Digit Health. 2025 Jan 24;11:20552076251314546. doi: 10.1177/20552076251314546. eCollection 2025 Jan-Dec.

ABSTRACT

PURPOSE: Prostate cancer (PCa) is the second most common cancer in males worldwide, requiring improvements in diagnostic imaging to identify and treat it at an early stage. Bi-parametric magnetic resonance imaging (bpMRI) is recognized as an essential diagnostic technique for PCa, providing shorter acquisition times and cost-effectiveness. Nevertheless, accurate diagnosis using bpMRI images is difficult due to the inconspicuous and diverse characteristics of malignant tumors and the intricate structure of the prostate gland. An automated system is required to assist the medical professionals in accurate and early diagnosis with less effort.

METHOD: This study recognizes the impact of zonal features on the advancement of the disease. The aim is to improve the diagnostic performance through a novel automated approach of a two-step mechanism using bpMRI images. First, pretraining a convolutional neural network (CNN)-based attention-guided U-Net model for segmenting the region of interest which is carried out in the prostate zone. Secondly, pretraining the same type of Attention U-Net is performed for lesion segmentation.

RESULTS: The performance of the pretrained models and training an attention-guided U-Net from the scratch for segmenting tumors on the prostate region is analyzed. The proposed attention-guided U-Net model achieved an area under the curve (AUC) of 0.85 and a dice similarity coefficient value of 0.82, outperforming some other pretrained deep learning models.

CONCLUSION: Our approach greatly enhances the identification and categorization of clinically significant PCa by including zonal data. Our approach exhibits exceptional performance in the accurate segmentation of bpMRI images compared to current techniques, as evidenced by thorough validation of a diverse dataset. This research not only enhances the field of medical imaging for oncology but also underscores the potential of deep learning models to progress PCa diagnosis and personalized patient care.

PMID:39866889 | PMC:PMC11758924 | DOI:10.1177/20552076251314546

Res Sq [Preprint]. 2025 Jan 9:rs.3.rs-5776937. doi: 10.21203/rs.3.rs-5776937/v1.

ABSTRACT

The G2PDeep-v2 server is a web-based platform powered by deep learning, for phenotype prediction and markers discovery from multi-omics data in any organisms including humans, plants, animals, and viruses. The server provides multiple services for researchers to create deep-learning models through an interactive interface and train these models using an automated hyperparameter tuning algorithm on high-performance computing resources. Users can visualize the results of phenotype and markers predictions and perform Gene Set Enrichment Analysis for the significant markers to provide insights into the molecular mechanisms underlying complex diseases, conditions and other biological phenotypes being studied. The G2PDeep-v2 server is publicly available at https://g2pdeep.org/ and can be utilized for all organisms.

PMID:39866874 | PMC:PMC11760241 | DOI:10.21203/rs.3.rs-5776937/v1

Comput Biol Med. 2025 Jan 25;186:109713. doi: 10.1016/j.compbiomed.2025.109713. Online ahead of print.

ABSTRACT

BACKGROUND: Ovarian cancer is among the most lethal gynecologic malignancy that threatens women's lives. Pathological diagnosis is a key tool for early detection and diagnosis of ovarian cancer, guiding treatment strategies. The evaluation of various ovarian cancer-related cells, based on morphological and immunohistochemical pathology images, is deemed an important step. Currently, the lack of a comprehensive deep learning framework for detecting various ovarian cells poses a performance bottleneck in ovarian cancer pathological diagnosis.

METHOD: This paper presents OCDet, an object detection model with channel attention, which achieves comprehensive detection of CD3, CD8, and CD20 positive lymphocytes in immunohistochemical pathology slides, and neutrophils and polyploid giant cancer cells in H&E slides of ovarian cancer. OCDet, utilizing CSPDarkNet as its backbone, incorporates an Efficient Channel Attention module for Resolution-Specified Embedding Refinement and Multi-Resolution Embedding Fusion, enabling the efficient extraction of pathological features.

RESULT: The experiment demonstrated that OCDet performed well in target detection of three types of positive lymphocytes in immunohistochemical images, as well as neutrophils and polyploid giant cancer cells in H&E images. The mAP@0.5 reached 98.82 %, 92.91 %, and 90.49 % respectively, all surpassing other compared models. The ablation experiment further highlighted the superiority of the introduced Efficient Channel Attention (ECA) mechanism.

CONCLUSION: The proposed OCDet enables accurate detection of multiple types of cells in immunohistochemical and morphological pathology images of ovarian cancer, serving as an efficient application tool for pathological diagnosis thereof. The proposed framework has the potential to be further applied to other cancer types.

PMID:39864335 | DOI:10.1016/j.compbiomed.2025.109713

Comput Biol Med. 2025 Jan 25;186:109720. doi: 10.1016/j.compbiomed.2025.109720. Online ahead of print.

ABSTRACT

Diabetes mellitus (DM) represents a major global health challenge, affecting a diverse range of demographic populations across all age groups. It has particular implications for women during pregnancy and the postpartum period. The contemporary prevalence of sedentary lifestyle patterns and suboptimal dietary practices has substantially contributed to the escalating incidence of this metabolic disorder. The timely identification of diabetes mellitus (DM) in the female population is crucial for preventing related complications and facilitating the implementation of effective therapeutic interventions. However, conventional predictive models frequently demonstrate limited external validity when applied across heterogeneous datasets, potentially compromising clinical utility. This study proposes a robust machine learning (ML) framework for diabetes prediction across diverse populations using two distinct datasets: the PIMA and BD datasets. The framework employs intra-dataset, inter-dataset, and partial fusion dataset validation techniques to comprehensively assess the generalizability and performance of various models. In intra-dataset validation, the Extreme Gradient Boosting (XGBoost) model achieved the highest accuracy on the PIMA dataset with 79%. In contrast, the Random Forest (RF) and Gradient Boosting (GB) models demonstrated accuracy close to 99% on the BD dataset. For inter-dataset validation, where models were trained on one dataset and tested on the other, the ensemble model outperformed others with 88% accuracy when trained on PIMA and tested on BD. However, model performance declined when trained on BD and tested on PIMA (74%), reflecting the challenges of inter-dataset generalization ability. Finally, during partial fusion data validation, the deep learning (DL) model achieved 74% accuracy when trained on the BD dataset augmented with 30% of the PIMA dataset. This accuracy increased to 98% when training on the PIMA dataset combined with 30% of the BD data. These findings emphasize the importance of dataset diversity and the partial fusion dataset that can significantly enhance the model's robustness and generalizability. This framework offers valuable insights into the complexities of diabetes prediction across heterogeneous environments.

PMID:39864329 | DOI:10.1016/j.compbiomed.2025.109720

J Hazard Mater. 2025 Jan 21;488:137325. doi: 10.1016/j.jhazmat.2025.137325. Online ahead of print.

ABSTRACT

Low levels of human norovirus (HuNoV) in food and environment present challenges for nucleic acid detection. This study reported an evaporation-enhanced hydrogel digital reverse transcription loop-mediated isothermal amplification (HD RT-LAMP) with interfacial enzymatic reaction for sensitive HuNoV quantification in food and water. By drying samples on a chamber array chip, HuNoV particles were enriched in situ. The interfacial amplification of nucleic acid at the hydrogel-chip interface was triggered after coating HD RT-LAMP system. Nanoconfined spaces in hydrogels provided a simple and rapid "digital format" to quantify single virus within 15 min. Through in situ evaporation for enrichment, the sensitivity level was increased by 20 times. The universality of the sensitivity-enhanced assay was also verified using other bacteria and virus. Furthermore, a deep learning model and smartphone app were developed for automatic amplicon analysis. Multiple actual samples, including 3 lake waters, strawberry, tap water and drinking water, were in situ enriched and detected for norovirus quantification using the chamber arrays. Therefore, the sensitivity-enhanced HD RT-LAMP is an efficient assay for testing biological hazards in food safety monitoring and environmental surveillance.

PMID:39864200 | DOI:10.1016/j.jhazmat.2025.137325

Zoology (Jena). 2025 Jan 20;168:126240. doi: 10.1016/j.zool.2025.126240. Online ahead of print.

ABSTRACT

Floods, which occur when the amount of precipitation surpasses the capacity of an area to drain it adequately, have detrimental consequences on the survival and future generations of fishes. However, few works have reported the prediction of this natural phenomenon in a relation to certain fish species, especially in fast-flowing rivers. In the specific context of the northern mountainous provinces of Vietnam, where the Spinibarbus sp. fish species resides, it has been observed through the current study that the fish population in Lang Son exhibits the lowest genetic diversity and genetic distance. Consequently, the population of Spinibarbus sp. in Lang Son shows a heightened susceptibility to floods, resulting in reduction in population size and compromised population resilience. In order to provide decision support information for managers, conservationists, and researchers, we have employed a genetic algorithm-support vector machine regression (GA-SVR) predictive model to map flood vulnerability using thirteen dependent variables. The study findings have unveiled a significant negative correlation between flood-sensitive regions and genetic diversity. These discoveries emphasize the significance of considering the impact of floods on the genetic diversity of Spinibarbus sp. in Lang Son through flood vulnerability mapping. This underscores the value of establishing a comprehensive framework based on the GA-SVR algorithm for early flood detection, thereby facilitating the implementation of effective measures to minimize damages and conserve this commercial fish species.

PMID:39864169 | DOI:10.1016/j.zool.2025.126240

United European Gastroenterol J. 2025 Jan 26. doi: 10.1002/ueg2.12723. Online ahead of print.

ABSTRACT

The rising incidence of pancreatic diseases, including acute and chronic pancreatitis and various pancreatic neoplasms, poses a significant global health challenge. Pancreatic ductal adenocarcinoma (PDAC) for example, has a high mortality rate due to late-stage diagnosis and its inaccessible location. Advances in imaging technologies, though improving diagnostic capabilities, still necessitate biopsy confirmation. Artificial intelligence, particularly machine learning and deep learning, has emerged as a revolutionary force in healthcare, enhancing diagnostic precision and personalizing treatment. This narrative review explores Artificial intelligence's role in pancreatic imaging, its technological advancements, clinical applications, and associated challenges. Following the PRISMA-DTA guidelines, a comprehensive search of databases including PubMed, Scopus, and Cochrane Library was conducted, focusing on Artificial intelligence, machine learning, deep learning, and radiomics in pancreatic imaging. Articles involving human subjects, written in English, and published up to March 31, 2024, were included. The review process involved title and abstract screening, followed by full-text review and refinement based on relevance and novelty. Recent Artificial intelligence advancements have shown promise in detecting and diagnosing pancreatic diseases. Deep learning techniques, particularly convolutional neural networks (CNNs), have been effective in detecting and segmenting pancreatic tissues as well as differentiating between benign and malignant lesions. Deep learning algorithms have also been used to predict survival time, recurrence risk, and therapy response in pancreatic cancer patients. Radiomics approaches, extracting quantitative features from imaging modalities such as CT, MRI, and endoscopic ultrasound, have enhanced the accuracy of these deep learning models. Despite the potential of Artificial intelligence in pancreatic imaging, challenges such as legal and ethical considerations, algorithm transparency, and data security remain. This review underscores the transformative potential of Artificial intelligence in enhancing the diagnosis and treatment of pancreatic diseases, ultimately aiming to improve patient outcomes and survival rates.

PMID:39865461 | DOI:10.1002/ueg2.12723

Eur J Nucl Med Mol Imaging. 2025 Jan 27. doi: 10.1007/s00259-024-07065-2. Online ahead of print.

ABSTRACT

PURPOSE: To develop and validate a prostate-specific membrane antigen (PSMA) PET/CT based multimodal deep learning model for predicting pathological lymph node invasion (LNI) in prostate cancer (PCa) patients identified as candidates for extended pelvic lymph node dissection (ePLND) by preoperative nomograms.

METHODS: [68Ga]Ga-PSMA-617 PET/CT scan of 116 eligible PCa patients (82 in the training cohort and 34 in the test cohort) who underwent radical prostatectomy with ePLND were analyzed in our study. The Med3D deep learning network was utilized to extract discriminative features from the entire prostate volume of interest on the PET/CT images. Subsequently, a multimodal model i.e., Multi kernel Support Vector Machine was constructed to combine the PET/CT deep learning features, quantitative PET and clinical parameters. The performance of the multimodal models was assessed using final histopathology as the reference standard, with evaluation metrics including area under the receiver operating characteristic curve (AUC), calibration curve, decision curve analysis, and compared with available nomograms and PET/CT visual evaluation result.

RESULTS: Our multimodal model incorporated clinical information, maximum standardized uptake value (SUVmax), and PET/CT deep learning features. The AUC for predicting LNI was 0.89 (95% confidence interval [CI] 0.81-0.97) for the final model. The proposed model demonstrated superior predictive accuracy in the test cohort compared to PET/CT visual evaluation result, the Memorial Sloan Kettering Cancer Center (MSKCC) and the Briganti-2017 nomograms (AUC 0.85 [95% CI 0.69-1.00] vs. 0.80 [95% CI 0.64-0.95] vs. 0.79 [95% CI 0.61-0.97] and 0.69 [95% CI 0.50-0.88], respectively). The proposed model showed similar calibration and higher net benefit as compared to the traditional nomograms.

CONCLUSION: Our multimodal deep learning model, which incorporates preoperative PSMA PET/CT imaging, shows enhanced predictive capabilities for LNI in clinically localized PCa compared to PSMA PET/CT visual evaluation result and existing nomograms like the MSKCC and Briganti-2017 nomograms. This model has the potential to reduce unnecessary ePLND procedures while minimizing the risk of missing cases of LNI.

PMID:39865180 | DOI:10.1007/s00259-024-07065-2

Sci Rep. 2025 Jan 26;15(1):3296. doi: 10.1038/s41598-025-87993-7.

ABSTRACT

In response to the pressing need for the detection of Monkeypox caused by the Monkeypox virus (MPXV), this study introduces the Enhanced Spatial-Awareness Capsule Network (ESACN), a Capsule Network architecture designed for the precise multi-class classification of dermatological images. Addressing the shortcomings of traditional Machine Learning and Deep Learning models, our ESACN model utilizes the dynamic routing and spatial hierarchy capabilities of CapsNets to differentiate complex patterns such as those seen in monkeypox, chickenpox, measles, and normal skin presentations. CapsNets' inherent ability to recognize and process crucial spatial relationships within images outperforms conventional CNNs, particularly in tasks that require the distinction of visually similar classes. Our model's superior performance, demonstrated through rigorous evaluation, exhibits significant improvements in accuracy, precision, recall, and F1 score, even with limited data. The results highlight the potential of ESACN as a reliable tool for enhancing diagnostic accuracy in medical settings. In our case study, the ESACN model was applied to a dataset comprising 659 images across four classes: 178 images of Monkeypox, 171 of Chickenpox, 80 of Measles, and 230 of Normal skin conditions. This case study underscores the model's effectiveness in real-world applications, providing robust and accurate classification that could greatly aid in early diagnosis and treatment planning in clinical environments.

PMID:39865160 | DOI:10.1038/s41598-025-87993-7

Nat Commun. 2025 Jan 26;16(1):1057. doi: 10.1038/s41467-025-56322-x.

ABSTRACT

Enhancing the ion conduction in solid electrolytes is critically important for the development of high-performance all-solid-state lithium-ion batteries (LIBs). Lithium thiophosphates are among the most promising solid electrolytes, as they exhibit superionic conductivity at room temperature. However, the lack of comprehensive understanding of their ion conduction mechanism, especially the effect of structural disorder on ionic conductivity, is a long-standing problem that limits further innovations in all-solid-state LIBs. Here, we address this challenge by establishing and employing a deep learning potential to simulate Li3PS4 electrolyte systems with varying levels of disorder. The results show that disorder-driven diffusion dynamics significantly enhances the room-temperature conductivity. We further establish bridges between dynamical characteristics, local structural features, and atomic rearrangements by applying a machine learning-based structure fingerprint termed "softness". This metric allows the classification of the disorder-induced "soft" hopping lithium ions. Our findings offer insights into ion conduction mechanisms in complex disordered structures, thereby contributing to the development of superior solid-state electrolytes for LIBs.

PMID:39865086 | DOI:10.1038/s41467-025-56322-x

Acta Med Indones. 2024 Oct;56(4):563-570.

ABSTRACT

The burden of undiagnosed diabetes mellitus (DM) is substantial, with approximately 240 million individuals globally unaware of their condition, disproportionately affecting low- and middle-income countries (LMICs), including Indonesia. Without screening, DM and its complications will impose significant pressure on healthcare systems. Current clinical practices for screening and diagnosing DM primarily involve blood or laboratory-based testing which possess limitations on access and cost. To address these challenges, researchers have developed risk-scoring tools to identify high-risk populations. However, considering generalizability, artificial intelligence (AI) technologies offer a promising approach, leveraging diverse data sources for improved accuracy. AI models (i.e., machine learning and deep learning) have yielded prediction performances of up to 98% in various diseases. This article underscores the potential of AI-driven approaches in reducing the burden of DM through accurate prediction of undiagnosed diabetes while highlighting the need for continued innovation and collaboration in healthcare delivery.

PMID:39865054

Ultrasound Med Biol. 2025 Jan 25:S0301-5629(24)00469-1. doi: 10.1016/j.ultrasmedbio.2024.12.008. Online ahead of print.

ABSTRACT

OBJECTIVE: To develop and compare methods to automatically estimate regional ultrasound image quality for echocardiography separate from view correctness.

METHODS: Three methods for estimating image quality were developed: (i) classic pixel-based metric: the generalized contrast-to-noise ratio (gCNR), computed on myocardial segments (region of interest) and left ventricle lumen (background), extracted by a U-Net segmentation model; (ii) local image coherence: the average local coherence as predicted by a U-Net model that predicts image coherence from B-mode ultrasound images at the pixel level; (iii) deep convolutional network: an end-to-end deep-learning model that predicts the quality of each region in the image directly. These methods were evaluated against manual regional quality annotations provided by three experienced cardiologists.

RESULTS: The results indicated poor performance of the gCNR metric, with Spearman correlation to annotations of ρ = 0.24. The end-to-end learning model obtained the best result, ρ = 0.69, comparable to the inter-observer correlation, ρ = 0.63. Finally, the coherence-based method, with ρ = 0.58, out-performed the classical metrics and was more generic than the end-to-end approach.

CONCLUSION: The deep convolutional network provided the most accurate regional quality prediction, while the coherence-based method offered a more generalizable solution. gCNR showed limited effectiveness in this study. The image quality prediction tool is available as an open-source Python library at https://github.com/GillesVanDeVyver/arqee.

PMID:39864961 | DOI:10.1016/j.ultrasmedbio.2024.12.008

Neurol Med Chir (Tokyo). 2025 Jan 24. doi: 10.2176/jns-nmc.2024-0163. Online ahead of print.

ABSTRACT

Non-enhanced head computed tomography is widely used for patients presenting with head trauma or stroke, given acute intracranial hemorrhage significantly influences clinical decision-making. This study aimed to develop a deep learning algorithm, referred to as DeepCT, to detect acute intracranial hemorrhage on non-enhanced head computed tomography images and evaluate its clinical applicability. We retrospectively collected 1,815 computed tomography image sets from a single center for model training. Additional computed tomography sets from 3 centers were used to construct an independent validation dataset (VAL) and 2 test datasets (GPS-C and DICH). A third test dataset (US-TW) comprised 150 cases, each from 1 hospital in Taiwan and 1 hospital in the United States of America. Our deep learning model, based on U-Net and ResNet architectures, was implemented using PyTorch. The deep learning algorithm exhibited high accuracy across the validation and test datasets, with overall accuracy ranging from 0.9343 to 0.9820. Our findings show that the deep learning algorithm effectively identifies acute intracranial hemorrhage in non-enhanced head computed tomography studies. Clinically, this algorithm can be used for hyperacute triage, reducing reporting times, and enhancing the accuracy of radiologist interpretations. The evaluation of the algorithm on both United States and Taiwan datasets further supports its universal reliability for detecting acute intracranial hemorrhage.

PMID:39864839 | DOI:10.2176/jns-nmc.2024-0163

Biosci Trends. 2025 Jan 25. doi: 10.5582/bst.2024.01370. Online ahead of print.

ABSTRACT

In human-computer interaction, gesture recognition based on physiological signals offers advantages such as a more natural and fast interaction mode and less constrained by the environment than visual-based. Surface electromyography-based gesture recognition has significantly progressed. However, since individuals have physical differences, researchers must collect data multiple times from each user to train the deep learning model. This data acquisition process can be particularly burdensome for non-healthy users. Researchers are currently exploring transfer learning and data augmentation techniques to enhance the accuracy of small-sample gesture recognition models. However, challenges persist, such as negative transfer and limited diversity in training samples, leading to suboptimal recognition performance. Therefore, We introduce motion information into sEMG-based recognition and propose a multimodal optimal matching and augmentation method for small sample gesture recognition, achieving efficient gesture recognition with only one acquisition per gesture. Firstly, this method utilizes the optimal matching signal selection module to select the most similar signals from the existing data to the new user as the training set, reducing inter-domain differences. Secondly, the similarity calculation augmentation module enhances the diversity of the training set. Finally, the Modal-type embedding enhances the information interaction between each mode signal. We evaluated the effectiveness on Self-collected Stroke Patient, the Ninapro DB1 dataset and the Ninapro DB5 dataset and achieved accuracies of 93.69%, 91.65% and 98.56%, respectively. These results demonstrate that the method achieved performance comparable to traditional recognition models while significantly reducing the collected data.

PMID:39864830 | DOI:10.5582/bst.2024.01370

J Cardiovasc Magn Reson. 2025 Jan 24:101844. doi: 10.1016/j.jocmr.2025.101844. Online ahead of print.

ABSTRACT

PURPOSE: To investigate image quality and agreement of derived cardiac function parameters in a novel joint image reconstruction and segmentation approach based on disentangled representation learning, enabling real-time cardiac cine imaging during free-breathing.

METHODS: A multi-tasking neural network architecture, incorporating disentangled representation learning, was trained using simulated examinations based on data from a public repository along with MR scans specifically acquired for model development. An exploratory feasibility study evaluated the method on undersampled real-time acquisitions using an in-house developed spiral bSSFP pulse sequence in eight healthy participants and five patients with intermittent atrial fibrillation. Images and predicted LV segmentations were compared to the reference standard of ECG-gated segmented Cartesian cine with repeated breath-holds and corresponding manual segmentation.

RESULTS: On a 5-point Likert scale, image quality of the real-time breath-hold approach and Cartesian cine was comparable in healthy participants (RT-BH: 1.99 ±.98, Cartesian: 1.94 ±.86, p=.052), but slightly inferior in free-breathing (RT-FB: 2.40 ±.98, p<.001). In patients with arrhythmia, both real-time approaches demonstrated favourable image quality (RT-BH: 2.10 ± 1.28, p<.001, RT-FB: 2.40 ± 1.13, p<.01, Cartesian: 2.68 ± 1.13). Intra-observer reliability was good (ICC=.77,95%-confidence interval [.75,.79], p<.001). In functional analysis, a positive bias was observed for ejection fractions derived from the proposed model compared to the clinical reference standard (RT-BH mean: 58.5 ± 5.6%, bias: +3.47%, 95%-confidence interval [-.86, 7.79%], RT-FB mean: 57.9 ± 10.6%, bias: +1.45%, [-3.02, 5.91%], Cartesian mean: 54.9 ± 6.7%).

CONCLUSION: The introduced real-time MR imaging technique enables high-quality cardiac cine data acquisitions in 1-2minutes, eliminating the need for ECG gating and breath-holds. This approach offers a promising alternative to the current clinical practice of segmented acquisition, with shorter scan times, improved patient comfort, and increased robustness to arrhythmia and patient non-compliance.

PMID:39864743 | DOI:10.1016/j.jocmr.2025.101844

Osteoarthritis Cartilage. 2025 Jan 24:S1063-4584(25)00018-4. doi: 10.1016/j.joca.2025.01.001. Online ahead of print.

ABSTRACT

OBJECTIVE: Knee-adjacent subcutaneous fat (kaSCF) has emerged as a potential biomarker and risk factor for OA progression. This study aims to develop an AI-based tool for the automatic segmentation of kaSCF thickness and evaluate the cross-sectional associations between kaSCF, cartilage thickness, MRI-based cartilage T2 relaxation time, knee pain, and muscle strength independent of BMI.

DESIGN: Baseline 3.0T MR images of the right knee from the entire Osteoarthritis Initiative (OAI) cohort (n=4796) were used to quantify average values of kaSCF, cartilage thickness, and T2 using deep learning algorithms. Regression models (adjusted for age, gender, BMI, and race) were used to evaluate the associations between standardized kaSCF and outcomes of cartilage thickness, T2, pain, and knee extension strength.

RESULTS: Model prediction CVs for kaSCF thickness ranged from 3.57% to 9.87% across femoral and tibial regions. Greater average kaSCF was associated with thinner cartilage in men (std. β= -0.029, 95% CI: -0.050 to -0.007, p=0.010) and higher T2 in women (std. β=0.169, 95% CI: 0.072 to 0.265, p=0.001). Greater kaSCF was also associated with lower knee extension force (std. β= -15.36, 95% CI: -20.39 to -10.33, p<0.001) and higher odds of frequent knee pain (std. OR=1.156, 95% CI: 1.046 to 1.278, p=0.005) across all participants.

CONCLUSIONS: Greater kaSCF was associated with thinner cartilage in men, higher T2 in women, reduced knee strength, and greater knee pain, independent of BMI. These findings suggest a potential role of kaSCF as a predictor for KOA-related structural, functional, and clinical outcomes independent of the effects of BMI.

PMID:39864732 | DOI:10.1016/j.joca.2025.01.001

Int J Med Inform. 2025 Jan 17;196:105797. doi: 10.1016/j.ijmedinf.2025.105797. Online ahead of print.

ABSTRACT

BACKGROUND: ANCA-associated vasculitis (AAV) is a rare but serious disease. Traditional case-identification methods using claims data can be time-intensive and may miss important subgroups. We hypothesized that a deep learning model analyzing electronic health records (EHR) can more accurately identify AAV cases.

METHODS: We examined the Mass General Brigham (MGB) repository of clinical documentation from 12/1/1979 to 5/11/2021, using expert-curated keywords and ICD codes to identify a large cohort of potential AAV cases. Three labeled datasets (I, II, III) were created, each containing note sections. We trained and evaluated a range of machine learning and deep learning algorithms for note-level classification, using metrics like positive predictive value (PPV), sensitivity, F-score, area under the receiver operating characteristic curve (AUROC), and area under the precision and recall curve (AUPRC). The hierarchical attention network (HAN) was further evaluated for its ability to classify AAV cases at the patient-level, compared with rule-based algorithms in 2000 randomly chosen samples.

RESULTS: Datasets I, II, and III comprised 6000, 3008, and 7500 note sections, respectively. HAN achieved the highest AUROC in all three datasets, with scores of 0.983, 0.991, and 0.991. The deep learning approach also had among the highest PPVs across the three datasets (0.941, 0.954, and 0.800, respectively). In a test cohort of 2000 cases, the HAN model achieved a PPV of 0.262 and an estimated sensitivity of 0.975. Compared to the best rule-based algorithm, HAN identified six additional AAV cases, representing 13% of the total.

CONCLUSION: The deep learning model effectively classifies clinical note sections for AAV diagnosis. Its application to EHR notes can potentially uncover additional cases missed by traditional rule-based methods.

PMID:39864108 | DOI:10.1016/j.ijmedinf.2025.105797

Radiol Med. 2025 Jan 26. doi: 10.1007/s11547-025-01957-5. Online ahead of print.

ABSTRACT

PURPOSE: To develop an artificial intelligence (AI) algorithm for automated measurements of spinopelvic parameters on lateral radiographs and compare its performance to multiple experienced radiologists and surgeons.

METHODS: On lateral full-spine radiographs of 295 consecutive patients, a two-staged region-based convolutional neural network (R-CNN) was trained to detect anatomical landmarks and calculate thoracic kyphosis (TK), lumbar lordosis (LL), sacral slope (SS), and sagittal vertical axis (SVA). Performance was evaluated on 65 radiographs not used for training, which were measured independently by 6 readers (3 radiologists, 3 surgeons), and the median per measurement was set as the reference standard. Intraclass correlation coefficient (ICC), mean absolute error (MAE), and standard deviation (SD) were used for statistical analysis; while, ANOVA was used to search for significant differences between the AI and human readers.

RESULTS: Automatic measurements (AI) showed excellent correlation with the reference standard, with all ICCs within the range of the readers (TK: 0.92 [AI] vs. 0.85-0.96 [readers]; LL: 0.95 vs. 0.87-0.98; SS: 0.93 vs. 0.89-0.98; SVA: 1.00 vs. 0.99-1.00; all p < 0.001). Analysis of the MAE (± SD) revealed comparable results to the six readers (TK: 3.71° (± 4.24) [AI] v.s 1.86-5.88° (± 3.48-6.17) [readers]; LL: 4.53° ± 4.68 vs. 2.21-5.34° (± 2.60-7.38); SS: 4.56° (± 6.10) vs. 2.20-4.76° (± 3.15-7.37); SVA: 2.44 mm (± 3.93) vs. 1.22-2.79 mm (± 2.42-7.11)); while, ANOVA confirmed no significant difference between the errors of the AI and any human reader (all p > 0.05). Human reading time was on average 139 s per case (range: 86-231 s).

CONCLUSION: Our AI algorithm provides spinopelvic measurements accurate within the variability of experienced readers, but with the potential to save time and increase reproducibility.

PMID:39864034 | DOI:10.1007/s11547-025-01957-5

Magn Reson Imaging. 2025 Jan 23:110334. doi: 10.1016/j.mri.2025.110334. Online ahead of print.

ABSTRACT

Magnetic Resonance Imaging is a cornerstone of medical diagnostics, providing high-quality soft tissue contrast through non-invasive methods. However, MRI technology faces critical limitations in imaging speed and resolution. Prolonged scan times not only increase patient discomfort but also contribute to motion artifacts, further compromising image quality. Compressed Sensing (CS) theory has enabled the acquisition of partial k-space data, which can then be effectively reconstructed to recover the original image using advanced reconstruction algorithms. Recently, deep learning has been widely applied to MRI reconstruction, aiming to reduce the artifacts in the image domain caused by undersampling in k-space and enhance image quality. As deep learning continues to evolve, the undersampling factors in k-space have gradually increased in recent years. However, these layers are limited in compensating for reconstruction errors in the unsampled areas, impeding further performance improvements. To address this, we propose a learnable spatial-frequency difference-aware module that complements the learnable data consistency layer, mapping k-space domain differences to the spatial image domain for perceptual compensation. Additionally, inspired by wavelet decomposition, we introduce explicit priors by decomposing images into mean and residual components, enforcing a refined zero-mean constraint on the residuals while maintaining computational efficiency. Comparative experiments on the FastMRI and Calgary-Campinas datasets demonstrate that our method achieves superior reconstruction performance against seven state-of-the-art techniques. Ablation studies further confirm the efficacy of our model's architecture, establishing a new pathway for enhanced MRI reconstruction.

PMID:39863026 | DOI:10.1016/j.mri.2025.110334

Neuroimage. 2025 Jan 23:121054. doi: 10.1016/j.neuroimage.2025.121054. Online ahead of print.

ABSTRACT

Magnetic resonance electrical properties tomography can extract the electrical properties of in-vivo tissue. To estimate tissue electrical properties, various reconstruction algorithms have been proposed. However, physics-based reconstructions are prone to various artifacts such as noise amplification and boundary artifact. Deep learning-based approaches are robust to these artifacts but need extensive training datasets and suffer from generalization to unseen data. To address these issues, we introduce a joint three-plane physics-constrained deep learning framework for polynomial fitting MR-EPT by merging physics-based weighted polynomial fitting with deep learning. Within this framework, deep learning is used to discern the optimal polynomial fitting weights for a physics based polynomial fitting reconstruction on the complex B1+ data. For the prediction of optimal fitting coefficients, three neural networks were separately trained on simulated heterogeneous brain models to predict optimal polynomial weighting parameters in three orthogonal planes. Then, the network weights were jointly optimized to estimate the polynomial weights in each plane for a combined conductivity reconstruction. Based on this physics-constrained deep learning approach, we achieved an improvement of conductivity estimation accuracy in comparison to a single plane estimation and a reduction of computational load. The results demonstrate that the proposed method based on 3D data exhibits superior performance in comparison to conventional polynomial fitting methods in terms of capturing anatomical detail and homogeneity. Crucially, in-vivo application of the proposed method showed that the method generalizes well to in-vivo data, without introducing significant errors or artifacts. This generalization makes the presented method a promising candidate for use in clinical applications.

PMID:39863005 | DOI:10.1016/j.neuroimage.2025.121054