Daniele La Forgia

Ovarian cancer (OC) is the second most common gynecological malignancy and remains one of the leading causes of gynecological cancer-related mortality worldwide. A major clinical challenge is the lack of an accurate and widely applicable strategy for identifying patients at high risk of malignancy at an early stage. In this context, artificial intelligence (AI) has emerged as a promising tool to improve diagnostic performance. Among AI technologies, large language models (LLMs) have recently shown considerable potential in healthcare applications. In this study, we evaluated the diagnostic performance of ChatGPT (GPT-5) in classifying 300 adnexal masses as benign or malignant and compared its performance with that of the IOTA Simple Rules, the ADNEX model, and expert subjective assessment. We also assessed ChatGPT’s ability to predict the most likely histological diagnosis for each lesion. All adnexal masses were described using the International Ovarian Tumor Analysis (IOTA) terminology, and histopathological examination served as the reference standard. Our findings showed that expert subjective assessment achieved the highest overall diagnostic performance for both benign/malignant classification (accuracy 87.3%; 95% CI, 83.0–90.9%) and prediction of the presumed histological diagnosis. ChatGPT A and ChatGPT B reached a sensitivity of 72.3% and 73.5%, a specificity of 74.5% and 75.9%, a positive predictive value of 75.2% and 76.5%, and a negative predictive value of 71.5% and 72.8%, respectively (inconclusive responses counted as misclassifications), with an overall accuracy of 73.3% and 74.7%. After adequate validation, large language models might complement existing decision-support tools for less experienced examiners, without replacing expert evaluation. Their ease of use and reliance on standardized ultrasound descriptors make them accessible to ultrasonographers with varying levels of expertise.

Background: This study investigates the impact of anatomically constrained preprocessing and deep learning architecture selection on benign versus malignant breast lesion classification in contrast-enhanced mammography (CEM), with the goal of improving robustness and clinical reliability across heterogeneous data sources. Methods: In this retrospective multicenter study, CEM images from 300 patients (314 lesions) were combined with 1003 publicly available CEM images, yielding a total of 1120 breast cases. Automatic breast segmentation was performed using the LIBRA framework to generate breast-mask images. Eleven deep learning models, including classical convolutional neural networks, attention-based networks, hybrid convolutional neural networks (CNNs), Transformer architectures, and mammography-specific models, were trained and evaluated using both original DICOM images and breast-mask inputs. Performance was assessed using accuracy, balanced accuracy, sensitivity, specificity, AUROC, and AUPRC on cross-validation and independent test sets. Hyperparameter optimization was conducted for the best-performing architecture. Results: Models trained on breast-mask images consistently outperformed those trained on original DICOM images across all architectures and metrics, with AUROC improvements ranging from +0.06 to +0.21. Among all models, ResNet50 trained on breast-mask images achieved the best performance (AUROC = 0.931; AUPRC = 0.933; balanced accuracy = 0.834), further improved after optimization (balanced accuracy = 0.886; sensitivity = 0.842; specificity = 0.930). Classical CNN architectures demonstrated performance comparable to or exceeding that of more complex hybrid CNN–Transformer models when anatomically focused preprocessing and rigorous optimization were applied. Conclusions: Anatomically constrained preprocessing through breast-mask segmentation substantially enhances deep learning performance and stability in CEM-based breast lesion classification. These findings indicate that input representation quality and training optimization are critical determinants of clinically relevant performance, often outweighing architectural complexity, and may support more reliable AI-assisted decision support in CEM workflows.

Deep-learning models applied to contrast-enhanced mammography (CEM) are known to be highly sensitive to the input image representation. However, preprocessing is often treated as a secondary step and rarely analyzed as an independent design variable. In this work, we present a systematic engineering analysis of a deterministic, label-independent preprocessing pipeline for CEM images. The pipeline integrates intensity normalization, global histogram matching, local contrast enhancement, denoising, and anatomically constrained breast masking. Using a controlled experimental design, identical deep-learning architectures were trained under different input representations to isolate the impact of preprocessing on classification performance and stability. Across convolutional neural network architectures, anatomically constrained preprocessing consistently improves discrimination performance, reduces variability across cross-validation folds, and enhances training stability. Breast mask-based representations demonstrate substantial gains in AUROC and AUPRC compared to raw DICOM inputs. These findings highlight image preprocessing as a first-class engineering component in medical AI pipelines. Breast masking significantly improves robustness and generalization, independently of network architecture complexity. From a clinical perspective, improving model robustness and sensitivity to malignant lesions may contribute to more reliable AI-assisted decision support in contrast-enhanced mammography, particularly in settings characterized by acquisition variability and heterogeneous patient populations.

Objective: The aim of this study was to evaluate the accuracy of machine and deep learning approaches on radiomics features obtained by Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) and contrast enhanced mammography (CEM) in the characterization of breast cancer and in the prediction of the tumor molecular profile. Methods: A total of 153 patients with malignant and benign lesions were analyzed and underwent MRI examinations. Considering the histological findings as the ground truth, three different types of findings were used in the analysis: (1) benign versus malignant lesions; (2) G1 + G2 vs. G3 classification; (3) the presence of human epidermal growth factor receptor 2 (HER2+ vs. HER2−). Radiomic features (n = 851) were extracted from manually segmented regions of interest using the PyRadiomics platform, following IBSI-compliant protocols. Highly correlated features were excluded, and the remaining features were standardized using z-score normalization. A feature selection process based on Elastic Net regularization (α = 0.5) was used to reduce dimensionality. Synthetic balancing of the training data was applied using the ROSE method to address class imbalance. Model performance was evaluated using repeated 10-fold cross-validation and AUC-based metrics. Results: Among the 153 patients enrolled in the studies, 113 were malignant lesions. Among the 113 malignant lesions, 32 had high grading (G3) and 66 had the HER2+ receptor. Radiomic features derived from both CEM and DCE-MRI showed strong discriminative performance for malignancy detection, with several features achieving AUCs above 0.80. Gradient Boosting Machine (GBM) achieved the highest accuracy (0.911) and AUC (0.907) in differentiating benign from malignant lesions. For tumor grading, the neural network model attained the best accuracy (0.848), while LASSO yielded the highest sensitivity (0.667) for detecting high-grade tumors. In predicting HER2+ status, the neural network also performed best (AUC = 0.669), with a sensitivity of 0.842. Conclusions: Radiomics-based machine learning models applied to multiparametric CEM and DCE-MRI images offer promising, non-invasive tools for breast cancer characterization. The models effectively distinguished benign from malignant lesions and showed potential in predicting histological grade and HER2 status. These results demonstrate that radiomic features extracted from CEM and DCE-MRI, when analyzed through machine and deep learning models, can support accurate breast cancer characterization. Such models may assist clinicians in early diagnosis, histological grading, and biomarker assessment, potentially enhancing personalized treatment planning and non-invasive decision-making in routine practice.

Venous thromboembolism (VTE) is considered the most common and potentially life-threatening cardiovascular complication in cancer and the second leading cause of death after cancer progression itself. In recent years, the steadily increasing rate of cancer-associated thrombosis (CAT) seems mainly related to amelioration in imaging techniques and the placements of central venous catheters (CVCs). The pivotal role of CVCs in the switch from hospital to home care is offset by its high thrombotic burden. The peripherally inserted central catheter (PICC) offers advantages (convenience, fast access, and cost-effectiveness) in comparison to centrally inserted devices (PORT), but increased thrombotic risk is reported. The aim of this narrative review was to offer a comprehensive overview of the existing literature about PICC-related thrombosis (PICC-VTE) by analyzing the current knowledge and related gaps. We further discussed advancements in insertion techniques, underscored the role of the novel PICC-PORT lines, and provided a “head-to-head” comparison among major guidelines on primary thromboprophylaxis.

Cancer is a remarkable prothrombotic disease, and cancer-associated thrombosis acts as a dreadful omen for poor prognosis. The cornerstone of venous thromboembolism therapy is anticoagulation; however, in patients with venous thromboembolism who are not suitable for anticoagulation (contraindication, failure, or complication), the inferior vena cava filter appears a valuable option in the therapeutic arsenal. The recently heightened trend of steady rise in filter placement mirrors the spread of retrievable devices, together with improvements in physicians’ insertion ability, medico-legal issue, and novel and fewer thrombogenic materials. Nevertheless, the exact role of the inferior vena cava filter in cancer has yet to be endorsed due to a dearth of robust evidence. Indeed, data that support the inferior vena cava filter are weak and even controversial, resulting in discrepancies in the interpretation and application of guidelines in daily practice. In this narrative review, we aim at clarifying the state of the art on inferior vena cava filter use in malignancies. Furthermore, we provide a feasible, conclusive 4-step algorithm for the treating physicians in order to offer a practical strategy to successfully employ the inferior vena cava filter as a priceless device in the current armamentarium against cancer.

Purpose: The purpose of this meta-analysis is to investigate the effectiveness of supplementing screening mammography with three-dimensional automated breast ultrasonography (3D ABUS) in improving breast cancer detection rates in asymptomatic women with dense breasts. Materials and Methods: We conducted a thorough review of scientific publications comparing 3D ABUS and mammography. Articles for inclusion were sourced from peer-reviewed journal databases, namely MEDLINE (PubMed) and Scopus, based on an initial screening of their titles and abstracts. To ensure a sufficient sample size for meaningful analysis, only studies evaluating a minimum of 20 patients were retained. Eligibility for evaluation was further limited to articles written in English. Additionally, selected studies were required to have participants aged 18 or above at the time of the study. We analyzed 25 studies published between 2000 and 2021, which included a total of 31,549 women with dense breasts. Among these women, 229 underwent mammography alone, while 347 underwent mammography in combination with 3D ABUS. The average age of the women was 50.86 years (±10 years standard deviation), with a range of 40–56 years. In our efforts to address and reduce bias, we applied a range of statistical analyses. These included assessing study variation through heterogeneity assessment, accounting for potential study variability using a random-effects model, exploring sources of bias via meta-regression analysis, and checking for publication bias through funnel plots and the Egger test. These methods ensured the reliability of our study findings. Results: According to the 25 studies included in this metanalysis, out of the total number of women, 27,495 were diagnosed with breast cancer. Of these, 211 were diagnosed through mammography alone, while an additional 329 women were diagnosed through the combination of full-field digital mammography (FFDSM) and 3D ABUS. This represents an increase of 51.5%. The rate of cancers detected per 1000 women screened was 23.25‰ (95% confidence interval [CI]: 21.20, 25.60; p < 0.001) with mammography alone. In contrast, the addition of 3D ABUS to mammography increased the number of tumors detected to 20.95‰ (95% confidence interval [CI]: 18.50, 23; p < 0.001) per 1000 women screened. Discussion: Even though variability in study results, lack of long-term outcomes, and selection bias may be present, this systematic review and meta-analysis confirms that supplementing mammography with 3D ABUS increases the accuracy of breast cancer detection in women with ACR3 to ACR4 breasts. Our findings suggest that the combination of mammography and 3D ABUS should be considered for screening women with dense breasts. Conclusions: Our research confirms that adding 3D automated breast ultrasound to mammography-only screening in patients with dense breasts (ACR3 and ACR4) significantly (p < 0.05) increases the cancer detection rate.

One of the most frequently detected neoplasms in women in Italy is breast cancer, for which high-sensitivity diagnostic techniques are essential for early diagnosis in order to minimize mortality rates. As addressed in Part I of this work, we have seen how conditions such as high glandular density or limitations related to mammographic sensitivity have driven the optimization of technology and the use of increasingly advanced and specific diagnostic methodologies. While the first part focused on analyzing the use of a mammography machine from a physical and dosimetric perspective, in this paper, we will examine other techniques commonly used in breast imaging: contrast-enhanced mammography, digital breast tomosynthesis, radio imaging, and include some notes on image processing. We will also explore the differences between these various techniques to provide a comprehensive overview of breast lesion detection techniques. We will examine the strengths and weaknesses of different diagnostic modalities and observe how, with the implementation of improvements over time, increasingly effective diagnoses can be achieved.

Cancer-associated thrombosis (CAT) is a devastating complication of cancer that can significantly impact a patient’s health and life. The incidence of CAT is approximately 20%, and 1 in 5 cancer patients will develop CAT annually. Indeed, CAT can promote pulmonary embolism and deep vein thrombosis, leading to increased morbidity and mortality that dramatically impact survival. CAT can also provoke delay or discontinuation of anticancer treatment, which may result in a lack of treatment efficacy and high costs for patients, institutions, and society. Current guidelines advocate direct oral anticoagulants (DOACs) as the first-line anticoagulant option in CAT. Compared to low-molecular-weight-heparins (LMWHs), DOACs are advantageous in that they typically have an oral route of administration, do not require laboratory monitoring, and have a more predictable anticoagulant effect. However, in patients with thrombocytopenia, renal failure, or those receiving anticancer regimens with potential for drug-drug interactions, LMWH is still the mainstay of care. The main limitation of current anticoagulant agents is related to bleeding risk (BR), both for DOACs and LMWHs. Specifically, DOACs have been associated with high BR in gastrointestinal and genitourinary cancers. In this challenging scenario, abelacimab, an anti-factor XI agent, could represent a viable option in the management of CAT due to its “hemostasis sparing” effect. The safe profile of abelacimab could be useful in patients with active malignancy and CAT, as long-term anticoagulant therapy is often required. Two ongoing international phase III trials (Aster and Magnolia) compare abelacimab with the standard of care (i.e., apixaban in patients with CAT and dalteparin in those with CAT and high BR, respectively). Abelacimab is a new and attractive anticoagulant for the management of CAT, especially in the insidious and critical scenario of active cancer patients with venous thromboembolism and high BR. The aim of this narrative review is to discuss the updated evidence on the performance of DOACs and LMWHs in the treatment of CAT and to focus on the potential role of abelacimab in CAT and its promising associated clinical trials.

A timely diagnosis is essential for improving breast cancer patients’ survival and designing targeted therapeutic plans. For this purpose, the screening timing, as well as the related waiting lists, are decisive. Nonetheless, even in economically advanced countries, breast cancer radiology centres fail in providing effective screening programs. Actually, a careful hospital governance should encourage waiting lists reduction programs, not only for improving patients care, but also for minimizing costs associated with the treatment of advanced cancers. Thus, in this work, we proposed a model to evaluate several scenarios for an optimal distribution of the resources invested in a Department of Breast Radiodiagnosis. Particularly, we performed a cost-benefit analysis as a technology assessment method to estimate both costs and health effects of the screening program, to maximise both benefits related to the quality of care and resources employed by the Department of Breast Radiodiagnosis of Istituto Tumori “Giovanni Paolo II” of Bari in 2019. Specifically, we determined the Quality-Adjusted Life Year (QALY) for estimating health outcomes, in terms of usefulness of two hypothetical screening strategies with respect to the current one. While the first hypothetical strategy adds one team made up of a doctor, a technician and a nurse, along with an ultrasound and a mammograph, the second one adds two afternoon teams. This study showed that the most cost-effective incremental ratio could be achieved by reducing current waiting lists from 32 to 16 months. Finally, our analysis revealed that this strategy would also allow to include more people in the screening programs (60,000 patients in 3 years).