Evaluation of a Cascaded Deep Learning-based Algorithm for Prostate Lesion Detection at Biparametric MRI.

Background Multiparametric MRI (mpMRI) improves prostate cancer (PCa) detection compared with systematic biopsy, but its interpretation is prone to interreader variation, which results in performance inconsistency. Artificial intelligence (AI) models can assist in mpMRI interpretation, but large training data sets and extensive model testing are required. Purpose To evaluate a biparametric MRI AI algorithm for intraprostatic lesion detection and segmentation and to compare its performance with radiologist readings and biopsy results. Materials and Methods This secondary analysis of a prospective registry included consecutive patients with suspected or known PCa who underwent mpMRI, US-guided systematic biopsy, or combined systematic and MRI/US fusion-guided biopsy between April 2019 and September 2022. All lesions were prospectively evaluated using Prostate Imaging Reporting and Data System version 2.1. The lesion- and participant-level performance of a previously developed cascaded deep learning algorithm was compared with histopathologic outcomes and radiologist readings using sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC). Results A total of 658 male participants (median age, 67 years [IQR, 61-71 years]) with 1029 MRI-visible lesions were included. At histopathologic analysis, 45% (294 of 658) of participants had lesions of International Society of Urological Pathology (ISUP) grade group (GG) 2 or higher. The algorithm identified 96% (282 of 294; 95% CI: 94%, 98%) of all participants with clinically significant PCa, whereas the radiologist identified 98% (287 of 294; 95% CI: 96%, 99%; P = .23). The algorithm identified 84% (103 of 122), 96% (152 of 159), 96% (47 of 49), 95% (38 of 40), and 98% (45 of 46) of participants with ISUP GG 1, 2, 3, 4, and 5 lesions, respectively. In the lesion-level analysis using radiologist ground truth, the detection sensitivity was 55% (569 of 1029; 95% CI: 52%, 58%), and the PPV was 57% (535 of 934; 95% CI: 54%, 61%). The mean number of false-positive lesions per participant was 0.61 (range, 0-3). The lesion segmentation DSC was 0.29. Conclusion The AI algorithm detected cancer-suspicious lesions on biparametric MRI scans with a performance comparable to that of an experienced radiologist. Moreover, the algorithm reliably predicted clinically significant lesions at histopathologic examination. ClinicalTrials.gov Identifier: NCT03354416 © RSNA, 2024 Supplemental material is available for this article.

Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.

PURPOSE: Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans. METHODS: A deep learning algorithm based on 2D Pix-2-Pix generative adversarial network (GAN) architecture was developed from paired AC-PET and NAC-PET images. 18F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (n = 183, 60, 59, respectively). Models were trained with two normalization strategies: Standard Uptake Value (SUV)-based and SUV-Nyul-based. Scan-level performance was evaluated by normalized mean square error (NMSE), mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Lesion-level analysis was performed in regions-of-interest prospectively from nuclear medicine physicians. SUV metrics were evaluated using intraclass correlation coefficient (ICC), repeatability coefficient (RC), and linear mixed-effects modeling. RESULTS: Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUVmax and SUVmean were 0.88 and 0.89, which indicated a high correlation between original and AI-generated quantitative imaging markers. Lesion location, density (Hounsfield units), and lesion uptake were all shown to impact relative error in generated SUV metrics (all p < 0.05). CONCLUSION: The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.

Simulated Misuse of Large Language Models and Clinical Credit Systems.

Large language models (LLMs) have been proposed to support many healthcare tasks, including disease diagnostics and treatment personalization. While AI may be applied to assist or enhance the delivery of healthcare, there is also a risk of misuse. LLMs could be used to allocate resources based on unfair, inaccurate, or unjust criteria. For example, a social credit system uses big data to assess trustworthiness in society, punishing those who score poorly based on evaluation metrics defined only by a power structure (corporate entity, governing body). Such a system may be amplified by powerful LLMs which can rate individuals based on multimodal data - financial transactions, internet activity, and other behavioural inputs. Healthcare data is perhaps the most sensitive information which can be collected and could potentially be used to violate civil liberty via a clinical credit system, which may include limiting or rationing access to standard care. This report simulates how clinical datasets might be exploited and proposes strategies to mitigate the risks inherent to the development of AI models for healthcare.

Automated Detection and Grading of Extraprostatic Extension of Prostate Cancer at MRI via Cascaded Deep Learning and Random Forest Classification.

RATIONALE AND OBJECTIVES: Extraprostatic extension (EPE) is well established as a significant predictor of prostate cancer aggression and recurrence. Accurate EPE assessment prior to radical prostatectomy can impact surgical approach. We aimed to utilize a deep learning-based AI workflow for automated EPE grading from prostate T2W MRI, ADC map, and High B DWI. MATERIAL AND METHODS: An expert genitourinary radiologist conducted prospective clinical assessments of MRI scans for 634 patients and assigned risk for EPE using a grading technique. The training set and held-out independent test set consisted of 507 patients and 127 patients, respectively. Existing deep-learning AI models for prostate organ and lesion segmentation were leveraged to extract area and distance features for random forest classification models. Model performance was evaluated using balanced accuracy, ROC AUCs for each EPE grade, as well as sensitivity, specificity, and accuracy compared to EPE on histopathology. RESULTS: A balanced accuracy score of .390 ± 0.078 was achieved using a lesion detection probability threshold of 0.45 and distance features. Using the test set, ROC AUCs for AI-assigned EPE grades 0-3 were 0.70, 0.65, 0.68, and 0.55 respectively. When using EPE≥ 1 as the threshold for positive EPE, the model achieved a sensitivity of 0.67, specificity of 0.73, and accuracy of 0.72 compared to radiologist sensitivity of 0.81, specificity of 0.62, and accuracy of 0.66 using histopathology as the ground truth. CONCLUSION: Our AI workflow for assigning imaging-based EPE grades achieves an accuracy for predicting histologic EPE approaching that of physicians. This automated workflow has the potential to enhance physician decision-making for assessing the risk of EPE in patients undergoing treatment for prostate cancer due to its consistency and automation.

Timing, incidence and management of delayed bleeding after partial nephrectomy in patients at risk for recurrent, bilateral, multifocal renal tumors.

INTRODUCTION: Delayed bleeding is a potentially serious complication after partial nephrectomy (PN), with reported rates of 1%-2%. Patients with multiple renal tumors, including those with hereditary forms of kidney cancer, are often managed with resection of multiple tumors in a single kidney which may increase the risk of delayed bleeding, though outcomes have not previously been reported specifically in this population. The objective of this study was to evaluate the incidence and timing of delayed bleeding as well as the impact of intervention on renal functional outcomes in a cohort primarily made up of patients at risk for bilateral, multifocal renal tumors. METHODS: A retrospective review of a prospectively maintained database of patients with known or suspected predisposition to bilateral, multifocal renal tumors who underwent PN from 2003 to 2023 was conducted. Patients who presented with delayed bleeding were identified. Patients with delayed bleeding were compared to those without. Comparative statistics and univariate logistic regression were used to determine potential risk factors for delayed bleeding. RESULTS: A total of 1256 PN were performed during the study period. Angiographic evidence of pseudoaneurysm, AV fistula and/or extravasation occurred in 24 cases (1.9%). Of these, 21 were symptomatic presenting with gross hematuria in 13 (54.2%), decreasing hemoglobin in 4(16.7%), flank pain in 2(8.3%), and mental status change in 2 (8.3%), while 3 patients were asymptomatic. Median number of resected tumors was 5 (IQR 2-8). All patients underwent angiogram with super-selective embolization. Median time to bleed event was 13.5 days (IQR 7-22). Factors associated with delayed bleeding included open approach (OR 2.2, IQR(1.06-5.46), P = 0.04 and left-sided surgery (OR 4.93, IQR(1.67-14.5), P = 0.004. Selective embolization had little impact on ultimate renal functional outcomes, with a median change of 11% from the baseline eGFR after partial nephrectomy and embolization. One patient required total nephrectomy for refractory bleeding after embolization. CONCLUSIONS: Delayed bleeding after PN in a cohort of patients with multifocal tumors is an infrequent event, with similar rates to single tumor series. Patients should be counseled regarding timing and symptoms of delayed bleeding and multidisciplinary management with interventional radiology is critical for timely diagnosis and treatment.

Reducing False-Positives Due to Urinary Stagnation in the Prostatic Urethra on 18F-DCFPyL PSMA PET/CT With MRI.

PURPOSE: Prostate-specific membrane antigen (PSMA)-targeting PET radiotracers reveal physiologic uptake in the urinary system, potentially misrepresenting activity in the prostatic urethra as an intraprostatic lesion. This study examined the correlation between midline 18F-DCFPyL activity in the prostate and hyperintensity on T2-weighted (T2W) MRI as an indication of retained urine in the prostatic urethra. PATIENTS AND METHODS: Eighty-five patients who underwent both 18F-DCFPyL PSMA PET/CT and prostate MRI between July 2017 and September 2023 were retrospectively analyzed for midline radiotracer activity and retained urine on postvoid T2W MRIs. Fisher's exact tests and unpaired t tests were used to compare residual urine presence and prostatic urethra measurements between patients with and without midline radiotracer activity. The influence of anatomical factors including prostate volume and urethral curvature on urinary stagnation was also explored. RESULTS: Midline activity on PSMA PET imaging was seen in 14 patients included in the case group, whereas the remaining 71 with no midline activity constituted the control group. A total of 71.4% (10/14) and 29.6% (21/71) of patients in the case and control groups had urethral hyperintensity on T2W MRI, respectively (P < 0.01). Patients in the case group had significantly larger mean urethral dimensions, larger prostate volumes, and higher incidence of severe urethral curvature compared with the controls. CONCLUSIONS: Stagnated urine within the prostatic urethra is a potential confounding factor on PSMA PET scans. Integrating PET imaging with T2W MRI can mitigate false-positive calls, especially as PSMA PET/CT continues to gain traction in diagnosing localized prostate cancer.

Image-Guided Transbronchial Pulmonary Cryoablation with a Flexible Cryoprobe in Swine: Performance and Radiology-Pathology Correlation.

PURPOSE: To evaluate the performance of a prototype flexible transbronchial cryoprobe compared with that of percutaneous transthoracic cryoablation and to define cone-beam computed tomography (CT) imaging and pathology cryolesion features in an in vivo swine model. MATERIALS AND METHODS: Transbronchial cryoablation was performed with a prototype flexible cryoprobe (3 central and 3 peripheral lung ablations in 3 swine) and compared with transthoracic cryoablation performed with a commercially available rigid cryoprobe (2 peripheral lung ablations in 1 swine). Procedural time and cryoablation success rates for endobronchial navigation and cryoneedle deployment were measured. Intraoperative cone-beam CT imaging features of cryolesions were characterized and correlated with gross pathology and hematoxylin and eosin-stained sections of the explanted cryolesions. RESULTS: The flexible cryoprobe was successfully navigated and delivered to each target through a steerable guiding sheath (6/6). At 4 minutes after ablation, 5 of 6 transbronchial and 2 of 2 transthoracic cryolesions were visible on cone-beam CT. The volumes on cone-beam CT images were 55.5 cm3 (SE ± 8.0) for central transbronchial ablations (n = 2), 72.5 cm3 (SE ± 8.1) for peripheral transbronchial ablations (n = 3), and 79.5 cm3 (SE ±11.6) for peripheral transthoracic ablations (n = 2). Pneumothorax developed in 1 animal after transbronchial ablation and during ablation in the transthoracic cryoablation. Images of cryoablation zones on cone-beam CT correlated well with the matched gross pathology and histopathology sections of the cryolesions. CONCLUSIONS: Transbronchial cryoablation with a flexible cryoprobe, delivered through a steerable guiding sheath, is feasible. Transbronchial cryoablation zones are imageable with cone-beam CT, with gross pathology and histopathology similar to those of transthoracic cryoablation.

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods.

OBJECTIVE: Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters. MATERIALS AND METHODS: A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model. RESULTS: 683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001). CONCLUSION: Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.

X-ray imageable, drug-loaded hydrogel that forms at body temperature for image-guided, needle- based locoregional drug delivery.

Liver cancer ranks as the fifth leading cause of cancer-related death globally. Direct intratumoral injections of anti-cancer therapeutics may improve therapeutic efficacy and mitigate adverse effects compared to intravenous injections. Some challenges of intratumoral injections are that the liquid drug formulation may not remain localized and have unpredictable volumetric distribution. Thus, drug delivery varies widely, highly-dependent upon technique. An x-ray imageable poloxamer 407 (POL)-based drug delivery gel was developed and characterized, enabling real-time feedback. Utilizing three needle devices, POL or a control iodinated contrast solution were injected into an ex vivo bovine liver. The 3D distribution was assessed with cone beam computed tomography (CBCT). The 3D distribution of POL gels demonstrated localized spherical morphologies regardless of the injection rate. In addition, the gel 3D conformal distribution could be intentionally altered, depending on the injection technique. When doxorubicin (DOX) was loaded into the POL and injected, DOX distribution on optical imaging matched iodine distribution on CBCT suggesting spatial alignment of DOX and iodine localization in tissue. The controllability and localized deposition of this formulation may ultimately reduce the dependence on operator technique, reduce systemic side effects, and facilitate reproducibility across treatments, through more predictable standardized delivery.

Evaluating Diagnostic Accuracy and Inter-reader Agreement of the Prostate Imaging After Focal Ablation Scoring System.

Background and objective: Focal therapy (FT) is increasingly recognized as a promising approach for managing localized prostate cancer (PCa), notably reducing treatment-related morbidities. However, post-treatment anatomical changes present significant challenges for surveillance using current imaging techniques. This study aimed to evaluate the inter-reader agreement and efficacy of the Prostate Imaging after Focal Ablation (PI-FAB) scoring system in detecting clinically significant prostate cancer (csPCa) on post-FT multiparametric magnetic resonance imaging (mpMRI). Methods: A retrospective cohort study was conducted involving patients who underwent primary FT for localized csPCa between 2013 and 2023, followed by post-FT mpMRI and a prostate biopsy. Two expert genitourinary radiologists retrospectively evaluated post-FT mpMRI using PI-FAB. The key measures included inter-reader agreement of PI-FAB scores, assessed by quadratic weighted Cohen's kappa (κ), and the system's efficacy in predicting in-field recurrence of csPCa, with a PI-FAB score cutoff of 3. Additional diagnostic metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and overall accuracy were also evaluated. Key findings and limitations: Scans from 38 patients were analyzed, revealing a moderate level of agreement in PI-FAB scoring (κ = 0.56). Both radiologists achieved sensitivity of 93% in detecting csPCa, although specificity, PPVs, NPVs, and accuracy varied. Conclusions and clinical implications: The PI-FAB scoring system exhibited high sensitivity with moderate inter-reader agreement in detecting in-field recurrence of csPCa. Despite promising results, its low specificity and PPV necessitate further refinement. These findings underscore the need for larger studies to validate the clinical utility of PI-FAB, potentially aiding in standardizing post-treatment surveillance. Patient summary: Focal therapy has emerged as a promising approach for managing localized prostate cancer, but limitations in current imaging techniques present significant challenges for post-treatment surveillance. The Prostate Imaging after Focal Ablation (PI-FAB) scoring system showed high sensitivity for detecting in-field recurrence of clinically significant prostate cancer. However, its low specificity and positive predictive value necessitate further refinement. Larger, more comprehensive studies are needed to fully validate its clinical utility.

VB-111 (ofranergene obadenovec) in combination with nivolumab in patients with microsatellite stable colorectal liver metastases: a single center, single arm, phase II trial.

BACKGROUND: Microsatellite stable colorectal liver metastases (MSS CLM) maintain an immunosuppressive tumor microenvironment (TME). Historically, immune-based approaches have been ineffective. VB-111 (ofranergene obadenovec) is a genetically-modified adenoviral vector targeting the TME; its unique dual mechanism induces an immune response and disrupts neovascularization. Checkpoint inhibition may synergize the immune response induced by viral-mediated anti-angiogenic gene therapy. We aimed to examine the safety and antitumor activity of VB-111 and nivolumab in patients with refractory MSS CLM and to characterize immunological treatment-response. METHODS: This was a phase II study of adult patients with histologically-confirmed MSS CLM who progressed on prior therapy. A priming dose of VB-111 1×1013 viral particles was given intravenously 2 weeks prior to starting biweekly nivolumab 240 mg and continued every 6 weeks. The combination continued until disease progression or unacceptable toxicity. The primary objectives were overall response rate and safety/tolerability. Secondary objectives included median overall survival and progression-free survival. Correlative studies were performed on paired tumor biopsies and blood. RESULTS: Between August 2020 and December 2021, 14 patients were enrolled with median age 50.5 years (40-75), and 14% were women. Median follow-up was 5.5 months. Of the 10 evaluable patients, the combination of VB-111 and nivolumab failed to demonstrate radiographic responses; at best, 2 patients had stable disease. Median overall survival was 5.5 months (95% CI: 2.3 to 10.8), and median progression-free survival was 1.8 months (95% CI: 1.4 to 1.9). The most common grade 3-4 treatment-related adverse events were fever/chills, influenza-like symptoms, and lymphopenia. No treatment-related deaths were reported. Qualitative analysis of immunohistochemical staining of paired tumor biopsies did not demonstrate significant immune infiltration after treatment, except for one patient who had exceptional survival (26.0 months). Immune analysis of peripheral blood mononuclear cells showed an increase of PD-1highKi67highCD8+ T cells and HLA-DRhigh T cells after VB-111 priming dose. Plasma cytokines interleukin-10 and tumor necrosis factor-α increased after treatment with both drugs. CONCLUSION: In patients with MSS CLM, VB-111 and nivolumab did not improve overall response rate or survival but were tolerated with minimal toxicities. While challenging to distinguish between antiviral or antitumor, correlative studies demonstrated an immune response with activation and proliferation of CD8+ T cells systemically that was poorly sustained. TRIAL REGISTRATION NUMBER: NCT04166383.

Combined immune checkpoint inhibition with durvalumab and tremelimumab with and without radiofrequency ablation in patients with advanced biliary tract carcinoma.

BACKGROUND: Current standard of care for advanced biliary tract cancer (BTC) is gemcitabine, cisplatin plus anti-PD1/PD-L1, but response rates are modest. The purpose of this study was to explore the efficacy and safety of durvalumab (anti-PD-L1) and tremelimumab (anti-CTLA-4), with and without an interventional radiology (IR) procedure in advanced BTC. METHODS: Eligible patients with advanced BTC who had received or refused at least one prior line of systemic therapy were treated with tremelimumab and durvalumab for four combined doses followed by monthly durvalumab alone with and without an IR procedure until the progression of disease or unacceptable toxicity. Objective response was assessed through CT or MRI by Response Evaluation Criteria in Solid Tumors (RECIST, version 1.1) every 8 weeks. Adverse events (AEs) were recorded and managed. The primary endpoint was 6-month progression-free survival (PFS). RESULTS: Twenty-three patients with advanced BTC were enrolled; 17 patients were assigned to treatment with durvalumab and tremelimumab (Durva/Treme); and 6 patients were treated with the combination of durvalumab, tremelimumab plus IR procedure (Durva/Treme + IR). The best clinical responses in the Durva/Treme arm were partial response (n = 1), stable disease (n = 5), progressive disease (n = 5), and in the Durva/Treme + IR arm: partial response (n = 0), stable disease (n = 3), progressive disease (n = 3). The median PFS was 2.2 months (95% CI: 1.3-3.1 months) in the Durva/Treme arm and 2.9 months (95% CI: 1.9-4.7 months) in the Durva/Treme + IR arm (p = 0.27). The median OS was 5.1 months (95% CI: 2.5-6.9 months) in the Durva/Treme arm and 5.8 months (95% CI: 2.9-40.1 months) in the Durva/Treme + IR arm (p = 0.31). The majority of AEs were grades 1-2. CONCLUSION: Durva/Treme and Durva/Treme + IR showed similar efficacy. With a manageable safety profile. Larger studies are needed to fully characterize the efficacy of Durva/Treme ± IR in advanced BTC.

Deep Learning-Based Detection and Classification of Bone Lesions on Staging Computed Tomography in Prostate Cancer: A Development Study.

RATIONALE AND OBJECTIVES: Efficiently detecting and characterizing metastatic bone lesions on staging CT is crucial for prostate cancer (PCa) care. However, it demands significant expert time and additional imaging such as PET/CT. We aimed to develop an ensemble of two automated deep learning AI models for 1) bone lesion detection and segmentation and 2) benign vs. metastatic lesion classification on staging CTs and to compare its performance with radiologists. MATERIALS AND METHODS: This retrospective study developed two AI models using 297 staging CT scans (81 metastatic) with 4601 benign and 1911 metastatic lesions in PCa patients. Metastases were validated by follow-up scans, bone biopsy, or PET/CT. Segmentation AI (3DAISeg) was developed using the lesion contours delineated by a radiologist. 3DAISeg performance was evaluated with the Dice similarity coefficient, and classification AI (3DAIClass) performance on AI and radiologist contours was assessed with F1-score and accuracy. Training/validation/testing data partitions of 70:15:15 were used. A multi-reader study was performed with two junior and two senior radiologists within a subset of the testing dataset (n = 36). RESULTS: In 45 unseen staging CT scans (12 metastatic PCa) with 669 benign and 364 metastatic lesions, 3DAISeg detected 73.1% of metastatic (266/364) and 72.4% of benign lesions (484/669). Each scan averaged 12 extra segmentations (range: 1-31). All metastatic scans had at least one detected metastatic lesion, achieving a 100% patient-level detection. The mean Dice score for 3DAISeg was 0.53 (median: 0.59, range: 0-0.87). The F1 for 3DAIClass was 94.8% (radiologist contours) and 92.4% (3DAISeg contours), with a median false positive of 0 (range: 0-3). Using radiologist contours, 3DAIClass had PPV and NPV rates comparable to junior and senior radiologists: PPV (semi-automated approach AI 40.0% vs. Juniors 32.0% vs. Seniors 50.0%) and NPV (AI 96.2% vs. Juniors 95.7% vs. Seniors 91.9%). When using 3DAISeg, 3DAIClass mimicked junior radiologists in PPV (pure-AI 20.0% vs. Juniors 32.0% vs. Seniors 50.0%) but surpassed seniors in NPV (pure-AI 93.8% vs. Juniors 95.7% vs. Seniors 91.9%). CONCLUSION: Our lesion detection and classification AI model performs on par with junior and senior radiologists in discerning benign and metastatic lesions on staging CTs obtained for PCa.

Predicting 18F-DCFPyL-PET/CT Scan Positivity in Prostate Cancer Patients with Biochemical Recurrence.

RATIONALE AND OBJECTIVES: To analyze variables that can predict the positivity of 18F-DCFPyL- positron emission tomography/computed tomography (PET/CT) and extent of disease in patients with biochemically recurrent (BCR) prostate cancer after primary local therapy with either radical prostatectomy or radiation therapy. MATERIALS AND METHODS: This is a retrospective analysis of a prospective single institutional review board-approved study. We included 199 patients with biochemical recurrence and negative conventional imaging after primary local therapies (radical prostatectomy n = 127, radiation therapy n = 72). All patients underwent 18F-DCFPyL-PET/CT. Univariate and multivariate logistic regression analyses were used to determine predictors of a positive scan for both cohort of patients. Regression-based coefficients were used to develop nomograms predicting scan positivity and extra-pelvic disease. Decision curve analysis (DCA) was implemented to quantify nomogram's clinical benefit. RESULTS: Of the 127 (63%) post-radical prostatectomy patients, 91 patients had positive scans - 61 of those with intrapelvic lesions and 30 with extra-pelvic lesions (i.e., retroperitoneal or distant nodes and/or bone/organ lesions). Of the 72 post-radiation therapy patients, 65 patients had positive scans - 39 of them had intrapelvic lesions and 26 extra-pelvic lesions. In the radical prostatectomy cohort, multivariate regression analysis revealed original International Society of Urological Pathology category, prostate-specific antigen (PSA), prostate-specific antigen doubling time (PSAdt), and time from BCR (mo) to scan were predictors for scan positivity and presence of extra-pelvic disease, with an area under the curve of 80% and 78%, respectively. Positive versus negative tumor margin after radical prostatectomy was not related to scan positivity or to the presence of positive extra-pelvic foci. In the radiation therapy cohort, multivariate regression analysis revealed that PSA, PSAdt, and time to BCR (mo) were predictors of extra-pelvic disease, with area under the curve of 82%. Because only seven patients in the radiation therapy cohort had negative scans, a prediction model for scan positivity could not be analyzed and only the presence of extra-pelvic disease was evaluated. CONCLUSION: PSA and PSAdt are consistently significant predictors of 18F-DCFPyL PET/CT positivity and extra-pelvic disease in BCR prostate cancer patients. Stratifying the patient population into primary local treatment group enables the use of other variables as predictors, such as time since BCR. This nomogram may guide selection of the most suitable candidates for 18F-DCFPyL-PET/CT imaging.

PI-RADS Version 2.0 Versus Version 2.1: Comparison of Prostate Cancer Gleason Grade Upgrade and Downgrade Rates From MRI-Targeted Biopsy to Radical Prostatectomy.

BACKGROUND. Precise risk stratification through MRI/ultrasound (US) fusion-guided targeted biopsy (TBx) can guide optimal prostate cancer (PCa) management. OBJECTIVE. The purpose of this study was to compare PI-RADS version 2.0 (v2.0) and PI-RADS version 2.1 (v2.1) in terms of the rates of International Society of Urological Pathology (ISUP) grade group (GG) upgrade and downgrade from TBx to radical prostatectomy (RP). METHODS. This study entailed a retrospective post hoc analysis of patients who underwent 3-T prostate MRI at a single institution from May 2015 to March 2023 as part of three prospective clinical trials. Trial participants who underwent MRI followed by MRI/US fusion-guided TBx and RP within a 1-year interval were identified. A single genitourinary radiologist performed clinical interpretations of the MRI examinations using PI-RADS v2.0 from May 2015 to March 2019 and PI-RADS v2.1 from April 2019 to March 2023. Upgrade and downgrade rates from TBx to RP were compared using chi-square tests. Clinically significant cancer was defined as ISUP GG2 or greater. RESULTS. The final analysis included 308 patients (median age, 65 years; median PSA density, 0.16 ng/mL2). The v2.0 group (n = 177) and v2.1 group (n = 131) showed no significant difference in terms of upgrade rate (29% vs 22%, respectively; p = .15), downgrade rate (19% vs 21%, p = .76), clinically significant upgrade rate (14% vs 10%, p = .27), or clinically significant downgrade rate (1% vs 1%, p > .99). The upgrade rate and downgrade rate were also not significantly different between the v2.0 and v2.1 groups when stratifying by index lesion PI-RADS category or index lesion zone, as well as when assessed only in patients without a prior PCa diagnosis (all p > .01). Among patients with GG2 or GG3 at RP (n = 121 for v2.0; n = 103 for v2.1), the concordance rate between TBx and RP was not significantly different between the v2.0 and v2.1 groups (53% vs 57%, p = .51). CONCLUSION. Upgrade and downgrade rates from TBx to RP were not significantly different between patients whose MRI examinations were clinically interpreted using v2.0 or v2.1. CLINICAL IMPACT. Implementation of the most recent PI-RADS update did not improve the incongruence in PCa grade assessment between TBx and surgery.

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.

Deep Learning-Based Interpretable AI for Prostate T2W MRI Quality Evaluation.

RATIONALE AND OBJECTIVES: Prostate MRI quality is essential in guiding prostate biopsies. However, assessment of MRI quality is subjective with variation. Quality degradation sources exert varying impacts based on the sequence under consideration, such as T2W versus DWI. As a result, employing sequence-specific techniques for quality assessment could yield more advantageous outcomes. This study aims to develop an AI tool that offers a more consistent evaluation of T2W prostate MRI quality, efficiently identifying suboptimal scans while minimizing user bias. MATERIALS AND METHODS: This retrospective study included 1046 patients from three cohorts (ProstateX [n = 347], All-comer in-house [n = 602], enriched bad-quality MRI in-house [n = 97]) scanned between January 2011 and May 2022. An expert reader assigned T2W MRIs a quality score. A train-validation-test split of 70:15:15 was applied, ensuring equal distribution of MRI scanners and protocols across all partitions. T2W quality AI classification model was based on 3D DenseNet121 architecture using MONAI framework. In addition to multiclassification, binary classification was utilized (Classes 0/1 vs. 2). A score of 0 was given to scans considered non-diagnostic or unusable, a score of 1 was given to those with acceptable diagnostic quality with some usability but with some quality distortions present, and a score of 2 was given to those considered optimal diagnostic quality and usability. Partial occlusion sensitivity maps were generated for anatomical correlation. Three body radiologists assessed reproducibility within a subgroup of 60 test cases using weighted Cohen Kappa. RESULTS: The best validation multiclass accuracy of 77.1% (121/157) was achieved during training. In the test dataset, multiclassification accuracy was 73.9% (116/157), whereas binary accuracy was 84.7% (133/157). Sub-class sensitivity for binary quality distortion classification for class 0 was 100% (18/18), and sub-class specificity for T2W classification of absence/minimal quality distortions for class 2 was 90.5% (95/105). All three readers showed moderate to substantial agreement with ground truth (R1-R3 κ = 0.588, κ = 0.649, κ = 0.487, respectively), moderate to substantial agreement with each other (R1-R2 κ = 0.599, R1-R3 κ = 0.612, R2-R3 κ = 0.685), fair to moderate agreement with AI (R1-R3 κ = 0.445, κ = 0.410, κ = 0.292, respectively). AI showed substantial agreement with ground truth (κ = 0.704). 3D quality heatmap evaluation revealed that the most critical non-diagnostic quality imaging features from an AI perspective related to obscuration of the rectoprostatic space (94.4%, 17/18). CONCLUSION: The 3D AI model can assess T2W prostate MRI quality with moderate accuracy and translate whole sequence-level classification labels into 3D voxel-level quality heatmaps for interpretation. Image quality has a significant downstream impact on ruling out clinically significant cancers. AI may be able to help with reproducible identification of MRI sequences requiring re-acquisition with explainability.

A Review of Ultrasound-Mediated Checkpoint Inhibitor Immunotherapy.

Over the past decade, immunotherapy has emerged as a major modality in cancer medicine. However, despite its unprecedented success, immunotherapy currently benefits only a subgroup of patients, may induce responses of limited duration and is associated with potentially treatment-limiting side effects. In addition, responses to immunotherapeutics are sometimes diminished by the emergence of a complex array of resistance mechanisms. The efficacy of immunotherapy depends on dynamic interactions between tumour cells and the immune landscape in the tumour microenvironment. Ultrasound, especially in conjunction with cavitation-promoting agents such as microbubbles, can assist in the uptake and/or local release of immunotherapeutic agents at specific target sites, thereby increasing treatment efficacy and reducing systemic toxicity. There is also increasing evidence that ultrasound and/or cavitation may themselves directly stimulate a beneficial immune response. In this review, we summarize the latest developments in the use of ultrasound and cavitation agents to promote checkpoint inhibitor immunotherapy.

Quality of T2-weighted MRI re-acquisition versus deep learning GAN image reconstruction: A multi-reader study.

PURPOSE: To evaluate CycleGAN's ability to enhance T2-weighted image (T2WI) quality. METHOD: A CycleGAN algorithm was used to enhance T2WI quality. 96 patients (192 scans) were identified from patients who underwent multiple axial T2WI due to poor quality on the first attempt (RAD1) and improved quality on re-acquisition (RAD2). CycleGAN algorithm gave DL classifier scores (0-1) for quality quantification and produced enhanced versions of QI1 and QI2 from RAD1 and RAD2, respectively. A subset (n = 20 patients) was selected for a blinded, multi-reader study, where four radiologists rated T2WI on a scale of 1-4 for quality. The multi-reader study presented readers with 60 image pairs (RAD1 vs RAD2, RAD1 vs QI1, and RAD2 vs QI2), allowing for selecting sequence preferences and quantifying the quality changes. RESULTS: The DL classifier correctly discerned 71.9 % of quality classes, with 90.6 % (96/106) as poor quality and 48.8 % (42/86) as diagnostic in original sequences (RAD1, RAD2). CycleGAN images (QI1, QI2) demonstrated quantitative improvements, with consistently higher DL classifier scores than original scans (p < 0.001). In the multi-reader analysis, CycleGAN demonstrated no qualitative improvements, with diminished overall quality and motion in QI2 in most patients compared to RAD2, with noise levels remaining similar (8/20). No readers preferred QI2 to RAD2 for diagnosis. CONCLUSION: Despite quantitative enhancements with CycleGAN, there was no qualitative boost in T2WI diagnostic quality, noise, or motion. Expert radiologists didn't favor CycleGAN images over standard scans, highlighting the divide between quantitative and qualitative metrics.

C-DARL: Contrastive diffusion adversarial representation learning for label-free blood vessel segmentation.

Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine. Unfortunately, manual annotation of the vessel masks is challenging and resource-intensive due to subtle branches and complex structures. To overcome this issue, this paper presents a self-supervised vessel segmentation method, dubbed the contrastive diffusion adversarial representation learning (C-DARL) model. Our model is composed of a diffusion module and a generation module that learns the distribution of multi-domain blood vessel data by generating synthetic vessel images from diffusion latent. Moreover, we employ contrastive learning through a mask-based contrastive loss so that the model can learn more realistic vessel representations. To validate the efficacy, C-DARL is trained using various vessel datasets, including coronary angiograms, abdominal digital subtraction angiograms, and retinal imaging. Experimental results confirm that our model achieves performance improvement over baseline methods with noise robustness, suggesting the effectiveness of C-DARL for vessel segmentation.Our source code is available at https://github.com/boahK/MEDIA_CDARL.2.