Performance of O-RADS MRI Score in Differentiating Benign From Malignant Ovarian Teratomas: MR Feature Analysis for Differentiating O-RADS 4 From O-RADS 2.

OBJECTIVE: The aim of the study is to evaluate the performance of the ovarian-adnexal reporting and data system magnetic resonance imaging (O-RADS MRI) score and perform individual MRI feature analysis for differentiating between benign and malignant ovarian teratomas. METHODS: In this institutional review board-approved retrospective study, consecutive patients with a pathology-proven fat-containing ovarian mass imaged with contrast-enhanced MRI (1.5T or 3T) from 2013 to 2022 were included. Two blinded radiologists independently evaluated masses per the O-RADS MRI lexicon, including having a "characteristic" or "large" Rokitansky nodule (RN). Additional features analyzed included the following: nodule size/percentage volume relative to total teratoma volume, presence of bulk/intravoxel fat in the nodule, diffusion restriction in the nodule, angular interface, nodule extension through the teratoma border, presence/type of nodule enhancement pattern (solid versus peripheral), and evidence for metastatic disease. An overall O-RADS MRI score was assigned. Patient and lesion features associated with malignancy were evaluated and used to create a malignant teratoma score. χ2, Fisher's exact tests, receiver operating characteristic curve, and κ analysis was performed. RESULTS: One hundred thirty-seven women (median age 34, range 9-84 years) with 123 benign and 14 malignant lesions were included. Mean teratoma size was 7.3 cm (malignant: 14.4 cm, benign: 6.5 cm). 18/123 (14.6%) of benign teratomas were assigned an O-RADS 4 based on the presence of a "large" (11/18) or "noncharacteristic" (12/18) RN. 12/14 malignant nodules occupied >25% of the total teratoma volume (P = 0.09). Features associated with malignancy included the following: age <18 years, an enhancing noncharacteristic RN, teratoma size >12 cm, irregular cystic border, and extralesional extension; these were incorporated into a malignant teratoma score, with a score of 2 or more associated with area under the curve of 0.991 for reviewer 1 and 0.993 for reviewer 2. Peripheral enhancement in a RN was never seen with malignancy (64/123 benign, 0/14 malignant) and would have appropriated downgraded 9/18 overcalled O-RADS 4 benign teratomas. CONCLUSIONS: O-RADS MRI overcalled 15% (18/123) benign teratomas as O-RADS 4 but correctly captured all malignant teratomas. We propose defining a "characteristic" RN as an intravoxel or bulk fat-containing nodule. Observation of a peripheral rim of enhancement in a noncharacteristic RN allowed more accurate prediction of benignity and should be added to the MRI lexicon for improved O-RADS performance.

Utility of ADC Values for Differentiating Uterine Sarcomas From Leiomyomas: Systematic Review and Meta-Analysis.

Background: Uterine sarcomas are rare; however, they display imaging features that overlap those of leiomyomas. The potential for undetected uterine sarcomas is clinically relevant because minimally invasive treatment of leiomyomas may lead to cancer dissemination. ADC values have shown potential for differentiating benign and malignant uterine masses. Objective: The purpose of this study was to perform a systematic review of the diagnostic performance of ADC values in differentiating uterine sarcomas from leiomyomas. Evidence acquisition: We searched three electronic databases (MEDLINE, EMBASE, and Cochrane databases) for studies distinguishing uterine sarcomas from leiomyomas using MRI, including ADC, with pathologic tissue confirmation or imaging follow-up as the reference standard. Data extraction and QUADAS-2 quality assessment were performed. Sensitivity and specificity were pooled using hierarchic models, including bivariate and hierarchic summary ROC models. Metaregression was used to assess the impact of various factors on heterogeneity. Evidence synthesis: Twenty-one studies met study inclusion criteria. Pooled sensitivity and specificity were 89% (95% CI, 82-94%) and 86% (95% CI, 78-92%), respectively. Area under the summary ROC curve was 94% (95% CI, 92-96%). Context of ADC interpretation (i.e., standalone vs part of multiparametric MRI [mpMRI]) was the only factor found to account significantly for heterogeneity (p = .01). Higher specificity (95% [95% CI, 92-99%] vs 82% [95% CI, 75-89%]) and similar sensitivity (94% [95% CI, 89-99%] vs 88% [95% CI, 82-93%]) were observed when ADC was evaluated among mpMRI features as compared with standalone ADC assessment. ADC cutoff values ranged (0.87-1.29 × 10-3 mm2/s) but were not associated with statistically different performance (p = .37). Pooled mean ADC values in sarcomas and leiomyomas were 0.904 × 10-3 mm2/s and 1.287 × 10-3 mm2/s, respectively. Conclusion: As part of mpMRI evaluation of uterine masses, mass ADC value less than 0.904 × 10-3 mm2/s may be a useful test-positive threshold for uterine sarcoma, consistent with a prior expert consensus statement. Institutional protocols may influence locally selected ADC values. Clinical Impact: Using ADC as part of mpMRI assessment improves detection of uterine sarcoma, which could influence candidate selection for minimally invasive treatments.

FastMRI Prostate: A public, biparametric MRI dataset to advance machine learning for prostate cancer imaging.

Magnetic resonance imaging (MRI) has experienced remarkable advancements in the integration of artificial intelligence (AI) for image acquisition and reconstruction. The availability of raw k-space data is crucial for training AI models in such tasks, but public MRI datasets are mostly restricted to DICOM images only. To address this limitation, the fastMRI initiative released brain and knee k-space datasets, which have since seen vigorous use. In May 2023, fastMRI was expanded to include biparametric (T2- and diffusion-weighted) prostate MRI data from a clinical population. Biparametric MRI plays a vital role in the diagnosis and management of prostate cancer. Advances in imaging methods, such as reconstructing under-sampled data from accelerated acquisitions, can improve cost-effectiveness and accessibility of prostate MRI. Raw k-space data, reconstructed images and slice, volume and exam level annotations for likelihood of prostate cancer are provided in this dataset for 47468 slices corresponding to 1560 volumes from 312 patients. This dataset facilitates AI and algorithm development for prostate image reconstruction, with the ultimate goal of enhancing prostate cancer diagnosis.

Feasibility of Accelerated Prostate Diffusion-Weighted Imaging on 0.55 T MRI Enabled With Random Matrix Theory Denoising.

INTRODUCTION: Prostate cancer diffusion weighted imaging (DWI) MRI is typically performed at high-field strength (3.0 T) in order to overcome low signal-to-noise ratio (SNR). In this study, we demonstrate the feasibility of prostate DWI at low field enabled by random matrix theory (RMT)-based denoising, relying on the MP-PCA algorithm applied during image reconstruction from multiple coils. METHODS: Twenty-one volunteers and 2 prostate cancer patients were imaged with a 6-channel pelvic surface array coil and an 18-channel spine array on a prototype 0.55 T system created by ramping down a commercial magnetic resonance imaging system (1.5 T MAGNETOM Aera Siemens Healthcare) with 45 mT/m gradients and 200 T/m/s slew rate. Diffusion-weighted images were acquired with 4 non-collinear directions, for which b = 50 s/mm 2 was used with 8 averages and b = 1000 s/mm 2 with 40 averages; 2 extra b = 50 s/mm 2 were used as part of the dynamic field correction. Standard and RMT-based reconstructions were applied on DWI over different ranges of averages. Accuracy/precision was evaluated using the apparent diffusion coefficient (ADC), and image quality was evaluated over 5 separate reconstructions by 3 radiologists with a 5-point Likert scale. For the 2 patients, we compare image quality and lesion visibility of the RMT reconstruction versus the standard one on 0.55 T and on clinical 3.0 T. RESULTS: The RMT-based reconstruction in this study reduces the noise floor by a factor of 5.8, thereby alleviating the bias on prostate ADC. Moreover, the precision of the ADC in prostate tissue after RMT increases over a range of 30%-130%, with the increase in both signal-to-noise ratio and precision being more prominent for a low number of averages. Raters found that the images were consistently of moderate to good overall quality (3-4 on the Likert scale). Moreover, they determined that b = 1000 s/mm 2 images from a 1:55-minute scan with the RMT-based reconstruction were on par with the corresponding images from a 14:20-minute scan with standard reconstruction. Prostate cancer was visible on ADC and calculated b = 1500 images even with the abbreviated 1:55-minute scan reconstructed with RMT. CONCLUSIONS: Prostate imaging using DWI is feasible at low field and can be performed more rapidly with noninferior image quality compared with standard reconstruction.

FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging.

The fastMRI brain and knee dataset has enabled significant advances in exploring reconstruction methods for improving speed and image quality for Magnetic Resonance Imaging (MRI) via novel, clinically relevant reconstruction approaches. In this study, we describe the April 2023 expansion of the fastMRI dataset to include biparametric prostate MRI data acquired on a clinical population. The dataset consists of raw k-space and reconstructed images for T2-weighted and diffusion-weighted sequences along with slice-level labels that indicate the presence and grade of prostate cancer. As has been the case with fastMRI, increasing accessibility to raw prostate MRI data will further facilitate research in MR image reconstruction and evaluation with the larger goal of improving the utility of MRI for prostate cancer detection and evaluation. The dataset is available at https://fastmri.med.nyu.edu.

Comparison of a Deep Learning-Accelerated vs. Conventional T2-Weighted Sequence in Biparametric MRI of the Prostate.

BACKGROUND: Demand for prostate MRI is increasing, but scan times remain long even in abbreviated biparametric MRIs (bpMRI). Deep learning can be leveraged to accelerate T2-weighted imaging (T2WI). PURPOSE: To compare conventional bpMRIs (CL-bpMRI) with bpMRIs including a deep learning-accelerated T2WI (DL-bpMRI) in diagnosing prostate cancer. STUDY TYPE: Retrospective. POPULATION: Eighty consecutive men, mean age 66 years (47-84) with suspected prostate cancer or prostate cancer on active surveillance who had a prostate MRI from December 28, 2020 to April 28, 2021 were included. Follow-up included prostate biopsy or stability of prostate-specific antigen (PSA) for 1 year. FIELD STRENGTH AND SEQUENCES: A 3 T MRI. Conventional axial and coronal T2 turbo spin echo (CL-T2), 3-fold deep learning-accelerated axial and coronal T2-weighted sequence (DL-T2), diffusion weighted imaging (DWI) with b = 50 sec/mm2 , 1000 sec/mm2 , calculated b = 1500 sec/mm2 . ASSESSMENT: CL-bpMRI and DL-bpMRI including the same conventional diffusion-weighted imaging (DWI) were presented to three radiologists (blinded to acquisition method) and to a deep learning computer-assisted detection algorithm (DL-CAD). The readers evaluated image quality using a 4-point Likert scale (1 = nondiagnostic, 4 = excellent) and graded lesions using Prostate Imaging Reporting and Data System (PI-RADS) v2.1. DL-CAD identified and assigned lesions of PI-RADS 3 or greater. STATISTICAL TESTS: Quality metrics were compared using Wilcoxon signed rank test, and area under the receiver operating characteristic curve (AUC) were compared using Delong's test. SIGNIFICANCE: P = 0.05. RESULTS: Eighty men were included (age: 66 ± 9 years; 17/80 clinically significant prostate cancer). Overall image quality results by the three readers (CL-T2, DL-T2) are reader 1: 3.72 ± 0.53, 3.89 ± 0.39 (P = 0.99); reader 2: 3.33 ± 0.82, 3.31 ± 0.74 (P = 0.49); reader 3: 3.67 ± 0.63, 3.51 ± 0.62. In the patient-based analysis, the reader results of AUC are (CL-bpMRI, DL-bpMRI): reader 1: 0.77, 0.78 (P = 0.98), reader 2: 0.65, 0.66 (P = 0.99), reader 3: 0.57, 0.60 (P = 0.52). Diagnostic statistics from DL-CAD (CL-bpMRI, DL-bpMRI) are sensitivity (0.71, 0.71, P = 1.00), specificity (0.59, 0.44, P = 0.05), positive predictive value (0.23, 0.24, P = 0.25), negative predictive value (0.88, 0.88, P = 0.48). CONCLUSION: Deep learning-accelerated T2-weighted imaging may potentially be used to decrease acquisition time for bpMRI. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Automated deep-learning system in the assessment of MRI-visible prostate cancer: comparison of advanced zoomed diffusion-weighted imaging and conventional technique.

BACKGROUND: Deep-learning-based computer-aided diagnosis (DL-CAD) systems using MRI for prostate cancer (PCa) detection have demonstrated good performance. Nevertheless, DL-CAD systems are vulnerable to high heterogeneities in DWI, which can interfere with DL-CAD assessments and impair performance. This study aims to compare PCa detection of DL-CAD between zoomed-field-of-view echo-planar DWI (z-DWI) and full-field-of-view DWI (f-DWI) and find the risk factors affecting DL-CAD diagnostic efficiency. METHODS: This retrospective study enrolled 354 consecutive participants who underwent MRI including T2WI, f-DWI, and z-DWI because of clinically suspected PCa. A DL-CAD was used to compare the performance of f-DWI and z-DWI both on a patient level and lesion level. We used the area under the curve (AUC) of receiver operating characteristics analysis and alternative free-response receiver operating characteristics analysis to compare the performances of DL-CAD using f- DWI and z-DWI. The risk factors affecting the DL-CAD were analyzed using logistic regression analyses. P values less than 0.05 were considered statistically significant. RESULTS: DL-CAD with z-DWI had a significantly better overall accuracy than that with f-DWI both on patient level and lesion level (AUCpatient: 0.89 vs. 0.86; AUClesion: 0.86 vs. 0.76; P < .001). The contrast-to-noise ratio (CNR) of lesions in DWI was an independent risk factor of false positives (odds ratio [OR] = 1.12; P < .001). Rectal susceptibility artifacts, lesion diameter, and apparent diffusion coefficients (ADC) were independent risk factors of both false positives (ORrectal susceptibility artifact = 5.46; ORdiameter, = 1.12; ORADC = 0.998; all P < .001) and false negatives (ORrectal susceptibility artifact = 3.31; ORdiameter = 0.82; ORADC = 1.007; all P ≤ .03) of DL-CAD. CONCLUSIONS: Z-DWI has potential to improve the detection performance of a prostate MRI based DL-CAD. TRIAL REGISTRATION: ChiCTR, NO. ChiCTR2100041834 . Registered 7 January 2021.

A concurrent, deep learning-based computer-aided detection system for prostate multiparametric MRI: a performance study involving experienced and less-experienced radiologists.

OBJECTIVES: To evaluate the effect of a deep learning-based computer-aided diagnosis (DL-CAD) system on experienced and less-experienced radiologists in reading prostate mpMRI. METHODS: In this retrospective, multi-reader multi-case study, a consecutive set of 184 patients examined between 01/2018 and 08/2019 were enrolled. Ground truth was combined targeted and 12-core systematic transrectal ultrasound-guided biopsy. Four radiologists, two experienced and two less-experienced, evaluated each case twice, once without (DL-CAD-) and once assisted by DL-CAD (DL-CAD+). ROC analysis, sensitivities, specificities, PPV and NPV were calculated to compare the diagnostic accuracy for the diagnosis of prostate cancer (PCa) between the two groups (DL-CAD- vs. DL-CAD+). Spearman's correlation coefficients were evaluated to assess the relationship between PI-RADS category and Gleason score (GS). Also, the median reading times were compared for the two reading groups. RESULTS: In total, 172 patients were included in the final analysis. With DL-CAD assistance, the overall AUC of the less-experienced radiologists increased significantly from 0.66 to 0.80 (p = 0.001; cutoff ISUP GG ≥ 1) and from 0.68 to 0.80 (p = 0.002; cutoff ISUP GG ≥ 2). Experienced radiologists showed an AUC increase from 0.81 to 0.86 (p = 0.146; cutoff ISUP GG ≥ 1) and from 0.81 to 0.84 (p = 0.433; cutoff ISUP GG ≥ 2). Furthermore, the correlation between PI-RADS category and GS improved significantly in the DL-CAD + group (0.45 vs. 0.57; p = 0.03), while the median reading time was reduced from 157 to 150 s (p = 0.023). CONCLUSIONS: DL-CAD assistance increased the mean detection performance, with the most significant benefit for the less-experienced radiologist; with the help of DL-CAD less-experienced radiologists reached performances comparable to that of experienced radiologists. KEY POINTS: • DL-CAD used as a concurrent reading aid helps radiologists to distinguish between benign and cancerous lesions in prostate MRI. • With the help of DL-CAD, less-experienced radiologists may achieve detection performances comparable to that of experienced radiologists. • DL-CAD assistance increases the correlation between PI-RADS category and cancer grade.

Accelerated T2-weighted MRI of the liver at 3 T using a single-shot technique with deep learning-based image reconstruction: impact on the image quality and lesion detection.

PURPOSE: Fat-suppressed T2-weighted imaging (T2-FS) requires a long scan time and can be wrought with motion artifacts, urging the development of a shorter and more motion robust sequence. We compare the image quality of a single-shot T2-weighted MRI prototype with deep-learning-based image reconstruction (DL HASTE-FS) with a standard T2-FS sequence for 3 T liver MRI. METHODS: 41 consecutive patients with 3 T abdominal MRI examinations including standard T2-FS and DL HASTE-FS, between 5/6/2020 and 11/23/2020, comprised the study cohort. Three radiologists independently reviewed images using a 5-point Likert scale for artifact and image quality measures, while also assessing for liver lesions. RESULTS: DL HASTE-FS acquisition time was 54.93 ± 16.69, significantly (p < .001) shorter than standard T2-FS (114.00 ± 32.98 s). DL HASTE-FS received significantly higher scores for sharpness of liver margin (4.3 vs 3.3; p < .001), hepatic vessel margin (4.2 vs 3.3; p < .001), pancreatic duct margin (4.0 vs 1.9; p < .001); in-plane (4.0 vs 3.2; p < .001) and through-plane (3.9 vs 3.4; p < .001) motion artifacts; other ghosting artifacts (4.3 vs 2.9; p < .001); and overall image quality (4.0 vs 2.9; p < .001), in addition to receiving a higher score for homogeneity of fat suppression (3.7 vs 3.4; p = .04) and liver-fat contrast (p = .03). For liver lesions, DL HASTE-FS received significantly higher scores for sharpness of lesion margin (4.4 vs 3.7; p = .03). CONCLUSION: Novel single-shot T2-weighted MRI with deep-learning-based image reconstruction demonstrated superior image quality compared with the standard T2-FS sequence for 3 T liver MRI, while being acquired in less than half the time.

MR Imaging of Endometriosis of the Adnexa.

Endometriosis is the presence of ectopic endometrial glands outside of the uterus. MR imaging is particularly useful for characterizing deep infiltrating endometriosis but can also be useful in characterizing endometriomas and hematosalpinges, characterizing broad ligament deposits, assessing for endometriosis-associated malignancy, and differentiating malignancy from decidualized endometriomas. Masses and cysts with hemorrhagic or proteinaceous contents can sometimes be difficult to distinguish from endometriomas. Imaging protocols should include pre-contrast T1-weighted imaging with fat saturation, T2-weighted imaging without fat saturation, opposed- and in-phase or Dixon imaging, administration of contrast media, and subtraction imaging.

Axumin (18F-Fluciclovine) PET imaging in men exhibiting no clinically significant cancer on initial negative biopsy of PI-RADS 4 and 5 regions of interest.

PURPOSE: The objective of the study was to determine whether Axumin (18F-Fluciclovine) PET/MRI informs the decision to perform an early repeat biopsy of PI-RADS 4/5 region of interest (ROI) exhibiting no clinically significant prostate cancer (csPCa) on initial biopsy. METHODS: This prospective study enrolled men with at least one PI-RADS 4/5 ROI on multi-parametric MRI and no csPCa on prior biopsy defined as Gleason grade group (GGG) > 1. All men underwent an Axumin PET/MRI and only-persistent PI-RADS > 2 ROI were advised to undergo a repeat biopsy. A PET cancer suspicion score (PETCSS) was internally developed to stratify PET avid lesions according to their suspicion of harboring csPCa. The sensitivity, specificity, positive (PPV) and negative predictive value (NPV) of the PETCSS for predicting csPCa were assessed. Relative risk was calculated to analyze the association of baseline variables with csPCa on repeat biopsy. RESULTS: Thirty-eight ROI on 36 enrolled men were analyzed. Fourteen (36.8%) were downgraded to PI-RADS 1/2 and were not subjected to repeat biopsy. Thirteen (92.9%) of these downgraded scans also exhibited low-risk PETCSS. Overall, 18/22 (81.2%) subjects underwent a repeat per protocol biopsy. Of the 20 ROI subjected to repeat biopsy, eight (40%) were found to harbour csPCa. The sensitivity, specificity, PPV and NPV of the PETCSS were 50, 50, 40, and 60%, respectively. No predictor of csPCa was found in the risk analysis. CONCLUSION: Our pilot study showed that both MRI and PET sequences have limited performance for identifying those persistently suspicious PI-RADS 4/5 ROI that are found to harbor csPCa on repeat biopsy.

Safety of stereotactic body radiation therapy for localized prostate cancer without treatment planning MRI.

BACKGROUND: The use of treatment planning prostate MRI for Stereotactic Body Radiation Therapy (SBRT) is largely a standard, yet not all patients can receive MRI for a variety of clinical reasons. Thus, we aim to investigate the safety of patients who received CT alone based SBRT planning for the definitive treatment of localized prostate cancer. METHODS: Our study analyzed 3410 patients with localized prostate cancer who were treated with SBRT at a single academic institution between 2006 and 2020. Acute and late toxicity was evaluated using the Common Terminology Criteria for Adverse Events version 5.0. Expanded Prostate Cancer Index Composite (EPIC) questionnaires evaluated QOL and PSA nadir was evaluated to detect biochemical failures. RESULTS: A total of 162 patients (4.75%) received CT alone for treatment planning. The CT alone group was older relative to the MRI group (69.9 vs 67.2, p < 0.001) and had higher risk and grade disease (p < 0.001). Additionally, the CT group exhibited a trend in larger CTVs (82.56 cc vs 76.90 cc; p = 0.055), lower total radiation doses (p = 0.048), and more frequent pelvic nodal radiation versus the MRI group (p < 0.001). There were only two reported cases of Grade 3 + toxicity within the CT alone group. Quality of life data within the CT alone group revealed declines in urinary and bowel scores at one month with return to baseline at subsequent follow up. Early biochemical failure data at median time of 2.3 years revealed five failures by Phoenix definition. CONCLUSIONS: While clinical differences existed between the MRI and CT alone group, we observed tolerable toxicity profiles in the CT alone cohort, which was further supported by EPIC questionnaire data. The overall clinical outcomes appear comparable in patients unable to receive MRI for their SBRT treatment plan with early clinical follow up.

Comparison of Prostate Imaging and Reporting Data System V2.0 and V2.1 for Evaluation of Transition Zone Lesions: A 5-Reader 202-Patient Analysis.

OBJECTIVE: The aim of the study was to compare the distribution of Prostate Imaging and Reporting Data System (PI-RADS) scores, interreader agreement, and diagnostic performance of PI-RADS v2.0 and v2.1 for transition zone (TZ) lesions. METHODS: The study included 202 lesions in 202 patients who underwent 3T prostate magnetic resonance imaging showing a TZ lesion that was later biopsied with magnetic resonance imaging/ultrasound fusion. Five abdominal imaging faculty reviewed T2-weighted imaging and high b value/apparent diffusion coefficient images in 2 sessions. Cases were randomized using a crossover design whereby half in the first session were reviewed using v2.0 and the other half using v2.1, and vice versa for the 2nd session. Readers provided T2-weighted imaging and DWI scores, from which PI-RADS scores were derived. RESULTS: Interreader agreement for all PI-RADS scores had κ of 0.37 (v2.0) and 0.26 (v2.1). For 4 readers, the percentage of lesions retrospectively scored PI-RADS 1 increased greater than 5% and PI-RADS 2 score decreased greater than 5% from v2.0 to v2.1. For 2 readers, the percentage scored PI-RADS 3 decreased greater than 5% and, for 2 readers, increased greater than 5%. The percentage of PI-RADS 4 and 5 lesions changed less than 5% for all readers. For the 4 readers with increased frequency of PI-RADS 1 using v2.1, 4% to 16% were Gleason score ≥3 + 4 tumor. Frequency of Gleason score ≥3 + 4 in PI-RADS 3 lesions increased for 2 readers and decreased for 1 reader. Sensitivity of PI-RADS of 3 or greater for Gleason score ≥3 + 4 ranged 76% to 90% (v2.0) and 69% to 96% (v2.1). Specificity ranged 32% to 64% (v2.0) and 25% to 72% (v2.1). Positive predictive value ranged 43% to 55% (v2.0) and 41% to 58% (v2.1). Negative predictive value ranged 82% to 87% (v2.0) and 81% to 91% (v2.1). CONCLUSIONS: Poor interreader agreement and lack of improvement in diagnostic performance indicate an ongoing need to refine evaluation of TZ lesions.

Deep Learning Reconstruction Enables Highly Accelerated Biparametric MR Imaging of the Prostate.

BACKGROUND: Early diagnosis and treatment of prostate cancer (PCa) can be curative; however, prostate-specific antigen is a suboptimal screening test for clinically significant PCa. While prostate magnetic resonance imaging (MRI) has demonstrated value for the diagnosis of PCa, the acquisition time is too long for a first-line screening modality. PURPOSE: To accelerate prostate MRI exams, utilizing a variational network (VN) for image reconstruction. STUDY TYPE: Retrospective. SUBJECTS: One hundred and thirteen subjects (train/val/test: 70/13/30) undergoing prostate MRI. FIELD STRENGTH/SEQUENCE: 3.0 T; a T2 turbo spin echo (TSE) T2-weighted image (T2WI) sequence in axial and coronal planes, and axial echo-planar diffusion-weighted imaging (DWI). ASSESSMENT: Four abdominal radiologists evaluated the image quality of VN reconstructions of retrospectively under-sampled biparametric MRIs (bp-MRI), and standard bp-MRI reconstructions for 20 test subjects (studies). The studies included axial and coronal T2WI, DWI B50 seconds/mm2 and B1000 seconds/mm (4-fold T2WI, 3-fold DWI), all of which were evaluated separately for image quality on a Likert scale (1: non-diagnostic to 5: excellent quality). In another 10 test subjects, three readers graded lesions on bp-MRI-which additionally included calculated B1500 seconds/mm2 , and apparent diffusion coefficient map-according to the Prostate Imaging Reporting and Data System (PI-RADS v2.1), for both VN and standard reconstructions. Accuracy of PI-RADS ≥3 for clinically significant cancer was computed. Projected scan time of the retrospectively under-sampled biparametric exam was also computed. STATISTICAL TESTS: One-sided Wilcoxon signed-rank test was used for comparison of image quality. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for lesion detection and grading. Generalized estimating equation with cluster effect was used to compare differences between standard and VN bp-MRI. A P-value of <0.05 was considered statistically significant. RESULTS: Three of four readers rated no significant difference for overall quality between the standard and VN axial T2WI (Reader 1: 4.00 ± 0.56 (Standard), 3.90 ± 0.64 (VN) P = 0.33; Reader 2: 4.35 ± 0.74 (Standard), 3.80 ± 0.89 (VN) P = 0.003; Reader 3: 4.60 ± 0.50 (Standard), 4.55 ± 0.60 (VN) P = 0.39; Reader 4: 3.65 ± 0.99 (Standard), 3.60 ± 1.00 (VN) P = 0.38). All four readers rated no significant difference for overall quality between standard and VN DWI B1000 seconds/mm2 (Reader 1: 2.25 ± 0.62 (Standard), 2.45 ± 0.75 (VN) P = 0.96; Reader 2: 3.60 ± 0.92 (Standard), 3.55 ± 0.82 (VN) P = 0.40; Reader 3: 3.85 ± 0.72 (Standard), 3.55 ± 0.89 (VN) P = 0.07; Reader 4: 4.70 ± 0.76 (Standard); 4.60 ± 0.73 (VN) P = 0.17) and three of four readers rated no significant difference for overall quality between standard and VN DWI B50 seconds/mm2 (Reader 1: 3.20 ± 0.70 (Standard), 3.40 ± 0.75 (VN) P = 0.98; Reader 2: 2.85 ± 0.81 (Standard), 3.00 ± 0.79 (VN) P = 0.93; Reader 3: 4.45 ± 0.72 (Standard), 4.05 ± 0.69 (VN) P = 0.02; Reader 4: 4.50 ± 0.69 (Standard), 4.45 ± 0.76 (VN) P = 0.50). In the lesion evaluation study, there was no significant difference in the number of PI-RADS ≥3 lesions identified on standard vs. VN bp-MRI (P = 0.92, 0.59, 0.87) with similar sensitivity and specificity for clinically significant cancer. The average scan time of the standard clinical biparametric exam was 11.8 minutes, and this was projected to be 3.2 minutes for the accelerated exam. DATA CONCLUSION: Diagnostic accelerated biparametric prostate MRI exams can be performed using deep learning methods in <4 minutes, potentially enabling rapid screening prostate MRI. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 5.

Association of Sodium-Glucose Cotransporter-2 Inhibitors With Fracture Risk in Older Adults With Type 2 Diabetes.

Importance: Whether sodium-glucose cotransporter-2 inhibitors (SGLT-2i) are associated with an increased risk of fractures in older adults with type 2 diabetes (T2D) outside of clinical trials remains unknown. Objective: To examine the association of incident fracture among older adults with T2D with initiating an SGLT-2i compared with initiating a dipeptidyl peptidase 4 inhibitor (DPP-4i) or a glucagon-like peptide 1 receptor agonist (GLP-1RA). Design, Setting, and Participants: This is a population-based, new-user cohort study including older adults (aged ≥65 years) with T2D enrolled in Medicare fee-for-service from April 2013 to December 2017. Data analysis was performed from October 2020 to April 2021. Exposures: New users of an SGLT-2i, DPP-4i, or GLP-1RA without a previous fracture were matched in a 1:1:1 ratio using 3-way propensity score matching. Main Outcomes and Measures: The primary outcome was a composite end point of nontraumatic pelvic fracture, hip fracture requiring surgery, or humerus, radius, or ulna fracture requiring intervention within 30 days. After 3-way 1:1:1 propensity score matching, multivariable Cox proportional hazards regression models were used to generate hazard ratios (HRs) for SGLT-2i compared with DPP-4i and GLP-1RA and Kaplan-Meier curves to visualize fracture risk over time across groups. Results: Of 466 933 new initiators of study drugs, 62 454 patients were new SGLT-2i users. After 3-way matching, 45 889 (73%) new SGLT-2i users were matched to new users of DPP-4i and GLP-1RA, yielding a cohort of 137 667 patients (mean [SD] age, 72 [5] years; 64 126 men [47%]) matched 1:1:1 for analyses. There was no difference in the risk of fracture in SGLT-2i users compared with DPP-4i users (HR, 0.90; 95% CI, 0.73-1.11) or GLP-1RA users (HR, 1.00; 95% CI, 0.80-1.25). Results were consistent across categories of sex, frailty (nonfrail, prefrail, and frail), age (<75 and ≥75 years), and insulin use (baseline users and nonusers). Conclusions and Relevance: In this nationwide Medicare cohort, initiating an SGLT-2i was not associated with an increased risk of fracture in older adults with T2D compared with initiating a DPP-4i or GLP-1RA, with consistent results across categories of frailty, age, and insulin use. These findings add to the evidence base evaluating the potential risks associated with SGLT-2i use for older adults outside of randomized clinical trials.

Assessment of Renal Cell Carcinoma by Texture Analysis in Clinical Practice: A Six-Site, Six-Platform Analysis of Reliability.

BACKGROUND. Multiple commercial and open-source software applications are available for texture analysis. Nonstandard techniques can cause undesirable variability that impedes result reproducibility and limits clinical utility. OBJECTIVE. The purpose of this study is to measure agreement of texture metrics extracted by six software packages. METHODS. This retrospective study included 40 renal cell carcinomas with contrast-enhanced CT from The Cancer Genome Atlas and Imaging Archive. Images were analyzed by seven readers at six sites. Each reader used one of six software packages to extract commonly studied texture features. Inter- and intrareader agreement for segmentation was assessed with intraclass correlation coefficients (ICCs). First-order (available in six packages) and second-order (available in three packages) texture features were compared between software pairs using Pearson correlation. RESULTS. Inter- and intrareader agreement was excellent (ICC, 0.93-1). First-order feature correlations were strong (r ≥ 0.8, p < .001) between 75% (21/28) of software pairs for mean intensity and SD, 48% (10/21) for entropy, 29% (8/28) for skewness, and 25% (7/28) for kurtosis. Of 15 second-order features, only cooccurrence matrix correlation, gray-level nonuniformity, and run-length nonuniformity showed strong correlation between software packages (r = 0.90-1, p < .001). CONCLUSION. Variability in first- and second-order texture features was common across software configurations and produced inconsistent results. Standardized algorithms and reporting methods are needed before texture data can be reliably used for clinical applications. CLINICAL IMPACT. It is important to be aware of variability related to texture software processing and configuration when reporting and comparing outputs.

A Novel Deep Learning Based Computer-Aided Diagnosis System Improves the Accuracy and Efficiency of Radiologists in Reading Biparametric Magnetic Resonance Images of the Prostate: Results of a Multireader, Multicase Study.

OBJECTIVE: The aim of this study was to evaluate the effect of a deep learning based computer-aided diagnosis (DL-CAD) system on radiologists' interpretation accuracy and efficiency in reading biparametric prostate magnetic resonance imaging scans. MATERIALS AND METHODS: We selected 100 consecutive prostate magnetic resonance imaging cases from a publicly available data set (PROSTATEx Challenge) with and without histopathologically confirmed prostate cancer. Seven board-certified radiologists were tasked to read each case twice in 2 reading blocks (with and without the assistance of a DL-CAD), with a separation between the 2 reading sessions of at least 2 weeks. Reading tasks were to localize and classify lesions according to Prostate Imaging Reporting and Data System (PI-RADS) v2.0 and to assign a radiologist's level of suspicion score (scale from 1-5 in 0.5 increments; 1, benign; 5, malignant). Ground truth was established by consensus readings of 3 experienced radiologists. The detection performance (receiver operating characteristic curves), variability (Fleiss κ), and average reading time without DL-CAD assistance were evaluated. RESULTS: The average accuracy of radiologists in terms of area under the curve in detecting clinically significant cases (PI-RADS ≥4) was 0.84 (95% confidence interval [CI], 0.79-0.89), whereas the same using DL-CAD was 0.88 (95% CI, 0.83-0.94) with an improvement of 4.4% (95% CI, 1.1%-7.7%; P = 0.010). Interreader concordance (in terms of Fleiss κ) increased from 0.22 to 0.36 (P = 0.003). Accuracy of radiologists in detecting cases with PI-RADS ≥3 was improved by 2.9% (P = 0.10). The median reading time in the unaided/aided scenario was reduced by 21% from 103 to 81 seconds (P < 0.001). CONCLUSIONS: Using a DL-CAD system increased the diagnostic accuracy in detecting highly suspicious prostate lesions and reduced both the interreader variability and the reading time.

MRI predicts prostatic urethral involvement in men undergoing radical prostatectomy: implications for cryo-ablation of localized prostate cancer.

PURPOSE: To determine whether multi-parametric magnetic resonance imaging (mpMRI) can reliably predict proximity of prostate cancer to the prostatic urethra in a contemporary series of men undergoing radical prostatectomy (RP) at two academic centers. METHODS: Clinical characteristics of consecutive men undergoing pre-operative mpMRI prior to RP and whole-mount axial serial step-sectioned pathology examination at two academic centers between Jun 2016 and Oct 2018 were analyzed retrospectively. Every tumor was characterized by its pathologic minimum distance to the prostatic urethral lumen (pMDUL). Only the cancer closest to the urethra represented the prostatic urethral index lesion. The radiologic minimum distance of the index lesion to the prostatic urethral lumen was measured and noted as ≤ 5 mm versus > 5 mm. The sensitivity, specificity, positive and negative predicting values (PPV and NPV) and area under the receivers operating characteristics curve (AUC) were calculated for performance of mpMRI for predicting pMDUL ≤ 5 mm. RESULTS: Of the 163 surgical specimens examined, 112 (69%) exhibited a pMDUL ≤ 5 mm. These men had significantly higher grade group (GG) and advanced pathological and clinical stage. The rates of high PI-RADS score and presence of gross extracapsular extension were also significantly greater for the group with pMDUL ≤ 5 mm. The AUC, sensitivity, specificity, PPV, and NPV were 0.641, 51.8, 76.5, 82.9, and 42.4%, respectively, for mpMRI to predict pMDUL < 5 mm. CONCLUSIONS: Nearly 70% of men undergoing RP present with tumor within 5 mm of the prostatic urethra. These tumors present higher risk characteristics, and mpMRI exhibited moderate performance and high PPV in their pre-operative detection. Physicians performing partial gland ablation should take these results into consideration during treatment selection and planning.

Response assessment of hepatocellular carcinoma treated with yttrium-90 radioembolization: inter-reader variability, comparison with 3D quantitative approach, and role in the prediction of clinical outcomes.

OBJECTIVES: To assess the inter-reader variability in response assessment for HCC treated with radioembolization (TARE) compared with 3D quantitative criteria (qEASL); and to evaluate their role in prediction of pathological necrosis and clinical outcomes. MATERIALS AND METHODS: 57 patients with 77 HCCs who underwent TARE were included. Five radiologists recorded multiple imaging features and assigned mRECIST/LIRADS Treatment Response (TR) categories on post-treatment MRI at 4-6 weeks and 6-9 months after TARE. qEASL categories were assigned by a separate reader. Inter-reader variability between LIRADS TR/mRECIST/qEASL were evaluated and hazards regression was used in predicting clinical outcomes. RESULTS: Inter-reader agreement was fair for mRECIST (K = 0.43 and 0.34 at first and second follow-up respectively); moderate for LIRADS TR (K = 0.48 and 0.53 at first and second follow-up respectively). Inter-criterion agreement was moderate to substantial (r = 0.41-0.65 and r = 0.54-0.60 at first and second follow-up) for mRECIST-qEASL. LIRADS TR correlated well with qEASL for all readers at both follow-ups (K = 0.45-0.78; K = 0.39-0.77 for first and second follow-up). qEASL was the most accurate in predicting Tumor-Free Survival (TFS) on first (HR 2.23 [1.44-3.46], p < 0.001) and second (HR 1.69 [1.15-2.48], p = 0.008) follow-up. LIRADS TR was the most accurate in predicting histopathological necrosis (8 patients underwent liver transplantation and 1 patient underwent tumor resection during the period of the study). CONCLUSIONS: HCC response assessment following TARE is challenging, resulting in poor to moderate inter-reader agreement for mRECIST, and moderate inter-reader agreement for LIRADS TR response assessment criteria. qEASL outperformed mRECIST criteria for early identification of responders and predicting TFS, suggesting an advantage in volumetric tumor response assessment. LIRADS TR outperformed other criteria in predicting pathological necrosis.