This study aimed to objectively and quantitatively analyze fetal motor behavior using DeepLabCut (DLC), a markerless posture estimation tool based on deep learning, applied to four-dimensional ultrasound (4DUS) data collected during the second trimester. We propose a novel clinical method for precise assessment of fetal neurodevelopment. Fifty 4DUS video recordings of normal singleton fetuses aged 12 to 22 gestational weeks were analyzed. Eight fetal joints were manually labeled in 2% of each video to train a customized DLC model. The model's accuracy was evaluated using likelihood scores. Intra- and inter-rater reliability of manual labeling were assessed using intraclass correlation coefficients (ICC). Angular velocity time series derived from joint coordinates were analyzed to quantify fetal movement patterns and developmental coordination. Manual labeling demonstrated excellent reproducibility (inter-rater ICC = 0.990, intra-rater ICC = 0.961). The trained DLC model achieved a mean likelihood score of 0.960, confirming high tracking accuracy. Kinematic analysis revealed developmental trends: localized rapid limb movements were common at 12-13 weeks; movements became more coordinated and systemic by 18-20 weeks, reflecting advancing neuromuscular maturation. Although a modest increase in tracking accuracy was observed with gestational age, this trend did not reach statistical significance (p < 0.001). DLC enables precise quantitative analysis of fetal motor behavior from 4DUS recordings. This AI-driven approach offers a promising, noninvasive alternative to conventional qualitative assessments, providing detailed insights into early fetal neurodevelopmental trajectories and potential early screening for neurodevelopmental disorders.

Liver cancer ranks among the most lethal cancers. Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and better diagnostic tools are needed to diagnose patients at risk. The aim is to develop a machine learning algorithm that enhances the sensitivity and specificity of the Contrast-Enhanced Ultrasound Liver Imaging Reporting and Data System (CEUS-LIRADS) in classifying indeterminate at-risk liver nodules (LR-M, LR-3, LR-4) as HCC or non-HCC. Our study includes patients at risk for HCC with untreated indeterminate focal liver observations detected on US or contrast-enhanced CT or MRI performed as part of their clinical standard of care from January 2018 to November 2022. Recursive partitioning was used to improve HCC diagnosis in indeterminate at-risk nodules. Demographics, blood biomarkers, and CEUS imaging features were evaluated as potential predictors for the algorithm to classify nodules as HCC or non-HCC. We evaluated 244 indeterminate liver nodules from 224 patients (mean age 62.9 y). Of the nodules, 73.2% (164/224) were from males. The algorithm was trained on a random 2/3 partition of 163 liver nodules and correctly reclassified more than half of the HCC liver nodules previously categorized as indeterminate in the independent 1/3 test partition of 81 liver nodules, achieving a sensitivity of 56.3% (95% CI: 42.0%, 70.2%) and specificity of 93.9% (95% CI: 84.4%, 100.0%). Machine learning was applied to the multicenter, multinational study of CEUS LI-RADS indeterminate at-risk liver nodules and correctly diagnosed HCC in more than half of the HCC nodules.

Polycystic ovary syndrome (PCOS) has a significant impact on endocrine metabolism, reproductive function, and mental health in women of reproductive age. Ultrasound remains an essential diagnostic tool for PCOS, particularly in individuals presenting with oligomenorrhea or ovulatory dysfunction accompanied by polycystic ovaries, as well as hyperandrogenism associated with polycystic ovaries. However, the accuracy of ultrasound in identifying polycystic ovarian morphology remains variable. To develop a deep learning model capable of rapidly and accurately identifying PCOS using ovarian ultrasound images. Prospective diagnostic accuracy study. This prospective study included data from 1,751 women with suspected PCOS who presented at two affiliated hospitals at Central South University, with clinical and ultrasound information collected and archived. Patients from center 1 were randomly divided into a training set and an internal validation set in a 7:3 ratio, while patients from center 2 served as the external validation set. Using the YOLOv11 deep learning framework, an automated recognition model for ovarian ultrasound images in PCOS cases was constructed, and its diagnostic performance was evaluated. Ultrasound images from 933 patients (781 from center 1 and 152 from center 2) were analyzed. The mean average precision of the YOLOv11 model in detecting the target ovary was 95.7%, 97.6%, and 97.8% for the training, internal validation, and external validation sets, respectively. For diagnostic classification, the model achieved an F1 score of 95.0% in the training set and 96.9% in both validation sets. The area under the curve values were 0.953, 0.973, and 0.967 for the training, internal validation, and external validation sets respectively. The model also demonstrated significantly faster evaluation of a single ovary compared to clinicians (doctor, 5.0 seconds; model, 0.1 seconds; <i>p</i> < 0.01). The YOLOv11-based automatic recognition model for PCOS ovarian ultrasound images exhibits strong target detection and diagnostic performance. This approach can streamline the follicle counting process in conventional ultrasound and enhance the efficiency and generalizability of ultrasound-based PCOS assessment.

Prostate cancer remains one of the most prevalent malignancies and a leading cause of cancer-related deaths among men worldwide. Despite advances in traditional diagnostic methods such as Prostate-specific antigen testing, digital rectal examination, and multiparametric Magnetic resonance imaging, these approaches remain constrained by modality-specific limitations, suboptimal sensitivity and specificity, and reliance on expert interpretation, which may introduce diagnostic inconsistency. Multimodal deep learning and machine learning fusion, which integrates diverse data sources including imaging, clinical, and molecular information, has emerged as a promising strategy to enhance the accuracy of prostate cancer classification. This review aims to outline the current state-of-the-art deep learning and machine learning based fusion techniques for prostate cancer classification, focusing on their implementation, performance, challenges, and clinical applicability. Following the PRISMA guidelines, a total of 131 studies were identified, of which 27 met the inclusion criteria for studies published between 2021 and 2025. Extracted data included input techniques, deep learning architectures, performance metrics, and validation approaches. The majority of the studies used an early fusion approach with convolutional neural networks to integrate the data. Clinical and imaging data were the most commonly used modalities in the reviewed studies for prostate cancer research. Overall, multimodal deep learning and machine learning-based fusion significantly advances prostate cancer classification and outperform unimodal approaches.

The composition of urinary calculi serves as a critical determinant for personalized surgical strategies; however, such compositional data are often unavailable preoperatively. This study aims to develop a machine learning-based preoperative prediction model for stone composition and evaluate its clinical utility. A retrospective cohort study design was employed to include patients with urinary calculi admitted to the Department of Urology at the Second Affiliated Hospital of Zhengzhou University from 2019 to 2024. Feature selection was performed using least absolute shrinkage and selection operator (LASSO) regression combined with multivariate logistic regression, and a binary prediction model for urinary calculi was subsequently constructed. Model validation was conducted using metrics such as the area under the curve (AUC), while Shapley Additive Explanations(SHAP) values were applied to interpret the predictive outcomes. Among 708 eligible patients, distinct prediction models were established for four stone types: calcium oxalate stones: Logistic regression achieved optimal performance (AUC = 0.845), with maximum stone CT value, 24-hour urinary oxalate, and stone size as top predictors (SHAP-ranked); infection stones: Logistic regression (AUC = 0.864) prioritized stone size, urinary pH, and recurrence history; uric acid stones: LASSO-ridge-elastic net model demonstrated exceptional accuracy (AUC = 0.961), driven by maximum CT value, 24-hour oxalate, and urinary calcium; calcium-containing stones: Logistic regression attained better prediction (AUC = 0.953), relying on CT value, 24-hour calcium, and stone size. This study developed a machine learning prediction model based on multi-algorithm integration, achieving accurate preoperative discrimination of urinary stone composition. The integration of key imaging features with metabolic indicators enhanced the model's predictive performance.

Cervical cancer is a significant global health issue, and high-dose-rate brachytherapy (HDR-BT) is crucial for its treatment. However, manually creating HDR-BT plans is time-consuming and heavily relies on the planner's expertise, making standardization difficult. This study introduces two advanced deep learning models to address this need: Bi-branch Cross-Attention UNet (BiCA-UNet) and Dendrite Cross-Attention UNet (DCA-UNet). BiCA-UNet enhances the correlation between the CT scan and segmentation maps of the clinical target volume (CTV), applicator, bladder, and rectum. It uses two branches: one processes the stacked input of CT scans and segmentations, and the other focuses on the CTV segmentation. A cross-attention mechanism integrates these branches, improving the model's understanding of the CTV region for accurate dose predictions. Building on BiCA-UNet, DCA-UNet further introduces a primary branch of stacked inputs and three secondary branches for CTV, bladder, and rectum segmentations forming a dendritic structure. Cross attention with bladder and rectum segmentation helps the model understand the regions of organs at risk (OAR), refining dose prediction. Evaluation of these models using multiple metrics indicates that both BiCA-UNet and DCA-UNet significantly improve HDR-BT dose prediction accuracy for various applicator types. The cross-attention mechanisms enhance the feature representation of critical anatomical regions, leading to precise and reliable treatment plans. This research highlights the potential of BiCA-UNet and DCA-UNet in advancing HDR-BT planning, contributing to the standardization of treatment plans, and offering promising directions for future research to improve patient outcomes in the source data.

Cervical cancer is a leading cause of death from malignant tumors in women, and accurate evaluation of occult lymph node metastasis (OLNM) is crucial for optimal treatment. This study aimed to develop several predictive models-including Clinical model, Radiomics models (RD), Deep Learning models (DL), Radiomics-Deep Learning fusion models (RD-DL), and a Clinical-RD-DL combined model-for assessing the risk of OLNM in cervical cancer patients.The study included 130 patients from Center 1 (training set) and 55 from Center 2 (test set). Clinical data and imaging sequences (T1, T2, and DWI) were used to extract features for model construction. Model performance was assessed using the DeLong test, and SHAP analysis was used to examine feature contributions. Results showed that both the RD-combined (AUC = 0.803) and DL-combined (AUC = 0.818) models outperformed single-sequence models as well as the standalone Clinical model (AUC = 0.702). The RD-DL model yielded the highest performance, achieving an AUC of 0.981 in the training set and 0.903 in the test set. Notably, integrating clinical variables did not further improve predictive performance; the Clinical-RD-DL model performed comparably to the RD-DL model. SHAP analysis showed that deep learning features had the greatest impact on model predictions. Both RD and DL models effectively predict OLNM, with the RD-DL model offering superior performance. These findings provide a rapid, non-invasive clinical prediction method.

We developed a machine learning model comprising morphological characteristics, enhancement dynamics, and extracellular volume (ECV) fractions for distinguishing malignant and benign small renal masses (SRMs), supporting personalised management. This retrospective analysis involved 230 patients who underwent SRM resection with preoperative imaging, including 185 internal and 45 external cases. The internal cohort was split into training (n=136) and validation (n=49) sets. Histopathological evaluation categorised the lesions as renal cell carcinomas (n=183) or benign masses (n=47). Eleven multiphasic contrast-enhanced computed tomography (CT) parameters, including the ECV fraction, were manually measured, along with clinical and laboratory data. Feature selection involved univariate analysis and least absolute shrinkage and selection operator regularisation. Feature selection informed various machine learning classifiers, and performance was evaluated using receiver operating characteristic curves and classification tests. The optimal model was interpreted using SHapley Additive exPlanations (SHAP). The analysis included 183 carcinoma and 47 benign SRM cases. Feature selection identified seven discriminative parameters, including the ECV fraction, which informed multiple machine learning models. The Extreme Gradient Boosting model incorporating ECV exhibited optimal performance in distinguishing malignant and benign SRMs, achieving area under the curve values of 0.993 (internal training set), 0.986 (internal validation set), and 0.951 (external test set). SHAP analysis confirmed ECV as the top contributor to SRM characterisation. The integration of multiphase contrast-enhanced CT-derived ECV fraction with conventional contrast-enhanced CT parameters demonstrated diagnostic efficacy in differentiating malignant and benign SRMs.

This study aims to construct and evaluate 8 machine learning models by integrating ultrasound imaging features, clinical characteristics, and serological features to assess the risk of gallbladder cancer (GBC) occurrence in patients. A retrospective analysis was conducted on ultrasound and clinical data of 300 suspected GBC patients who visited the Second Affiliated Hospital of Fujian Medical University from January 2020 to January 2024 and 69 patients who visited the Zhongshan Hospital Affiliated to Xiamen University from January 2024 to January 2025. Key relevant features were selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression. Predictive models were constructed using XGBoost, logistic regression, support vector machine, k-nearest neighbors, random forest, decision tree, naive Bayes, and neural network, with the SHapley Additive exPlanations (SHAP) method employed to explain model interpretability. The LASSO regression demonstrated that gender, age, alkaline phosphatase (ALP), clarity of interface with liver, stratification of the gallbladder wall, intracapsular anechoic lesions, and intracapsular punctiform strong lesions were key features for GBC. The XGBoost model demonstrated an area under receiver operating characteristic curve (AUC) of 0.934, 0.916, and 0.813 in the training, validating, and test sets. SHAP analysis revealed the importance ranking of factors as clarity of interface with liver, stratification of the gallbladder wall, intracapsular anechoic lesions, and intracapsular punctiform strong lesions, ALP, gender, and age. Personalized prediction explanations through SHAP values demonstrated the contribution of each feature to the final prediction, enhancing result interpretability. Furthermore, decision plots were generated to display the influence trajectory of each feature on model predictions, aiding in analyzing which features had the greatest impact on these mispredictions; thereby facilitating further model optimization or feature adjustment. This study proposed a GBC ML model based on ultrasound, clinical, and serological characteristics, indicating the superior performance of the XGBoost model and enhancing the interpretability of the model through the SHAP method.

Decreased kidney volume is a sign of renal aging and/or decreased vascularization. The aim of this study was to determine whether renal volume changes 24 months after exclusion of an abdominal aortic aneurysm (AAA), and to compare fenestrated (FEVAR) and subrenal (EVAR) stents. Retrospective single-center study from a prospective registry, including patients between 60 and 80 years with normal preoperative renal function (eGFR≥60 ml/min/1.73 m^-2) who underwent fenestrated (FEVAR) or infrarenal (EVAR) stent grafts between 2015 and 2021. Patients had to have had an CT scan at 24 months of the study to be included. Exclusion criteria were renal branches, the presence of preoperative renal insufficiency, a single kidney, embolization or coverage of an accessory renal artery, occlusion of a renal artery during follow-up and mention of AAA rupture. Renal volume was measured using sizing software (EndoSize, therenva) based on fully automatic deep-learning segmentation of several anatomical structures (arterial lumen, bone structure, thrombus, heart, etc.), including the kidneys. In the presence of renal cysts, these were manually excluded from the segmentation. Forty-eight patients were included (24 EVAR vs. 24 FEVAR), 96 kidneys were segmented. There was no difference between groups in age (78.9±6.7 years vs. 69.4±6.8, p=0.89), eGFR 85.8 ± 12.4 [62-107] ml/min/1.73 m^-2 vs. 81 ± 16.2 [42-107] (p=0.36), and renal volume 170.9 ± 29.7 [123-276] mL vs. 165.3 ± 37.4 [115-298] (p=0.12). At 24 months in the EVAR group, there was a non-significant reduction in eGFR 84.1 ± 17.2 [61-128] ml/min/1.73 m^-2 vs. 81 ± 16.2 [42-107] (p=0.36) or renal volume 170.9 ± 29.7 [123-276] mL vs. 165.3 ± 37.4 [115-298] (p=0.12). In the FEVAR group, at 24 months there was a non-significant fall in eGFR 84.1 ± 17.2 [61-128] ml/min/1.73 m^-2 vs. 73.8 ± 21.4 [40-110] (p=0.09), while renal volume decreased significantly 182 ± 37.8 [123-293] mL vs. 158.9 ± 40.2 [45-258] (p=0.007). In this study, there appears to be a significant decrease in renal volume without a drop in eGFR 24 months after fenestrated stenting. This decrease may reflect changes in renal perfusion and could potentially be predictive of long-term renal impairment, although this cannot be confirmed within the limits of this small sample. Further studies with long-term follow-up are needed.