Atypia of Undetermined Significance (AUS), classified as Category III in the Bethesda Thyroid Cytopathology Reporting System, presents significant diagnostic challenges for clinicians. This study aims to develop a clinical decision support system that integrates structural equation modeling (SEM) and machine learning to predict malignancy in AUS thyroid nodules. The model integrates preoperative clinical data, ultrasonography (USG) findings, and cytopathological and morphometric variables. This retrospective cohort study was conducted between 2011 and 2019 at Karadeniz Technical University (KTU) Farabi Hospital. The dataset included 56 variables derived from 204 thyroid nodules diagnosed via ultrasound-guided fine-needle aspiration biopsy (FNAB) in 183 patients over 18 years. Logistic regression (LR) and SEM were used to identify risk factors for early thyroid cancer detection. Subsequently, machine learning algorithms-including Support Vector Machines (SVM), Naive Bayes (NB), and Decision Trees (DT) were used to construct decision support models. After feature selection with SEM, the SVM model achieved the highest performance, with an accuracy of 82 %, a specificity of 97 %, and an AUC value of 84 %. Additional models were developed for different scenarios, and their performance metrics were compared. Accurate preoperative prediction of malignancy in thyroid nodules is crucial for avoiding unnecessary surgeries. The proposed model supports more informed clinical decision-making by effectively identifying benign cases, thereby reducing surgical risk and improving patient care.

Immune checkpoint inhibitors (ICIs) and targeted therapies have revolutionized the management of metastatic renal cell carcinoma (mRCC). Currently, the frontline standard of care for patients with mRCC involves the provision of systemic ICI-based combination therapy with no clear guidelines on holding or de-escalating treatment, even with a complete or partial radiological response. Treatments usually continue until disease progression or unacceptable toxicity, frequently leading to overtreatment, which can elevate the risk of toxicity without providing a corresponding increase in therapeutic efficacy. In addition, the ongoing use of expensive antineoplastic drugs increases the financial burden on the already overstretched health care systems and on patients and their families. De-escalation strategies could be designed by integrating contemporary technologies, such as circulating tumor DNA, and advanced imaging techniques, such as computed tomography (CT) scans, positron emission tomography CT, magnetic resonance imaging, and machine learning models. Treatment de-escalation, when appropriate, can minimize treatment-related toxicities, reduce health care costs, and optimize the patients' quality of life while maintaining effective cancer control. This paper discusses the advantages, challenges, and clinical implications of de-escalation strategies in the management of mRCC. PATIENT SUMMARY: In this report, we describe the burden of overtreatment in patients who are never able to stop treatments for metastatic kidney cancer. We discuss the application of the latest technology that can help in making de-escalation decisions.

Imaging is crucial to assess disease extent, activity, and outcomes in inflammatory bowel disease (IBD). Artificial intelligence (AI) image interpretation requires automated exploitation of studies at scale as an initial step. Here we evaluate natural language processing to classify Crohn's disease (CD) on CTE. From our population representative IBD registry a sample of CD patients (male: 44.6%, median age: 50 IQR37-60) and controls (n = 981 each) CTE reports were extracted and split into training- (n = 1568), development- (n = 196), and testing (n = 198) datasets each with around 200 words and balanced numbers of labels, respectively. Predictive classification was evaluated with CNN, Bi-LSTM, BERT-110M, LLaMA-3.3-70B-Instruct and DeepSeek-R1-Distill-LLaMA-70B. While our custom IBDBERT finetuned on expert IBD knowledge (i.e. ACG, AGA, ECCO guidelines), outperformed rule- and rationale extraction-based classifiers (accuracy 88.6% with pre-tuning learning rate 0.00001, AUC 0.945) in predictive performance, LLaMA, but not DeepSeek achieved overall superior results (accuracy 91.2% vs. 88.9%, F1 0.907 vs. 0.874).

This systematic review investigates the potential of artificial intelligence (AI) in improving the accuracy and efficiency of prostate-specific membrane antigen positron emission tomography (PSMA PET) scans for detecting metastatic prostate cancer. A comprehensive literature search was conducted across Medline, Embase, and Web of Science, adhering to PRISMA guidelines. Key search terms included "artificial intelligence," "machine learning," "deep learning," "prostate cancer," and "PSMA PET." The PICO framework guided the selection of studies focusing on AI's application in evaluating PSMA PET scans for staging lymph node and distant metastasis in prostate cancer patients. Inclusion criteria prioritized original English-language articles published up to October 2024, excluding studies using non-PSMA radiotracers, those analyzing only the CT component of PSMA PET-CT, studies focusing solely on intra-prostatic lesions, and non-original research articles. The review included 22 studies, with a mix of prospective and retrospective designs. AI algorithms employed included machine learning (ML), deep learning (DL), and convolutional neural networks (CNNs). The studies explored various applications of AI, including improving diagnostic accuracy, sensitivity, differentiation from benign lesions, standardization of reporting, and predicting treatment response. Results showed high sensitivity (62% to 97%) and accuracy (AUC up to 98%) in detecting metastatic disease, but also significant variability in positive predictive value (39.2% to 66.8%). AI demonstrates significant promise in enhancing PSMA PET scan analysis for metastatic prostate cancer, offering improved efficiency and potentially better diagnostic accuracy. However, the variability in performance and the "black box" nature of some algorithms highlight the need for larger prospective studies, improved model interpretability, and the continued involvement of experienced nuclear medicine physicians in interpreting AI-assisted results. AI should be considered a valuable adjunct, not a replacement, for expert clinical judgment.

To investigate the prediction of a model constructed by combining machine learning (ML) with clinical features and ultrasound radiomics in the clinical staging of cervical cancer. General clinical and ultrasound data of 227 patients with cervical cancer who received transvaginal ultrasonography were retrospectively analyzed. The region of interest (ROI) radiomics profiles of the original image and derived image were retrieved and profile screening was performed. The chosen profiles were employed in radiomics model and Radscore formula construction. Prediction models were developed utilizing several ML algorithms by Python based on an integrated dataset of clinical features and ultrasound radiomics. Model performances were evaluated via AUC. Plot calibration curves and clinical decision curves were used to assess model efficacy. The model developed by support vector machine (SVM) emerged as the superior model. Integrating clinical characteristics with ultrasound radiomics, it showed notable performance metrics in both the training and validation datasets. Specifically, in the training set, the model obtained an AUC of 0.88 (95% Confidence Interval (CI): 0.83-0.93), alongside a 0.84 accuracy, 0.68 sensitivity, and 0.91 specificity. When validated, the model maintained an AUC of 0.77 (95% CI: 0.63-0.88), with 0.77 accuracy, 0.62 sensitivity, and 0.83 specificity. The calibration curve aligned closely with the perfect calibration line. Additionally, based on the clinical decision curve analysis, the model offers clinical utility over wide-ranging threshold possibilities. The clinical- and radiomics-based SVM model provides a noninvasive tool for predicting cervical cancer stage, integrating ultrasound radiomics and key clinical factors (age, abortion history) to improve risk stratification. This approach could guide personalized treatment (surgery vs. chemoradiation) and optimize staging accuracy, particularly in resource-limited settings where advanced imaging is scarce.

Ultrasound assessment of fetal size and growth is the mainstay of monitoring fetal well-being during pregnancy, as being small for gestational age (SGA) or large for gestational age (LGA) poses significant risks for both the fetus and the mother. This study aimed to enhance the prediction accuracy of abnormal fetal growth. We developed a deep learning model, trained on a dataset of 433,096 ultrasound images derived from 94,538 examinations conducted on 65,752 patients. The deep learning model performed significantly better in detecting both SGA (58% vs 70%) and LGA compared with the current clinical standard, the Hadlock formula (41% vs 55%), p < 0.001. Additionally, the model estimates were significantly less biased across all demographic and technical variables compared to the Hadlock formula. Incorporating key anatomical features such as cortical structures, liver texture, and skin thickness was likely to be responsible for the improved prediction accuracy observed.

Effective radiotherapy planning requires precise delineation of organs at risk (OARs), but the traditional manual method is laborious and subject to variability. This study explores using convolutional neural networks (CNNs) for automating OAR segmentation in pelvic CT images, focusing on the bladder, prostate, rectum, and femoral heads (FHs) as an efficient alternative to manual segmentation. Utilizing the Medical Open Network for AI (MONAI) framework, we implemented and compared U-Net, ResU-Net, SegResNet, and Attention U-Net models and explored different loss functions to enhance segmentation accuracy. Our study involved 240 patients for prostate segmentation and 220 patients for the other organs. The models' performance was evaluated using metrics such as the Dice similarity coefficient (DSC), Jaccard index (JI), and the 95th percentile Hausdorff distance (95thHD), benchmarking the results against expert segmentation masks. SegResNet outperformed all models, achieving DSC values of 0.951 for the bladder, 0.829 for the prostate, 0.860 for the rectum, 0.979 for the left FH, and 0.985 for the right FH (p < 0.05 vs. U-Net and ResU-Net). Attention U-Net also excelled, particularly for bladder and rectum segmentation. Experiments with loss functions on SegResNet showed that Dice loss consistently delivered optimal or equivalent performance across OARs, while DiceCE slightly enhanced prostate segmentation (DSC = 0.845, p = 0.0138). These results indicate that advanced CNNs, especially SegResNet, paired with optimized loss functions, provide a reliable, efficient alternative to manual methods, promising improved precision in radiotherapy planning.

BackgroundAcute appendicitis remains a challenging diagnosis in pediatric populations, with high rates of misdiagnosis and negative appendectomies despite advances in imaging modalities. Current diagnostic tools, including clinical scoring systems like Alvarado and Pediatric Appendicitis Score (PAS), lack sufficient sensitivity and specificity, while reliance on CT scans raises concerns about radiation exposure, contrast hazards and sedation in children. Moreover, no established tool effectively predicts progression from uncomplicated to complicated appendicitis, creating a critical gap in clinical decision-making. ObjectiveTo develop and evaluate a machine learning model that integrates clinical, laboratory, and radiological findings for accurate diagnosis and complication prediction in pediatric appendicitis and to deploy this model as an interpretable web-based tool for clinical decision support. MethodsWe analyzed data from 780 pediatric patients (ages 0-18) with suspected appendicitis admitted to Childrens Hospital St. Hedwig, Regensburg, between 2016 and 2021. For severity prediction, our dataset was augmented with 430 additional cases from published literature and only the confirmed cases of acute appendicitis(n=602) were used. After feature selection using statistical methods and recursive feature elimination, we developed a Random Forest model named Dharma, optimized through hyperparameter tuning and cross-validation. Model performance was evaluated on independent test sets and compared with conventional diagnostic tools. ResultsDharma demonstrated superior diagnostic performance with an AUC-ROC of 0.96 ({+/-}0.02 SD) in cross-validation and 0.97-0.98 on independent test sets. At an optimal threshold of 64%, the model achieved specificity of 88%-98%, sensitivity of 89%-95%, and positive predictive value of 93%-99%. For complication prediction, Dharma attained a sensitivity of 93% ({+/-}0.05 SD) in cross-validation and 96% on the test set, with a negative predictive value of 98%. The model maintained strong performance even in cases where the appendix could not be visualized on ultrasonography (AUC-ROC 0.95, sensitivity 89%, specificity 87% at the threshold of 30%). ConclusionDharma is a novel, interpretable machine learning based clinical decision support tool designed to address the diagnostic challenges of pediatric appendicitis by integrating easily obtainable clinical, laboratory, and radiological data into a unified, real-time predictive framework. Unlike traditional scoring systems and imaging modalities, which may lack specificity or raise safety concerns in children, Dharma demonstrates high accuracy in diagnosing appendicitis and predicting progression from uncomplicated to complicated cases, potentially reducing unnecessary surgeries and CT scans. Its robust performance, even with incomplete imaging data, underscores its utility in resource-limited settings. Delivered through an intuitive, transparent, and interpretable web application, Dharma supports frontline providers--particularly in low- and middle-income settings--in making timely, evidence-based decisions, streamlining patient referrals, and improving clinical outcomes. By bridging critical gaps in current diagnostic and prognostic tools, Dharma offers a practical and accessible 21st-century solution tailored to real-world pediatric surgical care across diverse healthcare contexts. Furthermore, the underlying framework and concepts of Dharma may be adaptable to other clinical challenges beyond pediatric appendicitis, providing a foundation for broader applications of machine learning in healthcare. Author SummaryAccurate diagnosis of pediatric appendicitis remains challenging, with current clinical scores and imaging tests limited by sensitivity, specificity, predictive values, and safety concerns. We developed Dharma, an interpretable machine learning model that integrates clinical, laboratory, and radiological data to assist in diagnosing appendicitis and predicting its severity in children. Evaluated on a large dataset supplemented by published cases, Dharma demonstrated strong diagnostic and prognostic performance, including in cases with incomplete imaging--making it potentially especially useful in resource-limited settings for early decision-making and streamlined referrals. Available as a web-based tool, it provides real-time support to healthcare providers in making evidence-based decisions that could reduce negative appendectomies while avoiding hazards associated with advanced imaging modalities such as sedation, contrast, or radiation exposure. Furthermore, the open-access concepts and framework underlying Dharma have the potential to address diverse healthcare challenges beyond pediatric appendicitis.

The diagnosis of liver fibrosis is usually based on histopathological examination of liver puncture specimens. Although liver puncture is accurate, it has invasive risks and high economic costs, which are difficult for some patients to accept. Therefore, this study uses deep learning technology to build a liver fibrosis diagnosis model to achieve non-invasive staging of liver fibrosis, avoid complications, and reduce costs. This study uses ultrasound examination to obtain pure liver parenchyma image section data. With the consent of the patient, combined with the results of percutaneous liver puncture biopsy, the degree of liver fibrosis indicated by ultrasound examination data is judged. The concept of Fibrosis Contrast Layer (FCL) is creatively introduced in our experimental method, which can help our model more keenly capture the significant differences in the characteristics of liver fibrosis of various grades. Finally, through label fusion (LF), the characteristics of liver specimens of the same fibrosis stage are abstracted and fused to improve the accuracy and stability of the diagnostic model. Experimental evaluation demonstrated that our model achieved an accuracy of 85.6%, outperforming baseline models such as ResNet (81.9%), InceptionNet (80.9%), and VGG (80.8%). Even under a small-sample condition (30% data), the model maintained an accuracy of 84.8%, significantly outperforming traditional deep-learning models exhibiting sharp performance declines. The training results show that in the whole sample data set and 30% small sample data set training environments, the FCLLF model's test performance results are better than those of traditional deep learning models such as VGG, ResNet, and InceptionNet. The performance of the FCLLF model is more stable, especially in the small sample data set environment. Our proposed FCLLF model effectively improves the accuracy and stability of liver fibrosis staging using non-invasive ultrasound imaging.

Liver cirrhosis represents the end stage of chronic liver disease, characterized by extensive fibrosis and nodular regeneration that significantly increases mortality risk. While magnetic resonance imaging (MRI) offers a non-invasive assessment, accurately segmenting cirrhotic livers presents substantial challenges due to morphological alterations and heterogeneous signal characteristics. Deep learning approaches show promise for automating these tasks, but progress has been limited by the absence of large-scale, annotated datasets. Here, we present CirrMRI600+, the first comprehensive dataset comprising 628 high-resolution abdominal MRI scans (310 T1-weighted and 318 T2-weighted sequences, totaling nearly 40,000 annotated slices) with expert-validated segmentation labels for cirrhotic livers. The dataset includes demographic information, clinical parameters, and histopathological validation where available. Additionally, we provide benchmark results from 11 state-of-the-art deep learning experiments to establish performance standards. CirrMRI600+ enables the development and validation of advanced computational methods for cirrhotic liver analysis, potentially accelerating progress toward automated Cirrhosis visual staging and personalized treatment planning.