Rationale for adopting a combination of monoparametric MRI with the prostate-specific antigen in detecting clinically significant prostate cancer: comparison with standard biparametric and multiparametric MRI.

OBJECTIVES: To compare prostate monoparametric MRI (monoMRI), which uses only diffusion-weighted imaging (DWI), with biparametric (bpMRI) and multiparametric MRI (mpMRI) in detecting clinically significant cancer (CSC) and to evaluate the effect of the combination of monoMRI results and prostate-specific antigen (PSA) level. METHODS: In this study, 193 patients (average age 70.5 years; average PSA 7.9 ng/mL) underwent prebiopsy MRI and subsequent prostate biopsy from January 2020 to February 2022. Two radiologists independently reviewed the 3 MRI protocols using the Prostate Imaging Reporting and Data System (PI-RADS). Interreader agreement was assessed using the intraclass correlation coefficient (ICC), and diagnostic performance was evaluated with receiver operating characteristic (ROC) curve analysis. The Youden index was used to determine the new cutoff value of PSA for detecting CSCs in patients with negative monoMRI results. RESULTS: CSC was confirmed in 109 patients (56.5%). The interreader agreement on monoMRI (ICC = 0.798) was comparable to that on bpMRI and mpMRI (ICC = 0.751 and 0.714, respectively). ROC curve analysis of the 3 protocols revealed no difference in detecting CSCs (P > 0.05). Applying a new PSA cutoff value (9.5 and 7.4 ng/mL, respectively) in monoMRI-negative patients improved the sensitivity of monoMRI from 89.9% to 96.3% for Reader 1, and from 95.4% to 99.1% for Reader 2. CONCLUSIONS: MonoMRI based solely on DWI demonstrated similar diagnostic performance to bpMRI and mpMRI in detecting CSCs, and the combination of PSA level with monoMRI has the potential to effectively triage patients with a high likelihood of CSCs. ADVANCES IN KNOWLEDGE: Monoparametric MRI conducted only with diffusion-weighted imaging (DWI), may show comparable performance to biparametric and multiparametric MRI in detecting clinically significant prostate cancer. In patients with negative monoparametric MRI results, implementing a new PSA cutoff value to determine the need for a biopsy could decrease the number of missed prostate cancer.

Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets.

Purpose To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. Materials and Methods This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. Results For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. Conclusion UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024.

External validation of an artificial intelligence model for Gleason grading of prostate cancer on prostatectomy specimens.

OBJECTIVES: To externally validate the performance of the DeepDx Prostate artificial intelligence (AI) algorithm (Deep Bio Inc., Seoul, South Korea) for Gleason grading on whole-mount prostate histopathology, considering potential variations observed when applying AI models trained on biopsy samples to radical prostatectomy (RP) specimens due to inherent differences in tissue representation and sample size. MATERIALS AND METHODS: The commercially available DeepDx Prostate AI algorithm is an automated Gleason grading system that was previously trained using 1133 prostate core biopsy images and validated on 700 biopsy images from two institutions. We assessed the AI algorithm's performance, which outputs Gleason patterns (3, 4, or 5), on 500 1-mm2 tiles created from 150 whole-mount RP specimens from a third institution. These patterns were then grouped into grade groups (GGs) for comparison with expert pathologist assessments. The reference standard was the International Society of Urological Pathology GG as established by two experienced uropathologists with a third expert to adjudicate discordant cases. We defined the main metric as the agreement with the reference standard, using Cohen's kappa. RESULTS: The agreement between the two experienced pathologists in determining GGs at the tile level had a quadratically weighted Cohen's kappa of 0.94. The agreement between the AI algorithm and the reference standard in differentiating cancerous vs non-cancerous tissue had an unweighted Cohen's kappa of 0.91. Additionally, the AI algorithm's agreement with the reference standard in classifying tiles into GGs had a quadratically weighted Cohen's kappa of 0.89. In distinguishing cancerous vs non-cancerous tissue, the AI algorithm achieved a sensitivity of 0.997 and specificity of 0.88; in classifying GG ≥2 vs GG 1 and non-cancerous tissue, it demonstrated a sensitivity of 0.98 and specificity of 0.85. CONCLUSION: The DeepDx Prostate AI algorithm had excellent agreement with expert uropathologists and performance in cancer identification and grading on RP specimens, despite being trained on biopsy specimens from an entirely different patient population.

Sex-specific survival gene mutations are discovered as clinical predictors of clear cell renal cell carcinoma.

Although sex differences have been reported in patients with clear cell renal cell carcinoma (ccRCC), biological sex has not received clinical attention and genetic differences between sexes are poorly understood. This study aims to identify sex-specific gene mutations and explore their clinical significance in ccRCC. We used data from The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma (TCGA-KIRC), The Renal Cell Cancer-European Union (RECA-EU) and Korean-KIRC. A total of 68 sex-related genes were selected from TCGA-KIRC through machine learning, and 23 sex-specific genes were identified through verification using the three databases. Survival differences according to sex were identified in nine genes (ACSS3, ALG13, ASXL3, BAP1, JADE3, KDM5C, KDM6A, NCOR1P1, and ZNF449). Female-specific survival differences were found in BAP1 in overall survival (OS) (TCGA-KIRC, p = 0.004; RECA-EU, p = 0.002; and Korean-KIRC, p = 0.003) and disease-free survival (DFS) (TCGA-KIRC, p = 0.001 and Korean-KIRC, p = 0.000004), and NCOR1P1 in DFS (TCGA-KIRC, p = 0.046 and RECA-EU, p = 0.00003). Male-specific survival differences were found in ASXL3 (OS, p = 0.017 in TCGA-KIRC; and OS, p = 0.005 in RECA-EU) and KDM5C (OS, p = 0.009 in RECA-EU; and DFS, p = 0.016 in Korean-KIRC). These results suggest that biological sex may be an important predictor and sex-specific tailored treatment may improve patient care in ccRCC.

Inter-reader Agreement for Prostate Cancer Detection Using Micro-ultrasound: A Multi-institutional Study.

Background and objective: Micro-ultrasound (MUS) uses a high-frequency transducer with superior resolution to conventional ultrasound, which may differentiate prostate cancer from normal tissue and thereby allow targeted biopsy. Preliminary evidence has shown comparable sensitivity to magnetic resonance imaging (MRI), but consistency between users has yet to be described. Our objective was to assess agreement of MUS interpretation across multiple readers. Methods: After institutional review board approval, we prospectively collected MUS images for 57 patients referred for prostate biopsy after multiparametric MRI from 2022 to 2023. MUS images were interpreted by six urologists at four institutions with varying experience (range 2-6 yr). Readers were blinded to MRI results and clinical data. The primary outcome was reader agreement on the locations of suspicious lesions, measured in terms of Light's κ and positive percent agreement (PPA). Reader sensitivity for identification of grade group (GG) ≥2 prostate cancer was a secondary outcome. Key findings and limitations: Analysis revealed a κ value of 0.30 (95% confidence interval [CI] 0.21-0.39). PPA was 33% (95% CI 25-42%). The mean patient-level sensitivity for GG ≥2 cancer was 0.66 ± 0.05 overall and 0.87 ± 0.09 when cases with anterior lesions were excluded. Readers were 12 times more likely to detect higher-grade cancers (GG ≥3), with higher levels of agreement for this subgroup (κ 0.41, PPA 45%). Key limitations include the inability to prospectively biopsy reader-delineated targets and the inability of readers to perform live transducer maneuvers. Conclusions and clinical implications: Inter-reader agreement on the location of suspicious lesions on MUS is lower than rates previously reported for MRI. MUS sensitivity for cancer in the anterior gland is lacking. Patient summary: The ability to find cancer on imaging scans can vary between doctors. We found that there was frequent disagreement on the location of prostate cancer when doctors were using a new high-resolution scan method called micro-ultrasound. This suggests that the performance of micro-ultrasound is not yet consistent enough to replace MRI (magnetic resonance imaging) for diagnosis of prostate cancer.

Assessment of Deep Learning-Based Triage Application for Acute Ischemic Stroke on Brain MRI in the ER.

RATIONALE AND OBJECTIVES: To assess a deep learning application (DLA) for acute ischemic stroke (AIS) detection on brain magnetic resonance imaging (MRI) in the emergency room (ER) and the effect of T2-weighted imaging (T2WI) on its performance. MATERIALS AND METHODS: We retrospectively analyzed brain MRIs taken through the ER from March to October 2021 that included diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) sequences. MRIs were processed by the DLA, and sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were evaluated, with three neuroradiologists establishing the gold standard for detection performance. In addition, we examined the impact of axial T2WI, when available, on the accuracy and processing time of DLA. RESULTS: The study included 947 individuals (mean age ± standard deviation, 64 years ± 16; 461 men, 486 women), with 239 (25%) positive for AIS. The overall performance of DLA was as follows: sensitivity, 90%; specificity, 89%; accuracy, 89%; and AUROC, 0.95. The average processing time was 24 s. In the subgroup with T2WI, T2WI did not significantly impact MRI assessments but did result in longer processing times (35 s without T2WI compared to 48 s with T2WI, p < 0.001). CONCLUSION: The DLA successfully identified AIS in the ER setting with an average processing time of 24 s. The absence of performance acquire with axial T2WI suggests that the DLA can diagnose AIS with just axial DWI and FLAIR sequences, potentially shortening the exam duration in the ER.

Discovery and Validation of Survival-Specific Genes in Papillary Renal Cell Carcinoma Using a Customized Next-Generation Sequencing Gene Panel.

PURPOSE: Papillary renal cell carcinoma (PRCC), the second most common kidney cancer, is morphologically, genetically, and molecularly heterogeneous with diverse clinical manifestations. Genetic variations of PRCC and their association with survival are not yet well-understood. This study aimed to identify and validate survival-specific genes in PRCC and explore their clinical utility. MATERIALS AND METHODS: Using machine learning, 293 patients from the Cancer Genome Atlas-Kidney Renal Papillary Cell Carcinoma (TCGA-KIRP) database were analyzed to derive genes associated with survival. To validate these genes, DNAs were extracted from the tissues of 60 Korean PRCC patients. Next generation sequencing was conducted using a customized PRCC gene panel of 202 genes, including 171 survival-specific genes. Kaplan-Meier and Log-rank tests were used for survival analysis. Fisher's exact test was performed to assess the clinical utility of variant genes. RESULTS: A total of 40 survival-specific genes were identified in the TCGA-KIRP database through machine learning and statistical analysis. Of them, 10 (BAP1, BRAF, CFDP1, EGFR, ITM2B, JAK1, NODAL, PCSK2, SPATA13, and SYT5) were validated in the Korean-KIRP database. Among these survival gene signatures, three genes (BAP1, PCSK2, and SPATA13) showed survival specificity in both overall survival (OS) (p = 0.00004, p = 1.38 × 10-7, and p = 0.026, respectively) and disease-free survival (DFS) (p = 0.00002, p = 1.21 × 10-7, and p = 0.036, respectively). Notably, the PCSK2 mutation demonstrated survival specificity uniquely in both the TCGA-KIRP (OS: p = 0.010 and DFS: p = 0.301) and Korean-KIRP (OS: p = 1.38 × 10-7 and DFS: p = 1.21 × 10-7) databases. CONCLUSIONS: We discovered and verified genes specific for the survival of PRCC patients in the TCGA-KIRP and Korean-KIRP databases. The survival gene signature, including PCSK2 commonly obtained from the 40 gene signature of TCGA and the 10 gene signature of the Korean database, is expected to provide insight into predicting the survival of PRCC patients and developing new treatment.

Deep Learning-Based Approach for Identifying and Measuring Focal Liver Lesions on Contrast-Enhanced MRI.

BACKGROUND: The number of focal liver lesions (FLLs) detected by imaging has increased worldwide, highlighting the need to develop a robust, objective system for automatically detecting FLLs. PURPOSE: To assess the performance of the deep learning-based artificial intelligence (AI) software in identifying and measuring lesions on contrast-enhanced magnetic resonance imaging (MRI) images in patients with FLLs. STUDY TYPE: Retrospective. SUBJECTS: 395 patients with 1149 FLLs. FIELD STRENGTH/SEQUENCE: The 1.5 T and 3 T scanners, including T1-, T2-, diffusion-weighted imaging, in/out-phase imaging, and dynamic contrast-enhanced imaging. ASSESSMENT: The diagnostic performance of AI, radiologist, and their combination was compared. Using 20 mm as the cut-off value, the lesions were divided into two groups, and then divided into four subgroups: <10, 10-20, 20-40, and ≥40 mm, to evaluate the sensitivity of radiologists and AI in the detection of lesions of different sizes. We compared the pathologic sizes of 122 surgically resected lesions with measurements obtained using AI and those made by radiologists. STATISTICAL TESTS: McNemar test, Bland-Altman analyses, Friedman test, Pearson's chi-squared test, Fisher's exact test, Dice coefficient, and intraclass correlation coefficients. A P-value <0.05 was considered statistically significant. RESULTS: The average Dice coefficient of AI in segmentation of liver lesions was 0.62. The combination of AI and radiologist outperformed the radiologist alone, with a significantly higher detection rate (0.894 vs. 0.825) and sensitivity (0.883 vs. 0.806). The AI showed significantly sensitivity than radiologists in detecting all lesions <20 mm (0.848 vs. 0.788). Both AI and radiologists achieved excellent detection performance for lesions ≥20 mm (0.867 vs. 0.881, P = 0.671). A remarkable agreement existed in the average tumor sizes among the three measurements (P = 0.174). DATA CONCLUSION: AI software based on deep learning exhibited practical value in automatically identifying and measuring liver lesions. TECHNICAL EFFICACY: Stage 2.

Advanced MRI techniques in abdominal imaging.

Magnetic resonance imaging (MRI) is a crucial modality for abdominal imaging evaluation of focal lesions and tissue properties. However, several obstacles, such as prolonged scan times, limitations in patients' breath-hold capacity, and contrast agent-associated artifacts, remain in abdominal MR images. Recent techniques, including parallel imaging, three-dimensional acquisition, compressed sensing, and deep learning, have been developed to reduce the scan time while ensuring acceptable image quality or to achieve higher resolution without extending the scan duration. Quantitative measurements using MRI techniques enable the noninvasive evaluation of specific materials. A comprehensive understanding of these advanced techniques is essential for accurate interpretation of MRI sequences. Herein, we therefore review advanced abdominal MRI techniques.

Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography.

Computed tomography (CT) has been used worldwide as a non-invasive test to assist in diagnosis. However, the ionizing nature of X-ray exposure raises concerns about potential health risks such as cancer. The desire for lower radiation doses has driven researchers to improve reconstruction quality. Although previous studies on low-dose computed tomography (LDCT) denoising have demonstrated the effectiveness of learning-based methods, most were developed on the simulated data. However, the real-world scenario differs significantly from the simulation domain, especially when using the multi-slice spiral scanner geometry. This paper proposes a two-stage method for the commercially available multi-slice spiral CT scanners that better exploits the complete reconstruction pipeline for LDCT denoising across different domains. Our approach makes good use of the high redundancy of multi-slice projections and the volumetric reconstructions while leveraging the over-smoothing issue in conventional cascaded frameworks caused by aggressive denoising. The dedicated design also provides a more explicit interpretation of the data flow. Extensive experiments on various datasets showed that the proposed method could remove up to 70% of noise without compromised spatial resolution, while subjective evaluations by two experienced radiologists further supported its superior performance against state-of-the-art methods in clinical practice. Code is available at https://github.com/YCL92/TMD-LDCT.

Comparison of non-contrast abbreviated MRI and ultrasound as surveillance modalities for HCC.

BACKGROUND & AIMS: Ultrasound (US) is recommended for HCC surveillance in high-risk patients but has limited performance in detecting early-stage HCC. We aimed to compare the diagnostic performance of biannual US and annual non-contrast abbreviated magnetic resonance imaging (NC-AMRI) as HCC surveillance modalities in high-risk patients. METHODS: This prospective, multicenter cohort study enrolled participants with an estimated annual risk of HCC greater than 5% between October 2015 and April 2017. Participants underwent six rounds of HCC surveillance at 6-month intervals, with both US and NC-AMRI at rounds 1, 3, and 5, and only US at rounds 2, 4, and 6. The sensitivity, diagnostic yield (DY), and false referral rate (FRR) for HCC detection by US and NC-AMRI were compared. RESULTS: In total, 208 participants underwent 980 US and 516 NC-AMRI examinations during 30 months of follow-up. Among them, 34 HCCs were diagnosed in 31 participants, with 20 (64.5%) classified as very early-stage and 11 (35.5%) as early-stage HCC. The sensitivity of annual NC-AMRI (71.0%, 22/31) was marginally higher than that of biannual US (45.2%, 14/31; p = 0.077). NC-AMRI showed a significantly higher DY than US (4.26% vs. 1.43%, p <0.001), with a similar FRR (2.91% vs. 3.06%, p = 0.885). A simulation of alternating US and NC-AMRI at 6-month intervals yielded a sensitivity of 83.9% (26/31), significantly exceeding that of biannual US (p = 0.006). CONCLUSIONS: Annual NC-AMRI showed a marginally higher sensitivity than biannual US for HCC detection in high-risk patients. The DY of annual NC-AMRI was significantly higher than that of biannual US, without increasing the FRR. Thus, alternating US and NC-AMRI at 6-month intervals could be an optimal surveillance strategy for high-risk patients. IMPACT AND IMPLICATIONS: Current guidelines permit the use of magnetic resonance imaging (MRI) as a surveillance tool for hepatocellular carcinoma in patients in whom ultrasonography (US) is inadequate. However, the specific indications, imaging sequences, and intervals for MRI surveillance remain unclear. In our study, we found that annual non-contrast abbreviated MRI exhibited marginally higher sensitivity and significantly better diagnostic yield than biannual US in patients at high risk of hepatocellular carcinoma. Alternating US and non-contrast abbreviated MRI at 6-month intervals led to significantly improved sensitivity compared to biannual US, making it a potentially optimal surveillance strategy for high-risk patients. GOV IDENTIFIER: NCT02551250.

Development and Validation of a Deep-Learning-Based Algorithm for Detecting and Classifying Metallic Implants in Abdominal and Spinal CT Topograms.

PURPOSE: To develop and validate a deep-learning-based algorithm (DLA) that is designed to segment and classify metallic objects in topograms of abdominal and spinal CT. METHODS: DLA training for implant segmentation and classification was based on a U-net-like architecture with 263 annotated hip implant topograms and 2127 annotated spine implant topograms. The trained DLA was validated with internal and external datasets. Two radiologists independently reviewed the external dataset consisting of 2178 abdomen anteroposterior (AP) topograms and 515 spine AP and lateral topograms, all collected in a consecutive manner. Sensitivity and specificity were calculated per pixel row and per patient. Pairwise intersection over union (IoU) was also calculated between the DLA and the two radiologists. RESULTS: The performance parameters of the DLA were consistently >95% in internal validation per pixel row and per patient. DLA can save 27.4% of reconstruction time on average in patients with metallic implants compared to the existing iMAR. The sensitivity and specificity of the DLA during external validation were greater than 90% for the detection of spine implants on three different topograms and for the detection of hip implants on abdominal AP and spinal AP topograms. The IoU was greater than 0.9 between the DLA and the radiologists. However, the DLA training could not be performed for hip implants on spine lateral topograms. CONCLUSIONS: A prototype DLA to detect metallic implants of the spine and hip on abdominal and spinal CT topograms improves the scan workflow with good performance for both spine and hip implants.

Rim enhancement of pancreatic ductal adenocarcinoma: investigating the relationship with DCE-MRI-based radiomics and next-generation sequencing.

Purpose: To identify the clinical and genetic variables associated with rim enhancement of pancreatic ductal adenocarcinoma (PDAC) and to develop a dynamic contrast-enhanced (DCE) MRI-based radiomics model for predicting the genetic status from next-generation sequencing (NGS). Materials and methods: Patients with PDAC, who underwent pretreatment pancreatic DCE-MRI between November 2019 and July 2021, were eligible in this prospective study. Two radiologists evaluated presence of rim enhancement in PDAC, a known radiological prognostic indicator, on DCE MRI. NGS was conducted for the tissue from the lesion. The Mann-Whitney U and Chi-square tests were employed to identify clinical and genetic variables associated with rim enhancement in PDAC. For continuous variables predicting rim enhancement, the cutoff value was set based on the Youden's index from the receiver operating characteristic (ROC) curve. Radiomics features were extracted from a volume-of-interest of PDAC on four DCE maps (Ktrans, Kep, Ve, and iAUC). A random forest (RF) model was constructed using 10 selected radiomics features from a pool of 392 original features. This model aimed to predict the status of significant NGS variables associated with rim enhancement. The performance of the model was validated using test set. Results: A total of 55 patients (32 men; median age 71 years) were randomly assigned to the training (n = 41) and test (n = 14) sets. In the training set, KRAS, TP53, CDKN2A, and SMAD4 mutation rates were 92.3%, 61.8%, 14.5%, and 9.1%, respectively. Tumor size and KRAS variant allele frequency (VAF) differed between rim-enhancing (n = 12) and nonrim-enhancing (n = 29) PDACs with a cutoff of 17.22%. The RF model's average AUC from 10-fold cross-validation for predicting KRAS VAF status was 0.698. In the test set comprising 6 tumors with low KRAS VAF and 8 with high KRAS VAF, the RF model's AUC reached 1.000, achieving a sensitivity of 75.0%, specificity of 100% and accuracy of 87.5%. Conclusion: Rim enhancement of PDAC is associated with KRAS VAF derived from NGS-based genetic information. For predicting the KRAS VAF status in PDAC, a radiomics model based on DCE maps showed promising results.

Low-dose versus conventional CT urography using dual-source CT with different time-current product values and the same tube voltage: image quality and diagnostic performance in various diagnoses.

OBJECTIVES: To compare the image quality and diagnostic performance of low-dose CT urography to that of concurrently acquired conventional CT using dual-source CT. METHODS: This retrospective study included 357 consecutive CT urograms performed by third-generation dual-source CT in a single institution between April 2020 and August 2021. Two-phase CT images (unenhanced phase, excretory phase with split bolus) were obtained with two different tube current-time products (280 mAs for the conventional-dose protocol and 70 mAs for the low-dose protocol) and the same tube voltage (90 kVp) for the two X-ray tubes. Iterative reconstruction was applied for both protocols. Two radiologists independently performed quantitative and qualitative image quality analysis and made diagnoses. The correlation between the noise level or the effective radiation dose and the patients' body weight was evaluated. RESULTS: Significantly higher noise levels resulting in a significantly lower liver signal-to-noise ratio and contrast-to-noise ratio were noted in low-dose images compared to conventional images (P < .001). Qualitative analysis by both radiologists showed significantly lower image quality in low-dose CT than in conventional CT images (P < .001). Patient's body weight was positively correlated with noise and effective radiation dose (P < .001). Diagnostic performance for various diseases, including urolithiasis, inflammation, and mass, was not different between the two protocols. CONCLUSIONS: Despite inferior image quality, low-dose CT urography with 70 mAs and 90 kVp and iterative reconstruction demonstrated diagnostic performance equivalent to that of conventional CT for identifying various diseases of the urinary tract. ADVANCES IN KNOWLEDGE: Low-dose CT (25% radiation dose) with low tube current demonstrated diagnostic performance comparable to that of conventional CT for a variety of urinary tract diseases.

Deep learning-accelerated T2-weighted imaging versus conventional T2-weighted imaging in the female pelvic cavity: image quality and diagnostic performance.

BACKGROUND: The deep learning (DL)-based reconstruction algorithm reduces noise in magnetic resonance imaging (MRI), thereby enabling faster MRI acquisition. PURPOSE: To compare the image quality and diagnostic performance of conventional turbo spin-echo (TSE) T2-weighted (T2W) imaging with DL-accelerated sagittal T2W imaging in the female pelvic cavity. METHODS: This study evaluated 149 consecutive female pelvic MRI examinations, including conventional T2W imaging with TSE (acquisition time = 2:59) and DL-accelerated T2W imaging with breath hold (DL-BH) (1:05 [0:14 × 3 breath-holds]) in the sagittal plane. In 294 randomly ordered sagittal T2W images, two radiologists independently assessed image quality (sharpness, subjective noise, artifacts, and overall image quality), made a diagnosis for uterine leiomyomas, and scored diagnostic confidence. For the uterus and piriformis muscle, quantitative imaging analysis was also performed. Wilcoxon signed rank tests were used to compare the two sets of T2W images. RESULTS: In the qualitative analysis, DL-BH showed similar or significantly higher scores for all features than conventional T2W imaging (P <0.05). In the quantitative analysis, the noise in the uterus was lower in DL-BH, but the noise in the muscle was lower in conventional T2W imaging. In the uterus and muscle, the signal-to-noise ratio was significantly lower in DL-BH than in conventional T2W imaging (P <0.001). The diagnostic performance of the two sets of T2W images was not different for uterine leiomyoma. CONCLUSIONS: DL-accelerated sagittal T2W imaging obtained with three breath-holds demonstrated superior or comparable image quality to conventional T2W imaging with no significant difference in diagnostic performance for uterine leiomyomas.

Automated classification of liver fibrosis stages using ultrasound imaging.

BACKGROUND: Ultrasound imaging is the most frequently performed for the patients with chronic hepatitis or liver cirrhosis. However, ultrasound imaging is highly operator dependent and interpretation of ultrasound images is subjective, thus well-trained radiologist is required for evaluation. Automated classification of liver fibrosis could alleviate the shortage of skilled radiologist especially in low-to-middle income countries. The purposed of this study is to evaluate deep convolutional neural networks (DCNNs) for classifying the degree of liver fibrosis according to the METAVIR score using US images. METHODS: We used ultrasound (US) images from two tertiary university hospitals. A total of 7920 US images from 933 patients were used for training/validation of DCNNs. All patient were underwent liver biopsy or hepatectomy, and liver fibrosis was categorized based on pathology results using the METAVIR score. Five well-established DCNNs (VGGNet, ResNet, DenseNet, EfficientNet and ViT) was implemented to predict the METAVIR score. The performance of DCNNs for five-level (F0/F1/F2/F3/F4) classification was evaluated through area under the receiver operating characteristic curve (AUC) with 95% confidential interval, accuracy, sensitivity, specificity, positive and negative likelihood ratio. RESULTS: Similar mean AUC values were achieved for five models; VGGNet (0.96), ResNet (0.96), DenseNet (0.95), EfficientNet (0.96), and ViT (0.95). The same mean accuracy (0.94) and specificity values (0.96) were yielded for all models. In terms of sensitivity, EffcientNet achieved highest mean value (0.85) while the other models produced slightly lower values range from 0.82 to 0.84. CONCLUSION: In this study, we demonstrated that DCNNs can classify the staging of liver fibrosis according to METAVIR score with high performance using conventional B-mode images. Among them, EfficientNET that have fewer parameters and computation cost produced highest performance. From the results, we believe that DCNNs based classification of liver fibrosis may allow fast and accurate diagnosis of liver fibrosis without needs of additional equipment for add-on test and may be powerful tool for supporting radiologists in clinical practice.

Quantitative Analysis of Prostate MRI: Correlation between Contrast-Enhanced Magnetic Resonance Fingerprinting and Dynamic Contrast-Enhanced MRI Parameters.

This research aimed to assess the relationship between contrast-enhanced (CE) magnetic resonance fingerprinting (MRF) values and dynamic contrast-enhanced (DCE) MRI parameters including (Ktrans, Kep, Ve, and iAUC). To evaluate the correlation between the MRF-derived values (T1 and T2 values, CE T1 and T2 values, T1 and T2 change) and DCE-MRI parameters and the differences in the parameters between prostate cancer and noncancer lesions in 68 patients, two radiologists independently drew regions-of-interest (ROIs) at the focal prostate lesions. Prostate cancer was identified in 75% (51/68) of patients. The CE T2 value was significantly lower in prostate cancer than in noncancer lesions in the peripheral zone and transition zone. Ktrans, Kep, and iAUC were significantly higher in prostate cancer than noncancer lesions in the peripheral zone (p < 0.05), but not in the transition zone. The CE T1 value was significantly correlated with Ktrans, Ve, and iAUC in prostate cancer, and the CE T2 value was correlated to Ve in noncancer. Some CE MRF values are different between prostate cancer and noncancer tissues and correlate with DCE-MRI parameters. Prostate cancer and noncancer tissues may have different characteristics regarding contrast enhancement.

Predicting resection margin status of pancreatic neuroendocrine tumors on CT: performance of NCCN resectability criteria.

OBJECTIVE: To test the performance of the National Comprehensive Cancer Network (NCCN) CT resectability criteria for predicting the surgical margin status of pancreatic neuroendocrine tumor (PNET) and to identify factors associated with margin-positive resection. METHODS: Eighty patients with pre-operative CT and upfront surgery were retrospectively enrolled. Two radiologists assessed the CT resectability (resectable [R], borderline resectable [BR], unresectable [UR]) of the PNET according to NCCN criteria. Logistic regression was used to identify factors associated with resection margin status. κ statistics were used to evaluate interreader agreements. Kaplan-Meier method with log-rank test was used to estimate and compare recurrence-free survival (RFS). RESULTS: Forty-five patients (56.2%) received R0 resection and 35 (43.8%) received R1 or R2 resection. R0 resection rates were 63.6-64.2%, 20.0-33.3%, and 0% for R, BR, and UR diseases, respectively (all p ≤ 0.002), with a good interreader agreement (κ, 0.74). Tumor size (<2 cm, 2-4 cm, and >4 cm; odds ratio (OR), 9.042-18.110; all p ≤ 0.007) and NCCN BR/UR diseases (OR, 5.918; p = 0.032) were predictors for R1 or R2 resection. The R0 resection rate was 91.7% for R disease <2 cm and decreased for larger R disease. R0 resection and smaller tumor size in R disease improved RFS. CONCLUSION: NCCN resectability criteria can stratify patients with PNET into distinct groups of R0 resectability. Adding tumor size to R disease substantially improves the prediction of R0 resection, especially for PNETs <2 cm. ADVANCES IN KNOWLEDGE: Tumor size and radiologic resectability independently predicted margin status of PNETs.

Differentiation of autoimmune pancreatitis from pancreatic adenocarcinoma using CT characteristics: a systematic review and meta-analysis.

OBJECTIVES: To determine informational CT findings for distinguishing autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC) and to review their diagnostic accuracy. METHODS: A systematic and detailed literature review was performed through PubMed, EMBASE, and the Cochrane library. Similar descriptors to embody the identical image finding were labeled as a single CT characteristic. We calculated the pooled diagnostic odds ratios (DORs) of each CT characteristic using a bivariate random-effects model. RESULTS: A total of 145 various descriptors from 15 studies (including 562 AIP and 869 PDAC patients) were categorized into 16 CT characteristics. According to the pooled DOR, 16 CT characteristics were classified into three groups (suggesting AIP, suggesting PDAC, and not informational). Seven characteristics suggesting AIP were diffuse pancreatic enlargement (DOR, 48), delayed homogeneous enhancement (DOR, 46), capsule-like rim (DOR, 34), multiple pancreatic masses (DOR, 16), renal involvement (DOR, 15), retroperitoneal fibrosis (DOR, 13), and bile duct involvement (DOR, 8). Delayed homogeneous enhancement showed a pooled sensitivity of 83% and specificity of 85%. The other six characteristics showed relatively low sensitivity (12-63%) but high specificity (93-99%). Four characteristics suggesting PDAC were discrete pancreatic mass (DOR, 23), pancreatic duct cutoff (DOR, 16), upstream main pancreatic duct dilatation (DOR, 8), and upstream parenchymal atrophy (DOR, 7). CONCLUSION: Eleven CT characteristics were informational to distinguish AIP from PDAC. Diffuse pancreatic enlargement, delayed homogeneous enhancement, and capsule-like rim suggested AIP with the highest DORs, whereas discrete pancreatic mass suggested PDAC. However, pooled sensitivities of informational CT characteristics were moderate. CLINICAL RELEVANCE STATEMENT: This meta-analysis underscores eleven distinctive CT characteristics that aid in differentiating autoimmune pancreatitis from pancreatic adenocarcinoma, potentially preventing misdiagnoses in patients presenting with focal/diffuse pancreatic enlargement. KEY POINTS: • Diffuse pancreatic enlargement (pooled diagnostic odds ratio [DOR], 48), delayed homogeneous enhancement (46), and capsule-like rim (34) were CT characteristics suggesting autoimmune pancreatitis. • The CT characteristics suggesting autoimmune pancreatitis, except delayed homogeneous enhancement, had a general tendency to show relatively low sensitivity (12-63%) but high specificity (93-99%). • Discrete pancreatic mass (pooled diagnostic odds ratio, 23) was the CT characteristic suggesting pancreatic ductal adenocarcinoma with the highest pooled DORs.

Imaging features of the PI-RADS for predicting extraprostatic extension of prostate cancer: systematic review and meta-analysis.

OBJECTIVES: To systematically determine the diagnostic performance of each MRI feature of the PI-RADS for predicting extraprostatic extension (EPE) in prostate cancer. METHODS: A literature search in the MEDLINE and EMBASE databases was conducted to identify original studies reporting the accuracy of each feature on MRI for the dichotomous diagnosis of EPE. The meta-analytic pooled diagnostic odds ratio (DOR), sensitivity, specificity, and their 95% confidence intervals (CIs) were obtained using a bivariate random-effects model. RESULTS: After screening 1955 studies, 17 studies with a total of 3062 men were included. All six imaging features, i.e., bulging prostatic contour, irregular or spiculated margin, asymmetry or invasion of neurovascular bundle, obliteration of rectoprostatic angle, tumor-capsule interface > 10 mm, and breach of the capsule with evidence of direct tumor extension, were significantly associated with EPE. Breach of the capsule with direct tumor extension demonstrated the highest pooled DOR (15.6, 95% CI [7.7-31.5]) followed by tumor-capsule interface > 10 mm (10.5 [5.4-20.2]), asymmetry or invasion of neurovascular bundle (7.6 [3.8-15.2]), and obliteration of rectoprostatic angle (6.1 [3.8-9.8]). Irregular or spiculated margin showed the lowest pooled DOR (2.3 [1.3-4.2]). Breach of the capsule with direct tumor extension and tumor-capsule interface > 10 mm showed the highest pooled specificity (98.0% [96.2-99.0]) and sensitivity (86.3% [70.0-94.4]), respectively. CONCLUSIONS: Among the six MRI features of prostate cancer, breach of the capsule with direct tumor extension and tumor-capsule interface > 10 mm were the most predictive of EPE with the highest specificity and sensitivity, respectively.