Using a Recurrent Neural Network To Inform the Use of Prostate-specific Antigen (PSA) and PSA Density for Dynamic Monitoring of the Risk of Prostate Cancer Progression on Active Surveillance.

The global uptake of prostate cancer (PCa) active surveillance (AS) is steadily increasing. While prostate-specific antigen density (PSAD) is an important baseline predictor of PCa progression on AS, there is a scarcity of recommendations on its use in follow-up. In particular, the best way of measuring PSAD is unclear. One approach would be to use the baseline gland volume (BGV) as a denominator in all calculations throughout AS (nonadaptive PSAD, PSADNA), while another would be to remeasure gland volume at each new magnetic resonance imaging scan (adaptive PSAD, PSADA). In addition, little is known about the predictive value of serial PSAD in comparison to PSA. We applied a long short-term memory recurrent neural network to an AS cohort of 332 patients and found that serial PSADNA significantly outperformed both PSADA and PSA for follow-up prediction of PCa progression because of its high sensitivity. Importantly, while PSADNA was superior in patients with smaller glands (BGV ≤55 ml), serial PSA was better in men with larger prostates of >55 ml. Patient summary: Repeat measurements of prostate-specific antigen (PSA) and PSA density (PSAD) are the mainstay of active surveillance in prostate cancer. Our study suggests that in patients with a prostate gland of 55 ml or smaller, PSAD measurements are a better predictor of tumour progression, whereas men with a larger gland may benefit more from PSA monitoring.

Artificial intelligence (AI) in biomedical research: discussion on authors' declaration of AI in their articles title.

Artificial intelligence (AI) and its different approaches, from machine learning to deep learning, are not new. We discuss here about the declaration of AI in the title of those articles dealing with AI. From 1990 to 2021, while AI articles in the PubMed increased from 300 to 59,596, the percentage declaring AI in the title describes a U-like-shaped curve: about 30% in early 1990s, less than 13% in 2005-2014, again 30% in 2020-2021. A similar trend was observed for AI in medical imaging. While the initial decline could be due to the establishment of AI methods, the recent increase could be related to the capacity of AI to outperform humans, especially in image recognition, fuelled by the adoption of graphic processing units for general purpose computing. The recent increase may also be due to the relevance of open issues about AI, including the standardisation of methods, explainability of results, and concerns about AI-induced epoch-making transformations: to say "We are using AI" in the title may also reflect these concerns.

Mammography biomarkers of cardiovascular and musculoskeletal health: A review.

Breast density (BD) and breast arterial calcifications (BAC) can expand the role of mammography. In premenopause, BD is related to body fat composition: breast adipose tissue and total volume are potential indicators of fat storage in visceral depots, associated with higher risk of cardiovascular disease (CVD). Women with fatty breast have an increased likelihood of hypercholesterolemia. Women without cardiometabolic diseases with higher BD have a lower risk of diabetes mellitus, hypertension, chest pain, and peripheral vascular disease, while those with lower BD are at increased risk of cardiometabolic diseases. BAC, the expression of Monckeberg sclerosis, are associated with CVD risk. Their prevalence, 13 % overall, rises after menopause and is reduced in women aged over 65 receiving hormonal replacement therapy. Due to their distinct pathogenesis, BAC are associated with hypertension but not with other cardiovascular risk factors. Women with BAC have an increased risk of acute myocardial infarction, ischemic stroke, and CVD death; furthermore, moderate to severe BAC load is associated with coronary artery disease. The clinical use of BAC assessment is limited by their time-consuming manual/visual quantification, an issue possibly solved by artificial intelligence-based approaches addressing BAC complex topology as well as their large spectrum of extent and x-ray attenuations. A link between BD, BAC, and osteoporosis has been reported, but data are still inconclusive. Systematic, standardised reporting of BD and BAC should be encouraged.

Artificial intelligence for digital breast tomosynthesis: Impact on diagnostic performance, reading times, and workload in the era of personalized screening.

The ultimate goals of the application of artificial intelligence (AI) to digital breast tomosynthesis (DBT) are the reduction of reading times, the increase of diagnostic performance, and the reduction of interval cancer rates. In this review, after outlining the journey from computer-aided detection/diagnosis systems to AI applied to digital mammography (DM), we summarize the results of studies where AI was applied to DBT, noting that long-term advantages of DBT screening and its crucial ability to decrease the interval cancer rate are still under scrutiny. AI has shown the capability to overcome some shortcomings of DBT in the screening setting by improving diagnostic performance and by reducing recall rates (from -2 % to -27 %) and reading times (up to -53 %, with an average 20 % reduction), but the ability of AI to reduce interval cancer rates has not yet been clearly investigated. Prospective validation is needed to assess the cost-effectiveness and real-world impact of AI models assisting DBT interpretation, especially in large-scale studies with low breast cancer prevalence. Finally, we focus on the incoming era of personalized and risk-stratified screening that will first see the application of contrast-enhanced breast imaging to screen women with extremely dense breasts. As the diagnostic advantage of DBT over DM was concentrated in this category, we try to understand if the application of AI to DM in the remaining cohorts of women with heterogeneously dense or non-dense breast could close the gap in diagnostic performance between DM and DBT, thus neutralizing the usefulness of AI application to DBT.

Open issues for education in radiological research: data integrity, study reproducibility, peer-review, levels of evidence, and cross-fertilization with data scientists.

We are currently facing extraordinary changes. A harder and harder competition in the field of science is open in each country as well as in continents and worldwide. In this context, what should we teach to young students and doctors? There is a need to look backward and return to "fundamentals", i.e. the deep characteristics that must characterize the research in every field, even in radiology. In this article, we focus on data integrity (including the "declarations" given by the authors who submit a manuscript), reproducibility of study results, and the peer-review process. In addition, we highlight the need of raising the level of evidence of radiological research from the estimation of diagnostic performance to that of diagnostic impact, therapeutic impact, patient outcome, and social impact. Finally, on the emerging topic of radiomics and artificial intelligence, the recommendation is to aim for cross-fertilization with data scientists, possibly involving them in the clinical departments.

Transperineal Ultrasound Before and After Prostatectomy: Technical Approach and Description.

This study assessed the feasibility of dynamic transperineal ultrasound (TPUS) pre/post-radical prostatectomy (RP). Ninety-eight patients were scanned pre-operatively and at four time-points post-operatively. TPUS was performed in 98 patients using an abdominal transducer at rest, during pelvic floor contraction (PFC) and Valsalva (VS) maneuver in supine and standing positions. Urodynamic evaluations included bladder neck angle at rest/PFC/VS, and degree of bladder neck movement. Pre-operative and post-operative measurements were technically feasible in >85% (supine) and >90% (standing) of patients. TPUS offers a reliable non-invasive dynamic assessment of the pelvic floor post-prostatectomy and may prove a useful adjunct for guiding exercises to preserve continence.

Value of the capsular enhancement sign on dynamic contrast-enhanced prostate multiparametric MRI for the detection of extracapsular extension.

PURPOSE: To retrospectively determine the prevalence and diagnostic performance of the capsular enhancement sign (CES) on multiparametric (mp) MRI for the detection of prostate cancer (PCa) extracapsular extension (ECE). METHODS: This retrospective study included patients who underwent mpMRI prior to radical prostatectomy. CES was defined as an area of asymmetrical early hyperenhancement on DCE-MRI adjacent to a peripheral zone tumour, matched or exceeded the tumour circumferential diameter, and with persistent enhancement. Two uro-radiologists evaluated the presence of CES on mpMRI, independently and in consensus, with interobserver agreement calculated using bias and prevalence-adjusted kappa (PABAK). CES performance for predicting ECE was assessed using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: The study included 146 patients, with 91/146 (62%) having ECE on surgical pathology. Following initial review, Reader 1 identified 12/146 (8%) CES-positive cases, while Reader 2 reported 14/146 (10%) CES-positive cases, with 15/146 (10%) lesions determined as demonstrating the CES sign on consensus reading. PABAK for CES between the two readers was high at 0.90. All consensus determined CES-positive lesions represented pathological stage ≥ T3a disease, with the overall prevalence of CES among tumours with confirmed ECE being 15/91 (17%). The sign showed high specificity (100%) and PPV (100%) for ECE detection, but with low sensitivity, NPV, and accuracy at 16.5%, 41.3%, and 47.4%, respectively. CONCLUSIONS: CES was demonstrated to be a rare but highly specific ECE predictor on mpMRI that may improve local staging in the patients in whom it is demonstrated.

Use of an antagonist of HMGB1 in mice affected by malignant mesothelioma: a preliminary ultrasound and optical imaging study.

BACKGROUND: Malignant mesothelioma (MM) is an aggressive tumor, with a poor prognosis, usually unresectable due to late diagnosis, mainly treated with chemotherapy. BoxA, a truncated form of "high mobility group box 1" (HMGB1), acting as an HMGB1 antagonist, might exert a defensive action against MM. We investigated the potential of BoxA for MM treatment using experimental 40-MHz ultrasound and optical imaging (OI) in a murine model. METHODS: Murine MM cells infected with a lentiviral vector expressing the luciferase gene were injected into the peritoneum of 14 BALB/c mice (7 × 104 AB1-B/c-LUC cells). These mice were randomized to treatment with BoxA (n = 7) or phosphate-buffered saline (controls, n = 7). The experiment was repeated with 40 mice divided into two groups (n = 20 + 20) and treated as above to confirm the result and achieve greater statistical power. Tumor presence was investigated by experimental ultrasound and OI; suspected peritoneal masses underwent histopathology and immunohistochemistry examination. RESULTS: In the first experiment, none of the 7 controls survived beyond day 27, whereas 4/7 BoxA-treated mice (57.1%) survived up to day 70. In the second experiment, 6/20 controls (30.0%) and 16/20 BoxA-treated mice (80.0%) were still alive at day 34 (p = 0.004). In both experiments, histology confirmed the malignant nature of masses detected using experimental ultrasound and OI. CONCLUSION: In our preclinical experience on a murine model, BoxA seems to exert a protective role toward MM. Both experimental ultrasound and OI proved to be reliable techniques for detecting MM peritoneal masses.

Evaluation of image-based prognostic parameters of post-prostatectomy urinary incontinence: A literature review.

Prostate cancer is the second most common male cancer, and radical prostatectomy is a highly effective treatment for intermediate and high-risk disease. However, post-prostatectomy urinary incontinence remains a major functional side-effect in patients undergoing radical prostatectomy. Despite recent improvements in preoperative imaging quality and surgical techniques, it remains challenging to predict or prevent occurrence of this complication. The aim of this research was to review the current published literature on pre- and postoperative imaging evaluation of the prostate and pelvic structures, to identify added value in the prediction of post-prostatectomy urinary incontinence. A computerized bibliographic search of the PubMed library was carried out to identify imaging-based articles evaluating the pelvic floor and surrounding structures pre- and/or postradical prostatectomy to predict post-prostatectomy urinary incontinence. A total of 32 articles were included. Of these, 29 papers assessed the importance of magnetic resonance imaging evaluation, with a total of 16 parameters evaluated. The most common parameters were intravesical protrusion, the membranous urethral length, prostatic volume and periurethral fibrosis. Preoperative membranous urethral length and its preservation after surgery showed the strongest correlation with urinary incontinence. Three studies evaluated ultrasound, with all carried out postoperatively. This technique benefits from a dynamic evaluation, and the results are promising for proximal urethral hypermobility and the degree of bladder neck funneling on the Valsalva maneuver. Several imaging studies evaluated the predictors of post-prostatectomy urinary incontinence, with preoperative membranous urethral length offering the most promise. However, the current literature is limited by the single-center nature of studies, and the heterogeneity in patient populations and methodologies used.

Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients.

OBJECTIVE: To evaluate whether the initial chest X-ray (CXR) severity assessed by an AI system may have prognostic utility in patients with COVID-19. METHODS: This retrospective single-center study included adult patients presenting to the emergency department (ED) between February 25 and April 9, 2020, with SARS-CoV-2 infection confirmed on real-time reverse transcriptase polymerase chain reaction (RT-PCR). Initial CXRs obtained on ED presentation were evaluated by a deep learning artificial intelligence (AI) system and compared with the Radiographic Assessment of Lung Edema (RALE) score, calculated by two experienced radiologists. Death and critical COVID-19 (admission to intensive care unit (ICU) or deaths occurring before ICU admission) were identified as clinical outcomes. Independent predictors of adverse outcomes were evaluated by multivariate analyses. RESULTS: Six hundred ninety-seven 697 patients were included in the study: 465 males (66.7%), median age of 62 years (IQR 52-75). Multivariate analyses adjusting for demographics and comorbidities showed that an AI system-based score ≥ 30 on the initial CXR was an independent predictor both for mortality (HR 2.60 (95% CI 1.69 - 3.99; p < 0.001)) and critical COVID-19 (HR 3.40 (95% CI 2.35-4.94; p < 0.001)). Other independent predictors were RALE score, older age, male sex, coronary artery disease, COPD, and neurodegenerative disease. CONCLUSION: AI- and radiologist-assessed disease severity scores on CXRs obtained on ED presentation were independent and comparable predictors of adverse outcomes in patients with COVID-19. TRIAL REGISTRATION: ClinicalTrials.gov NCT04318366 ( https://clinicaltrials.gov/ct2/show/NCT04318366 ). KEY POINTS: • AI system-based score ≥ 30 and a RALE score ≥ 12 at CXRs performed at ED presentation are independent and comparable predictors of death and/or ICU admission in COVID-19 patients. • Other independent predictors are older age, male sex, coronary artery disease, COPD, and neurodegenerative disease. • The comparable performance of the AI system in relation to a radiologist-assessed score in predicting adverse outcomes may represent a game-changer in resource-constrained settings.

Synergic role of preoperative 18F-fluorodeoxyglucose PET and MRI parameters in predicting histopathological features of endometrial cancer.

BACKGROUND: The aim of the present study is to explore the correlation between PET and MRI parameters of primary tumour and clinicopathological features and to determine their synergic predictive role in patients with endometrial cancer candidate to surgery. METHODS: Retrospective study including 27 patients with endometrial cancer and preoperative 18F-fluorodeoxyglucose (18F-FDG)-PET and MRI scan. The following parameters, calculated on the primary tumour, were used for analysis: maximum standardized uptake value (SUVmax), SUVmean, metabolic tumour volume (MTV) and total lesion glycolysis (TLG) for PET scans; mean apparent diffusion coefficient (ADCmean) and volume index for MRI scans. FIGO stage, grade, histotype, lymphovascular space invasion (LVSI) and myometrial invasion were the considered clinicopathological features. RESULTS: MRI volume index was a good predictor for deep myometrial invasion [area under the curve (AUC) = 0.85; P = 0.003] and for LVSI (AUC = 0.74; P = 0.039). A cutoff value of 9.555 for MRI volume index was predictive for deep myometrial invasion (sensitivity = 84.6%; specificity = 76.9%); a cutoff of 12.165 was predictive for LVSI (sensitivity = 69.2%; specificity = 83.3%). A TLG cutoff value of 26.03 was predictive for deep myometrial invasion (sensitivity = 84.6%; specificity = 76.9%). A high-direct correlation was found with MRI volume index (rho = 0.722; P < 0.001); low-direct correlation with SUVmax (rho = 0.484; P = 0.012), SUVmean (rho = 0.47; P = 0.015) and TLG (rho = 0.482; P = 0.013) were identified. The SUVmax/ADCmean ratio showed a low-direct correlation with percentage of myometrial invasion (rho = 0.467; P = 0.016). CONCLUSION: Volume index, TLG and SUVmax/ADCmean ratio are associated with deep myometrial invasion. As myometrial invasion is the index used to predict lymph node involvement in endometrial cancer, the synergic use of these imaging parameters may be suggested to predict lymphnodal metastases.

A New Model of Chronic Mycobacterium abscessus Lung Infection in Immunocompetent Mice.

Pulmonary infections caused by Mycobacterium abscessus (MA) have increased over recent decades, affecting individuals with underlying pathologies such as chronic obstructive pulmonary disease, bronchiectasis and, especially, cystic fibrosis. The lack of a representative and standardized model of chronic infection in mice has limited steps forward in the field of MA pulmonary infection. To overcome this challenge, we refined the method of agar beads to establish MA chronic infection in immunocompetent mice. We evaluated bacterial count, lung pathology and markers of inflammation and we performed longitudinal studies with magnetic resonance imaging (MRI) up to three months after MA infection. In this model, MA was able to establish a persistent lung infection for up to two months and with minimal systemic spread. Lung histopathological analysis revealed granulomatous inflammation around bronchi characterized by the presence of lymphocytes, aggregates of vacuolated histiocytes and a few neutrophils, mimicking the damage observed in humans. Furthermore, MA lung lesions were successfully monitored for the first time by MRI. The availability of this murine model and the introduction of the successfully longitudinal monitoring of the murine lung lesions with MRI pave the way for further investigations on the impact of MA pathogenesis and the efficacy of novel treatments.

Elective Embolization of Splenic Artery Aneurysms with an Ethylene Vinyl Alcohol Copolymer Agent (Squid) and Detachable Coils.

PURPOSE: To report the safety and efficacy of the embolization of splenic artery aneurysms (SAAs) with coils plus ethylene vinyl alcohol copolymer (EVOH) agent. MATERIALS AND METHODS: A single-center retrospective study was conducted from 2016 to 2019 to collect SAAs. Twelve asymptomatic patients (mean age, 59 years) with 15 SAAs (mean size, 23.6 mm; size range, 15-40 mm) were treated with embolization. Embolization was performed with EVOH (Squid 8/34) and fibered detachable coils. Transfemoral embolization was performed with a microcatheter to achieve a splenic artery occlusion embolizing the SAA and its efferent and afferent branches. Follow-up was based on color Doppler ultrasound at 24 hours and on computed tomography (CT) angiography at 1 (n = 12) and 6 months (n = 12) after embolization. Mean number of coils and Squid vials used for each patient, major/minor complications, technical success, 30-day clinical success, cases of revascularization/reintervention, and mortality were assessed. Technical success was defined as complete exclusion of the aneurysmal segment and cessation of blood flow into the sac. Clinical success at 1 month was based on the absence of clinical symptoms and the exclusion of aneurysm revascularization on CT angiography. RESULTS: The mean number of coils and Squid vials was 5.75 (standard deviation [SD], 1.58; range, 3-9) and 1.41 (SD, 0.49; range, 1-2), respectively. Both technical and 30-day clinical success were 100%, with no cases of aneurysm revascularization (CT angiography performed in all patients at 1 month and 6 months and in 3 patients at 24 months). No major complications or fatal events were recorded. In terms of minor complications, 2 cases of mild pancreatitis (transient amylases increase) and 1 case of focal splenic ischemia without clinical sequelae were recorded. CONCLUSIONS: Embolization in SAAs using coils plus EVOH was safe and effective without SAA revascularization.

Psychological impact of different primary treatments for prostate cancer: A critical analysis.

Limited attention has been given to the psychological impact of primary treatments in patients with prostate cancer. Aim of our analysis was to critically analyse the current evidence on the psychological impact of different primary treatments (surgery, radiotherapy and active surveillance), in patients with prostate cancer, using validated questionnaires. We searched in the MEDLINE and Cochrane library database from the literature of the past 15 years (primary fields: prostate neoplasm, AND radical prostatectomy or radiotherapy or active surveillance AND psychological distress or anxiety or depression; secondary fields: urinary, sexual, bowel modifications, non-randomised and randomised trials). Overall eighteen original and review articles were included and critically evaluated. Either radical prostatectomy or active surveillance and radiotherapy are well-tolerated in terms of definite anxiety and depression during the post-treatment follow-up. A mutual influence between functional and psychological modifications induced by treatments has been demonstrated. Urinary symptoms related to incontinence more than sexual and bowel dysfunction are able to induce psychological distress worsening. In conclusion, patients and their clinicians might wish to know how functional and psychological aspects may differently be influenced by treatment choice.

Transcatheter embolization with Squid, combined with other embolic agents or alone, in different abdominal diseases: a single-center experience in 30 patients.

BACKGROUND: Squid, as Onyx, is an ethylene-vinyl alcohol copolymer (EVOH)-based liquid embolic agent developed for neuroradiologic interventions with poor application in abdominal district. Our aim was to evaluate safety, complications, and efficacy of transcatheter embolization using the two available formulations Squid-18 and 12, in 30 patients affected by different abdominal diseases. RESULTS: Transcatheter embolization with Squid, combined with other embolic agents, as poly vinyl alcohol (PVA) particles, coils and amplatzer plugs, or alone (type 2 endoleak), was performed in 30 patients, as follows: 10 portal vein embolizations (PVEs), 6 arteriovenous malformations (AVMs), 5 visceral artery aneurysms (VAAs), 4 type 2 endoleaks, 3 preoperative embolizations, 1 acute arterial bleeding, 1 female varicocele. Squid was always administered using dimethyl sulfoxide (DMSO) compatible microcatheters. Technical success, 30-day clinical success and complications were assessed. Technical success was 90%. 3 patients (2 AVMs, 1 VAA) required re-intervention successfully performed in all cases. Major complications, cases of microcatheter entrapment and DMSO-related poor pain control were not recorded. 30-day clinical success was 93.3%: in 2 patients submitted to PVE a sufficient future liver remnant (FLR) hypertrophy was not achieved. CONCLUSION: Squid was successfully used with low complication rate in many abdominal diseases showing a valid embolic action either combined with other embolic agents or alone in type 2 endoleak. The availability of different formulations (Squid-18 and Squid-12) variable for viscosity makes Squid preferable to Onyx as EVOH-based liquid embolic agent, even though comparable studies in different abdominal districts with a larger cohort of patients will be necessary.

Contrast-enhanced ultrasound for ovary assessment in a murine model: preliminary findings on the protective role of a gonadotropin-releasing hormone analogue from chemotherapy-induced ovarian damage.

The prolonged, gonadotoxic effect of chemotherapy can finally lead to infertility in female cancer survivors. There is controversial evidence regarding the protective role of gonadotropin-releasing hormone analogue (GnRH-a) on chemotherapy-induced ovarian damage. In the present study on a murine model, ultrasound (US) and contrast-enhanced US (CEUS) were firstly used to characterise ovarian glands in normal conditions to validate a preclinical model. In addition, preliminary findings were obtained on anatomical and vascular ovarian changes induced by GnRH-a based on decapeptyl administration. Ovaries were accurately assessed with US and CEUS in a murine model placed in prone position, providing quantitative and reproducible information. Ovaries were identified in 40/40 cases and CEUS analysis was successfully performed in 20/20 cases with 100% technical success. A statistically significant increase of the diameter of the dominant follicle at US and a statistically significant reduced vascularisation at CEUS in decapeptyl-treated mice compared to untreated control mice were recorded. Further studies using US and CEUS in the murine model combining GnRH-a and chemotherapeutic agents will be needed to obtain more translational information useful for clinical practice.

Applicability of a prognostic CT-based radiomic signature model trained on stage I-III non-small cell lung cancer in stage IV non-small cell lung cancer.

OBJECTIVES: Recently it has been shown that radiomic features of computed tomography (CT) have prognostic information in stage I-III non-small cell lung cancer (NSCLC) patients. We aim to validate this prognostic radiomic signature in stage IV adenocarcinoma patients undergoing chemotherapy. MATERIALS AND METHODS: Two datasets of chemo-naive stage IV adenocarcinoma patients were investigated, dataset 1: 285 patients with CTs performed in a single center; dataset 2: 223 patients included in a multicenter clinical trial. The main exclusion criteria were EGFR mutation or unknown mutation status and non-delineated primary tumor. Radiomic features were calculated for the primary tumor. The c-index of cox regression was calculated and compared to the signature performance for overall survival (OS). RESULTS: In total CT scans from 195 patients were eligible for analysis. Patients having a prognostic index (PI) lower than the signature median (n = 92) had a significantly better OS than patients with a PI higher than the median (n = 103, HR 1.445, 95% CI 1.07-1.95, p = 0.02, c-index 0.576, 95% CI 0.527-0.624). CONCLUSION: The radiomic signature, derived from daily practice CT scans, has prognostic value for stage IV NSCLC, however the signature performs less than previously described for stage I-III NSCLC stages. In the future, machine learning techniques can potentially lead to a better prognostic imaging based model for stage IV NSCLC.