World J Urol. 2025 Jan 10;43(1):65. doi: 10.1007/s00345-025-05440-8.

ABSTRACT

PURPOSE: To develop a deep learning (DL) model based on primary tumor tissue to predict the lymph node metastasis (LNM) status of muscle invasive bladder cancer (MIBC), while validating the prognostic value of the predicted aiN score in MIBC patients.

METHODS: A total of 323 patients from The Cancer Genome Atlas (TCGA) were used as the training and internal validation set, with image features extracted using a visual encoder called UNI. We investigated the ability to predict LNM status while assessing the prognostic value of aiN score. External validation was conducted on 139 patients from Renmin Hospital of Wuhan University (RHWU; Wuhan, China).

RESULTS: The DL model achieved area under the receiver operating characteristic curves of 0.79 (95% confidence interval [CI], 0.69-0.88) in the internal validation set for predicting LNM status, and 0.72 (95% CI, 0.68-0.75) in the external validation set. In multivariable Cox analysis, the model-predicted aiN score emerged as an independent predictor of survival for MIBC patients, with a hazard ratio of 1.608 (95% CI, 1.128-2.291; p = 0.008) in the TCGA cohort and 2.746 (95% CI, 1.486-5.076; p < 0.001) in the RHWU cohort. Additionally, the aiN score maintained prognostic value across different subgroups.

CONCLUSION: In this study, DL-based image analysis showed promising results by directly extracting relevant prognostic information from H&E-stained histology to predict the LNM status of MIBC patients. It might be used for personalized management of MIBC patients following prospective validation in the future.

PMID:39792275 | DOI:10.1007/s00345-025-05440-8

Eur Radiol. 2025 Jan 10. doi: 10.1007/s00330-024-11317-y. Online ahead of print.

ABSTRACT

OBJECTIVES: To evaluate the image quality and lung nodule detectability of ultralow-dose CT (ULDCT) with adaptive statistical iterative reconstruction-V (ASiR-V) post-processed using a deep learning image reconstruction (DLIR)-based image domain compared to low-dose CT (LDCT) and ULDCT without DLIR.

MATERIALS AND METHODS: A total of 210 patients undergoing lung cancer screening underwent LDCT (mean ± SD, 0.81 ± 0.28 mSv) and ULDCT (0.17 ± 0.03 mSv) scans. ULDCT images were reconstructed with ASiR-V (ULDCT-ASiR-V) and post-processed using DLIR (ULDCT-DLIR). The quality of the three CT images was analyzed. Three radiologists detected and measured pulmonary nodules on all CT images, with LDCT results serving as references. Nodule conspicuity was assessed using a five-point Likert scale, followed by further statistical analyses.

RESULTS: A total of 463 nodules were detected using LDCT. The image noise of ULDCT-DLIR decreased by 60% compared to that of ULDCT-ASiR-V and was lower than that of LDCT (p < 0.001). The subjective image quality scores for ULDCT-DLIR (4.4 [4.1, 4.6]) were also higher than those for ULDCT-ASiR-V (3.6 [3.1, 3.9]) (p < 0.001). The overall nodule detection rates for ULDCT-ASiR-V and ULDCT-DLIR were 82.1% (380/463) and 87.0% (403/463), respectively (p < 0.001). The percentage difference between diameters > 1 mm was 2.9% (ULDCT-ASiR-V vs. LDCT) and 0.5% (ULDCT-DLIR vs. LDCT) (p = 0.009). Scores of nodule imaging sharpness on ULDCT-DLIR (4.0 ± 0.68) were significantly higher than those on ULDCT-ASiR-V (3.2 ± 0.50) (p < 0.001).

CONCLUSION: DLIR-based image domain improves image quality, nodule detection rate, nodule imaging sharpness, and nodule measurement accuracy of ASiR-V on ULDCT.

KEY POINTS: Question Deep learning post-processing is simple and cheap compared with raw data processing, but its performance is not clear on ultralow-dose CT. Findings Deep learning post-processing enhanced image quality and improved the nodule detection rate and accuracy of nodule measurement of ultralow-dose CT. Clinical relevance Deep learning post-processing improves the practicability of ultralow-dose CT and makes it possible for patients with less radiation exposure during lung cancer screening.

PMID:39792163 | DOI:10.1007/s00330-024-11317-y

Eur Radiol. 2025 Jan 10. doi: 10.1007/s00330-024-11308-z. Online ahead of print.

ABSTRACT

OBJECTIVES: The use of deep learning models for quantitative measurements on coronary computed tomography angiography (CCTA) may reduce inter-reader variability and increase efficiency in clinical reporting. This study aimed to investigate the diagnostic performance of a recently updated deep learning model (CorEx-2.0) for quantifying coronary stenosis, compared separately with two expert CCTA readers as references.

METHODS: This single-center retrospective study included 50 patients that underwent CCTA to rule out obstructive coronary artery disease between 2017-2022. Two expert CCTA readers and CorEx-2.0 independently assessed all 150 vessels using Coronary Artery Disease-Reporting and Data System (CAD-RADS). Inter-reader agreement analysis and diagnostic performance of CorEx-2.0, compared with each expert reader as references, were evaluated using percent agreement, Cohen's kappa for the binary CAD-RADS classification (CAD-RADS 0-3 versus 4-5) at patient level, and linearly weighted kappa for the 6-group CAD-RADS classification at vessel level.

RESULTS: Overall, 50 patients and 150 vessels were evaluated. Inter-reader agreement using the binary classification at patient level was 91.8% (45/49) with a Cohen's kappa of 0.80. For the 6-group classification at vessel level, inter-reader agreement was 67.6% (100/148) with a linearly weighted kappa of 0.77. CorEx-2.0 showed 100% sensitivity for detecting CAD-RADS ≥ 4 and kappa values of 0.86 versus both readers using the binary classification at patient level. For the 6-group classification at vessel level, CorEx-2.0 demonstrated weighted kappa values of 0.71 versus reader 1 and 0.73 versus reader 2.

CONCLUSION: CorEx-2.0 identified all patients with severe stenosis (CAD-RADS ≥ 4) compared with expert readers and approached expert reader performance at vessel level (weighted kappa > 0.70).

KEY POINTS: Question Can deep learning models improve objectivity in coronary stenosis grading and reporting as coronary CT angiography (CTA) workloads rise? Findings The deep learning model (CorEx-2.0) identified all patients with severe stenoses when compared with expert readers and approached expert reader performance at vessel level. Clinical relevance CorEx-2.0 is a reliable tool for identifying patients with severe stenoses (≥ 70%), underscoring the potential of using this deep learning model to prioritize coronary CTA reading by flagging patients at risk of severe obstructive coronary artery disease.

PMID:39792162 | DOI:10.1007/s00330-024-11308-z

Med Image Comput Comput Assist Interv. 2024 Oct;15012:465-475. doi: 10.1007/978-3-031-72390-2_44. Epub 2024 Oct 23.

ABSTRACT

Recent advancements in Contrastive Language-Image Pre-training (CLIP) [21] have demonstrated notable success in self-supervised representation learning across various tasks. However, the existing CLIP-like approaches often demand extensive GPU resources and prolonged training times due to the considerable size of the model and dataset, making them poor for medical applications, in which large datasets are not always common. Meanwhile, the language model prompts are mainly manually derived from labels tied to images, potentially overlooking the richness of information within training samples. We introduce a novel language-image Contrastive Learning method with an Efficient large language model and prompt Fine-Tuning (CLEFT) that harnesses the strengths of the extensive pre-trained language and visual models. Furthermore, we present an efficient strategy for learning context-based prompts that mitigates the gap between informative clinical diagnostic data and simple class labels. Our method demonstrates state-of-the-art performance on multiple chest X-ray and mammography datasets compared with various baselines. The proposed parameter efficient framework can reduce the total trainable model size by 39% and reduce the trainable language model to only 4% compared with the current BERT encoder.

PMID:39791126 | PMC:PMC11709740 | DOI:10.1007/978-3-031-72390-2_44

Cureus. 2024 Dec 10;16(12):e75476. doi: 10.7759/cureus.75476. eCollection 2024 Dec.

ABSTRACT

This paper investigates the potential of artificial intelligence (AI) and machine learning (ML) to enhance the differentiation of cystic lesions in the sellar region, such as pituitary adenomas, Rathke cleft cysts (RCCs) and craniopharyngiomas (CP), through the use of advanced neuroimaging techniques, particularly magnetic resonance imaging (MRI). The goal is to explore how AI-driven models, including convolutional neural networks (CNNs), deep learning, and ensemble methods, can overcome the limitations of traditional diagnostic approaches, providing more accurate and early differentiation of these lesions. The review incorporates findings from critical studies, such as using the Open Access Series of Imaging Studies (OASIS) dataset (Kaggle, San Francisco, USA) for MRI-based brain research, highlighting the significance of statistical rigor and automated segmentation in developing reliable AI models. By drawing on these insights and addressing the challenges posed by small, single-institutional datasets, the paper aims to demonstrate how AI applications can improve diagnostic precision, enhance clinical decision-making, and ultimately lead to better patient outcomes in managing sellar region cystic lesions.

PMID:39791061 | PMC:PMC11717160 | DOI:10.7759/cureus.75476

Cardiovasc Diagn Ther. 2024 Dec 31;14(6):1161-1175. doi: 10.21037/cdt-24-409. Epub 2024 Dec 19.

ABSTRACT

BACKGROUND AND OBJECTIVE: Cardiovascular magnetic resonance (CMR) is a routine cross-sectional imaging modality in adults with congenital heart disease. Developing CMR techniques and the knowledge that CMR is well suited to assess long-term complications and to provide prognostic information for single ventricle (SV) patients makes CMR the ideal assessment tool for this patient cohort. Nevertheless, many of the techniques have not yet been incorporated into day-to-day practice. The aim of this review is to provide a comprehensive overview of CMR applications in SV patients together with recent scientific findings.

METHODS: Articles from 2009 to August 2024 retrieved from PubMed on CMR in SV patients were included. Case reports and non-English literature were excluded.

KEY CONTENT AND FINDINGS: CMR is essential for serial follow-up of SV patients and CMR-derived standard markers can improve patient management and prognosis assessment. Advanced CMR techniques likely will enhance our understanding of Fontan hemodynamics and are promising tools for a comprehensive patient evaluation and care.

CONCLUSIONS: There is increasing research that shows the advantages of CMR in Fontan patients. However, further research about the prognostic role of CMR in older Fontan patients and how new methods such as modeling and deep learning pipelines can be clinically implemented is warranted.

PMID:39790200 | PMC:PMC11707479 | DOI:10.21037/cdt-24-409

Neuroradiol J. 2025 Jan 9:19714009251313517. doi: 10.1177/19714009251313517. Online ahead of print.

ABSTRACT

This study evaluates the efficacy of deep learning models in identifying infarct tissue on computed tomography perfusion (CTP) scans from patients with acute ischemic stroke due to large vessel occlusion, specifically addressing the potential influence of varying noise reduction techniques implemented by different vendors. We analyzed CTP scans from 60 patients who underwent mechanical thrombectomy achieving a modified thrombolysis in cerebral infarction (mTICI) score of 2c or 3, ensuring minimal changes in the infarct core between the initial CTP and follow-up MR imaging. Noise reduction techniques, including principal component analysis (PCA), wavelet, non-local means (NLM), and a no denoising approach, were employed to create hemodynamic parameter maps. Infarct regions identified on follow-up diffusion-weighted imaging (DWI) within 48 hours were co-registered with initial CTP scans and refined with ADC maps to serve as ground truth for training a data-augmented U-Net model. The performance of this convolutional neural network (CNN) was assessed using Dice coefficients across different denoising methods and infarct sizes, visualized through box plots for each parameter map. Our findings show no significant differences in model accuracy between PCA and other denoising methods, with minimal variation in Dice scores across techniques. This study confirms that CNNs are adaptable and capable of handling diverse processing schemas, indicating their potential to streamline diagnostic processes and effectively manage CTP input data quality variations.

PMID:39789894 | DOI:10.1177/19714009251313517

Brief Bioinform. 2024 Nov 22;26(1):bbae705. doi: 10.1093/bib/bbae705.

ABSTRACT

Identifying the regulatory effects of noncoding variants presents a significant challenge. Recently, the accumulation of epigenomic profiling data in wheat has provided an opportunity to model the functional impacts of these variants. In this study, we introduce Language of Genome for Wheat (LOGOWheat), a deep learning-based tool designed to predict the regulatory effects of noncoding variants in wheat. LOGOWheat initially employs a self-attention-based, contextualized pretrained language model to acquire bidirectional representations of the unlabeled wheat reference genome. Epigenomic profiling data are also collected and utilized to fine-tune the model, enabling it to discern the regulatory code inherent in genomic sequences. The test results suggest that LOGOWheat is highly effective in predicting multiple chromatin features, achieving an average area under the receiver operating characteristic (AUROC) of 0.8531 and an average area under the precision-recall curve (AUPRC) of 0.7633. Two case studies illustrate and demonstrate the main functions provided by LOGOWheat: assigning scores and prioritizing causal variants within a given variant set and constructing a saturated mutagenesis map in silico to discover high-impact sites or functional motifs in a given sequence. Finally, we propose the concept of extracting potential functional variations from the wheat population by integrating evolutionary conservation information. LOGOWheat is available at http://logowheat.cn/.

PMID:39789857 | DOI:10.1093/bib/bbae705

Plant Commun. 2025 Jan 8:101240. doi: 10.1016/j.xplc.2025.101240. Online ahead of print.

ABSTRACT

In the face of climate change and the growing global population, there is an urgent need to accelerate the development of high-yielding crop varieties. To this end, vast amounts of genotype-to-phenotype data have been collected, and many machine learning (ML) models have been developed to predict phenotype from a given genotype. However, the requirement for high densities of single-nucleotide polymorphisms (SNPs) and the labor-intensive collection of phenotypic data are hampering the use of these models to advance breeding. Furthermore, recently developed genomic selection (GS) models such as deep learning (DL) are complicated and inconvenient for breeders to navigate and optimize within their breeding programs. Here, we present the development of an intelligent breeding platform named AutoGP (http://autogp.hzau.edu.cn), which integrates genotype extraction, phenotypic extraction, and GS models of genotype-to-phenotype within a user-friendly web interface. AutoGP has three main advantages over previously developed platforms: 1) we designed an efficient sequencing chip to identify high-quality, high-confidence SNPs throughout gene regulatory networks; 2) we developed a complete workflow for plant phenotypic extraction (such as plant height and leaf count) from smartphone-captured video; 3) we provided a broad model pool, allowing users to select from five ML models (SVM, XGBoost, GBDT, MLP, and RF) and four commonly used DL models (DeepGS, DLGWAS, DNNGP, and SoyDNGP). For the convenience of breeders, we employ datasets from the maize (Zea mays) CUBIC population as a case study to demonstrate the usefulness of AutoGP. We show that our genotype chips can effectively extract high-quality SNPs associated with the days to tasseling and plant height. The models present reliable predictive accuracy on different populations, which can provide effective guidance for breeders. Overall, AutoGP offers a practical solution to streamline the breeding process, enabling breeders to achieve more efficient and accurate genomic selection.

PMID:39789848 | DOI:10.1016/j.xplc.2025.101240

Expert Rev Proteomics. 2025 Jan 9. doi: 10.1080/14789450.2025.2451715. Online ahead of print.

ABSTRACT

INTRODUCTION: Molecular recognition features (MoRFs) are regions in protein sequences that undergo induced folding upon binding partner molecules. MoRFs are common in nature and can be predicted from sequences based on their distinctive sequence signatures.

AREAS COVERED: We overview twenty years of progress in the sequence-based prediction of MoRFs which resulted in the development of 25 predictors of MoRFs that interact with proteins, peptides and lipids. These methods range from simple discriminant analysis to sophisticated deep transformer networks that use protein language models. They generate relatively accurate predictions as evidenced by the results of a recently published community-driven assessment.

EXPERT OPINION: MoRFs prediction is a mature field of research that is poised to continue at a steady pace in the foreseeable future. We anticipate further expansion of the scope of MoRF predictions to additional partner molecules, such as nucleic acids, and continued use of recent machine learning advances. Other future efforts should concentrate on improving availability of MoRF predictions by releasing, maintaining and popularizing web servers and by depositing MoRF predictions to large databases of protein structure and function predictions. Furthermore, accurate MoRF predictions should be coupled with the equally accurate prediction and modeling of the resulting structures of complexes.

PMID:39789785 | DOI:10.1080/14789450.2025.2451715

AJNR Am J Neuroradiol. 2025 Jan 9:ajnr.A8645. doi: 10.3174/ajnr.A8645. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Diagnosis of tumefactive demyelination can be challenging. The diagnosis of indeterminate brain lesions on MRI often requires tissue confirmation via brain biopsy. Noninvasive methods for accurate diagnosis of tumor and non-tumor etiologies allows for tailored therapy, optimal tumor control, and a reduced risk of iatrogenic morbidity and mortality. Tumefactive demyelination has imaging features that mimic isocitrate dehydrogenase-wildtype glioblastoma (IDHwt GBM). We hypothesized that deep learning applied to postcontrast T1-weighted (T1C) and T2-weighted (T2) MRI images can discriminate tumefactive demyelination from IDHwt GBM.

MATERIALS AND METHODS: Patients with tumefactive demyelination (n=144) and IDHwt GBM (n=455) were identified by clinical registries. A 3D DenseNet121 architecture was used to develop models to differentiate tumefactive demyelination and IDHwt GBM using both T1C and T2 MRI images, as well as only T1C and only T2 images. A three-stage design was used: (i) model development and internal validation via five-fold cross validation using a sex-, age-, and MRI technology-matched set of tumefactive demyelination and IDHwt GBM, (ii) validation of model specificity on independent IDHwt GBM, and (iii) prospective validation on tumefactive demyelination and IDHwt GBM. Stratified AUCs were used to evaluate model performance stratified by sex, age at diagnosis, MRI scanner strength, and MRI acquisition.

RESULTS: The deep learning model developed using both T1C and T2 images had a prospective validation area under the receiver operator characteristic curve (AUC) of 88% (95% CI: 0.82 - 0.95). In the prospective validation stage, a model score threshold of 0.28 resulted in 91% sensitivity of correctly classifying tumefactive demyelination and 80% specificity (correctly classifying IDHwt GBM). Stratified AUCs demonstrated that model performance may be improved if thresholds were chosen stratified by age and MRI acquisition.

CONCLUSIONS: MRI images can provide the basis for applying deep learning models to aid in the differential diagnosis of brain lesions. Further validation is needed to evaluate how well the model generalizes across institutions, patient populations, and technology, and to evaluate optimal thresholds for classification. Next steps also should incorporate additional tumor etiologies such as CNS lymphoma and brain metastases.

ABBREVIATIONS: AUC = area under the receiver operator characteristic curve; CNS = central nervous system; CNSIDD = central nervous system inflammatory demyelinating disease; FeTS = federated tumor segmentation; GBM = glioblastoma; IDHwt = isocitrate dehydrogenase wildtype; IHC = immunohistochemistry; MOGAD = myelin oligodendrocyte glycoprotein antibody associated disorder; MS = multiple sclerosis; NMOSD = neuromyelitis optica spectrum disorder; wt = wildtype.

PMID:39788628 | DOI:10.3174/ajnr.A8645

J Pathol. 2025 Feb;265(2):198-210. doi: 10.1002/path.6378.

ABSTRACT

Colorectal cancer (CRC) is a histologically heterogeneous disease with variable clinical outcome. The role the tumour microenvironment (TME) plays in determining tumour progression is complex and not fully understood. To improve our understanding, it is critical that the TME is studied systematically within clinically annotated patient cohorts with long-term follow-up. Here we studied the TME in three clinical cohorts of metastatic CRC with diverse molecular subtype and treatment history. The MISSONI cohort included cases with microsatellite instability that received immunotherapy (n = 59, 24 months median follow-up). The BRAF cohort included BRAF V600E mutant microsatellite stable (MSS) cancers (n = 141, 24 months median follow-up). The VALENTINO cohort included RAS/RAF WT MSS cases who received chemotherapy and anti-EGFR therapy (n = 175, 32 months median follow-up). Using a Deep learning cell classifier, trained upon >38,000 pathologist annotations, to detect eight cell types within H&E-stained sections of CRC, we quantified the spatial tissue organisation and colocalisation of cell types across these cohorts. We found that the ratio of infiltrating endothelial cells to cancer cells, a possible marker of vascular invasion, was an independent predictor of progression-free survival (PFS) in the BRAF+MISSONI cohort (p = 0.033, HR = 1.44, CI = 1.029-2.01). In the VALENTINO cohort, this pattern was also an independent PFS predictor in TP53 mutant patients (p = 0.009, HR = 0.59, CI = 0.40-0.88). Tumour-infiltrating lymphocytes were an independent predictor of PFS in BRAF+MISSONI (p = 0.016, HR = 0.36, CI = 0.153-0.83). Elevated tumour-infiltrating macrophages were predictive of improved PFS in the MISSONI cohort (p = 0.031). We validated our cell classification using highly multiplexed immunofluorescence for 17 markers applied to the same sections that were analysed by the classifier (n = 26 cases). These findings uncovered important microenvironmental factors that underpin treatment response across and within CRC molecular subtypes, while providing an atlas of the distribution of 180 million cells in 375 clinically annotated CRC patients. © 2025 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

PMID:39788558 | DOI:10.1002/path.6378

Magn Reson Imaging. 2025 Jan 7:110325. doi: 10.1016/j.mri.2025.110325. Online ahead of print.

ABSTRACT

OBJECTIVE: To explore the application value of MRI-based imaging histology and deep learning model in the identification and classification of breast phyllodes tumors.

METHODS: Seventy-seven patients diagnosed as breast phyllodes tumors and fibroadenomas by pathological examination were retrospectively analyzed, and traditional radiomics features, subregion radiomics features, and deep learning features were extracted from MRI images, respectively. The features were screened and modeled using variance selection method, statistical test, random forest importance ranking method, Spearman correlation analysis, least absolute shrinkage and selection operator (LASSO). The efficacy of each model was assessed using the subject operating characteristic (ROC) curve, The DeLong test was used to assess the differences in the AUC values of the different models, and the clinical benefit of each model was assessed using the decision curve (DCA), and the predictive accuracy of the model was assessed using the calibration curve (CCA).

RESULTS: Among the constructed models for classification of breast phyllodes tumors, the fusion model (AUC: 0.97) had the best diagnostic efficacy and highest clinical benefit. The traditional radiomics model (AUC: 0.81) had better diagnostic efficacy compared with subregion radiomics model (AUC: 0.70). De-Long test, there is a statistical difference between the fusion model traditional radiomics model, and subregion radiomics model in the training group. Among the models constructed to distinguish phyllodes tumors from fibroadenomas in the breast, the TDT_CIDL model (AUC: 0.974) had the best predictive efficacy and the highest clinical benefit. De-Long test, the TDT_CI combination model was statistically different from the remaining five models in the training group.

CONCLUSION: Traditional radiomics models, subregion radiomics models and deep learning models based on MRI sequences can help to differentiate benign from junctional phyllodes tumors, phyllodes tumors from fibroadenomas, and provide personalized treatment for patients.

PMID:39788394 | DOI:10.1016/j.mri.2025.110325

Plant Methods. 2025 Jan 9;21(1):4. doi: 10.1186/s13007-025-01324-5.

ABSTRACT

Apricot trees, serving as critical agricultural resources, hold a significant role within the agricultural domain. Conventional methods for detecting pests and diseases in these trees are notably labor-intensive. Many conditions affecting apricot trees manifest distinct visual symptoms that are ideally suited for precise identification and classification via deep learning techniques. Despite this, the academic realm currently lacks extensive, realistic datasets and deep learning strategies specifically crafted for apricot trees. This study introduces ATZD01, a publicly accessible dataset encompassing 11 categories of apricot tree pests and diseases, meticulously compiled under genuine field conditions. Furthermore, we introduce an innovative detection algorithm founded on convolutional neural networks, specifically devised for the management of apricot tree pests and diseases. To enhance the accuracy of detection, we have developed a novel object detection framework, APNet, alongside a dedicated module, the Adaptive Thresholding Algorithm (ATA), tailored for the detection of apricot tree afflictions. Experimental evaluations reveal that our proposed algorithm attains an accuracy rate of 87.1% on ATZD01, surpassing the performance of all other leading algorithms tested, thereby affirming the effectiveness of our dataset and model. The code and dataset will be made available at https://github.com/meanlang/ATZD01 .

PMID:39789617 | DOI:10.1186/s13007-025-01324-5

BMC Med Inform Decis Mak. 2025 Jan 9;25(1):13. doi: 10.1186/s12911-024-02819-2.

ABSTRACT

BACKGROUND: Urinary tract infection (UTI) is a frequent health-threatening condition. Early reliable diagnosis of UTI helps to prevent misuse or overuse of antibiotics and hence prevent antibiotic resistance. The gold standard for UTI diagnosis is urine culture which is a time-consuming and also an error prone method. In this regard, complementary methods are demanded. In the recent decade, machine learning strategies that employ mathematical models on a dataset to extract the most informative hidden information are the center of interest for prediction and diagnosis purposes.

METHOD: In this study, machine learning approaches were used for finding the important variables for a reliable prediction of UTI. Several types of machines including classical and deep learning models were used for this purpose.

RESULTS: Eighteen selected features from urine test, blood test, and demographic data were found as the most informative features. Factors extracted from urine such as WBC, nitrite, leukocyte, clarity, color, blood, bilirubin, urobilinogen, and factors extracted from blood test like mean platelet volume, lymphocyte, glucose, red blood cell distribution width, and potassium, and demographic data such as age, gender and previous use of antibiotics were the determinative factors for UTI prediction. An ensemble combination of XGBoost, decision tree, and light gradient boosting machines with a voting scheme obtained the highest accuracy for UTI prediction (AUC: 88.53 (0.25), accuracy: 85.64 (0.20)%), according to the selected features. Furthermore, the results showed the importance of gender and age for UTI prediction.

CONCLUSION: This study highlighted the potential of machine learning strategies for UTI prediction.

PMID:39789596 | DOI:10.1186/s12911-024-02819-2

BMC Cancer. 2025 Jan 9;25(1):45. doi: 10.1186/s12885-025-13424-5.

ABSTRACT

OBJECTIVES: To construct a prediction model based on deep learning (DL) and radiomics features of diffusion weighted imaging (DWI), and clinical variables for evaluating TP53 mutations in endometrial cancer (EC).

METHODS: DWI and clinical data from 155 EC patients were included in this study, consisting of 80 in the training set, 35 in the test set, and 40 in the external validation set. Radiomics features, convolutional neural network-based DL features, and clinical variables were analyzed. Feature selection was performed using Mann-Whitney U test, LASSO regression, and SelectKBest. Prediction models were established by gaussian process (GP) and decision tree (DT) algorithms and evaluated by the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), calibration curves, and decision curve analysis (DCA).

RESULTS: Compared to the DL (AUCtraining = 0.830, AUCtest = 0.779, and AUCvalidation = 0.711), radiomics (AUCtraining = 0.810, AUCtest = 0.710, and AUCvalidation = 0.839), and clinical (AUCtraining = 0.780, AUCtest = 0.685, and AUCvalidation = 0.695) models, the combined model based on the GP algorithm, which consisted of four DL features, five radiomics features, and two clinical variables, not only demonstrated the highest diagnostic efficacy (AUCtraining = 0.949, AUCtest = 0.877, and AUCvalidation = 0.914) but also led to an improvement in risk reclassification of the TP53 mutation (NIRtraining = 66.38%, 56.98%, and 83.48%, NIRtest = 50.72%, 80.43%, and 89.49%, and NIRvalidation = 64.58%, 87.50%, and 120.83%, respectively). In addition, the combined model exhibited good agreement and clinical utility in calibration curves and DCA analyses, respectively.

CONCLUSIONS: A prediction model based on the GP algorithm and consisting of DL and radiomics features of DWI as well as clinical variables can effectively assess TP53 mutation in EC.

PMID:39789538 | DOI:10.1186/s12885-025-13424-5

Int J Cardiovasc Imaging. 2025 Jan 9. doi: 10.1007/s10554-025-03324-x. Online ahead of print.

ABSTRACT

The initial evaluation of stenosis during coronary angiography is typically performed by visual assessment. Visual assessment has limited accuracy compared to fractional flow reserve and quantitative coronary angiography, which are more time-consuming and costly. Applying deep learning might yield a faster and more accurate stenosis assessment. We developed a deep learning model to classify cine loops into left or right coronary artery (LCA/RCA) or "other". Data were obtained by manual annotation. Using these classifications, cine loops before revascularization were identified and curated automatically. Separate deep learning models for LCA and RCA were developed to estimate stenosis using these identified cine loops. From a cohort of 19,414 patients and 332,582 cine loops, we identified cine loops for 13,480 patients for model development and 5056 for internal testing. External testing was conducted using automated identified cine loops from 608 patients. For identification of significant stenosis (visual assessment of diameter stenosis > 70%), our model obtained a receiver operator characteristic (ROC) area under the curve (ROC-AUC) of 0.903 (95% CI: 0.900-0.906) on the internal test. The performance was evaluated on the external test set against visual assessment, 3D quantitative coronary angiography, and fractional flow reserve (≤ 0.80), obtaining ROC AUC values of 0.833 (95% CI: 0.814-0.852), 0.798 (95% CI: 0.741-0.842), and 0.780 (95% CI: 0.743-0.817), respectively. The deep-learning-based stenosis estimation models showed promising results for predicting stenosis. Compared to previous work, our approach demonstrates performance increase, includes all 16 segments, does not exclude revascularized patients, is externally tested, and is simpler using fewer steps.

PMID:39789341 | DOI:10.1007/s10554-025-03324-x

J Imaging Inform Med. 2025 Jan 9. doi: 10.1007/s10278-024-01351-z. Online ahead of print.

ABSTRACT

PURPOSE: To explore the information in routine digital subtraction angiography (DSA) and evaluate deep learning algorithms for automated identification of anatomic location in DSA sequences.

METHODS: DSA of the abdominal aorta, celiac, superior mesenteric, inferior mesenteric, and bilateral external iliac arteries was labeled with the anatomic location from retrospectively collected endovascular procedures performed between 2010 and 2020 at a tertiary care medical center. "Key" images within each sequence demonstrating the parent vessel and the first bifurcation were additionally labeled. Mode models aggregating single image predictions, trained with the full or "key" datasets, and a multiple instance learning (MIL) model were developed for location classification of the DSA sequences. Model performance was evaluated with a primary endpoint of multiclass classification accuracy and compared by McNemar's test.

RESULTS: A total of 819 unique angiographic sequences from 205 patients and 276 procedures were included in the training, validation, and testing data and split into partitions at the patient level to preclude data leakage. The data demonstrate substantial information sparsity as a minority of the images were designated as "key" with sufficient information for localization by a domain expert. A Mode model, trained and tested with "key" images, demonstrated an overall multiclass classification accuracy of 0.975 (95% CI 0.941-1). A MIL model, trained and tested with all data, demonstrated an overall multiclass classification accuracy of 0.966 (95% CI 0.932-0.992). Both the Mode model with "key" images (p < 0.001) and MIL model (p < 0.001) significantly outperformed a Mode model trained and tested with the full dataset. The MIL model additionally automatically identified a set of top-5 images with an average overlap of 92.5% to manually labelled "key" images.

CONCLUSION: Deep learning algorithms can identify anatomic locations in abdominopelvic DSA with high fidelity using manual or automatic methods to manage information sparsity.

PMID:39789320 | DOI:10.1007/s10278-024-01351-z

Clin Rheumatol. 2025 Jan 10. doi: 10.1007/s10067-025-07304-3. Online ahead of print.

ABSTRACT

OBJECTIVES: Predicting rheumatoid arthritis (RA) progression in undifferentiated arthritis (UA) patients remains a challenge. Traditional approaches combining clinical assessments and ultrasonography (US) often lack accuracy due to the complex interaction of clinical variables, and routine extensive US is impractical. Machine learning (ML) models, particularly those integrating the 18-joint ultrasound scoring system (US18), have shown potential to address these issues but remain underexplored. This study aims to evaluate ML models integrating US18 with clinical data to improve early identification of high-risk patients and support personalized treatment strategies.

METHODS: In this prospective cohort, 432 UA patients were followed for 1 year to track progression to RA. Four ML algorithms and one deep learning model were developed using baseline clinical and US18 data. Comparative experiments on a testing cohort identified the optimal model. SHAP (SHapley Additive exPlanations) analysis highlighted key variables, validated through an ablation experiment.

RESULTS: Of the 432 patients, 152 (35.2%) progressed to the RA group, while 280 (64.8%) remained in the non-RA group. The Random Forest (RnFr) model demonstrated the highest accuracy and sensitivity. SHAP analysis identified joint counts at US18 Grade 2, total US18 score, and swollen joint count as the most influential variables. The ablation experiment confirmed the importance of US18 in enhancing early RA detection.

CONCLUSIONS: Integrating the US18 assessment with clinical data in an RnFr model significantly improves early detection of RA progression in UA patients, offering potential for earlier and more personalized treatments. Key Points • A machine learning model integrating clinical and ultrasound features effectively predicts rheumatoid arthritis progression in undifferentiated arthritis patients. • The 18-joint ultrasound scoring system (US18) enhances predictive accuracy, particularly when incorporated with clinical variables in a Random Forest model. • SHAP analysis underscores that joint severity levels in US18 contribute significantly to early identification of high-risk patients. • This study offers a feasible and efficient approach for clinical implementation, supporting more personalized and timely RA treatment strategies.

PMID:39789318 | DOI:10.1007/s10067-025-07304-3

Int J Comput Assist Radiol Surg. 2025 Jan 9. doi: 10.1007/s11548-024-03319-4. Online ahead of print.

ABSTRACT

PURPOSE: This article introduces a novel deep learning approach to substantially improve the accuracy of colon segmentation even with limited data annotation, which enhances the overall effectiveness of the CT colonography pipeline in clinical settings.

METHODS: The proposed approach integrates 3D contextual information via guided sequential episodic training in which a query CT slice is segmented by exploiting its previous labeled CT slice (i.e., support). Segmentation starts by detecting the rectum using a Markov Random Field-based algorithm. Then, supervised sequential episodic training is applied to the remaining slices, while contrastive learning is employed to enhance feature discriminability, thereby improving segmentation accuracy.

RESULTS: The proposed method, evaluated on 98 abdominal scans of prepped patients, achieved a Dice coefficient of 97.3% and a polyp information preservation accuracy of 98.28%. Statistical analysis, including 95% confidence intervals, underscores the method's robustness and reliability. Clinically, this high level of accuracy is vital for ensuring the preservation of critical polyp details, which are essential for accurate automatic diagnostic evaluation. The proposed method performs reliably in scenarios with limited annotated data. This is demonstrated by achieving a Dice coefficient of 97.15% when the model was trained on a smaller number of annotated CT scans (e.g., 10 scans) than the testing dataset (e.g., 88 scans).

CONCLUSIONS: The proposed sequential segmentation approach achieves promising results in colon segmentation. A key strength of the method is its ability to generalize effectively, even with limited annotated datasets-a common challenge in medical imaging.

PMID:39789205 | DOI:10.1007/s11548-024-03319-4