How do large language models answer breast cancer quiz questions? A comparative study of GPT-3.5, GPT-4 and Google Gemini.

Applications of large language models (LLMs) in the healthcare field have shown promising results in processing and summarizing multidisciplinary information. This study evaluated the ability of three publicly available LLMs (GPT-3.5, GPT-4, and Google Gemini-then called Bard) to answer 60 multiple-choice questions (29 sourced from public databases, 31 newly formulated by experienced breast radiologists) about different aspects of breast cancer care: treatment and prognosis, diagnostic and interventional techniques, imaging interpretation, and pathology. Overall, the rate of correct answers significantly differed among LLMs (p = 0.010): the best performance was achieved by GPT-4 (95%, 57/60) followed by GPT-3.5 (90%, 54/60) and Google Gemini (80%, 48/60). Across all LLMs, no significant differences were observed in the rates of correct replies to questions sourced from public databases and newly formulated ones (p ≥ 0.593). These results highlight the potential benefits of LLMs in breast cancer care, which will need to be further refined through in-context training.

Radiologists' perceptions on AI integration: An in-depth survey study.

PURPOSE: To assess the perceptions and attitudes of radiologists toward the adoption of artificial intelligence (AI) in clinical practice. METHODS: A survey was conducted among members of the SIRM Lombardy. Radiologists' attitudes were assessed comprehensively, covering satisfaction with AI-based tools, propensity for innovation, and optimism for the future. The questionnaire consisted of two sections: the first gathered demographic and professional information using categorical responses, while the second evaluated radiologists' attitudes toward AI through Likert-type responses ranging from 1 to 5 (with 1 representing extremely negative attitudes, 3 indicating a neutral stance, and 5 reflecting extremely positive attitudes). Questionnaire refinement involved an iterative process with expert panels and a pilot phase to enhance consistency and eliminate redundancy. Exploratory data analysis employed descriptive statistics and visual assessment of Likert plots, supported by non-parametric tests for subgroup comparisons for a thorough analysis of specific emerging patterns. RESULTS: The survey yielded 232 valid responses. The findings reveal a generally optimistic outlook on AI adoption, especially among young radiologist (<30) and seasoned professionals (>60, p<0.01). However, while 36.2 % (84 out 232) of subjects reported daily use of AI-based tools, only a third considered their contribution decisive (30 %, 25 out of 84). AI literacy varied, with a notable proportion feeling inadequately informed (36 %, 84 out of 232), particularly among younger radiologists (46 %, p < 0.01). Positive attitudes towards the potential of AI to improve detection, characterization of anomalies and reduce workload (positive answers > 80 %) and were consistent across subgroups. Radiologists' opinions were more skeptical about the role of AI in enhancing decision-making processes, including the choice of further investigation, and in personalized medicine in general. Overall, respondents recognized AI's significant impact on the radiology profession, viewing it as an opportunity (61 %, 141 out of 232) rather than a threat (18 %, 42 out of 232), with a majority expressing belief in AI's relevance to future radiologists' career choices (60 %, 139 out of 232). However, there were some concerns, particularly among breast radiologists (20 of 232 responders), regarding the potential impact of AI on the profession. Eighty-four percent of the respondents consider the final assessment by the radiologist still to be essential. CONCLUSION: Our results indicate an overall positive attitude towards the adoption of AI in radiology, though this is moderated by concerns regarding training and practical efficacy. Addressing AI literacy gaps, especially among younger radiologists, is essential. Furthermore, proactively adapting to technological advancements is crucial to fully leverage AI's potential benefits. Despite the generally positive outlook among radiologists, there remains significant work to be done to enhance the integration and widespread use of AI tools in clinical practice.

Exploring the Potential of Artificial Intelligence in Breast Ultrasound.

Breast ultrasound has emerged as a valuable imaging modality in the detection and characterization of breast lesions, particularly in women with dense breast tissue or contraindications for mammography. Within this framework, artificial intelligence (AI) has garnered significant attention for its potential to improve diagnostic accuracy in breast ultrasound and revolutionize the workflow. This review article aims to comprehensively explore the current state of research and development in harnessing AI's capabilities for breast ultrasound. We delve into various AI techniques, including machine learning, deep learning, as well as their applications in automating lesion detection, segmentation, and classification tasks. Furthermore, the review addresses the challenges and hurdles faced in implementing AI systems in breast ultrasound diagnostics, such as data privacy, interpretability, and regulatory approval. Ethical considerations pertaining to the integration of AI into clinical practice are also discussed, emphasizing the importance of maintaining a patient-centered approach. The integration of AI into breast ultrasound holds great promise for improving diagnostic accuracy, enhancing efficiency, and ultimately advancing patient's care. By examining the current state of research and identifying future opportunities, this review aims to contribute to the understanding and utilization of AI in breast ultrasound and encourage further interdisciplinary collaboration to maximize its potential in clinical practice.

The Role of Artificial Intelligence and Texture Analysis in Interventional Radiological Treatments of Liver Masses: A Narrative Review.

Liver lesions, including both benign and malignant tumors, pose significant challenges in interventional radiological treatment planning and prognostication. The emerging field of artificial intelligence (AI) and its integration with texture analysis techniques have shown promising potential in predicting treatment outcomes, enhancing precision, and aiding clinical decision-making. This comprehensive review aims to summarize the current state-of-the-art research on the application of AI and texture analysis in determining treatment response, recurrence rates, and overall survival outcomes for patients undergoing interventional radiological treatment for liver lesions. Furthermore, the review addresses the challenges associated with the implementation of AI and texture analysis in clinical practice, including data acquisition, standardization of imaging protocols, and model validation. Future directions and potential advancements in this field are discussed. Integration of multi-modal imaging data, incorporation of genomics and clinical data, and the development of predictive models with enhanced interpretability are proposed as potential avenues for further research. In conclusion, the application of AI and texture analysis in predicting outcomes of interventional radiological treatment for liver lesions shows great promise in augmenting clinical decision-making and improving patient care. By leveraging these technologies, clinicians can potentially enhance treatment planning, optimize intervention strategies, and ultimately improve patient outcomes in the management of liver lesions.

Radiomics and Artificial Intelligence in Renal Lesion Assessment.

Radiomics, the extraction and analysis of quantitative features from medical images, has emerged as a promising field in radiology with the potential to revolutionize the diagnosis and management of renal lesions. This comprehensive review explores the radiomics workflow, including image acquisition, feature extraction, selection, and classification, and highlights its application in differentiating between benign and malignant renal lesions. The integration of radiomics with artificial intelligence (AI) techniques, such as machine learning and deep learning, can help patients' management and allow the planning of the appropriate treatments. AI models have shown remarkable accuracy in predicting tumor aggressiveness, treatment response, and patient outcomes. This review provides insights into the current state of radiomics and AI in renal lesion assessment and outlines future directions for research in this rapidly evolving field.

Artificial Intelligence in Bone Metastasis Imaging: Recent Progresses from Diagnosis to Treatment - A Narrative Review.

The introduction of artificial intelligence (AI) represents an actual revolution in the radiological field, including bone lesion imaging. Bone lesions are often detected both in healthy and oncological patients and the differential diagnosis can be challenging but decisive, because it affects the diagnostic and therapeutic process, especially in case of metastases. Several studies have already demonstrated how the integration of AI-based tools in the current clinical workflow could bring benefits to patients and to healthcare workers. AI technologies could help radiologists in early bone metastases detection, increasing the diagnostic accuracy and reducing the overdiagnosis and the number of unnecessary deeper investigations. In addition, radiomics and radiogenomics approaches could go beyond the qualitative features, visible to the human eyes, extrapolating cancer genomic and behavior information from imaging, in order to plan a targeted and personalized treatment. In this article, we want to provide a comprehensive summary of the most promising AI applications in bone metastasis imaging and their role from diagnosis to treatment and prognosis, including the analysis of future challenges and new perspectives.

Artificial Intelligence in Lung Cancer Imaging: From Data to Therapy.

Lung cancer remains a global health challenge, leading to substantial morbidity and mortality. While prevention and early detection strategies have improved, the need for precise diagnosis, prognosis, and treatment remains crucial. In this comprehensive review article, we explore the role of artificial intelligence (AI) in reshaping the management of lung cancer. AI may have different potential applications in lung cancer characterization and outcome prediction. Manual segmentation is a time-consuming task, with high inter-observer variability, that can be replaced by AI-based approaches, including deep learning models such as U-Net, BCDU-Net, and others, to quantify lung nodules and cancers objectively and to extract radiomics features for the characterization of the tissue. AI models have also demonstrated their ability to predict treatment responses, such as immunotherapy and targeted therapy, by integrating radiomic features with clinical data. Additionally, AI-based prognostic models have been developed to identify patients at higher risk and personalize treatment strategies. In conclusion, this review article provides a comprehensive overview of the current state of AI applications in lung cancer management, spanning from segmentation and virtual biopsy to outcome prediction. The evolving role of AI in improving the precision and effectiveness of lung cancer diagnosis and treatment underscores its potential to significantly impact clinical practice and patient outcomes.

Portable Dynamic Chest Radiography: Literature Review and Potential Bedside Applications.

Dynamic digital radiography (DDR) is a high-resolution radiographic imaging technique using pulsed X-ray emission to acquire a multiframe cine-loop of the target anatomical area. The first DDR technology was orthostatic chest acquisitions, but new portable equipment that can be positioned at the patient's bedside was recently released, significantly expanding its potential applications, particularly in chest examination. It provides anatomical and functional information on the motion of different anatomical structures, such as the lungs, pleura, rib cage, and trachea. Native images can be further analyzed with dedicated post-processing software to extract quantitative parameters, including diaphragm motility, automatically projected lung area and area changing rate, a colorimetric map of the signal value change related to respiration and motility, and lung perfusion. The dynamic diagnostic information along with the significant advantages of this technique in terms of portability, versatility, and cost-effectiveness represents a potential game changer for radiological diagnosis and monitoring at the patient's bedside. DDR has several applications in daily clinical practice, and in this narrative review, we will focus on chest imaging, which is the main application explored to date in the literature. However, studies are still needed to understand deeply the clinical impact of this method.

An optimized 1.5 Tesla MRI protocol of the brachial plexus.

PURPOSE: Creating an effective MRI protocol for examining the brachial plexus poses significant challenges, and despite the abundance of protocols in the literature, there is a lack of reference standards for basic sequences and essential parameters needed for replication. The aim of this study is to establish a reproducible 1.5 T brachial plexus imaging protocol, including patient positioning, coil selection, imaging planes, and essential sequence parameters. METHODS: We systematically investigated MRI sequences, testing each parameter through in vivo experiments, examining their effects on signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), visual quality scores, and acquisition time. Sequences were refined based on optimal quality and timing scores. The final protocol was tested on scanners from two other vendors for reliability. RESULTS: The final protocol included a combination of 2D turbo-spin-echo and 3D SPACE T1, SPACE STIR, and VIBE DIXON sequences. Recommendations for imaging planes, phase encoding, field of view, TR, TE, resolution, number of slices, slice thickness, fat and blood suppression, and acceleration strategies are provided. The protocol was successfully translated to other vendor's scanners with comparable quality. CONCLUSION: We present an optimized protocol detailing the essential parameters for reproducibility. Our comprehensive list of experiments describes the impact of each parameter on image quality and scan time, addressing common artifacts and potential solutions. This protocol can benefit both young radiologists new to the field and experienced professionals seeking to refine their existing protocols.

Correlation Analysis on Anatomical Variants of Accessory Foramina in the Sphenoid Bone for Oncological Surgery.

The sphenoid bone presents several anatomical variations, including accessory foramina, such as the foramen meningo-orbitale, the foramen of Vesalius, the canaliculus innominatus and the palatovaginal canal, which may be involved in tumor invasion or surgery of surrounding structures. Therefore, clinicians and surgeons have to consider these variants when planning surgical interventions of the cranial base. The prevalence of each variant is reported in the published literature, but very little information is available on the possible correlation among different variants. Here, 300 CT scans of patients (equally divided among males and females) were retrospectively assessed to investigate the presence of the foramen meningo-orbitale, the foramen of Vesalius, the canaliculus innominatus and the palatovaginal canal. Possible differences in the prevalence of each accessory foramen according to sex were assessed, as well as possible correlations among different variants through the Chi-square test (p < 0.01). Overall, the prevalence of the foramen meningo-orbitale, the foramen of Vesalius, the canaliculus innominatus and the palatovaginal canal was 30.7%, 67.7%, 14.0% and 35.3%, respectively, without any difference according to sex (p > 0.01). A significant positive correlation was found between the foramen of Vesalius and canaliculus innominatus, both in males and in females (p < 0.01). In detail, subjects with canaliculus innominatus in 85.7-100.0% of cases also showed the foramen of Vesalius, independently from sex and side. The present study provided novel data about the prevalence of four accessory foramina of the sphenoid bone in an Italian population, and a correlation between the foramen of Vesalius and the canaliculus innominatus was found for the first time. As these accessory foramina host neurovascular structures, the results of this study are thus useful for appropriate planning surgical procedures that are tailored to the anatomical configuration of the patient and for improving techniques to avoid accidental injuries in cranial base surgery. Knowledge of the topography, frequencies and the presence/absence of these additional foramina are pivotal for a successful procedure. Clinicians and surgeons may benefit from these novel data for appropriate recognition of the variants, decision-making, pre-operative and treatment planning, improvement of the procedures, screening of patients and prevention of misdiagnosis.

Artificial Intelligence in Lung Cancer Screening: The Future Is Now.

Lung cancer has one of the worst morbidity and fatality rates of any malignant tumour. Most lung cancers are discovered in the middle and late stages of the disease, when treatment choices are limited, and patients' survival rate is low. The aim of lung cancer screening is the identification of lung malignancies in the early stage of the disease, when more options for effective treatments are available, to improve the patients' outcomes. The desire to improve the efficacy and efficiency of clinical care continues to drive multiple innovations into practice for better patient management, and in this context, artificial intelligence (AI) plays a key role. AI may have a role in each process of the lung cancer screening workflow. First, in the acquisition of low-dose computed tomography for screening programs, AI-based reconstruction allows a further dose reduction, while still maintaining an optimal image quality. AI can help the personalization of screening programs through risk stratification based on the collection and analysis of a huge amount of imaging and clinical data. A computer-aided detection (CAD) system provides automatic detection of potential lung nodules with high sensitivity, working as a concurrent or second reader and reducing the time needed for image interpretation. Once a nodule has been detected, it should be characterized as benign or malignant. Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometric features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so-called "virtual biopsy". This narrative review aims to provide an overview of all possible AI applications in lung cancer screening.

Inter-reader agreement of breast magnetic resonance imaging and contrast-enhanced mammography in breast cancer diagnosis: a multi-reader retrospective study.

OBJECTIVE: Breast magnetic resonance imaging (MRI) and contrast-enhanced mammography (CEM) are nowadays used in breast imaging but studies about their inter-reader agreement are lacking. Therefore, we compared the inter-reader agreement of CEM and MRI in breast cancer diagnosis in the same patients. METHODS: Breast MRI and CEM exams performed in a single center (09/2020-09/2021) for an IRB-approved study were retrospectively and independently evaluated by four radiologists of two different centers with different levels of experience who were blinded to the clinical and other imaging data. The reference standard was the histological diagnosis or at least 1-year negative imaging follow-up. Inter-reader agreement was examined using Cohen's and Fleiss' kappa (κ) statistics and compared with the Wald test. RESULTS: Of the 750 patients, 395 met inclusion criteria (44.5 ± 14 years old), with 752 breasts available for CEM and MRI. Overall agreement was moderate (κ = 0.60) for MRI and substantial (κ = 0.74) for CEM. For expert readers, the agreement was substantial (κ = 0.77) for MRI and almost perfect (κ = 0.82) for CEM; for non-expert readers was fair (κ = 0.39); and for MRI and moderate (κ = 0.57) for CEM. Pairwise agreement between expert readers and non-expert readers was moderate (κ = 0.50) for breast MRI and substantial (κ = 0.74) for CEM and it showed a statistically superior agreement of the expert over the non-expert readers only for MRI (p = 0.011) and not for CEM (p = 0.062). CONCLUSIONS: The agreement of CEM was superior to that of MRI (p = 0.012), including for both expert (p = 0.031) and non-expert readers (p = 0.005).

Deep Learning-Based Versus Iterative Image Reconstruction for Unenhanced Brain CT: A Quantitative Comparison of Image Quality.

This exploratory retrospective study aims to quantitatively compare the image quality of unenhanced brain computed tomography (CT) reconstructed with an iterative (AIDR-3D) and a deep learning-based (AiCE) reconstruction algorithm. After a preliminary phantom study, AIDR-3D and AiCE reconstructions (0.5 mm thickness) of 100 consecutive brain CTs acquired in the emergency setting on the same 320-detector row CT scanner were retrospectively analyzed, calculating image noise reduction attributable to the AiCE algorithm, artifact indexes in the posterior cranial fossa, and contrast-to-noise ratios (CNRs) at the cortical and thalamic levels. In the phantom study, the spatial resolution of the two datasets proved to be comparable; conversely, AIDR-3D reconstructions showed a broader noise pattern. In the human study, median image noise was lower with AiCE compared to AIDR-3D (4.7 vs. 5.3, p < 0.001, median 19.6% noise reduction), whereas AIDR-3D yielded a lower artifact index than AiCE (7.5 vs. 8.4, p < 0.001). AiCE also showed higher median CNRs at the cortical (2.5 vs. 1.8, p < 0.001) and thalamic levels (2.8 vs. 1.7, p < 0.001). These results highlight how image quality improvements granted by deep learning-based (AiCE) and iterative (AIDR-3D) image reconstruction algorithms vary according to different brain areas.

Assessment of Anatomical Uniqueness of Maxillary Sinuses through 3D-3D Superimposition: An Additional Help to Personal Identification.

Paranasal sinuses represent one of the most individualizing structures of the human body and some of them have been already analyzed for possible applications to personal identification, such as the frontal and sphenoid sinuses. This study explores the application of 3D-3D superimposition to maxillary sinuses in personal identification. One hundred head CT-scans of adult subjects (equally divided among males and females) were extracted from a hospital database. Maxillary sinuses were segmented twice from each subject through ITK-SNAP software and the correspondent 3D models were automatically superimposed to obtain 100 matches (when they belonged to the same person) and 100 mismatches (when they were extracted from different individuals), both from the right and left side. Average RMS (root mean square) point-to-point distance was then calculated for all the superimpositions; differences according to sex, side, and group (matches and mismatches) were assessed through three-way ANOVA test (p < 0.017). On average, RMS values were lower in matches (0.26 ± 0.19 mm in males, 0.24 ± 0.18 mm in females) than in mismatches (2.44 ± 0.87 mm in males, 2.20 ± 0.73 mm in females) with a significant difference (p < 0.001). No significant differences were found according to sex or side (p > 0.017). The study verified the potential of maxillary sinuses as reliable anatomical structures for personal identification in the forensic context.

How do patients perceive the AI-radiologists interaction? Results of a survey on 2119 responders.

PURPOSE: In this study we investigate how patients perceive the interaction between artificial intelligence (AI) and radiologists by designing a survey. METHOD: We created a survey focused on the application of Artificial Intelligence in radiology which consisted of 20 questions distributed in three sections:Only completed questionnaires were considered for analysis. RESULTS: 2119 subjects completed the survey. Among them, 1216 respondents were over 60 years old, showing interest in AI even though they were not digital natives. Although >45% of the respondents reported a high level of education, only 3% said they were AI experts. 87% of respondents favored using AI to support diagnosis but would like to be informed. Only 10% would consult another specialist if their doctor used AI support. Most respondents (76%) said they would not feel comfortable if the diagnosis was made by the AI alone, highlighting the importance of the physician's role in the emotional management of the patient. Finally, 36% of respondents were willing to discuss the topic further in a focus group. CONCLUSION: Patients' perception of the use of AI in radiology was positive, although still strictly linked to the supervision of the radiologist. Respondents showed interest and willingness to learn more about AI in the medical field, confirming how patients' confidence in AI technology and its acceptance is central to its widespread use in clinical practice.

Ultrasound elastography in chronic kidney disease: a systematic review and meta-analysis.

Ultrasound elastography (USE) is a noninvasive technique for assessing tissue elasticity, and its application in nephrology has aroused growing interest in recent years. The purpose of this article is to systematically review the clinical application of USE in patients with chronic kidney disease (CKD), including native and transplanted kidneys, and quantitatively investigate differences in elasticity values between healthy individuals and CKD patients. Furthermore, we provide a qualitative analysis of the studies included, discussing the potential interplay between renal stiffness, estimated glomerular filtration rate, and fibrosis. In January 2022, a systematic search was carried out on the MEDLINE (PubMed) database, concerning studies on the application of USE in patients with CKD, including patients with transplanted kidneys. The results of the included studies were extracted by two independent researchers and presented mainly through a formal narrative summary. A meta-analysis of nine study parts from six studies was performed. A total of 647 studies were screened for eligibility and, after applying the exclusion and inclusion criteria, 69 studies were included, for a total of 6728 patients. The studies proved very heterogeneous in terms of design and results. The shear wave velocity difference of - 0.82 m/s (95% CI: - 1.72-0.07) between CKD patients and controls was not significant. This result agrees with the qualitative evaluation of included studies that found controversial results for the relationship between renal stiffness and glomerular filtration rate. On the contrary, a clear relationship seems to emerge between USE values and the degree of fibrosis. At present, due to the heterogeneity of results and technical challenges, large-scale application in the monitoring of CKD patients remains controversial.

Development of Predictive Models for the Response of Vestibular Schwannoma Treated with Cyberknife®: A Feasibility Study Based on Radiomics and Machine Learning.

PURPOSE: to predict vestibular schwannoma (VS) response to radiosurgery by applying machine learning (ML) algorithms on radiomic features extracted from pre-treatment magnetic resonance (MR) images. METHODS: patients with VS treated with radiosurgery in two Centers from 2004 to 2016 were retrospectively evaluated. Brain T1-weighted contrast-enhanced MR images were acquired before and at 24 and 36 months after treatment. Clinical and treatment data were collected contextually. Treatment responses were assessed considering the VS volume variation based on pre- and post-radiosurgery MR images at both time points. Tumors were semi-automatically segmented and radiomic features were extracted. Four ML algorithms (Random Forest, Support Vector Machine, Neural Network, and extreme Gradient Boosting) were trained and tested for treatment response (i.e., increased or non-increased tumor volume) using nested cross-validation. For training, feature selection was performed using the Least Absolute Shrinkage and Selection Operator, and the selected features were used as input to separately build the four ML classification algorithms. To overcome class imbalance during training, Synthetic Minority Oversampling Technique was used. Finally, trained models were tested on the corresponding held out set of patients to evaluate balanced accuracy, sensitivity, and specificity. RESULTS: 108 patients treated with Cyberknife® were retrieved; an increased tumor volume was observed at 24 months in 12 patients, and at 36 months in another group of 12 patients. The Neural Network was the best predictive algorithm for response at 24 (balanced accuracy 73% ± 18%, specificity 85% ± 12%, sensitivity 60% ± 42%) and 36 months (balanced accuracy 65% ± 12%, specificity 83% ± 9%, sensitivity 47% ± 27%). CONCLUSIONS: radiomics may predict VS response to radiosurgery avoiding long-term follow-up as well as unnecessary treatment.