Search Results (76)

Background/Objectives: Patients with breast cancer who do not achieve a complete response to neoadjuvant chemotherapy (NAC) may benefit from intensified adjuvant systemic therapy. However, such treatment escalation is typically delayed until after tumour resection, which occurs several months into the treatment course. Quantitative ultrasound (QUS) can detect early microstructural changes in tumours and may enable timely identification of non-responders during NAC, allowing for earlier treatment intensification. In our previous prospective observational study, 100 breast cancer patients underwent QUS imaging before and four times during NAC. Machine learning algorithms based on QUS texture features acquired in the first week of treatment were developed and achieved 78% accuracy in predicting treatment response. In the current study, we aimed to validate these algorithms in an independent prospective cohort to assess reproducibility and confirm their clinical utility. Methods: We included breast cancer patients eligible for NAC per standard of care, with tumours larger than 1.5 cm. QUS imaging was acquired at baseline and during the first week of treatment. Tumour response was defined as a ≥30% reduction in target lesion size on the resection specimen compared to baseline imaging. Results: A total of 51 patients treated between 2018 and 2021 were included (median age 49 years; median tumour size 3.6 cm). Most were estrogen receptor–positive (65%) or HER2-positive (33%), and the majority received dose-dense AC-T (n = 34, 67%) or FEC-D (n = 15, 29%) chemotherapy, with or without trastuzumab. The support vector machine algorithm achieved an area under the curve of 0.71, with 86% accuracy, 91% specificity, 50% sensitivity, 93% negative predictive value, and 43% positive predictive value for predicting treatment response. Misclassifications were primarily associated with poorly defined tumours and difficulties in accurately identifying the region of interest. Conclusions: Our findings validate QUS-based machine learning models for early prediction of chemotherapy response and support their potential as non-invasive tools for treatment personalization and clinical trial development focused on early treatment intensification. Full article

Coronary plaque vulnerability, more than luminal stenosis, drives acute coronary syndromes. Optical coherence tomography (OCT), intravascular ultrasound (IVUS), and coronary computed tomography angiography (CCTA) visualize plaque morphology in vivo, but manual interpretation is time-consuming and operator-dependent. We performed a narrative literature survey of artificial intelligence (AI) applications—focusing on machine learning (ML) architectures—for automated coronary plaque segmentation and risk characterization across OCT, IVUS, and CCTA. Recent ML models achieve expert-level lumen and plaque segmentation, reliably detecting features linked to vulnerability such as a lipid-rich necrotic core, calcification, positive remodelling, and a napkin-ring sign. Integrative radiomic and multimodal frameworks further improve prognostic stratification for major adverse cardiac events. Nonetheless, progress is constrained by small, single-centre datasets, heterogeneous validation metrics, and limited model interpretability. AI-enhanced plaque assessment offers rapid, reproducible, and comprehensive coronary imaging analysis. Future work should prioritize large multicentre repositories, explainable architectures, and prospective outcome-oriented validation to enable routine clinical adoption. Full article

Pancreatic ductal adenocarcinoma (PDAC) remains among the most lethal malignancies, with a five-year survival rate below 12%, largely attributable to its asymptomatic onset, late-stage diagnosis, and limited curative treatment options. Although PDAC accounts for approximately 3% of all cancers, it is projected to become the second leading cause of cancer-related mortality in the United States by 2030. A major contributor to its dismal prognosis is the lack of validated early detection strategies for asymptomatic individuals. In this review, we present a comprehensive synthesis of current advances in the early detection of PDAC, with a focus on the identification of high-risk populations, novel biomarker platforms, advanced imaging modalities, and artificial intelligence (AI)-driven tools. We highlight high-risk groups—such as those with new-onset diabetes after age 50, pancreatic steatosis, chronic pancreatitis, cystic precursor lesions, and hereditary cancer syndromes—as priority populations for targeted surveillance. Novel biomarker panels, including circulating tumor DNA (ctDNA), miRNAs, and exosomes, have demonstrated improved diagnostic accuracy in early-stage disease. Recent developments in imaging, such as multiparametric MRI, contrast-enhanced endoscopic ultrasound, and molecular imaging, offer improved sensitivity in detecting small or precursor lesions. AI-enhanced radiomics and machine learning models applied to prediagnostic CT scans and electronic health records are emerging as valuable tools for risk prediction prior to clinical presentation. We further refine the Define–Enrich–Find (DEF) framework to propose a clinically actionable strategy that integrates these innovations. Collectively, these advances pave the way for personalized, multimodal surveillance strategies with the potential to improve outcomes in this historically challenging malignancy. Full article

Background/Objectives: Degenerative joint diseases (DJDs) involve intricate molecular disruptions within bone, cartilage, and synovial tissues, often preceding overt radiographic changes. These tissues exhibit complex biomolecular architectures and their degeneration leads to microstructural disorganization and inflammation that are challenging to detect with conventional imaging techniques. This review aims to synthesize recent advances in imaging, computational modeling, and sequencing technologies that enable high-resolution, non-invasive characterization of joint tissue health. Methods: We examined advanced modalities including high-resolution MRI (e.g., T1ρ, sodium MRI), quantitative and dual-energy CT (qCT, DECT), and ultrasound elastography, integrating them with radiomics, deep learning, and multi-scale modeling approaches. We also evaluated RNA-seq, spatial transcriptomics, and mass spectrometry-based proteomics for omics-guided imaging biomarker discovery. Results: Emerging technologies now permit detailed visualization of proteoglycan content, collagen integrity, mineralization patterns, and inflammatory microenvironments. Computational frameworks ranging from convolutional neural networks to finite element and agent-based models enhance diagnostic granularity. Multi-omics integration links imaging phenotypes to gene and protein expression, enabling predictive modeling of tissue remodeling, risk stratification, and personalized therapy planning. Conclusions: The convergence of imaging, AI, and molecular profiling is transforming musculoskeletal diagnostics. These synergistic platforms enable early detection, multi-parametric tissue assessment, and targeted intervention. Widespread clinical integration requires robust data infrastructure, regulatory compliance, and physician education, but offers a pathway toward precision musculoskeletal care. Full article

Degenerative joint disease remains a leading cause of global disability, with early diagnosis posing a significant clinical challenge due to its gradual onset and symptom overlap with other musculoskeletal disorders. This review focuses on emerging diagnostic strategies by synthesizing evidence specifically from studies that integrate biochemical biomarkers, advanced imaging techniques, and machine learning models relevant to osteoarthritis. We evaluate the diagnostic utility of cartilage degradation markers (e.g., CTX-II, COMP), inflammatory cytokines (e.g., IL-1β, TNF-α), and synovial fluid microRNA profiles, and how they correlate with quantitative imaging readouts from T2-mapping MRI, ultrasound elastography, and dual-energy CT. Furthermore, we highlight recent developments in radiomics and AI-driven image interpretation to assess joint space narrowing, osteophyte formation, and subchondral bone changes with high fidelity. The integration of these datasets using multimodal learning approaches offers novel diagnostic phenotypes that stratify patients by disease stage and risk of progression. Finally, we explore the implementation of these tools in point-of-care diagnostics, including portable imaging devices and rapid biomarker assays, particularly in aging and underserved populations. By presenting a unified diagnostic pipeline, this article advances the future of early detection and personalized monitoring in joint degeneration. Full article

This manuscript examines the role of artificial intelligence (AI) in the diagnosis and treatment of uterine fibroids and uterine sarcomas, offering a comprehensive assessment of AI-supported diagnostic and therapeutic techniques. Through the use of radiomics, machine learning, and deep neural network models, AI shows promise in identifying benign and malignant uterine lesions, directing therapeutic decisions, and improving diagnostic accuracy. It also demonstrates significant capabilities in the timely detection of fibroids. Additionally, AI improves surgical precision, real-time structure detection, and patient outcomes by transforming surgical techniques such as myomectomy, robot-assisted laparoscopic surgery, and High-Intensity Focused Ultrasound (HIFU) ablation. By helping to forecast treatment outcomes and monitor progress during procedures like uterine fibroid embolization, AI also offers a fresh and fascinating perspective for improving the clinical management of these conditions. This review critically assesses the current literature, identifies the advantages and limitations of various AI approaches, and provides future directions for research and clinical implementation. Full article

The diagnosis of cholangiocarcinoma (CCA) remains challenging. Although new technologies have been developed and validated, their routine use in clinical practice is needed. Conventional cytology obtained during endoscopic retrograde cholangiopancreatography-guided brushings is the first-line technique for the diagnosis of CCA, but it has shown limited sensitivity when combined with endoscopic ultrasound-guided biopsy. Other diagnostic tools have been proposed for the diagnosis of CCA, with their respective advantages and limitations. Cholangioscopy with biopsy or cytology combined with FISH analysis, intraductal biliary ultrasound and confocal laser microscopy have made significant advances in the last decade. More recently, developments in the analytical “omics” sciences have allowed the mapping of the microbiota of patients with CCA, and liquid biopsy with proteomic and extracellular vesicle analysis has allowed the identification of new biomarkers that can be incorporated into the predictive diagnostics. Furthermore, in the preoperative setting, radiomics, radiogenomics and the integrated use of artificial intelligence may provide new useful foundations for integrated diagnosis and personalized therapy for hepatobiliary diseases. This review aims to evaluate the current diagnostic approaches and innovative translational research that can be integrated for the diagnosis of CCA. Full article

Background: Primary and secondary salivary gland malignancies differ significantly in treatment and prognosis. However, conventional ultrasonography often struggles to differentiate between these malignancies due to overlapping imaging features. We aimed to develop and evaluate noninvasive diagnostic models based on traditional ultrasound features, radiomics, and deep learning—independently or in combination—for distinguishing between primary and secondary salivary gland malignancies. Methods: This retrospective study included a total of 140 patients, comprising 68 with primary and 72 with secondary salivary gland malignancies, all pathologically confirmed, from four medical centers. Ultrasound features of salivary gland tumors were analyzed, and a radiomics model was established. Transfer learning with multiple pre-trained models was used to create deep learning (DL) models from which features were extracted and combined with radiomics features to construct a radiomics-deep learning (RadiomicsDL) model. A combined model was further developed by integrating ultrasound features. Least absolute shrinkage and selection operator (LASSO) regression and various machine learning algorithms were employed for feature selection and modeling. The optimal model was determined based on the area under the receiver operating characteristic curve (AUC), and interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: The RadiomicsDL model, which combines radiomics and deep learning features using the Multi-Layer Perceptron (MLP), demonstrated the best performance on the test set with an AUC of 0.807. This surpassed the performances of the ultrasound (US), radiomics, DL, and combined models, which achieved AUCs of 0.421, 0.636, 0.763, and 0.711, respectively. SHAP analysis revealed that the radiomic feature Wavelet_LHH_glcm_SumEntropy contributed most significantly to the mode. Conclusions: The RadiomicsDL model based on ultrasound images provides an efficient and non-invasive method to differentiate between primary and secondary salivary gland malignancies. Full article

This work was conducted in order to validate a pre-treatment quantitative ultrasound (QUS) and texture derivative analyses-based prediction model proposed in our previous study to identify responders and non-responders to neoadjuvant chemotherapy in patients with breast cancer. The validation cohort consisted of 56 breast cancer patients diagnosed between the years 2018 and 2021. Among all patients, 53 were treated with neoadjuvant chemotherapy and three had unplanned changes in their chemotherapy cycles. Radio Frequency (RF) data were collected volumetrically prior to the start of chemotherapy. In addition to tumour region (core), a 5 mm tumour-margin was also chosen for parameters estimation. The prediction model, which was developed previously based on quantitative ultrasound, texture derivative, and tumour molecular subtypes, was used to identify responders and non-responders. The actual response, which was determined by clinical and pathological assessment after lumpectomy or mastectomy, was then compared to the predicted response. The sensitivity, specificity, positive predictive value, negative predictive value, and F1 score for determining chemotherapy response of all patients in the validation cohort were 94%, 67%, 96%, 57%, and 95%, respectively. Removing patients who had unplanned changes in their chemotherapy resulted in a sensitivity, specificity, positive predictive value, negative predictive value, and F1 score of all patients in the validation cohort of 94%, 100%, 100%, 50%, and 97%, respectively. Explanations for the misclassified cases included unplanned modifications made to the type of chemotherapy during treatment, inherent limitations of the predictive model, presence of DCIS in tumour structure, and an ill-defined tumour border in a minority of cases. Validation of a model was conducted in an independent cohort of patient for the first time to predict the tumour response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivate, and molecular features in patients with breast cancer. Further research is needed to improve the positive predictive value and evaluate whether the treatment outcome can be improved in predicted non-responders by switching to other treatment options. Full article

Background: Breast cancer (BC) is the most frequently diagnosed cancer in women and the leading cause of cancer-related deaths in women globally. Carriers of P/LP variants in the BRCA1, BRCA2, TP53, PTEN, CDH1, PALB2, and STK11 genes have an increased risk of developing BC, which is why more and more guidelines recommend prophylactic mastectomy in this group of patients. Because traditional genetic testing is expensive and can cause delays in patient management, radiomics based on diagnostic imaging could be an alternative. This study aims to evaluate whether ultrasound-based radiomics features can predict P/LP variant status in BC patients. Methods: This retrospective study included 88 breast tumors in patients tested with multigene panel tests, including all seven above-mentioned genes. Ultrasound images were acquired prior to any treatment, and the tumoral and peritumoral areas were used to extract radiomics data. The study population was divided into P/LP and non-P/LP variant groups. Radiomics features were analyzed using machine learning models, alone or in combination with clinical features, with the aim of predicting the genetic status of BC patients. Results: We observed significant differences in radiomics features between P/LP- and non-P/LP-variant-driven tumors. The developed radiomics model achieved a maximum mean accuracy of 85.7% in identifying P/LP variant carriers. Including features from the peritumoral area yielded the same maximum accuracy. Conclusions: Radiomics models based on ultrasound images of breast tumors may provide a promising alternative for predicting P/LP variant status in BC patients. This approach could reduce dependence on costly genetic testing and expedite the diagnostic process. However, further validation in larger and more diverse populations is needed. Full article

Objective (1): To develop and validate a machine learning (ML) model using radiomic features (RFs) extracted from [18F]FDG PET-CT to predict abdominal aortic aneurysm (AAA) growth rate. Methods (2): This retrospective study included 98 internal and 55 external AAA patients undergoing [18F]FDG PET-CT. RFs were extracted from manual segmentations of AAAs using PyRadiomics. Recursive feature elimination (RFE) reduced features for model optimisation. A multi-layer perceptron (MLP) was developed for AAA growth prediction and compared against Random Forest (RF), XGBoost, and Support Vector Machine (SVM). Accuracy was evaluated via cross-validation, with uncertainty quantified using dropout (MLP), standard deviation (RF), and 95% prediction intervals (XGBoost). External validation used independent data from two centres. Ground truth growth rates were calculated from serial ultrasound (US) measurements or CT volumes. Results (3): From 93 initial RFs, 29 remained after RFE. The MLP model achieved an MAE ± SEM of 1.35 ± 3.2e−4 mm/year with the full feature set and 1.35 ± 2.5e−4 mm/year with RFE. External validation yielded 1.8 ± 8.9e−8 mm/year. RF, XGBoost, and SVM models produced comparable accuracies internally (1.4–1.5 mm/year) but showed higher errors during external validation (1.9–1.97 mm/year). The MLP model demonstrated reduced uncertainty with the full feature set across all datasets. Conclusions (4): An MLP model leveraging [18F]FDG PET-CT radiomics accurately predicted AAA growth rates and generalised well to external data. In the future, more sophisticated stratification could guide individualised patient care, facilitating risk-tailored management of AAAs. Full article

In recent years, novel findings have progressively and promisingly supported the potential role of Artificial intelligence (AI) in transforming the management of various neoplasms, including hepatocellular carcinoma (HCC). HCC represents the most common primary liver cancer. Alarmingly, the HCC incidence is dramatically increasing worldwide due to the simultaneous “pandemic” spreading of metabolic dysfunction-associated steatotic liver disease (MASLD). MASLD currently constitutes the leading cause of chronic hepatic damage (steatosis and steatohepatitis), fibrosis, and liver cirrhosis, configuring a scenario where an HCC onset has been reported even in the early disease stage. On the other hand, HCC represents a serious plague, significantly burdening the outcomes of chronic hepatitis B (HBV) and hepatitis C (HCV) virus-infected patients. Despite the recent progress in the management of this cancer, the overall prognosis for advanced-stage HCC patients continues to be poor, suggesting the absolute need to develop personalized healthcare strategies further. In this “cold war”, machine learning techniques and neural networks are emerging as weapons, able to identify the patterns and biomarkers that would have normally escaped human observation. Using advanced algorithms, AI can analyze large volumes of clinical data and medical images (including routinely obtained ultrasound data) with an elevated accuracy, facilitating early diagnosis, improving the performance of predictive models, and supporting the multidisciplinary (oncologist, gastroenterologist, surgeon, radiologist) team in opting for the best “tailored” individual treatment. Additionally, AI can significantly contribute to enhancing the effectiveness of metabolomics–radiomics-based models, promoting the identification of specific HCC-pathogenetic molecules as new targets for realizing novel therapeutic regimens. In the era of precision medicine, integrating AI into routine clinical practice appears as a promising frontier, opening new avenues for liver cancer research and treatment. Full article

Background: Accurate prognostic models are essential for optimizing treatment strategies for glioblastoma, the most aggressive primary brain tumor. While other neuroimaging modalities have demonstrated utility in predicting overall survival (OS), intraoperative ultrasound (iUS) remains underexplored for this purpose. This study aimed to evaluate the prognostic potential of iUS radiomics in glioblastoma patients in a multi-institutional cohort. Methods: This retrospective study included patients diagnosed with glioblastoma from the multicenter Brain Tumor Intraoperative (BraTioUS) database. A single 2D iUS slice, showing the largest tumor diameter, was selected for each patient. Radiomic features were extracted and subjected to feature selection, and clinical data were collected. Using a fivefold cross-validation strategy, Cox proportional hazards models were built using radiomic features alone, clinical data alone, and their combination. Model performance was assessed via the concordance index (C-index). Results: A total of 114 patients met the inclusion criteria, with a mean age of 56.88 years, a median OS of 382 days, and a median preoperative tumor volume of 32.69 cm³. Complete tumor resection was achieved in 51.8% of the patients. In the testing cohort, the combined model achieved a mean C-index of 0.87 (95% CI: 0.76–0.98), outperforming the radiomic model (C-index: 0.72, 95% CI: 0.57–0.86) and the clinical model (C-index: 0.73, 95% CI: 0.60–0.87). Conclusions: Intraoperative ultrasound relies on acoustic properties for tissue characterization, capturing unique features of glioblastomas. This study demonstrated that radiomic features derived from this imaging modality have the potential to support the development of survival models. Full article

Purpose: To evaluate the diagnostic value of ultrasound radiomics in distinguishing between benign and malignant breast nodules in women who have undergone silicone breast augmentation. Methods: A retrospective study was conducted of 99 breast nodules detected by ultrasound in 93 women who had undergone silicone breast augmentation. The ultrasound data were collected between 1 January 2006 and 1 September 2023. The nodules were allocated into a training set (n = 69) and a validation set (n = 30). Regions of interest (ROIs) were manually delineated using 3D Slicer software, and radiomic features were extracted and selected using Python programming. Eight machine learning algorithms were applied to build predictive models, and their performance was assessed using sensitivity, specificity, area under the ROC curve (AUC), accuracy, Brier score, and log loss. Model performance was further evaluated using ROC curves and calibration curves, while clinical utility was assessed via decision curve analysis (DCA). Results: The random forest model exhibited superior performance in differentiating benign from malignant nodules in the validation set, achieving sensitivity of 0.765, specificity of 0.838, and an AUC of 0.787 (95% CI: 0.561–0.960). The model’s accuracy, Brier score, and log loss were 0.796, 0.197, and 0.599, respectively. DCA suggested potential clinical utility of the model. Conclusion: Ultrasound radiomics demonstrates promising diagnostic accuracy in differentiating benign from malignant breast nodules in women with silicone breast prostheses. This approach has the potential to serve as an additional diagnostic tool for patients following silicone breast augmentation. Full article

Pancreatic cystic lesions (PCLs) represent a spectrum of non-neoplasms and neoplasms with varying malignant potential, posing significant challenges in diagnosis and management. While some PCLs are precursors to pancreatic cancer, others remain benign, necessitating accurate differentiation for optimal patient care. Conventional approaches to PCL management rely heavily on radiographic imaging, and endoscopic ultrasound (EUS) guided fine-needle aspiration (FNA), coupled with clinical and biochemical data. However, the observer-dependent nature of image interpretation and the complex morphology of PCLs can lead to diagnostic uncertainty and variability in patient management strategies. This review critically evaluates current PCL diagnosis and surveillance practices, showing features of the different lesions and highlighting the potential limitations of conventional methods. We then explore the potential of artificial intelligence (AI) to transform PCL management. AI-driven strategies, including deep learning algorithms for automated pancreas and lesion segmentation, and radiomics for analyzing heterogeneity, can improve diagnostic accuracy and risk stratification. These advanced techniques can provide more objective and reproducible assessments, aiding clinicians in decision-making regarding follow-up intervals and surgical interventions. Early results suggest that AI-driven methods can significantly improve patient outcomes by enabling earlier detection of high-risk lesions and reducing unnecessary procedures for benign cysts. Finally, this review emphasizes that AI-driven approaches could potentially reshape the landscape of PCL management, ultimately leading to improved pancreatic cancer prevention. Full article