Lupus Sci Med. 2025 Jan 30;12(1):e001362. doi: 10.1136/lupus-2024-001362.

ABSTRACT

OBJECTIVES: Patients with SLE take multiple medications. Within a large prospective longitudinal SLE cohort, we characterised medication-related hospitalisations and their preventability.

METHODS: We identified consecutive admissions to our tertiary hospitals between 2015 and 2020. Two independent adjudicators evaluated if medication-related events contributed to the hospitalisation, considering (1) adverse drug events (ADEs) and (2) events from medication non-adherence, using the Leape and Bates method. We classified ADEs as potentially preventable/ameliorable if we identified modifiable factors. Logistic regressions with generalised estimating equations evaluated associations between participant characteristics and medication-related hospitalisations, accounting for repeat hospitalisations within the same participant.

RESULTS: We studied 68 hospitalisations among 45 participants (91% female). At first hospitalisation, the median age was 38 years (IQR 26.5-53.0) and median SLE duration was 12 years (IQR 5.5-19.5). One or more ADEs contributed to 20 (29%) hospitalisations (11/23 (48%) ADEs being preventable/ameliorable), and SLE flares associated with medication non-adherence contributed to 7 (10%) hospitalisations. Adjusting for age and sex, current prednisone use (adjusted OR (aOR) 3.7, 95% CI 1.1 to 13.0) or ≥1 current immunosuppressant (aOR 11.5, 95% CI 2.7 to 50.0), renal involvement at SLE diagnosis (aOR 6.5, 95% CI 2.7 to 15.7) and polypharmacy (≥5 medications; aOR 11.3, 95% CI 1.2 to 103.8) were associated with having an ADE-related (vs non-ADE) hospitalisation. Age at SLE diagnosis<18 years (OR 5.9, 95% CI 1.3 to 26.6) was associated with hospitalisation for a flare related to non-adherence.

CONCLUSION: Forty per cent of SLE hospitalisations were medication-related, while half were potentially preventable/ameliorable. Renal involvement, polypharmacy, prednisone and immunosuppressant use were associated with hospitalisation related to an ADE, highlighting a vulnerable group.

PMID:39884714 | DOI:10.1136/lupus-2024-001362

J Med Internet Res. 2025 Jan 30;27:e58760. doi: 10.2196/58760.

ABSTRACT

BACKGROUND: Primary intracranial germ cell tumors (iGCTs) are highly malignant brain tumors that predominantly occur in children and adolescents, with an incidence rate ranking third among primary brain tumors in East Asia (8%-15%). Due to their insidious onset and impact on critical functional areas of the brain, these tumors often result in irreversible abnormalities in growth and development, as well as cognitive and motor impairments in affected children. Therefore, early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life.

OBJECTIVE: This study aimed to investigate the application of facial recognition technology in the early detection of iGCTs in children and adolescents. Early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life.

METHODS: A multicenter, phased approach was adopted for the development and validation of a deep learning model, GVisageNet, dedicated to the screening of midline brain tumors from normal controls (NCs) and iGCTs from other midline brain tumors. The study comprised the collection and division of datasets into training (n=847, iGCTs=358, NCs=300, other midline brain tumors=189) and testing (n=212, iGCTs=79, NCs=70, other midline brain tumors=63), with an additional independent validation dataset (n=336, iGCTs=130, NCs=100, other midline brain tumors=106) sourced from 4 medical institutions. A regression model using clinically relevant, statistically significant data was developed and combined with GVisageNet outputs to create a hybrid model. This integration sought to assess the incremental value of clinical data. The model's predictive mechanisms were explored through correlation analyses with endocrine indicators and stratified evaluations based on the degree of hypothalamic-pituitary-target axis damage. Performance metrics included area under the curve (AUC), accuracy, sensitivity, and specificity.

RESULTS: On the independent validation dataset, GVisageNet achieved an AUC of 0.938 (P<.01) in distinguishing midline brain tumors from NCs. Further, GVisageNet demonstrated significant diagnostic capability in distinguishing iGCTs from the other midline brain tumors, achieving an AUC of 0.739, which is superior to the regression model alone (AUC=0.632, P<.001) but less than the hybrid model (AUC=0.789, P=.04). Significant correlations were found between the GVisageNet's outputs and 7 endocrine indicators. Performance varied with hypothalamic-pituitary-target axis damage, indicating a further understanding of the working mechanism of GVisageNet.

CONCLUSIONS: GVisageNet, capable of high accuracy both independently and with clinical data, shows substantial potential for early iGCTs detection, highlighting the importance of combining deep learning with clinical insights for personalized health care.

PMID:39883924 | DOI:10.2196/58760

Comput Methods Biomech Biomed Engin. 2025 Jan 30:1-29. doi: 10.1080/10255842.2025.2456487. Online ahead of print.

ABSTRACT

Cardiac arrhythmias are major global health concern and their early detection is critical for diagnosis. This study comprehensively evaluates the effectiveness of CNNs and LSTMs for the classification of cardiac arrhythmias, considering three PhysioNet datasets. ECG records are segmented to accommodate around ∼10s of ECG data. Followed by transformation to scalograms using DWT for training VGG-16; and WTS for feature extraction and dimensionality reduction for training LSTM network. VGG-16 achieved 96.44% test accuracy while LSTM achieved 92%. Results also highlight the effectiveness of VGG-16 for short-duration ECG analysis, while LSTM excels in long-term monitoring on edge devices for personalized healthcare.

PMID:39883911 | DOI:10.1080/10255842.2025.2456487

J Chem Inf Model. 2025 Jan 30. doi: 10.1021/acs.jcim.4c02060. Online ahead of print.

ABSTRACT

Machine learning approaches often involve evaluating a wide range of models due to various available architectures. This standard strategy can lead to a lack of depth in exploring established methods. In this study, we concentrated our efforts on a single deep learning architecture type to assess whether a focused approach could enhance performance in fault diagnosis. We selected the benchmark Tennessee Eastman Process data set as our case study and investigated modifications on a reference convolutional neural network-based model. Results indicate a considerable improvement in the overall classification, reaching a maximum average F1-score of 89.85%, 7.47% above the baseline model, which is also a considerable improvement compared to other performances reported in the literature. These results emphasize the potential of this focused approach, indicating it could be further explored and applied to other data sets in future work.

PMID:39883649 | DOI:10.1021/acs.jcim.4c02060

J Am Med Inform Assoc. 2025 Jan 30:ocae327. doi: 10.1093/jamia/ocae327. Online ahead of print.

ABSTRACT

BACKGROUND: With the global population aging and advancements in the medical system, long-term care in healthcare institutions and home settings has become essential for older adults with disabilities. However, the diverse and scattered care requirements of these individuals make developing effective long-term care plans heavily reliant on professional nursing staff, and even experienced caregivers may make mistakes or face confusion during the care plan development process. Consequently, there is a rigid demand for intelligent systems that can recommend comprehensive long-term care plans for older adults with disabilities who have stable clinical conditions.

OBJECTIVE: This study aims to utilize deep learning methods to recommend comprehensive care plans for the older adults with disabilities.

METHODS: We model the care data of older adults with disabilities using a bipartite graph. Additionally, we employ a prediction-based graph self-supervised learning (SSL) method to mine deep representations of graph nodes. Furthermore, we propose a novel graph Transformer architecture that incorporates eigenvector centrality to augment node features and uses graph structural information as references for the self-attention mechanism. Ultimately, we present the Bipartite Graph Transformer (BiT) model to provide personalized long-term care plan recommendation.

RESULTS: We constructed a bipartite graph comprising of 1917 nodes and 195 240 edges derived from real-world care data. The proposed model demonstrates outstanding performance, achieving an overall F1 score of 0.905 for care plan recommendations. Each care service item reached an average F1 score of 0.897, indicating that the BiT model is capable of accurately selecting services and effectively balancing the trade-off between incorrect and missed selections.

DISCUSSION: The BiT model proposed in this paper demonstrates strong potential for improving long-term care plan recommendations by leveraging bipartite graph modeling and graph SSL. This approach addresses the challenges of manual care planning, such as inefficiency, bias, and errors, by offering personalized and data-driven recommendations. While the model excels in common care items, its performance on rare or complex services could be enhanced with further refinement. These findings highlight the model's ability to provide scalable, AI-driven solutions to optimize care planning, though future research should explore its applicability across diverse healthcare settings and service types.

CONCLUSIONS: Compared to previous research, the novel model proposed in this article effectively learns latent topology in bipartite graphs and achieves superior recommendation performance. Our study demonstrates the applicability of SSL and graph transformers in recommending long-term care plans for older adults with disabilities.

PMID:39883541 | DOI:10.1093/jamia/ocae327

Pulmonology. 2025 Dec 31;31(1):2425503. doi: 10.1080/25310429.2024.2425503. Epub 2024 Nov 12.

ABSTRACT

Fibrotic hypersensitivity pneumonitis (f-HP) is an interstitial lung disease in which various antigens in susceptible individuals may play a pathogenetic role. This study evaluates the role of transbronchial lung cryobiopsy (TBLC) and bronchoalveolar lavage (BAL) in identifying a UIP-like pattern and its association with fibrosis progression. We conducted a multicentre retrospective cohort study of patients diagnosed with f-HP who underwent BAL and TBLC between 2011 and 2023. A UIP-like pattern was defined by the presence of (A) patchy fibrosis and fibroblastic foci or (B) honeycombing ± (A). We investigated BAL's role in predicting UIP-like patterns within a clinical-radiological-serological framework, examining disease progression in these patients using spirometry and mortality data. A total of 195 patients were enrolled, 59 (30%) of whom exhibited a UIP-like pattern. These patients showed greater lung function decline, lower BAL lymphocytosis (14.4% vs. 37.4%, p < 0.001), higher nintedanib prescription (35% vs. 14%, p < 0.001), and higher 10-year mortality (HR 2.8, 95% CI 1.3-5.8, p = 0.004). f-HP patients with a UIP-like pattern exhibit worse clinical outcomes and higher mortality. In cases of low BAL lymphocytosis with a high pre-test clinical suspicion of f-HP, lung biopsy may not be necessary as it increases the likelihood of identifying a UIP-like pattern.

PMID:39883494 | DOI:10.1080/25310429.2024.2425503

ACS Synth Biol. 2025 Jan 30. doi: 10.1021/acssynbio.4c00672. Online ahead of print.

ABSTRACT

Fungi, especially filamentous fungi, are a relatively understudied, biotechnologically useful resource with incredible potential for commercial applications. These multicellular eukaryotic organisms have long been exploited for their natural production of useful commodity chemicals and proteins such as enzymes used in starch processing, detergents, food and feed production, pulping and paper making and biofuels production. The ability of filamentous fungi to use a wide range of feedstocks is another key advantage. As chassis organisms, filamentous fungi can express cellular machinery, and metabolic and signal transduction pathways from both prokaryotic and eukaryotic origins. Their genomes abound with novel genetic elements and metabolic processes that can be harnessed for biotechnology applications. Synthetic biology tools are becoming inexpensive, modular, and expansive while systems biology is beginning to provide the level of understanding required to design increasingly complex synthetic systems. This review covers the challenges of working in filamentous fungi and offers a perspective on the approaches needed to exploit fungi as microbial cell factories.

PMID:39883596 | DOI:10.1021/acssynbio.4c00672

PLoS Biol. 2025 Jan 30;23(1):e3002730. doi: 10.1371/journal.pbio.3002730. eCollection 2025 Jan.

ABSTRACT

Food presents a multisensory experience, with visual, taste, and olfactory cues being important in allowing an animal to determine the safety and nutritional value of a given substance. Texture, however, remains a surprisingly unexplored aspect, despite providing key information about the state of the food through properties such as hardness, liquidity, and granularity. Food perception is achieved by specialised sensory neurons, which themselves are defined by the receptor genes they express. While it was assumed that sensory neurons respond to one or few closely related stimuli, more recent findings challenge this notion and support evidence that certain sensory neurons are more broadly tuned. In the Drosophila taste system, gustatory neurons respond to cues of opposing hedonic valence or to olfactory cues. Here, we identified that larvae ingest and navigate towards specific food substrate hardnesses and probed the role of gustatory organs in this behaviour. By developing a genetic tool targeting specifically gustatory organs, we show that these organs are major contributors for evaluation of food hardness and ingestion decision-making. We find that ablation of gustatory organs not only results in loss of chemosensation, but also navigation and ingestion preference to varied substrate hardnesses. Furthermore, we show that certain neurons in the primary taste organ exhibit varied and concurrent physiological responses to mechanical and multimodal stimulation. We show that individual neurons house independent mechanisms for multiple sensory modalities, challenging assumptions about capabilities of sensory neurons. We propose that further investigations, across the animal kingdom, may reveal higher sensory complexity than currently anticipated.

PMID:39883595 | DOI:10.1371/journal.pbio.3002730

Age Ageing. 2025 Jan 6;54(1):afaf008. doi: 10.1093/ageing/afaf008.

ABSTRACT

BACKGROUND: Immune checkpoint inhibitors (ICIs) have revolutionised cancer therapy, yet they carry a unique spectrum of immune-related adverse events (irAEs). Given the ageing global population and the underrepresentation of older adults in clinical trials for ICIs, we investigated the occurrence and characteristics of irAEs in older versus younger adults as well as among different age subsets within the older adult population.

METHODS: We analysed the U.S. Food and Drug Administration Adverse Event Reporting System database reports from 2015 to 2023, focusing on ICIs. We categorised irAEs into 11 distinct types and performed descriptive and multivariate analyses to compare the prevalence and clinical characteristics of irAEs across different age groups, adjusting for potential confounding factors.

RESULTS: Among 47 513 patients aged 18-100 reporting irAEs, the 65-74 and 75-84 age groups had significantly increased risks compared to 18-64 (OR 1.13, 95% CI [1.09-1.18]; 1.15 [1.1-1.21]). Cardiovascular irAEs rose with age, peaking at 75-84, while endocrine irAEs decreased. Hepatobiliary, gastrointestinal and ocular irAEs decreased with age, but renal and musculoskeletal irAEs increased, showing higher risks in older adults. Serious outcomes slightly decreased in the 85+ group, while the proportion of deaths increased with age.

CONCLUSION: We discuss the potential changes in the immune system contributing to the decreased prevalence of irAEs in the oldest age group. Additionally, conservative treatment approaches and underreporting of irAEs in older patients may influence these findings. Our findings highlight the need for personalised decision-making for ICI therapies, considering performance status and comorbidities rather than age alone.

PMID:39883592 | DOI:10.1093/ageing/afaf008

Infection. 2025 Jan 30. doi: 10.1007/s15010-025-02478-z. Online ahead of print.

ABSTRACT

BACKGROUND: Lung transplantation is the ultimate treatment option for patients with advanced cystic fibrosis. Chronic colonization of these recipients with multidrug-resistant (MDR) pathogens may constitute a risk factor for an adverse outcome. We sought to analyze whether colonization with MDR pathogens, as outlined in the German classification of multiresistant Gram-negative bacteria (MRGN), was associated with the success of lung transplantation.

METHODS: We performed a monocentric retrospective analysis of 361 lung transplantations performed in Homburg, Germany, between 1995 and 2020. All recipients with a main diagnosis of cystic fibrosis (n = 69) were stratified into two groups based on colonization with Pseudomonas aeruginosa in view of MRGN before transplantation: no colonization and colonization without (n = 23) or with (n = 46) resistance to three or four antibiotic groups (3MRGN/4MRGN). Multivariable analyses were performed including various clinical parameters (preoperative data, postoperative data).

RESULTS: CF patients colonized with multidrug-resistant pathogens (Pseudomonas aeruginosa) classified as 3MRGN/4MRGN had poorer survival (median survival 16 years (without MRGN) versus 8 years (with MRGN), P = 0.048). Extracorporeal support (P = 0.014, HR = 2.929), re-transplantation (P = 0.023, HR = 2.303), female sex (P = 0.019, HR = 2.244) and 3MRGN/4MRGN (P = 0.036, HR = 2.376) were predictors of poor outcomes in the multivariate analysis. Co-colonization with the mold Aspergillus fumigatus was further associated with mortality risk in the 3MRGN/4MRGN group (P = 0.037, HR = 2.150).

CONCLUSION: Patients with cystic fibrosis and MDR colonization (Pseudomonas aeruginosa) are risk candidates for lung transplantation, targeted diagnostics and tailored anti-infective strategies are essential for survival after surgery. MDR colonization as expressed by MRGN may help to identify patients at increased risk to improve the organ allocation process.

PMID:39883262 | DOI:10.1007/s15010-025-02478-z

Eur J Pediatr. 2025 Jan 30;184(2):161. doi: 10.1007/s00431-025-05969-1.

ABSTRACT

It is known that in most cases of congenital central hypoventilation syndrome (CCHS), apnoeas and hypoventilation occur at birth. Nevertheless, a detailed description of initial symptoms, including pregnancy events and diagnostic tests performed, is warranted in infants with neonatal onset of CCHS, that is, in the first month of life. The European Central Hypoventilation Syndrome Consortium created an online patient registry from which 97 infants (44 females) with CCHS of neonatal onset and PHOX2B mutation from 10 countries were selected. The typical pregnancy is characterized by polyhydramnios (44%), fetal heart rate abnormalities on cardiotocography (36%), emergency cesarean sections. (30%) and a normal gestational age (14% preterm birth). The typical findings within the first days are the presence of respiratory distress (96%), often necessitating rapid intubation (44%) and, less frequently, cardiopulmonary resuscitation at birth (14%). These symptoms lead to a suspicion of CCHS after (median [interquartile]) 7 days [4; 12] since birth that is confirmed by genotype testing at 32 days [22; 61]. Daytime evaluation of blood gas is a frequent assessment leading to CCHS suspicion (n = 61/97, 63%; 95% confidence interval: 52-72) while a polysomnography is obtained in 45/97 infants (46%, 95% confidence interval: 36-57), demonstrating NREM hypoventilation in 44/45 infants (98%).

CONCLUSION: Our multicentre descriptive study shows that polyhydramnios is overrepresented during pregnancy, rapid respiratory failure is the main symptom leading to intubation in approximately half of infants and daytime alveolar hypoventilation is the main indicator prompting genetic testing.

WHAT IS KNOWN: • The initial symptoms and exams leading to congenital central hypoventilation syndrome diagnosis have mainly been described in single centre studies.

WHAT IS NEW: • Our multicentre European study confirms that polyhydramnios is overrepresented during pregnancy and that polysomnography is obtained in half of the infants only.

PMID:39883186 | DOI:10.1007/s00431-025-05969-1

J Med Chem. 2025 Jan 30. doi: 10.1021/acs.jmedchem.4c02547. Online ahead of print.

ABSTRACT

Cystic fibrosis (CF) is a genetic disorder caused by mutations in the cystic fibrosis transmembrane conductance regulator (CFTR) gene, which regulates ion and fluid transport across epithelial cells. Mutations lead to complications, with life-limiting lung disease being the most severe manifestation. Traditional treatments focused on managing symptoms, but advances in understanding CF's molecular basis led to small-molecule CFTR modulators. Ivacaftor, which is a potentiator, was approved for gating mutations. Dual combinations like ivacaftor/lumacaftor and ivacaftor/tezacaftor brought together a potentiator and a class 1 corrector for F508del homozygous patients. Triple-combination CFTR modulators, including ivacaftor/tezacaftor/elexacaftor with an additional class 2 corrector, are now the standard of care for most CF patients, transforming the outlook for this disease. These drugs stabilize and potentiate the CFTR protein, improving lung function, sweat chloride levels, quality of life, and survival. This Perspective discusses CFTR structure and mutations, biological assays, medicinal chemistry research in identifying CFTR modulators, and clinical data of these agents.

PMID:39882833 | DOI:10.1021/acs.jmedchem.4c02547

Med Biol Eng Comput. 2025 Jan 30. doi: 10.1007/s11517-025-03295-0. Online ahead of print.

ABSTRACT

With the advancement of artificial intelligence technology, more and more effective methods are being used to identify and classify Electroencephalography (EEG) signals to address challenges in healthcare and brain-computer interface fields. The applications and major achievements of Graph Convolution Network (GCN) techniques in EEG signal analysis are reviewed in this paper. Through an exhaustive search of the published literature, a module-by-module discussion is carried out for the first time to address the current research status of GCN. An exhaustive classification of methods and a systematic analysis of key modules, such as brain map construction, node feature extraction, and GCN architecture design, are presented. In addition, we pay special attention to several key research issues related to GCN. This review enhances the understanding of the future potential of GCN in the field of EEG signal analysis. At the same time, several valuable development directions are sorted out for researchers in related fields, such as analysing the applicability of different GCN layers, building task-oriented GCN models, and improving adaptation to limited data.

PMID:39883372 | DOI:10.1007/s11517-025-03295-0

EJNMMI Phys. 2025 Jan 30;12(1):9. doi: 10.1186/s40658-025-00724-9.

ABSTRACT

Single photon emission computed tomography (SPECT), a technique capable of capturing functional and molecular information, has been widely adopted in theranostics applications across various fields, including cardiology, neurology, and oncology. The spatial resolution of SPECT imaging is relatively poor, which poses a significant limitation, especially the visualization of small lesions. The main factors affecting the limited spatial resolution of SPECT include projection sampling techniques, hardware and software. Both hardware and software innovations have contributed substantially to improved SPECT imaging quality. The present review provides an overview of state-of-the-art methods for improving spatial resolution in clinical and pre-clinical SPECT systems. It delves into advancements in detector design and modifications, projection sampling techniques, traditional reconstruction algorithm development and optimization, and the emerging role of deep learning. Hardware enhancements can result in SPECT systems that are both lighter and more compact, while also improving spatial resolution. Software innovations can mitigate the costs of hardware modifications. This survey offers a thorough overview of the rapid advancements in resolution enhancement techniques within the field of SPECT, with the objective of identifying the most recent trends. This is anticipated to facilitate further optimization and improvement of clinical systems, enabling the visualization of small lesions in the early stages of tumor detection, thereby enhancing accurate localization and facilitating both diagnostic imaging and radionuclide therapy, ultimately benefiting both clinicians and patients.

PMID:39883257 | DOI:10.1186/s40658-025-00724-9

Adv Biotechnol (Singap). 2024 Mar 1;2(1):9. doi: 10.1007/s44307-024-00018-8.

ABSTRACT

Engineering microbial cell factories have achieved much progress in producing fuels, natural products and bulk chemicals. However, in industrial fermentation, microbial cells often face various predictable and stochastic disturbances resulting from intermediate metabolites or end product toxicity, metabolic burden and harsh environment. These perturbances can potentially decrease productivity and titer. Therefore, strain robustness is essential to ensure reliable and sustainable production efficiency. In this review, the current strategies to improve host robustness were summarized, including knowledge-based engineering approaches, such as transcription factors, membrane/transporters and stress proteins, and the traditional adaptive laboratory evolution based on natural selection. Computation-assisted (e.g. GEMs, deep learning and machine learning) design of robust industrial hosts was also introduced. Furthermore, the challenges and future perspectives on engineering microbial host robustness are proposed to promote the development of green, efficient and sustainable biomanufacturers.

PMID:39883204 | DOI:10.1007/s44307-024-00018-8

Eur Spine J. 2025 Jan 30. doi: 10.1007/s00586-025-08672-9. Online ahead of print.

ABSTRACT

PURPOSE: Lumbar spinal stenosis (LSS) is a frequently occurring condition defined by narrowing of the spinal or nerve root canal due to degenerative changes. Physicians use MRI scans to determine the severity of stenosis, occasionally complementing it with X-ray or CT scans during the diagnostic work-up. However, manual grading of stenosis is time-consuming and induces inter-reader variability as a standardized grading system is lacking. Machine Learning (ML) has the potential to aid physicians in this process by automating segmentation and classification of LSS. However, it is unclear what models currently exist to perform these tasks.

METHODS: A systematic review of literature was performed by searching the Cochrane Library, Embase, Emcare, PubMed, and Web of Science databases for studies describing an ML-based algorithm to perform segmentation or classification of the lumbar spine for LSS. Risk of bias was assessed through an adjusted version of the Newcastle-Ottawa Quality Assessment Scale that was more applicable to ML studies. Qualitative analyses were performed based on type of algorithm (conventional ML or Deep Learning (DL)) and task (segmentation or classification).

RESULTS: A total of 27 articles were included of which nine on segmentation, 16 on classification and 2 on both tasks. The majority of studies focused on algorithms for MRI analysis. There was wide variety among the outcome measures used to express model performance. Overall, ML algorithms are able to perform segmentation and classification tasks excellently. DL methods tend to demonstrate better performance than conventional ML models. For segmentation the best performing DL models were U-Net based. For classification U-Net and unspecified CNNs powered the models that performed the best for the majority of outcome metrics. The number of models with external validation was limited.

CONCLUSION: DL models achieve excellent performance for segmentation and classification tasks for LSS, outperforming conventional ML algorithms. However, comparisons between studies are challenging due to the variety in outcome measures and test datasets. Future studies should focus on the segmentation task using DL models and utilize a standardized set of outcome measures and publicly available test dataset to express model performance. In addition, these models need to be externally validated to assess generalizability.

PMID:39883162 | DOI:10.1007/s00586-025-08672-9

Eur Radiol. 2025 Jan 30. doi: 10.1007/s00330-025-11385-8. Online ahead of print.

ABSTRACT

OBJECTIVES: We aimed to use artificial intelligence to accurately identify molecular subgroups of medulloblastoma (MB), predict clinical outcomes, and incorporate deep learning-based imaging features into the risk stratification.

METHODS: The MRI features were extracted for molecular subgroups by a novel multi-parameter convolutional neural network (CNN) called Bi-ResNet-MB. Then, MR features were used to establish a prognosis model based on XGBoost. Finally, a novel risk stratification system to stratify the patients based on the M2R Score (Machine learning-based Medulloblastoma Risk Score) was proposed.

RESULTS: A total of 139 MB patients (36 female, average age 7.27 ± 3.62 years) were treated at Beijing Tiantan Hospital. The Bi-ResNet-MB model excelled in molecular subgroup classification, achieving an average AUC of 0.946 (95% CI: 0.899-0.993). For prognostic prediction, our models achieved AUCs of 0.840 (95% CI: 0.792-0.888), 0.949 (95% CI: 0.899-0.999), and 0.960 (95% CI: 0.915-1.000) for OS, and 0.946 (95% CI: 0.905-0.987), 0.932 (95% CI: 0.875-0.989), and 0.964 (95% CI: 0.921-1.000) for PFS at 1, 3, and 5 years. In an independent validation dataset of 108 patients (33 female, average age 7.11 ± 2.92 years), the average AUC of molecular subgroup classification reached 0.894 (95% CI: 0.797-1.000). For PFS prediction at 1, 3, and 5 years, the AUCs were 0.832 (95% CI: 0.724-0.920), 0.875 (95% CI: 0.781-0.967), and 0.907 (95% CI: 0.760-1.000), respectively.

CONCLUSIONS: Based on machine learning and MRI data, models for MB molecular subgroups and prognosis prediction and the novel risk stratification system may significantly benefit patients.

KEY POINTS: Question Medulloblastoma exhibits significant heterogeneity, leading to considerable variations in patient prognosis and there is a lack of effective risk assessment strategies. Findings We have constructed a comprehensive machine learning system that excels in subgrouping diagnosis, prognosis assessment, and risk stratification for medulloblastoma patients preoperatively. Clinical relevance The utilization of non-invasive preoperative diagnosis and assessment is advantageous for clinicians in creating personalized treatment plans, particularly for high-risk patients. Additionally, it lays a foundation for the subsequent implementation of neoadjuvant therapy for medulloblastoma.

PMID:39883158 | DOI:10.1007/s00330-025-11385-8

Eur J Nucl Med Mol Imaging. 2025 Jan 30. doi: 10.1007/s00259-025-07090-9. Online ahead of print.

ABSTRACT

BACKGROUND: Pathological grade is a critical determinant of clinical outcomes and decision-making of follicular lymphoma (FL). This study aimed to develop a deep learning model as a digital biopsy for the non-invasive identification of FL grade.

METHODS: This study retrospectively included 513 FL patients from five independent hospital centers, randomly divided into training, internal validation, and external validation cohorts. A multimodal fusion Transformer model was developed integrating 3D PET tumor images with tabular data to predict FL grade. Additionally, the model is equipped with explainable modules, including Gradient-weighted Class Activation Mapping (Grad-CAM) for PET images, SHapley Additive exPlanations analysis for tabular data, and the calculation of predictive contribution ratios for both modalities, to enhance clinical interpretability and reliability. The predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) and accuracy, and its prognostic value was also assessed.

RESULTS: The Transformer model demonstrated high accuracy in grading FL, with AUCs of 0.964-0.985 and accuracies of 90.2-96.7% in the training cohort, and similar performance in the validation cohorts (AUCs: 0.936-0.971, accuracies: 86.4-97.0%). Ablation studies confirmed that the fusion model outperformed single-modality models (AUCs: 0.974 - 0.956, accuracies: 89.8%-85.8%). Interpretability analysis revealed that PET images contributed 81-89% of the predictive value. Grad-CAM highlighted the tumor and peri-tumor regions. The model also effectively stratified patients by survival risk (P < 0.05), highlighting its prognostic value.

CONCLUSIONS: Our study developed an explainable multimodal fusion Transformer model for accurate grading and prognosis of FL, with the potential to aid clinical decision-making.

PMID:39883138 | DOI:10.1007/s00259-025-07090-9

Arch Gynecol Obstet. 2025 Jan 30. doi: 10.1007/s00404-025-07960-5. Online ahead of print.

ABSTRACT

OBJECTIVE: To assess and compare the diagnostic accuracy of radiologist, MR findings, and radiomics-clinical models in the diagnosis of placental implantation disorders.

METHODS: Retrospective collection of MR images from patients suspected of having placenta accreta spectrum (PAS) was conducted across three institutions: Institution I (n = 505), Institution II (n = 67), and Institution III (n = 58). Data from Institution I were utilized to form a training set, while data from Institutions II and III served as an external test set. Radiologist diagnosis was performed by radiologists of varying levels of experience. The interpretation of MR findings was conducted by two radiologists with 10-15 years of experience in pelvic MR diagnosis, following the guidelines for diagnosis. Radiomics analysis extracted features from sagittal T2-weighted images and combined them with prenatal clinical features to construct predictive models. These models were then evaluated for discrimination and calibration to assess their performance.

RESULTS: As measured by the area under the receiver operating characteristic curve (AUC), the diagnostic efficacy was 0.587 (0.542-0.630) for junior radiologists from Institution I, 0.568 (0.441-0.689) from Institution II, and 0.507 (0.373-0.641) from Institution III. The AUC was 0.623 (0.580-0.666) for senior radiologists from Institution I, 0.635 (0.508-0.749) from Institution II, and 0.632 (0.495-0.755) from Institution III. The diagnostic efficacy of MR findings was 0.648 (0.601-0.695) for Institution I, 0.569 (0.429-0.709) for Institution II, and 0.588 (0.442-0.735) for Institution III. The diagnostic efficacy of the radiomics-clinical model was significantly higher, with an AUC of 0.794 (0.754-0.833) for Institution I, 0.783 (0.664-0.903) for Institution II, and 0.816 (0.704-0.927) for Institution III. The diagnostic efficacy of the Fusion model was significantly higher, with an AUC of 0.867 (0.836-0.899) for Institution I, 0.849 (0.753-0.944) for Institution II, and 0.823 (0.708-0.939) for Institution III.

CONCLUSION: The fusion models demonstrated superior diagnostic efficacy compared to radiologists, MR findings, and the radiomics-clinical models. Furthermore, the diagnostic accuracy of PAS was notably higher when utilizing the radiomics-clinical models than when relying solely on radiologist diagnosis or MR findings.

ADVANCES IN KNOWLEDGE: Radiomics analysis substantially augments the diagnostic precision in PAS, providing a significant enhancement over conventional radiologist and MRI findings. The diagnostic efficacy of the fusion model is notably superior to that of individual diagnostic modalities.

PMID:39883136 | DOI:10.1007/s00404-025-07960-5

Clin Nucl Med. 2025 Jan 28. doi: 10.1097/RLU.0000000000005685. Online ahead of print.

ABSTRACT

PURPOSE: The common approach for organ segmentation in hybrid imaging relies on coregistered CT (CTAC) images. This method, however, presents several limitations in real clinical workflows where mismatch between PET and CT images are very common. Moreover, low-dose CTAC images have poor quality, thus challenging the segmentation task. Recent advances in CT-less PET imaging further highlight the necessity for an effective PET organ segmentation pipeline that does not rely on CT images. Therefore, the goal of this study was to develop a CT-less multitracer PET segmentation framework.

PATIENTS AND METHODS: We collected 2062 PET/CT images from multiple scanners. The patients were injected with either 18F-FDG (1487) or 68Ga-PSMA (575). PET/CT images with any kind of mismatch between PET and CT images were detected through visual assessment and excluded from our study. Multiple organs were delineated on CT components using previously trained in-house developed nnU-Net models. The segmentation masks were resampled to coregistered PET images and used to train 4 different deep learning models using different images as input, including noncorrected PET (PET-NC) and attenuation and scatter-corrected PET (PET-ASC) for 18F-FDG (tasks 1 and 2, respectively using 22 organs) and PET-NC and PET-ASC for 68Ga tracers (tasks 3 and 4, respectively, using 15 organs). The models' performance was evaluated in terms of Dice coefficient, Jaccard index, and segment volume difference.

RESULTS: The average Dice coefficient over all organs was 0.81 ± 0.15, 0.82 ± 0.14, 0.77 ± 0.17, and 0.79 ± 0.16 for tasks 1, 2, 3, and 4, respectively. PET-ASC models outperformed PET-NC models (P < 0.05) for most of organs. The highest Dice values were achieved for the brain (0.93 to 0.96 in all 4 tasks), whereas the lowest values were achieved for small organs, such as the adrenal glands. The trained models showed robust performance on dynamic noisy images as well.

CONCLUSIONS: Deep learning models allow high-performance multiorgan segmentation for 2 popular PET tracers without the use of CT information. These models may tackle the limitations of using CT segmentation in PET/CT image quantification, kinetic modeling, radiomics analysis, dosimetry, or any other tasks that require organ segmentation masks.

PMID:39883026 | DOI:10.1097/RLU.0000000000005685