AJNR Am J Neuroradiol. 2025 Jan 8;46(1):41-48. doi: 10.3174/ajnr.A8482.

ABSTRACT

BACKGROUND AND PURPOSE: DWI is crucial for detecting infarction stroke. However, its spatial resolution is often limited, hindering accurate lesion visualization. Our aim was to evaluate the image quality and diagnostic confidence of deep learning (DL)-based super-resolution reconstruction for brain DWI of infarction stroke.

MATERIALS AND METHODS: This retrospective study enrolled 114 consecutive participants who underwent brain DWI. The DWI images were reconstructed with 2 schemes: 1) DL-based super-resolution reconstruction (DWIDL); and 2) conventional compressed sensing reconstruction (DWICS). Qualitative image analysis included overall image quality, lesion conspicuity, and diagnostic confidence in infarction stroke of different lesion sizes. Quantitative image quality assessments were performed by measurements of SNR, contrast-to-noise ratio (CNR), ADC, and edge rise distance. Group comparisons were conducted by using a paired t test for normally distributed data and the Wilcoxon test for non-normally distributed data. The overall agreement between readers for qualitative ratings was assessed by using the Cohen κ coefficient. A P value less than .05 was considered statistically significant.

RESULTS: A total of 114 DWI examinations constituted the study cohort. For the qualitative assessment, overall image quality, lesion conspicuity, and diagnostic confidence in infarction stroke lesions (lesion size <1.5 cm) improved by DWIDL compared with DWICS (all P < .001). For the quantitative analysis, edge rise distance of DWIDL was reduced compared with that of DWICS (P < .001), and no significant difference in SNR, CNR, and ADC values (all P > .05).

CONCLUSIONS: Compared with the conventional compressed sensing reconstruction, the DL-based super-resolution reconstruction demonstrated superior image quality and was feasible for achieving higher diagnostic confidence in infarction stroke.

PMID:39779291 | DOI:10.3174/ajnr.A8482

J Clin Neurol. 2025 Jan;21(1):21-30. doi: 10.3988/jcn.2024.0175.

ABSTRACT

BACKGROUND AND PURPOSE: Parkinson's disease (PD) is characterized by various prodromal symptoms, and these symptoms are mostly investigated retrospectively. While some symptoms such as rapid eye movement sleep behavior disorder are highly specific, others are common. This makes it challenging to predict those at risk of PD based solely on less-specific prodromal symptoms. The prediction accuracy when using only less-specific symptoms can be improved by analyzing the vast amount of information available using sophisticated deep-learning techniques. This study aimed to improve the performance of deep-learning-based screening in detecting prodromal PD using medical-claims data, including prescription information.

METHODS: We sampled 820 PD patients and 8,200 age- and sex-matched non-PD controls from Korean National Health Insurance cohort data. A deep-learning algorithm was developed using various combinations of diagnostic codes, medication codes, and prodromal periods.

RESULTS: During the prodromal period from year -3 to year 0, predicting PD using only diagnostic codes yielded a high accuracy of 0.937. Adding medication codes for the same period did not increase the accuracy (0.931-0.935). For the earlier prodromal period (year -6 to year -3), the accuracy of PD prediction decreased to 0.890 when using only diagnostic codes. The inclusion of all medication-codes data increased that accuracy markedly to 0.922.

CONCLUSIONS: A deep-learning algorithm using both prodromal diagnostic and medication codes was effective in screening PD. Developing a surveillance system with automatically collected medical-claims data for those at risk of developing PD could be cost-effective. This approach could streamline the process of developing disease-modifying drugs by focusing on the most-appropriate candidates for inclusion in accurate diagnostic tests.

PMID:39778564 | DOI:10.3988/jcn.2024.0175

Neural Netw. 2024 Dec 31;184:107098. doi: 10.1016/j.neunet.2024.107098. Online ahead of print.

ABSTRACT

Modifying the structure of an existing network is a common method to further improve the performance of the network. However, modifying some layers in network often results in pre-trained weight mismatch, and fine-tune process is time-consuming and resource-inefficient. To address this issue, we propose a novel technique called Identity Model Transformation (IMT), which keep the output before and after transformation in an equal form by rigorous algebraic transformations. This approach ensures the preservation of the original model's performance when modifying layers. Additionally, IMT significantly reduces the total training time required to achieve optimal results while further enhancing network performance. IMT has established a bridge for rapid transformation between model architectures, enabling a model to quickly perform analytic continuation and derive a family of tree-like models with better performance. This model family possesses a greater potential for optimization improvements compared to a single model. Extensive experiments across various object detection tasks validated the effectiveness and efficiency of our proposed IMT solution, which saved 94.76% time in fine-tuning the basic model YOLOv4-Rot on DOTA 1.5 dataset, and by using the IMT method, we saw stable performance improvements of 9.89%, 6.94%, 2.36%, and 4.86% on the four datasets: AI-TOD, DOTA1.5, coco2017, and MRSAText, respectively.

PMID:39778291 | DOI:10.1016/j.neunet.2024.107098

J Inherit Metab Dis. 2025 Jan;48(1):e12835. doi: 10.1002/jimd.12835.

ABSTRACT

Inborn errors of metabolism (IEMs) are rare genetic conditions with significant morbidity and mortality. Technological advances have increased therapeutic options, making it challenging to remain up to date. A centralized therapy knowledgebase is needed for early diagnosis and targeted treatment. This study aimed to identify all treatable IEMs through a scoping literature review, followed by data extraction and analysis according to the Treatabolome principles. Knowledge of treatable IEMs, therapeutic categories, efficacy, and evidence was integrated into the Inborn Errors of Metabolism Knowledgebase (IEMbase), an online database encompassing all IEMs. The study identified 275 treatable IEMs, 18% of all currently known 1564 IEMs, according to the International Classification of Inherited Metabolic Disorders. Disorders of fatty acid and ketone body metabolism had the highest treatability (67%), followed by disorders of vitamin and cofactor metabolism (60%), and disorders of lipoprotein metabolism (42%). The most common treatment strategies were pharmacological therapy (34%), nutritional therapy (34%), and vitamin and trace element supplementation (12%). Treatment effects were most commonly observed in nervous system abnormalities (34%), metabolism/homeostasis abnormalities (33%), and growth (7%). Predominant evidence sources included case reports with evidence levels 4 (48%) and 5 (12%), and individual cohort studies with evidence level 2b (12%). Our study generated the Metabolic Treatabolome 2024. IEMs are the largest group of monogenic disorders amenable to disease-modifying therapy. With drug repurposing efforts and advancements in gene therapies, this number will expand. IEMbase now provides up-to-date, comprehensive information on clinical and biochemical symptoms and therapeutic options, empowering patients, families, healthcare professionals, and researchers in improving patient outcomes.

PMID:39777714 | DOI:10.1002/jimd.12835

Zhonghua Yi Xue Yi Chuan Xue Za Zhi. 2025 Oct 10;42(10):34-40. doi: 10.3760/cma.j.cn511374-20240809-00433.

ABSTRACT

OBJECTIVE: To explore the clinical and genetic characteristics of two children diagnosed with two rare genetic diseases simultaneously.

METHODS: Two children with comorbidity of two genetic diseases due to dual genetic mutations diagnosed at the Third Affiliated Hospital of Zhengzhou University respectively in May 2022 and March 2023 were selected as the study subjects. Clinical and genetic data of the two children were retrospectively analyzed. This study has been approved by the Ethics Committee of the Third Affiliated Hospital of Zhengzhou University (Ethic No. 2021-062-01).

RESULTS: Child 1 was a 2-year-and-4-month-old boy whose clinical manifestations included facial dysmorphism, developmental delay, short stature, microcephaly, cleft palate, cryptorchidism, hypospadias, recurrent infections and immunological abnormalities. Whole exome sequencing revealed that he had harbored a heterozygous c.6595delT (p.Y2199Ifs*65) variant of the KMT2D gene and a heterozygous c.1892G>A (p.R631Q) variant of the PIK3R1 gene. This has led to a dual genetic diagnosis of Kabuki syndrome and PI3Kδ-related immunodeficiency type 36. Child 2 was a 15-year-old girl whose clinical manifestations included epilepsy, Albright's hereditary osteodystrophy, long body trunk, short limbs, hypocalcemia, hyperphosphatemia and hyperparathyroidism. The child also had a family history of short stature. Whole exome sequencing revealed that she had harbored a heterozygous c.2T>C (p.Met1?) variant of the GNAS gene and deletion of exons 2 to 6 of the SHOX gene. The two variants have led to dual diagnose of pseudohypoparathyroidism and X-linked idiopathic short stature.

CONCLUSION: When the clinical phenotype of a genetic disease is complex and cannot be fully explained with a single genetic variant, multiple pathogenic variants should be considered, and this may lead to the diagnosis of co-morbid genetic diseases. To adopt or supplement corresponding genetic testing in time and re-analyze the genetic data may facilitate accurate diagnosis of co-morbid genetic diseases.

PMID:39779334 | DOI:10.3760/cma.j.cn511374-20240809-00433

Epidemiol Serv Saude. 2024 Dec 20;33:e20240204. doi: 10.1590/S2237-96222024v33e20240204.en. eCollection 2024.

ABSTRACT

OBJECTIVE: To analyze the first referral service for rare diseases accredited by the Brazilian Ministry of Health, focusing on referral from the primary healthcare network through to diagnosis.

METHODS: This is a descriptive study with patients treated between 2016 and 2021 at a referral hospital service located in Curitiba, Paraná, Brazil. Clinical and epidemiological data were obtained from medical records, as were the results of genetic tests at the hospital's clinical analysis laboratory. Qualitative data were expressed as absolute and relative frequencies, while quantitative data were expressed as medians and interquartile ranges and compared using the Kruskal-Wallis test.

RESULTS: The study included 1,751 cases, 34.1% were diagnosed with rare diseases, with average time until diagnosis being 3.0 years, whereby mucopolysaccharidosis type II (4.0%) and tuberous sclerosis (3.9%) were the most common. Greater length of time for obtaining diagnosis (p-value 0.004) and receiving specialized care (p-value<0.001) was found in patients from the interior region of Paraná state, compared to those residing in Curitiba city and its metropolitan region.

CONCLUSION: Diagnosis of rare diseases occurred in approximately one third of cases. The average time until diagnosis suggests a possible positive impact of implementing the referral service. The longer time until diagnosis and specialized care found among patients from the interior region of Paraná represent challenges regarding adequate referral to specialized services.

PMID:39776132 | DOI:10.1590/S2237-96222024v33e20240204.en

Nature. 2025 Jan 8. doi: 10.1038/s41586-024-08391-z. Online ahead of print.

ABSTRACT

Transcriptional regulation, which involves a complex interplay between regulatory sequences and proteins, directs all biological processes. Computational models of transcription lack generalizability to accurately extrapolate to unseen cell types and conditions. Here we introduce GET (general expression transformer), an interpretable foundation model designed to uncover regulatory grammars across 213 human fetal and adult cell types1,2. Relying exclusively on chromatin accessibility data and sequence information, GET achieves experimental-level accuracy in predicting gene expression even in previously unseen cell types3. GET also shows remarkable adaptability across new sequencing platforms and assays, enabling regulatory inference across a broad range of cell types and conditions, and uncovers universal and cell-type-specific transcription factor interaction networks. We evaluated its performance in prediction of regulatory activity, inference of regulatory elements and regulators, and identification of physical interactions between transcription factors and found that it outperforms current models4 in predicting lentivirus-based massively parallel reporter assay readout5,6. In fetal erythroblasts7, we identified distal (greater than 1 Mbp) regulatory regions that were missed by previous models, and, in B cells, we identified a lymphocyte-specific transcription factor-transcription factor interaction that explains the functional significance of a leukaemia risk predisposing germline mutation8-10. In sum, we provide a generalizable and accurate model for transcription together with catalogues of gene regulation and transcription factor interactions, all with cell type specificity.

PMID:39779852 | DOI:10.1038/s41586-024-08391-z

Osteoporos Int. 2025 Jan 8. doi: 10.1007/s00198-024-07352-6. Online ahead of print.

ABSTRACT

BACKGROUD: Hypoparathyroidism (hypoPT) is characterized by acute and chronic complications due to insufficient parathyroid hormone (PTH) production or action. Several management guidelines have been developed, but mostly based on evidence from Western countries. Data from Eastern countries have not been systematically compared with those from Western countries.

METHODS: Literatures regarding to the epidemiology, genetics, risk factors, clinical manifestations and therapies for hypoPT in Easten and Western countries, including China, South Korea, Japan, India, and USA, Canada, Italy, and etc., were searched through PubMed and CNKI. This review was officially endorsed by European Calcified Tissue Society (ECTS) board.

RESULTS: Postoperative hypoPT is the major form of hypoPT in both Western and Eastern countries. The genetic profiles and clinical features of hypoPT are similar in Eastern and Western countries. The most commonly used medications in Eastern countries are calcium and native vitamin D or active vitamin D analogues, similar to their Western counterparts. While PTH replacement therapy is not available and approved to use in most Eastern countries.

CONCLUSION: Physicians and surgeons should follow the guidelines on the management of thyroid nodules, taking more care of protecting parathyroid glands during surgery. The cross-talk between East and West in the management of hypoPT should be continued. Direct comparisons of the management strategies in patients with hypoPT between Eastern and Wester countries regarding to the morbidity, mortality, quality of life, optimal dosage, efficacies and side-effects of conventional therapies or newer medications, as well as pharmacogenetics and pharmacoeconomics, would be valuable.

PMID:39777494 | DOI:10.1007/s00198-024-07352-6

NPJ Biofilms Microbiomes. 2025 Jan 8;11(1):8. doi: 10.1038/s41522-024-00637-y.

ABSTRACT

Chronic infections represent a significant global health and economic challenge. Biofilms, which are bacterial communities encased in an extracellular polysaccharide matrix, contribute to approximately 80% of these infections. In particular, pathogens such as Pseudomonas aeruginosa and Staphylococcus aureus are frequently co-isolated from the sputum of patients with cystic fibrosis and are commonly found in chronic wound infections. Within biofilms, bacteria demonstrate a remarkable increase in resistance and tolerance to antimicrobial treatment. We investigated the efficacy of combining the last-line antibiotic colistin with a membrane- and stringent stress response-targeting anti-biofilm peptide DJK-5 against co-biofilms comprised of multidrug-resistant P. aeruginosa and methicillin-resistant S. aureus (MRSA). Colistin lacks canonical activity against S. aureus. However, our study revealed that under co-biofilm conditions, the antibiofilm peptide DJK-5 synergized with colistin against S. aureus. Similar enhancement was observed when daptomycin, a cyclic lipopeptide against Gram-positive bacteria, was combined with DJK-5, resulting in increased activity against P. aeruginosa. The combinatorial treatment induced morphological changes in both P. aeruginosa and S. aureus cell shape and size within co-biofilms. Importantly, our findings also demonstrate synergistic activity against both P. aeruginosa and S. aureus in a murine subcutaneous biofilm-like abscess model. In conclusion, combinatorial treatments with colistin or daptomycin and the anti-biofilm peptide DJK-5 show significant potential for targeting co-biofilm infections. These findings offer promising avenues for developing new therapeutic approaches to combat complex chronic infections.

PMID:39779734 | DOI:10.1038/s41522-024-00637-y

J Cyst Fibros. 2025 Jan 7:S1569-1993(24)01860-5. doi: 10.1016/j.jcf.2024.12.009. Online ahead of print.

ABSTRACT

BACKGROUND: Cystic fibrosis (CF) is caused by variants in a gene that encodes a protein essential for water and ion transport in the epithelial cells of exocrine organs. Given the possible relationship of this protein and conjunctival and corneal epithelium, the aim of this study was to evaluate ophthalmologic alterations in people with CF.

METHODS: Forty-five people with CF underwent pulmonary evaluation including inflammatory score (IS). These people along with 98 sex-matched controls underwent ophthalmologic evaluation including dry eye disease (DED) testing, corneal topography using Pentacam™ and macular and peripapillary retinal nerve fiber layer (pRNFL) thickness with optical coherence tomography (OCT).

RESULTS: The CF group presented a higher percentage of pathologic tear break-up time (T-BUT) (55.6 % vs 25 %, p = 0.001) and Schirmer's test 1 (40 % versus 19.4 %, p = 0.009) than the control group. In the CF group, an inverse correlation was observed between T-BUT and IS (r=- 0.373, p = 0.012), as well as T-BUT and peripheral eosinophilia (r=-0.338; p = 0.023). People with CF presented lower values of central corneal thickness (p = 0.009), thinnest point (p = 0.006), anterior chamber volume (p = 0.034), and anterior chamber angle (p = 0.011) than the control group and lower pRNLF thickness in the superior temporal sector (p = 0.002).

CONCLUSIONS: Our findings indicate a higher prevalence of dry eye disease (DED) among people with CF compared to controls. The severity of the condition increases with higher systemic inflammation. Additionally, CF may affect the anterior segment of the eye, leading to a reduction in the nerve fiber layer and early signs of glaucoma.

PMID:39779380 | DOI:10.1016/j.jcf.2024.12.009

J Clin Pathol. 2025 Jan 8:jcp-2024-209899. doi: 10.1136/jcp-2024-209899. Online ahead of print.

ABSTRACT

AIMS: In cystic fibrosis lung transplant recipients (LTRs), graft dysfunction due to acute infections, rejection or chronic lung allograft dysfunction (CLAD) is difficult to distinguish. Characterisation of the airway inflammatory milieu could help detect and prevent graft dysfunction. We speculated that an eosinophil or neutrophil-rich milieu is associated with higher risk of CLAD.

METHODS: A retrospective, single-centre observational study of cystic fibrosis LTRs between 2002 and 2021 was performed. Data from biopsy slides, pulmonary function testing and bronchoalveolar lavage fluid microbiology tests were collected. The primary outcome was bronchiolitis obliterans syndrome (BOS) or death after transplant, with an 8-year follow-up period.

RESULTS: 40 patients were identified with an average age of 35.3 at first transplantation, including 5 redo lung transplants. Fungal infections were correlated with higher rejection scores (p<0.01) and survival status (p=0.027). Fungal and bacterial infection rates were reduced in later transplants (2014-2021) compared with earlier (2002-2014). Fungal infections were associated with significantly worsened outcomes (p≤0.001). Eosinophils in large airways was associated with worse BOS-free survival (p=0.03).

CONCLUSIONS: Subcategorisation of the inflammatory milieu (particularly noting eosinophils) in surveillance biopsies may help detect CLAD earlier and improve long-term outcomes in cystic fibrosis LTRs.

PMID:39779317 | DOI:10.1136/jcp-2024-209899

Eur Respir Rev. 2025 Jan 8;34(175):240131. doi: 10.1183/16000617.0131-2024. Print 2025 Jan.

ABSTRACT

The systemic use of corticosteroids for patients with severe community-acquired pneumonia (sCAP) remains controversial in clinical practice, particularly in terms of the safety profile of these drugs. This narrative review aims to analyse the available literature data concerning the safety of short-term steroid use in the treatment of sCAP, while also highlighting potential future research directions. Several trials and meta-analyses have evaluated corticosteroid therapy as an adjuvant treatment for sCAP, yielding heterogeneous results regarding its efficacy and safety. Despite the wide variability in results, it is generally accepted that steroids are not associated with a significant risk of healthcare-associated infections, gastrointestinal bleeding or acute kidney injury in patients with sCAP in the short term. Nevertheless, such drugs are linked to hyperglycaemia, necessitating regular monitoring and appropriate management. The influence of steroids on long-term outcomes and their potential risks in viral sCAP still needs to be investigated.

PMID:39778921 | DOI:10.1183/16000617.0131-2024

Int Forum Allergy Rhinol. 2025 Jan 8. doi: 10.1002/alr.23524. Online ahead of print.

ABSTRACT

BACKGROUND: Steroid rinses and steroid-eluting stents are both options for preventing postoperative stenosis after frontal sinus surgery. This study aimed to assess whether steroid-eluting stents offer added benefit over steroid rinses alone in postoperative healing and long-term frontal sinus patency.

METHODS: A randomized controlled trial enrolled patients with CRS with nasal polyps (CRSwNP) who underwent surgery for bilateral and equal frontal sinusitis after failing prior medical therapy. Each patient served as their own control, with each patient randomized to stent placement in either right or left frontal sinuses. Exclusion criteria included unequal frontal sinusitis, aspirin exacerbated respiratory disease, cystic fibrosis, primary ciliary dyskinesia, and immunocompromise. All patients used steroid rinses postoperatively. Scarring, edema, patency, and the need for additional treatments were assessed at 1, 3, 12, and 24 weeks postoperatively. Univariate and multivariate analyses were performed.

RESULTS: Sixty-two patients were enrolled. Postoperatively, scarring, edema, patency, and the need for further treatment were similar in both groups at 24 weeks (p = 0.878, 0.688, 0.817, 1.00, and 1.00, respectively). Multivariable regression analysis identified time as an independent risk factor for scarring (OR = 1.32, [1.03‒1.71]) and patency (OR = 1.39, [1.10‒1.82]), while it was an independent protective factor for edema (OR = 0.40, [0.32‒0.49]). The steroid-eluting stent did not significantly affect this.

CONCLUSION: For CRSwNP, with or without asthma, without other underlying systemic disease factors, steroid-eluting stents may not add benefit over steroid rinses in reducing postoperative scarring and edema, improving long-term frontal sinus patency, or reducing the need for additional treatments, as long as patients continue topical therapy and know how to rinse effectively.

PMID:39778085 | DOI:10.1002/alr.23524

Pediatr Pulmonol. 2025 Jan 7:e27471. doi: 10.1002/ppul.27471. Online ahead of print.

ABSTRACT

INTRODUCTION: While the diagnosis of cystic fibrosis (CF) is often straightforward and reliant on correlation between genetic testing and clinical signs and symptoms, there is a subset where the distinction is not nearly as clearcut. This has previously been reported in patients identified through newborn screening but not meeting full CF diagnostic criteria, earning the label of CF Screen Positive, Inconclusive Diagnosis (CFSPID) instead. A homologous diagnostic category in adults is named CF Transmembrane Conductance Regulator-Related Disorder (CFTR-RD).

METHODS: Through a retrospective chart review, this study reports on a relatively large adult cohort (n = 23) that presented to pulmonology clinic at a single center with intermediate or positive sweat chloride tests but non-diagnostic full CFTR gene analysis.

RESULTS: Median sweat chloride result was 48 mmol/L, and a majority of the cohort had chronic lung disease with atypical pathogens on sputum culture, including Pseudomonas aeruginosa, non-tuberculous Mycobacteria, Acinetobacter species, amongst others.

CONCLUSIONS: This clinical picture suggests CFTR dysfunction or similar mechanism in the absence of an identified genetic cause. Alternate chloride channels and their respective genes or candidates of genetic modifiers to the CF-phenotype could be targets of further research in this cohort or similar patients. Such genetic modifiers include loci that have been implicated in inflammation, the CFTR interactome, and/or co-/post-translational modification of CFTR.

PMID:39778078 | DOI:10.1002/ppul.27471

BMC Med Inform Decis Mak. 2025 Jan 8;25(1):10. doi: 10.1186/s12911-024-02843-2.

ABSTRACT

Vitiligo, alopecia areata, atopic, and stasis dermatitis are common skin conditions that pose diagnostic and assessment challenges. Skin image analysis is a promising noninvasive approach for objective and automated detection as well as quantitative assessment of skin diseases. This review provides a systematic literature search regarding the analysis of computer vision techniques applied to these benign skin conditions, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The review examines deep learning architectures and image processing algorithms for segmentation, feature extraction, and classification tasks employed for disease detection. It also focuses on practical applications, emphasizing quantitative disease assessment, and the performance of various computer vision approaches for each condition while highlighting their strengths and limitations. Finally, the review denotes the need for disease-specific datasets with curated annotations and suggests future directions toward unsupervised or self-supervised approaches. Additionally, the findings underscore the importance of developing accurate, automated tools for disease severity score calculation to improve ML-based monitoring and diagnosis in dermatology. TRIAL REGISTRATION: Not applicable.

PMID:39780145 | DOI:10.1186/s12911-024-02843-2

BMC Oral Health. 2025 Jan 8;25(1):42. doi: 10.1186/s12903-024-05345-9.

ABSTRACT

BACKGROUND: A comprehensive analysis of the occlusal plane (OP) inclination in predicting anteroposterior mandibular position (APMP) changes is still lacking. This study aimed to analyse the relationships between inclinations of different OPs and APMP metrics and explore the feasibility of OP inclination in predicting changes in APMP.

METHODS: Overall, 115 three-dimensional (3D) models were reconstructed using deep learning-based cone-beam computed tomography (CBCT) segmentation, and their accuracy in supporting cusps was compared with that of intraoral scanning models. The anatomical landmarks of seven OPs and three APMP metrics were identified, and their values were measured on the sagittal reference plane. The receiver operating characteristic curves of inclinations of seven OPs in distinguishing different anteroposterior skeletal patterns and correlations between inclinations of these OPs and APMP metrics were calculated and compared. For the OP inclination with the highest area under the curve (AUC) values and correlation coefficients, the regression models between this OP inclination and APMP metrics were further calculated.

RESULTS: The deviations in supporting cusps between deep learning-based and intraoral scanning models were < 0.300 mm. The improved functional OP (IFOP) inclination could distinguish different skeletal classification determinations (AUC Class I VS Class II = 0.693, AUC Class I VS Class III = 0.763, AUC Class II VS Class III = 0.899, all P values < 0.01) and the AUC value in skeletal Classes II and III determination was statistically higher than the inclinations of other OPs (all P values < 0.01). Moreover, the IFOP inclination showed statistical correlations with APMP metrics (rAPDI = -0.557, rANB = 0.543, rAF-BF = 0.731, all P values < 0.001) and had the highest correlation coefficients among all OP inclinations (all P values < 0.05). The regression analysis models of IFOP inclination and APMP metrics were yAPDI = -0.917x + 91.144, yANB = 0.395x + 0.292, and yAF-BF = 0.738x - 2.331.

CONCLUSIONS: Constructing the OP using deep learning-based 3D models from CBCT data is feasible. IFOP inclination could be used in predicting the APMP changes. A steeper IFOP inclination corresponded to a more retrognathic mandibular posture.

PMID:39780117 | DOI:10.1186/s12903-024-05345-9

BMC Bioinformatics. 2025 Jan 8;26(1):7. doi: 10.1186/s12859-024-05949-6.

ABSTRACT

BACKGROUND: Natural language processing (NLP) enables the extraction of information embedded within unstructured texts, such as clinical case reports and trial eligibility criteria. By identifying relevant medical concepts, NLP facilitates the generation of structured and actionable data, supporting complex tasks like cohort identification and the analysis of clinical records. To accomplish those tasks, we introduce a deep learning-based and lexicon-based named entity recognition (NER) tool for texts in Spanish. It performs medical NER and normalization, medication information extraction and detection of temporal entities, negation and speculation, and temporality or experiencer attributes (Age, Contraindicated, Negated, Speculated, Hypothetical, Future, Family_member, Patient and Other). We built the tool with a dedicated lexicon and rules adapted from NegEx and HeidelTime. Using these resources, we annotated a corpus of 1200 texts, with high inter-annotator agreement (average F1 = 0.841% ± 0.045 for entities, and average F1 = 0.881% ± 0.032 for attributes). We used this corpus to train Transformer-based models (RoBERTa-based models, mBERT and mDeBERTa). We integrated them with the dictionary-based system in a hybrid tool, and distribute the models via the Hugging Face hub. For an internal validation, we used a held-out test set and conducted an error analysis. For an external validation, eight medical professionals evaluated the system by revising the annotation of 200 new texts not used in development.

RESULTS: In the internal validation, the models yielded F1 values up to 0.915. In the external validation with 100 clinical trials, the tool achieved an average F1 score of 0.858 (± 0.032); and in 100 anonymized clinical cases, it achieved an average F1 score of 0.910 (± 0.019).

CONCLUSIONS: The tool is available at https://claramed.csic.es/medspaner . We also release the code ( https://github.com/lcampillos/medspaner ) and the annotated corpus to train the models.

PMID:39780059 | DOI:10.1186/s12859-024-05949-6

BMC Med Imaging. 2025 Jan 8;25(1):12. doi: 10.1186/s12880-024-01538-4.

ABSTRACT

PROBLEM: Breast cancer is a leading cause of death among women, and early detection is crucial for improving survival rates. The manual breast cancer diagnosis utilizes more time and is subjective. Also, the previous CAD models mostly depend on manmade visual details that are complex to generalize across ultrasound images utilizing distinct techniques. Distinct imaging tools have been utilized in previous works such as mammography and MRI. However, these imaging tools are costly and less portable than ultrasound imaging. Also, ultrasound imaging is a non-invasive method commonly used for breast cancer screening. Hence, the paper presents a novel deep learning model, BCDNet, for classifying breast tumors as benign or malignant using ultrasound images.

AIM: The primary aim of the study is to design an effective breast cancer diagnosis model that can accurately classify tumors in their early stages, thus reducing mortality rates. The model aims to optimize the weight and parameters using the RPAOSM-ESO algorithm to enhance accuracy and minimize false negative rates.

METHODS: The BCDNet model utilizes transfer learning from a pre-trained VGG16 network for feature extraction and employs an AHDNAM classification approach, which includes ASPP, DTCN, 1DCNN, and an attention mechanism. The RPAOSM-ESO algorithm is used to fine-tune the weights and parameters.

RESULTS: The RPAOSM-ESO-BCDNet-based breast cancer diagnosis model provided 94.5 accuracy rates. This value is relatively higher than the previous models such as DTCN (88.2), 1DCNN (89.6), MobileNet (91.3), and ASPP-DTC-1DCNN-AM (93.8). Hence, it is guaranteed that the designed RPAOSM-ESO-BCDNet produces relatively accurate solutions for the classification than the previous models.

CONCLUSION: The BCDNet model, with its sophisticated feature extraction and classification techniques optimized by the RPAOSM-ESO algorithm, shows promise in accurately classifying breast tumors using ultrasound images. The study suggests that the model could be a valuable tool in the early detection of breast cancer, potentially saving lives and reducing the burden on healthcare systems.

PMID:39780045 | DOI:10.1186/s12880-024-01538-4

Med Phys. 2025 Jan 8. doi: 10.1002/mp.17599. Online ahead of print.

ABSTRACT

BACKGROUND: Modern reconstruction algorithms for computed tomography (CT) can exhibit nonlinear properties, including non-stationarity of noise and contrast dependence of both noise and spatial resolution. Model observers have been recommended as a tool for the task-based assessment of image quality (Samei E et al., Med Phys. 2019; 46(11): e735-e756), but the common Fourier domain approach to their calculation assumes quasi-stationarity.

PURPOSE: A practical spatial-domain approach is proposed for the calculation of the nonprewhitening (NPW) family of model observers in CT, avoiding the disadvantages of the Fourier domain. The methodology avoids explicit estimation of a noise covariance matrix. A formula is also provided for the uncertainty on estimates of detectability index, for a given number of slices and repeat scans. The purpose of this work is to demonstrate the method and provide comparisons to the conventional Fourier approach for both iterative reconstruction (IR) and a deep Learning-based reconstruction (DLR) algorithm.

MATERIALS AND METHODS: Acquisitions were made on a Revolution CT scanner (GE Healthcare, Waukesha, Wisconsin, USA) and reconstructed using the vendor's IR and DLR algorithms (ASiR-V and TrueFidelity). Several reconstruction kernels were investigated (Standard, Lung, and Bone for IR and Standard for DLR). An in-house developed phantom with two flat contrast levels (2 and 8 mgI/mL) and varying feature size (1-10 mm diameter) was used. Two single-energy protocols (80 and 120 kV) were investigated with two dose levels (CTDIvol = 5 and 13 mGy). The spatial domain calculations relied on repeated scanning, region-of-interest placement and simple operations with image matrices. No more repeat scans were utilized than required for Fourier domain estimations. Fourier domain calculations were made using techniques described in a previous publication (Thor D et al., Med Phys. 2023;50(5):2775-2786). Differences between the calculations in the two domains were assessed using the normalized root-mean-square discrepancy (NMRSD).

RESULTS: Fourier domain calculations agreed closely with those in the spatial domain for all zero-strength IR reconstructions, which most closely resemble traditional filtered backprojection. The Fourier-based calculations, however, displayed higher detectability compared to those in the spatial domain for IR with strong iterative strength and for the DLR algorithm. The NRMSD remained within 10% for the NPW model observer without eye filter, but reached larger values when an eye filter was included. The formula for the uncertainty on the detectability index was validated by bootstrap estimates.

CONCLUSION: A practical methodology was demonstrated for calculating NPW observers in the spatial domain. In addition to being a valuable tool for verifying the applicability of typical Fourier-based methodologies, it lends itself to routine calculations for features embedded in a phantom. Higher estimates of detectability were observed when adopting the Fourier domain methodology for IR and for a DLR algorithm, demonstrating that use of the Fourier domain can indicate greater benefit to noise suppression than suggested by spatial domain calculations. This is consistent with the results of previous authors for the Fourier domain, who have compared to human and other model observers, but not, as in this study, to the NPW model observer calculated in the spatial domain.

PMID:39780034 | DOI:10.1002/mp.17599

Nature. 2025 Jan;637(8045):319-326. doi: 10.1038/s41586-024-08328-6. Epub 2025 Jan 8.

ABSTRACT

Tabular data, spreadsheets organized in rows and columns, are ubiquitous across scientific fields, from biomedicine to particle physics to economics and climate science1,2. The fundamental prediction task of filling in missing values of a label column based on the rest of the columns is essential for various applications as diverse as biomedical risk models, drug discovery and materials science. Although deep learning has revolutionized learning from raw data and led to numerous high-profile success stories3-5, gradient-boosted decision trees6-9 have dominated tabular data for the past 20 years. Here we present the Tabular Prior-data Fitted Network (TabPFN), a tabular foundation model that outperforms all previous methods on datasets with up to 10,000 samples by a wide margin, using substantially less training time. In 2.8 s, TabPFN outperforms an ensemble of the strongest baselines tuned for 4 h in a classification setting. As a generative transformer-based foundation model, this model also allows fine-tuning, data generation, density estimation and learning reusable embeddings. TabPFN is a learning algorithm that is itself learned across millions of synthetic datasets, demonstrating the power of this approach for algorithm development. By improving modelling abilities across diverse fields, TabPFN has the potential to accelerate scientific discovery and enhance important decision-making in various domains.

PMID:39780007 | DOI:10.1038/s41586-024-08328-6