique to measure and map brain activity by detecting changes in blood flow and oxygenation. The proposed paper correlates the results using an explainable deep learning approach to identify the significant regions of SZ patients using group-level analysis for both structural MRI (sMRI) and fMRI data. The study found that the heat maps for Grad-CAM show clear visualization in the frontal lobe for the classification of SZ and CN with a 97.33% accuracy. The group difference analysis reveals that sMRI data shows intense voxel activity in the right superior frontal gyrus of the frontal lobe in SZ patients. Also, the group difference between SZ and CN during n-back tasks of fMRI data indicates significant voxel activation in the frontal cortex of the frontal lobe. These findings suggest that the frontal lobe plays a crucial role in the diagnosis of SZ, aiding clinicians in planning the treatment.

PMID:40096788 | DOI:10.1016/j.pscychresns.2025.111969

Int J Pediatr Otorhinolaryngol. 2025 Mar 13;192:112311. doi: 10.1016/j.ijporl.2025.112311. Online ahead of print.

ABSTRACT

IMPORTANCE: The ability to augment routine post-operative tube check appointments with at-home digital otoscopes and deep learning AI could improve health care access as well as reduce financial and time burden on families.

OBJECTIVE: Tympanostomy tube checks are necessary but are also burdensome to families and impact access to care for other children seeking otolaryngologic care. Telemedicine care would be ideal, but ear exams are limited. This study aimed to assess whether an artificial intelligence (AI) algorithm trained with images from an over-the-counter digital otoscope can accurately assess tube status as in place and patent, extruded, or absent.

DESIGN: A prospective study of children aged 10 months to 10 years being seen for tympanostomy tube follow-up was carried out in three clinics from May-November 2023. A smartphone otoscope was used by non-MDs to capture images of the ear canal and tympanic membranes. Pediatric otolaryngologist exam findings (tube in place, extruded, absent) were used as a gold standard. A deep learning algorithm was trained and tested with these images. Statistical analysis was performed to determine the performance of the algorithm.

SETTING: 3 urban, pediatric otolaryngology clinics within an academic medical center.

PARTICIPANTS: Pediatric patients aged 10 months to 10 years with a past or current history of tympanostomy tubes were recruited. Patients were excluded from this study if they had a history of myringoplasty, tympanoplasty, or cholesteatoma. Main Outcome MeasureCalculated accuracy, sensitivity, and specificity for the deep learning algorithm in classifying tubal status as either in place and patent, extruded in external ear canal, or absent.

RESULTS: A heterogeneous group of 69 children yielded 296 images. Multiple types of tympanostomy tubes were included. The image capture success rate was 90.8 % in all subjects and 80 % in children with developmental delay/autism spectrum disorder. The classification accuracy was 97.1 %, sensitivity 97.1 %, and specificity 98.6 %.

CONCLUSION: A deep learning algorithm was trained with images from a representative pediatric population. It was highly accurate, sensitive, and specific. These results suggest that AI technology could be used to augment tympanostomy tube checks.

PMID:40096786 | DOI:10.1016/j.ijporl.2025.112311

Comput Biol Med. 2025 Mar 16;189:110002. doi: 10.1016/j.compbiomed.2025.110002. Online ahead of print.

ABSTRACT

Assessing fetal health traditionally involves techniques like echocardiography, which require skilled professionals and specialized equipment, making them unsuitable for low-resource settings. An emerging alternative is Phonocardiography (PCG), which offers affordability but suffers from challenges related to accuracy and complexity. To address these limitations, we propose a deep learning model, Fetal Heart Sounds U-NetR (FHSU-NETR), capable of extracting both fetal and maternal heart rates directly from raw PCG signals. FHSU-NETR is designed for practical implementation in various healthcare environments, enhancing accessibility and reliability of fetal monitoring. Due to its enhanced capacity to simulate remote interactions and capture global context, the suggested pipeline utilizes the self-attention mechanism of the transformer. Validated with data from 20 normal subjects, including a case of fetal tachycardia arrhythmia, FHSU-NETR demonstrated exceptional performance. It accurately identified most of the fetal heartbeat locations with a low mean difference in fetal heart rate estimation (-2.55±10.25 bpm) across the entire dataset, and successfully detected the arrhythmia case. Similarly, FHSU-NETR showed a low mean difference in maternal heart rate estimation (-1.15±5.76 bpm) compared to the ground-truth maternal ECG. The model's exceptional ability to identify arrhythmia cases within the dataset underscores its potential for real-world application and generalization. By leveraging the capabilities of deep learning, our proposed model holds promise to reduce the reliance on medical experts for the interpretation of extensive PCG recordings, thereby enhancing efficiency in clinical settings.

PMID:40096767 | DOI:10.1016/j.compbiomed.2025.110002