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.

Computed-Tomography-Guided Lung Biopsy: A Practice-Oriented Document on Techniques and Principles and a Review of the Literature.

Computed tomography (CT)-guided lung biopsy is one of the oldest and most widely known minimally invasive percutaneous procedures. Despite being conceptually simple, this procedure needs to be performed rapidly and can be subject to meaningful complications that need to be managed properly. Therefore, knowledge of principles and techniques is required by every general or interventional radiologist who performs the procedure. This review aims to contain all the information that the operator needs to know before performing the procedure. The paper starts with the description of indications, devices, and types of percutaneous CT-guided lung biopsies, along with their reported results in the literature. Then, pre-procedural evaluation and the practical aspects to be considered during procedure (i.e., patient positioning and breathing) are discussed. The subsequent section is dedicated to complications, with their incidence, risk factors, and the evidence-based measures necessary to both prevent or manage them; special attention is given to pneumothorax and hemorrhage. After conventional CT, this review describes other available CT modalities, including CT fluoroscopy and cone-beam CT. At the end, more advanced techniques, which are already used in clinical practice, like fusion imaging, are included.

Prostate Artery Embolization (PAE) with Small Beads for the Treatment of Benign Prostatic Hyperplasia (BPH).

Benign Prostatic Hyperplasia (BPH) is the most frequent cause of Lower Urinary Tract Symptoms (LUTSs) in elderly populations. Minimally invasive treatments of BPH are safe and effective and are gaining popularity among both professionals and patients. Prostate Artery Embolization (PAE) has proven to be effective in Trans-Urethral Resection of the Prostate (TURP) in terms of prostate volume reduction and LUTS relief. PAE entails the selective catheterization of the prostatic artery and later embolization of distal vessels with beads of various calibers. Universal consensus regarding the ideal particle size is yet to be defined. We retrospectively evaluated 24 consecutive patients (median age: 75 years; range: 59-86 years) treated with PAE at our institution from October 2015 to November 2022. Particles of different sizes were employed; 12 patients were treated with 40-120 µm particles, 5 with 100 µm, 5 with 100-300 µm and 2 with 250 µm. Technical success, defined as selective prostate artery catheterization and controlled release of embolizing beads, was achieved in all patients. Removal vs. retention of the urinary catheter at the first post-procedural urological visit was the main clinical objective. No major peri-procedural complications were recorded, with 56% of patients successfully removing the urinary catheter.

Transperineal Laser Ablation of the Prostate for Symptomatic Benign Prostatic Hyperplasia: Long-Term Follow-Up in 40 Patients.

PURPOSE: To evaluate the durability, effectiveness, and safety of transperineal laser ablation (TPLA) of the prostate. MATERIALS AND METHODS: Patients with symptomatic benign prostatic hyperplasia (BPH) underwent TPLA with a 1,064-nm continuous-wave diode laser. International Prostate Symptom Score (IPSS), quality of life (QoL), postvoid residual (PVR), and prostate volume were evaluated at baseline and successive timepoints. RESULTS: Forty prospectively enrolled patients had follow-up of ≥36 months; median duration of follow-up was 57 months (range, 36-76 months). Compared with baseline, the median reduction in IPSS at 12-month follow-up was 74% (interquartile range [IQR], 60%-81%) (P < .001). Median QoL score at 12 months was improved from 5 (IQR, 4-5) at baseline to 1 (IQR, 0-1) (P < .001). Median PVR at 12 months decreased from 108 mL (IQR, 38-178 mL) to 13.5 mL (IQR, 0-40.5 mL) (P < .001), a median reduction of 88% (IQR, 61%-100%). At 12 months, median prostate volume was significantly reduced from 66 mL (IQR, 48.5-86.5 mL) to 46 mL (IQR, 36-65 mL) (P < .001), a median reduction of 32% (IQR, 21%-45%). For all of these parameters, the benefit of TPLA persisted at last follow-up, and all changes were statistically significant compared with baseline. There were no intraprocedural adverse events; periprocedural adverse events consisted of 1 case of prostatitis and 1 case of urinary tract infection (both Society of Interventional Radiology [SIR] Grade I). CONCLUSIONS: TPLA for symptomatic BPH produced durable benefits across a range of clinical outcomes and was well tolerated in follow-up at median duration of 57 months.

Role of Flex-Dose Delivery Program in Patients Affected by HCC: Advantages in Management of Tare in Our Experience.

Background: Introduced in the latest BCLC 2022, endovascular trans-arterial radioembolization (TARE) has an important role in the treatment of unresectable hepatocellular carcinoma (HCC) as a "bridge" or "downstaging" of disease. The evolution of TARE technology allows a more flexible and personalized target treatment, based on the anatomy and vascular characteristics of each HCC. The flex-dose delivery program is part of this perspective, which allows us to adjust the dose and its radio-embolizing power in relation to the size and type of cancer and to split the therapeutic dose of Y90 in different injections (split-bolus). Methods: From January 2020 to January 2022, we enrolled 19 patients affected by unresectable HCC and candidates for TARE treatment. Thirteen patients completed the treatment following the flex-dose delivery program. Response to treatment was assessed using the mRECIST criteria with CT performed 6 and 9 months after treatment. Two patients did not complete the radiological follow-up and were not included in this retrospective study. The final cohort of this study counts eleven patients. Results: According to mRECIST criteria, six months of follow-up were reported: five cases of complete response (CR, 45.4% of cases), four cases of partial response (PR, 36.4%), and two cases of progression disease (PD, 18.2%). Nine months follow-up reported five cases of complete response (CR, 45.4%), two cases of partial response (PR, 18.2%), and four cases of progression disease (PD, 36.4%). No intra and post-operative complications were described. The average absorbed doses to the hepatic lesion and to the healthy liver tissue were 319 Gy (range 133-447 Gy) and 9.5 Gy (range 2-19 Gy), respectively. Conclusions: The flex-dose delivery program represents a therapeutic protocol capable of "saving" portions of healthy liver parenchyma by designing a "custom-made" treatment for the patient.

Patients' Perceptions and Attitudes to the Use of Artificial Intelligence in Breast Cancer Diagnosis: A Narrative Review.

Breast cancer remains the most prevalent cancer among women worldwide, necessitating advancements in diagnostic methods. The integration of artificial intelligence (AI) into mammography has shown promise in enhancing diagnostic accuracy. However, understanding patient perspectives, particularly considering the psychological impact of breast cancer diagnoses, is crucial. This narrative review synthesizes literature from 2000 to 2023 to examine breast cancer patients' attitudes towards AI in breast imaging, focusing on trust, acceptance, and demographic influences on these views. Methodologically, we employed a systematic literature search across databases such as PubMed, Embase, Medline, and Scopus, selecting studies that provided insights into patients' perceptions of AI in diagnostics. Our review included a sample of seven key studies after rigorous screening, reflecting varied patient trust and acceptance levels towards AI. Overall, we found a clear preference among patients for AI to augment rather than replace the diagnostic process, emphasizing the necessity of radiologists' expertise in conjunction with AI to enhance decision-making accuracy. This paper highlights the importance of aligning AI implementation in clinical settings with patient needs and expectations, emphasizing the need for human interaction in healthcare. Our findings advocate for a model where AI augments the diagnostic process, underlining the necessity for educational efforts to mitigate concerns and enhance patient trust in AI-enhanced diagnostics.

Quantitative and Qualitative Radiological Assessment of Sarcopenia and Cachexia in Cancer Patients: A Systematic Review.

Sarcopenia, an extremely common condition in cancer patients, is described as a progressive and generalized musculoskeletal disorder that is associated with an increased likelihood of adverse outcomes, including falls, fractures, physical disability, and mortality. By contrast, cachexia is defined as a syndrome characterized by weight loss with the concomitant loss of muscle and/or fat mass. Cancer cachexia leads to functional impairment, reduced physical performance, and decreased survival, and is often accompanied by cancer progression and reduced response to therapy. The literature states that cancer patients with cachexia or sarcopenia have many more complications than patients without these conditions. The interplay between physiologic sarcopenia and cancer cachexia is, in part, responsible for the complexity of studying wasting disorders in the cancer population, particularly in the geriatric population. For these reasons, a comprehensive assessment of the body composition and physical function of these patients is necessary. There are several modalities adapted to measure skeletal muscle mass, such as dual-energy X-ray absorptiometry (DEXA), bioelectrical impedance analysis (BIA), computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound (US). The gold standard for the measurement of quantitative and qualitative changes in body composition in patients with cancer is the analysis of tissue density using a CT scan. However, this technique remains poorly implemented in clinical practice because of the use of ionizing radiation. Similarly, DEXA, MRI, and US have been proposed, but their use is limited. In this review, we present and compare the imaging techniques that have been developed so far for the nutritional assessment of cancer patients.

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.

MR sialographic assessment of the masseter muscle and the ductal kinking in patients with recurrent parotitis.

Dysfunction of the masseter muscle may cause pathological kinking of the parotid duct leading to parotitis; MR sialography is a non-invasive radiological examination that allows to evaluate dynamically the ductal system of the parotid glands. In the present study we aimed to assess the relationships between Stensen's duct and masseter muscle and their implications in the aetiopathogenesis of recurrent parotitis secondary to masseter muscle dysfunction. Forty-one patients with recurrent unilateral parotitis and nine with bilateral recurrent parotitis, all with a clinical suspicious of masseter muscle hypertrophy due to bruxism were enrolled. They underwent ultrasonography as a first line examination and then MR sialography and sialendoscopy. Different anatomical features were studied. Involved parotid glands had a wider duct compared to contralateral unaffected parotid glands of patients with recurrent parotitis (p = 0.00134); male subjects with parotitis had a longer duct compared to the salivary glands of healthy patients (p = 0.00943 for affected glands and p = 0.00629 for the contralateral). A concordance between the evidence of an acute duct angle during sialendoscopy and a wider duct in patients with parotitis was observed although not statistically significant. These initial findings suggest that the masticatory muscle dysfunction related to bruxism seems to condition alteration of parotid duct course and anatomy thus favouring the occurrence of recurrent parotitis. A specific diagnostic iter based on clinical evaluation, dynamic ultrasonography and MR sialography, is therefore, mandatory to confirm the relationship between masseter muscle anatomy and parotid duct anomalies; this is the premise for an adequate therapeutic approach to underlying masticatory muscle disorder.

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.

Is it a complication or a consequence - a new perspective on adverse outcomes in Interventional Radiology.

The aim of the article is to introduce a new term in post-procedural events related to the procedure itself. All the Societies and Councils report these events as complications and they are divided in mild, moderate and severe or immediate and delayed.On the other hand the term error is known as the application of a wrong plan, or strategy to achieve a goal.For the first time, we are trying to introduce the term "consequence"; assuming that the procedure is the only available and the best fit to clinical indication, a consequence should be seen as an expected and unavoidable occurrence of an "adverse event" despite correct technical execution.

Pseudoaneurysms embolization with glue via percutaneous direct puncture: a multicenter experience on 54 patients.

BACKGROUND: This retrospective multicentric study aims to report on technical safety and effectiveness of pseudoaneurysms embolization with glue (N-butyl cyanoacrylate) adopting a percutaneous direct puncture approach. RESULTS: Fifty-four patients data were collected from five centers. All patients at the time of treatment presented with unruptured PAs and were hemodynamically stable. True aneurysms and lesions treated with embolics other than glue were excluded. Pseudoaneurysms diagnosis was based on CT and anamnestic data; initial investigation with digital-subtracted arteriography was acquired in all cases; then, percutaneous embolizations were performed in the angio-suite (ultrasound, fluoroscopy, ConeBeam CT guidance) or in CT. Technical success was considered as complete pseudoaneurysm embolization at final imaging with sole percutaneous strategy, without need for additional endovascular embolization. Clinical success was intended as pseudoaneurysm resolution within one week follow-up with stabilization or restored clinical conditions. Pseudoaneurysms origins were traumatic (57.4%), inflammatory (24.1%) or spontaneous (18.5%); 39 patients (72.2%) were symptomatic, presenting with pain and/or pulsatile mass. Mean lesions diameter was 19.3 mm (range: 7-30); pseudoaneurysms were located in abdomen (48.1%), limbs (42.6%) and thorax (9.3%). Coagulation function was impaired in 16.6% and 48.1% was under antiplatelets/anticoagulation therapy. In 16.6% the percutaneous approach followed previous treatments failure. The image-guidance modality for percutaneous puncture was most often ultrasound combined with fluoroscopy (38%). Clinical success was obtained in all patients while technical success occurred in 94.4% because 3 patients required an additional endovascular embolization. Complications were registered in 14.8%, all of low grade without clinical sequelae neither prolonged recovery (7 non target embolizations, 1 post-embolization syndrome). CONCLUSIONS: In this study, pseudoaneurysms embolization with glue via percutaneous direct puncture was safe and effective with a low rate of minor complications.

Perioperative and Survival Outcomes of Patients Treated With Robot-Assisted Partial Nephrectomy and Percutaneous Microwave Ablation for Small Renal Masses: A Single Center Experience.

BACKGROUND: Robot assisted partial nephrectomy (RAPN) and microwave ablation (MWA) are 2 of the most advanced techniques for the management of localized small renal masses. PURPOSE: To compare the perioperative, functional and oncological results of RAPN and MWA. MATERIALS AND METHODS: Data from 171 consecutive patients undergoing either RAPN or MWA for a localized small renal mass at a single academic center was retrospectively collected. Baseline features included patients' demographics and masses' characteristics. Procedures were compared in terms of perioperative outcomes and renal function variation Progression of a persistent lesion or local recurrence after a complete treatment defined local tumor progression. Descriptive statistics and survival analysis tested the association between predictors and local tumor progression. RESULTS: Of all, 109 and 62 patients underwent RAPN and MWA. Patients in the MWA group were older (P = .002) had higher Charlson Comorbidity Index (CCI) (P < .001) and higher frequency of preoperative chronic kidney disease (P < .001). MWA led to a shorter postoperative hospitalization time (P < .001) and lower incidence of medical complications (6.5% vs. 22.9%, P = .02) than RAPN. GFR decline was similar between groups both at discharge (P = .39) and at the time of last follow up (P = 1.00). A lower rate of secondary interventions (11.7% vs. 2.8%, P = .037) and a better disease-free survival (83.2% vs. 96.5%, P = .027) were reported after RAPN. Conversely, cancer specific and overall survival were comparable (P > .05). At univariate regression analysis, MWA was associated with local tumor progression (HR 3.46, P = .040). CONCLUSION: MWA displayed a lower perioperative impact, while functional outcomes were similar after each intervention. RAPN resulted superior in terms of tumor eradication, but no difference was noted regarding cancer specific survival. Thus, MWA represents a valid alternative in frail patients, though less radical than RAPN.

Smartphone Augmented Reality Outperforms Conventional CT Guidance for Composite Ablation Margins in Phantom Models.

PURPOSE: To develop and evaluate a smartphone augmented reality (AR) system for a large 50-mm liver tumor ablation with treatment planning for composite overlapping ablation zones. MATERIALS AND METHODS: A smartphone AR application was developed to display tumor, probe, projected probe paths, ablated zones, and real-time percentage of the ablated target tumor volume. Fiducial markers were attached to phantoms and an ablation probe hub for tracking. The system was evaluated with tissue-mimicking thermochromic phantoms and gel phantoms. Four interventional radiologists performed 2 trials each of 3 probe insertions per trial using AR guidance versus computed tomography (CT) guidance approaches in 2 gel phantoms. Insertion points and optimal probe paths were predetermined. On Gel Phantom 2, serial ablated zones were saved and continuously displayed after each probe placement/adjustment, enabling feedback and iterative planning. The percentages of tumor ablated for AR guidance versus CT guidance, and with versus without display of recorded ablated zones, were compared among interventional radiologists with pairwise t-tests. RESULTS: The means of percentages of tumor ablated for CT freehand and AR guidance were 36% ± 7 and 47% ± 4 (P = .004), respectively. The mean composite percentages of tumor ablated for AR guidance were 43% ± 1 (without) and 50% ± 2 (with display of ablation zone) (P = .033). There was no strong correlation between AR-guided percentage of ablation and years of experience (r < 0.5), whereas there was a strong correlation between CT-guided percentage of ablation and years of experience (r > 0.9). CONCLUSIONS: A smartphone AR guidance system for dynamic iterative large liver tumor ablation was accurate, performed better than conventional CT guidance, especially for less experienced interventional radiologists, and enhanced more standardized performance across experience levels for ablation of a 50-mm tumor.

Dual-Layer Spectral CT as Innovative Imaging Guidance in Lung Biopsies: Could Color-Coded Z-Effective Images Allow More Diagnostic Samplings and Biomarkers Information?

The aim of the study was to try to obtain more information on diagnostic samplings and biomarkers using dual-layer spectral CT in lung biopsies. Lung biopsies were performed by merging images obtained with CBCT with those from spectral CT to use them as functional guidance, experimenting with double sampling to determine the difference between the area with a higher Z-effective number and that with a lower Z-effective number. Ten patients with large lung lesions on spectral CT were selected and underwent percutaneous transthoracic lung mass biopsy. Technical success was calculated. The percentage of neoplastic, inflammatory, fibrotic, necrotic cells, or non-neoplastic lung parenchyma was reported. The possibility of carrying out immunohistochemical or molecular biology investigations was analyzed. All lesions were results malignant in 10/10 samples in the Zmax areas; in the Zmin areas, malignant cells were found in 7/10 samples. Technical success was achieved in 100% of cases for Zmax sampling and in 70% for Zmin sampling (p-value: 0.2105). The biomolecular profile was detected in 9/10 (90%) cases in Zmax areas, while in 4/10 (40%) cases in Zmin areas (p-value: 0.0573). The advantage of Z-effective imaging would be to identify a region of the lesion that is highly vascularized and probably richer in neoplastic cells, thus decreasing the risk of obtaining a non-diagnostic biopsy sample.