Prediction of upgrade to clinically significant prostate cancer in patients under active surveillance: Performance of a fully automated AI-algorithm for lesion detection and classification.

BACKGROUND: Multiparametric MRI (mpMRI) improves the detection of aggressive prostate cancer (PCa) subtypes. As cases of active surveillance (AS) increase and tumor progression triggers definitive treatment, we evaluated whether an AI-driven algorithm can detect clinically significant PCa (csPCa) in patients under AS. METHODS: Consecutive patients under AS who received mpMRI (PI-RADSv2.1 protocol) and subsequent MR-guided ultrasound fusion (targeted and extensive systematic) biopsy between 2017 and 2020 were retrospectively analyzed. Diagnostic performance of an automated clinically certified AI-driven algorithm was evaluated on both lesion and patient level regarding the detection of csPCa. RESULTS: Analysis of 56 patients resulted in 93 target lesions. Patient level sensitivity and specificity of the AI algorithm was 92.5%/31% for the detection of ISUP ≥ 1 and 96.4%/25% for the detection of ISUP ≥ 2, respectively. The only case of csPCa missed by the AI harbored only 1/47 Gleason 7a core (systematic biopsy; previous and subsequent biopsies rendered non-csPCa). CONCLUSIONS: AI-augmented lesion detection and PI-RADS scoring is a robust tool to detect progression to csPCa in patients under AS. Integration in the clinical workflow can serve as reassurance for the reader and streamline reporting, hence improve efficiency and diagnostic confidence.

Development of PSMA-PET-guided CT-based radiomic signature to predict biochemical recurrence after salvage radiotherapy.

PURPOSE: To develop a CT-based radiomic signature to predict biochemical recurrence (BCR) in prostate cancer patients after sRT guided by positron-emission tomography targeting prostate-specific membrane antigen (PSMA-PET). MATERIAL AND METHODS: Consecutive patients, who underwent 68Ga-PSMA11-PET/CT-guided sRT from three high-volume centers in Germany, were included in this retrospective multicenter study. Patients had PET-positive local recurrences and were treated with intensity-modulated sRT. Radiomic features were extracted from volumes of interests on CT guided by focal PSMA-PET uptakes. After preprocessing, clinical, radiomics, and combined clinical-radiomic models were developed combining different feature reduction techniques and Cox proportional hazard models within a nested cross validation approach. RESULTS: Among 99 patients, median interval until BCR was the radiomic models outperformed clinical models and combined clinical-radiomic models for prediction of BCR with a C-index of 0.71 compared to 0.53 and 0.63 in the test sets, respectively. In contrast to the other models, the radiomic model achieved significantly improved patient stratification in Kaplan-Meier analysis. The radiomic and clinical-radiomic model achieved a significantly better time-dependent net reclassification improvement index (0.392 and 0.762, respectively) compared to the clinical model. Decision curve analysis demonstrated a clinical net benefit for both models. Mean intensity was the most predictive radiomic feature. CONCLUSION: This is the first study to develop a PSMA-PET-guided CT-based radiomic model to predict BCR after sRT. The radiomic models outperformed clinical models and might contribute to guide personalized treatment decisions.

The Lodwick classification for grading growth rate of lytic bone tumors: a decision tree approach.

The estimation of growth rate of lytic bone tumors based on conventional radiography has been extensively studied. While benign tumors exhibit slow growth, malignant tumors are more likely to show fast growth. The most frequently used algorithm for grading of growth rate on conventional radiography was published by Gwilym Lodwick. Based on the evaluation of the four descriptors (1) type of bone destruction (including the subdescriptor "margin" for geographic lesions), (2) penetration of cortex, (3) presence of a sclerotic rim, and (4) expanded shell, an overall growth grade (IA, IB, IC, II, III) can be assigned, with higher grade representing faster tumor growth. In this article, we provide an easy-to-use decision tree of Lodwick's original grading algorithm, suitable for teaching of students and residents. Subtleties of the grading algorithm and potential pitfalls in clinical practice are explained and illustrated. Exemplary conventional radiographs provided for each descriptor in the decision tree may be used as a guide and atlas for assisting in evaluation of individual features in daily clinical practice.

Uncovering the invisible-prevalence, characteristics, and radiomics feature-based detection of visually undetectable intraprostatic tumor lesions in 68GaPSMA-11 PET images of patients with primary prostate cancer.

INTRODUCTION: Primary prostate cancer (PCa) can be visualized on prostate-specific membrane antigen positron emission tomography (PSMA-PET) with high accuracy. However, intraprostatic lesions may be missed by visual PSMA-PET interpretation. In this work, we quantified and characterized the intraprostatic lesions which have been missed by visual PSMA-PET image interpretation. In addition, we investigated whether PSMA-PET-derived radiomics features (RFs) could detect these lesions. METHODOLOGY: This study consists of two cohorts of primary PCa patients: a prospective training cohort (n = 20) and an external validation cohort (n = 52). All patients underwent 68Ga-PSMA-11 PET/CT and histology sections were obtained after surgery. PCa lesions missed by visual PET image interpretation were counted and their International Society of Urological Pathology score (ISUP) was obtained. Finally, 154 RFs were derived from the PET images and the discriminative power to differentiate between prostates with or without visually undetectable lesions was assessed and areas under the receiver-operating curve (ROC-AUC) as well as sensitivities/specificities were calculated. RESULTS: In the training cohort, visual PET image interpretation missed 134 tumor lesions in 60% (12/20) of the patients, and of these patients, 75% had clinically significant (ISUP > 1) PCa. The median diameter of the missed lesions was 2.2 mm (range: 1-6). Standard clinical parameters like the NCCN risk group were equally distributed between patients with and without visually missed lesions (p < 0.05). Two RFs (local binary pattern (LBP) size-zone non-uniformality normalized and LBP small-area emphasis) were found to perform excellently in visually unknown PCa detection (Mann-Whitney U: p < 0.01, ROC-AUC: ≥ 0.93). In the validation cohort, PCa was missed in 50% (26/52) of the patients and 77% of these patients possessed clinically significant PCa. The sensitivities of both RFs in the validation cohort were ≥ 0.8. CONCLUSION: Visual PSMA-PET image interpretation may miss small but clinically significant PCa in a relevant number of patients and RFs can be implemented to uncover them. This could be used for guiding personalized treatments.

Intraindividual comparison between 68Ga-PSMA-PET/CT and mpMRI for intraprostatic tumor delineation in patients with primary prostate cancer: a retrospective analysis in 101 patients.

PURPOSE: Accurate delineation of intraprostatic gross tumor volume (GTV) is mandatory for successful fusion biopsy guidance and focal therapy planning of prostate cancer (PCa). Multiparametric magnetic resonance imaging (mpMRI) is the current gold standard for GTV delineation; however, prostate-specific membrane antigen positron emission tomography (PSMA-PET) is emerging as a promising alternative. This study compares GTV delineation between mpMRI and 68Ga-PSMA-PET in a large number of patients using validated contouring approaches. METHODS: One hundred one patients with biopsy-proven primary PCa who underwent mpMRI and 68Ga-PSMA-PET within 3 months before primary treatment were retrospectively enrolled. Clinical parameters (age, PSA, Gleason score in biopsy) were documented. GTV based on MRI and PET images were delineated; volumes measured and laterality determined. Additionally, biopsy data from 77 patients was analyzed. Univariate and multivariate binary logistic regression analyses were performed using concordance in laterality as the endpoint. RESULTS: In total mpMRI and 68Ga-PSMA-PET detected 151 and 159 lesions, respectively. Median GTV-MRI (2.8 ml, 95% CI 2.31-3.38 ml) was significantly (p < 0.0001) smaller than median GTV-PET (4.9 ml, 95% CI 3.9-6.6 ml). 68Ga-PSMA-PET detected significantly more bilateral lesions than mpMRI (71 vs 57, p = 0.03). Analysis of patients with bilateral lesions in biopsy showed a significant higher concordance of laterality in 68Ga-PSMA-PET (p = 0.03). In univariate analysis, PSA level and volume of GTV-MRI had an impact on concordance in laterality (p = 0.02 and p = 0.01), whereas in multivariate analysis, only GTV-MRI volume remained significant (p = 0.04). CONCLUSION: MpMRI and 68Ga-PSMA-PET detect a similar amount of PCa lesions. However, GTV-PET had approximately twice the volume (median 4.9 ml vs 2.8 ml) and detected significantly more bilateral lesions than mpMRI. Thus, 68Ga-PSMA-PET gives highly important complementary information. Since we could not find any strong evidence for parameters to guide when 68Ga-PSMA-PET is dispensable, it should be performed additionally to MRI in patients with intermediate and high-risk PCa according to D'Amico classification to improve GTV delineation.

Development of an online, publicly accessible naive Bayesian decision support tool for mammographic mass lesions based on the American College of Radiology (ACR) BI-RADS lexicon.

PURPOSE: To develop and validate a decision support tool for mammographic mass lesions based on a standardized descriptor terminology (BI-RADS lexicon) to reduce variability of practice. MATERIALS AND METHODS: We used separate training data (1,276 lesions, 138 malignant) and validation data (1,177 lesions, 175 malignant). We created naïve Bayes (NB) classifiers from the training data with tenfold cross-validation. Our "inclusive model" comprised BI-RADS categories, BI-RADS descriptors, and age as predictive variables; our "descriptor model" comprised BI-RADS descriptors and age. The resulting NB classifiers were applied to the validation data. We evaluated and compared classifier performance with ROC-analysis. RESULTS: In the training data, the inclusive model yields an AUC of 0.959; the descriptor model yields an AUC of 0.910 (P < 0.001). The inclusive model is superior to the clinical performance (BI-RADS categories alone, P < 0.001); the descriptor model performs similarly. When applied to the validation data, the inclusive model yields an AUC of 0.935; the descriptor model yields an AUC of 0.876 (P < 0.001). Again, the inclusive model is superior to the clinical performance (P < 0.001); the descriptor model performs similarly. CONCLUSION: We consider our classifier a step towards a more uniform interpretation of combinations of BI-RADS descriptors. We provide our classifier at www.ebm-radiology.com/nbmm/index.html . KEY POINTS: • We provide a decision support tool for mammographic masses at www.ebm-radiology.com/nbmm/index.html . • Our tool may reduce variability of practice in BI-RADS category assignment. • A formal analysis of BI-RADS descriptors may enhance radiologists' diagnostic performance.

Ex Vivo Fluorescence Confocal Microscopy of MRI-Guided Targeted Prostate Biopsies for Rapid Detection of Clinically Significant Carcinomas-A Feasibility Study.

BACKGROUND: MRI-guided prostate biopsies from visible tumor-specific lesions (TBx) can be used to diagnose clinically significant carcinomas (csPCa) requiring treatment more selectively than conventional systematic biopsies (SBx). Ex vivo fluorescence confocal microscopy (FCM) is a novel technique that can be used to examine TBx prior to conventional histologic workup. METHODS: TBx from 150 patients were examined with FCM on the day of collection. Preliminary findings were reported within 2 h of collection. The results were statistically compared with the final histology. RESULTS: 27/40 (68%) of the csPCa were already recognized in the intraday FCM in accordance with the results of conventional histology. Even non-significant carcinomas (cisPCa) of the intermediate and high-risk groups (serum prostate-specific antigen (PSA) > 10 or 20 ng/mL) according to conventional risk stratifications were reliably detectable. In contrast, small foci of cisPCa were often not detected or were difficult to distinguish from reactive changes. CONCLUSION: The rapid reporting of preliminary FCM findings helps to reduce the psychological stress on patients, and can improve the clinical management of csPCa. Additional SBx can be avoided in individual cases, leading to lower rates of complications and scarring in the future surgical area. Additional staging examinations can be arranged without losing time. FCM represents a promising basis for future AI-based diagnostic algorithms.

Ultrashort VIBE-Dixon versus Cine and late gadolinium enhancement MRI sequences for cardiac thrombus detection.

PURPOSE: To determine the diagnostic accuracy of volumetric interpolated breath-hold examination sequences with fat suppression in Dixon technique (VIBE-Dixon) for cardiac thrombus detection. METHOD: From our clinical database, we retrospectively identified consecutive patients between 2014 and 2022 who had definite diagnosis or exclusion of cardiac thrombus confirmed by an independent adjudication committee, serving as the reference standard. All patients received 2D-Cine plus 2D-Late-Gadolinium-Enhancement (Cine + LGE) and VIBE-Dixon sequences. Two blinded readers assessed all images for the presence of cardiac thrombus. The diagnostic accuracy of Cine + LGE and VIBE-Dixon was determined and compared. RESULTS: Among 141 MRI studies (116 male, mean age: 61 years) mean image examination time was 28.8 ± 3.1 s for VIBE-Dixon and 23.3 ± 2.5 min for Cine + LGE. Cardiac thrombus was present in 49 patients (prevalence: 35 %). For both readers sensitivity for thrombus detection was significantly higher in VIBE-Dixon compared with Cine + LGE (Reader 1: 96 % vs.73 %, Reader 2: 96 % vs. 78 %, p < 0.01 for both readers), whereas specificity did not differ significantly (Reader 1: 96 % vs. 98 %, Reader 2: 92 % vs. 93 %, p > 0.1). Overall diagnostic accuracy of VIBE-Dixon was higher than for Cine + LGE (95 % vs. 89 %, p = 0.02) and was non-inferior to the reference standard (Delta ≤ 5 % with probability > 95 %). CONCLUSIONS: Biplanar VIBE-Dixon sequences, acquired within a few seconds, provided a very high diagnostic accuracy for cardiac thrombus detection. They could be used as stand-alone sequences to rapidly screen for cardiac thrombus in patients not amenable to lengthy acquisition times.

A Machine Learning Framework Reduces the Manual Workload for Systematic Reviews of the Diagnostic Performance of Prostate Magnetic Resonance Imaging.

Prostate magnetic resonance imaging has become the imaging standard for prostate cancer in various clinical settings, with interpretation standardized according to the Prostate Imaging Reporting and Data System (PI-RADS). Each year, hundreds of scientific studies that report on the diagnostic performance of PI-RADS are published. To keep up with this ever-increasing evidence base, systematic reviews and meta-analyses are essential. As systematic reviews are highly resource-intensive, we investigated whether a machine learning framework can reduce the manual workload and speed up the screening process (title and abstract). We used search results from a living systematic review of the diagnostic performance of PI-RADS (1585 studies, of which 482 were potentially eligible after screening). A naïve Bayesian classifier was implemented in an active learning environment for classification of the titles and abstracts. Our outcome variable was the percentage of studies that can be excluded after 95% of relevant studies have been identified by the classifier (work saved over sampling: WSS@95%). In simulation runs of the entire screening process (controlling for classifier initiation and the frequency of classifier updating), we obtained a WSS@95% value of 28% (standard error of the mean ±0.1%). Applied prospectively, our classification framework would translate into a significant reduction in manual screening effort. Patient summary: Systematic reviews of scientific evidence are labor-intensive and take a lot of time. For example, many studies on prostate cancer diagnosis via MRI (magnetic resonance imaging) are published every year. We describe the use of machine learning to reduce the manual workload in screening search results. For a review of MRI for prostate cancer diagnosis, this approach reduced the screening workload by about 28%.

Investigation and benchmarking of U-Nets on prostate segmentation tasks.

In healthcare, a growing number of physicians and support staff are striving to facilitate personalized radiotherapy regimens for patients with prostate cancer. This is because individual patient biology is unique, and employing a single approach for all is inefficient. A crucial step for customizing radiotherapy planning and gaining fundamental information about the disease, is the identification and delineation of targeted structures. However, accurate biomedical image segmentation is time-consuming, requires considerable experience and is prone to observer variability. In the past decade, the use of deep learning models has significantly increased in the field of medical image segmentation. At present, a vast number of anatomical structures can be demarcated on a clinician's level with deep learning models. These models would not only unload work, but they can offer unbiased characterization of the disease. The main architectures used in segmentation are the U-Net and its variants, that exhibit outstanding performances. However, reproducing results or directly comparing methods is often limited by closed source of data and the large heterogeneity among medical images. With this in mind, our intention is to provide a reliable source for assessing deep learning models. As an example, we chose the challenging task of delineating the prostate gland in multi-modal images. First, this paper provides a comprehensive review of current state-of-the-art convolutional neural networks for 3D prostate segmentation. Second, utilizing public and in-house CT and MR datasets of varying properties, we created a framework for an objective comparison of automatic prostate segmentation algorithms. The framework was used for rigorous evaluations of the models, highlighting their strengths and weaknesses.

Enhancing Radiation Dose Efficiency in Prospective ECG-Triggered Coronary CT Angiography Using Calcium-Scoring CT.

BACKGROUND: This study investigates whether the scan length adjustment of prospectively ECG-triggered coronary CT angiography (CCTA) using calcium-scoring CT (CAS-CT) images can reduce overall radiation doses. METHODS: A retrospective analysis was conducted on 182 patients who underwent CAS-CT and prospectively ECG-triggered CCTA using a second-generation Dual-Source CT scanner. CCTA planning was based on CAS-CT images, for which simulated scout view planning was performed for comparison. Effective doses were compared between two scenarios: Scenario 1-CAS-CT-derived CCTA + CAS-CT and Scenario 2-scout-view-derived CCTA without CAS-CT. Dose differences were further analyzed with respect to scan mode and body mass index. RESULTS: Planning CCTA using CAS-CT led to a shorter scan length than planning via scout view (114.3 ± 9.7 mm vs. 133.7 ± 13.2 mm, p < 0.001). The whole-examination effective dose was slightly lower for Scenario 1 (3.2 [1.8-5.3] mSv vs. 3.4 [1.5-5.9] mSv; p < 0.001, n = 182). Notably, Scenario 1 resulted in a significantly lower radiation dose for sequential scans and obese patients. Only high-pitch spiral CCTA showed dose reduction in Scenario 2. CONCLUSIONS: Using CAS-CT for planning prospectively ECG-triggered CCTA reduced the overall radiation dose administered compared to scout view planning without CAS-CT, except for high-pitch spiral CCTA, where a slightly opposite effect was observed.

Accelerated Diffusion-Weighted Imaging in 3 T Breast MRI Using a Deep Learning Reconstruction Algorithm With Superresolution Processing: A Prospective Comparative Study.

OBJECTIVES: Diffusion-weighted imaging (DWI) enhances specificity in multiparametric breast MRI but is associated with longer acquisition time. Deep learning (DL) reconstruction may significantly shorten acquisition time and improve spatial resolution. In this prospective study, we evaluated acquisition time and image quality of a DL-accelerated DWI sequence with superresolution processing (DWI DL ) in comparison to standard imaging including analysis of lesion conspicuity and contrast of invasive breast cancers (IBCs), benign lesions (BEs), and cysts. MATERIALS AND METHODS: This institutional review board-approved prospective monocentric study enrolled participants who underwent 3 T breast MRI between August and December 2022. Standard DWI (DWI STD ; single-shot echo-planar DWI combined with reduced field-of-view excitation; b-values: 50 and 800 s/mm 2 ) was followed by DWI DL with similar acquisition parameters and reduced averages. Quantitative image quality was analyzed for region of interest-based signal-to-noise ratio (SNR) on breast tissue. Apparent diffusion coefficient (ADC), SNR, contrast-to-noise ratio, and contrast (C) values were calculated for biopsy-proven IBCs, BEs, and for cysts. Two radiologists independently assessed image quality, artifacts, and lesion conspicuity in a blinded independent manner. Univariate analysis was performed to test differences and interrater reliability. RESULTS: Among 65 participants (54 ± 13 years, 64 women) enrolled in the study, the prevalence of breast cancer was 23%. Average acquisition time was 5:02 minutes for DWI STD and 2:44 minutes for DWI DL ( P < 0.001). Signal-to-noise ratio measured in breast tissue was higher for DWI STD ( P < 0.001). The mean ADC values for IBC were 0.77 × 10 -3 ± 0.13 mm 2 /s in DWI STD and 0.75 × 10 -3 ± 0.12 mm 2 /s in DWI DL without significant difference when sequences were compared ( P = 0.32). Benign lesions presented with mean ADC values of 1.32 × 10 -3 ± 0.48 mm 2 /s in DWI STD and 1.39 × 10 -3 ± 0.54 mm 2 /s in DWI DL ( P = 0.12), and cysts presented with 2.18 × 10 -3 ± 0.49 mm 2 /s in DWI STD and 2.31 × 10 -3 ± 0.43 mm 2 /s in DWI DL . All lesions presented with significantly higher contrast in the DWI DL ( P < 0.001), whereas SNR and contrast-to-noise ratio did not differ significantly between DWI STD and DWI DL regardless of lesion type. Both sequences demonstrated a high subjective image quality (29/65 for DWI STD vs 20/65 for DWI DL ; P < 0.001). The highest lesion conspicuity score was observed more often for DWI DL ( P < 0.001) for all lesion types. Artifacts were scored higher for DWI DL ( P < 0.001). In general, no additional artifacts were noted in DWI DL . Interrater reliability was substantial to excellent (k = 0.68 to 1.0). CONCLUSIONS: DWI DL in breast MRI significantly reduced scan time by nearly one half while improving lesion conspicuity and maintaining overall image quality in a prospective clinical cohort.

Multiparametric magnetic resonance imaging for radiation therapy response monitoring in soft tissue sarcomas: a histology and MRI co-registration algorithm.

Rationale: To establish a spatially exact co-registration procedure between in vivo multiparametric magnetic resonance imaging (mpMRI) and (immuno)histopathology of soft tissue sarcomas (STS) to identify imaging parameters that reflect radiation therapy response of STS. Methods: The mpMRI-Protocol included diffusion-weighted (DWI), intravoxel-incoherent motion (IVIM), and dynamic contrast-enhancing (DCE) imaging. The resection specimen was embedded in 6.5% agarose after initial fixation in formalin. To ensure identical alignment of histopathological sectioning and in vivo imaging, an ex vivo MRI scan of the specimen was rigidly co-registered with the in vivo mpMRI. The deviating angulation of the specimen to the in vivo location of the tumor was determined. The agarose block was trimmed accordingly. A second ex vivo MRI in a dedicated localizer with a 4 mm grid was performed, which was matched to a custom-built sectioning machine. Microtomy sections were stained with hematoxylin and eosin. Immunohistochemical staining was performed with anti-ALDH1A1 antibodies as a radioresistance and anti-MIB1 antibodies as a proliferation marker. Fusion of the digitized microtomy sections with the in vivo mpMRI was accomplished through nonrigid co-registration to the in vivo mpMRI. Co-registration accuracy was qualitatively assessed by visual assessment and quantitatively evaluated by computing target registration errors (TRE). Results: The study sample comprised nine tumor sections from three STS patients. Visual assessment after nonrigid co-registration showed a strong morphological correlation of the histopathological specimens with ex vivo MRI and in vivo mpMRI after neoadjuvant radiation therapy. Quantitative assessment of the co-registration procedure using TRE analysis of different pairs of pathology and MRI sections revealed highly accurate structural alignment, with a total median TRE of 2.25 mm (histology - ex vivo MRI), 2.22 mm (histology - in vivo mpMRI), and 2.02 mm (ex vivo MRI - in vivo mpMRI). There was no significant difference between TREs of the different pairs of sections or caudal, middle, and cranial tumor parts, respectively. Conclusion: Our initial results show a promising approach to obtaining accurate co-registration between histopathology and in vivo MRI for STS. In a larger cohort of patients, the method established here will enable the prospective identification and validation of in vivo imaging biomarkers for radiation therapy response prediction and monitoring in STS patients via precise molecular and cellular correlation.

Living systematic review and meta-analysis of the prostate MRI diagnostic test with Prostate Imaging Reporting and Data System (PI-RADS) assessment for the detection of prostate cancer: study protocol.

INTRODUCTION: The Prostate Imaging Reporting and Data System (PI-RADS) standardises reporting of prostate MRI for the detection of clinically significant prostate cancer. We provide the protocol of a planned living systematic review and meta-analysis for (1) diagnostic accuracy (sensitivity and specificity), (2) cancer detection rates of assessment categories and (3) inter-reader agreement. METHODS AND ANALYSIS: Retrospective and prospective studies reporting on at least one of the outcomes of interest are included. Each step that requires literature evaluation and data extraction is performed by two independent reviewers. Since PI-RADS is intended as a living document itself, a 12-month update cycle of the systematic review and meta-analysis is planned.This protocol is in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses-Protocols statement. The search strategies including databases, study eligibility criteria, index and reference test definitions, outcome definitions and data analysis processes are detailed. A full list of extracted data items is provided.Summary estimates of sensitivity and specificity (for PI-RADS ≥3 and PI-RADS ≥4 considered positive) are derived with bivariate binomial models. Summary estimates of cancer detection rates are calculated with random intercept logistic regression models for single proportions. Summary estimates of inter-reader agreement are derived with random effects models. ETHICS AND DISSEMINATION: No original patient data are collected, ethical review board approval, therefore, is not necessary. Results are published in peer-reviewed, open-access scientific journals. We make the collected data accessible as supplemental material to guarantee transparency of results. PROSPERO REGISTRATION NUMBER: CRD42022343931.

Cancer detection rates of the PI-RADSv2.1 assessment categories: systematic review and meta-analysis on lesion level and patient level.

BACKGROUND: The Prostate Imaging Reporting and Data System, version 2.1 (PI-RADSv2.1) standardizes reporting of multiparametric MRI of the prostate. Assigned assessment categories are a risk stratification algorithm, higher categories indicate a higher probability of clinically significant cancer compared to lower categories. PI-RADSv2.1 does not define these probabilities numerically. We conduct a systematic review and meta-analysis to determine the cancer detection rates (CDR) of the PI-RADSv2.1 assessment categories on lesion level and patient level. METHODS: Two independent reviewers screen a systematic PubMed and Cochrane CENTRAL search for relevant articles (primary outcome: clinically significant cancer, index test: prostate MRI reading according to PI-RADSv2.1, reference standard: histopathology). We perform meta-analyses of proportions with random-effects models for the CDR of the PI-RADSv2.1 assessment categories for clinically significant cancer. We perform subgroup analysis according to lesion localization to test for differences of CDR between peripheral zone lesions and transition zone lesions. RESULTS: A total of 17 articles meet the inclusion criteria and data is independently extracted by two reviewers. Lesion level analysis includes 1946 lesions, patient level analysis includes 1268 patients. On lesion level analysis, CDR are 2% (95% confidence interval: 0-8%) for PI-RADS 1, 4% (1-9%) for PI-RADS 2, 20% (13-27%) for PI-RADS 3, 52% (43-61%) for PI-RADS 4, 89% (76-97%) for PI-RADS 5. On patient level analysis, CDR are 6% (0-20%) for PI-RADS 1, 9% (5-13%) for PI-RADS 2, 16% (7-27%) for PI-RADS 3, 59% (39-78%) for PI-RADS 4, 85% (73-94%) for PI-RADS 5. Higher categories are significantly associated with higher CDR (P < 0.001, univariate meta-regression), no systematic difference of CDR between peripheral zone lesions and transition zone lesions is identified in subgroup analysis. CONCLUSIONS: Our estimates of CDR demonstrate that PI-RADSv2.1 stratifies lesions and patients as intended. Our results might serve as an initial evidence base to discuss management strategies linked to assessment categories.

More Than Detection of Adenocarcinoma - Indications and Findings in Prostate MRI in Benign Prostatic Disorders.

BACKGROUND: Multiparametric MRI of the prostate has become a fundamental tool in the diagnostic pathway for prostate cancer and is recommended before (or after negative) biopsy to guide biopsy and increase accuracy, as a staging examination (high-risk setting), and prior to inclusion into active surveillance. Despite this main field of application, prostate MRI can be utilized to obtain information in a variety of benign disorders of the prostate. METHODS: Systematic bibliographical research with extraction of studies, national (German) as well as international guidelines (EAU, AUA), and consensus reports on MRI of benign disorders of the prostate was performed. Indications and imaging findings of prostate MRI were identified for a) imaging the enlarged prostate, b) prostate MRI in prostatic artery embolization, c) imaging in prostatitis and d) imaging in congenital anomalies. RESULTS AND CONCLUSIONS: Different phenotypes of the enlarged prostate that partly correlate with severity of symptoms are discussed. We provide an overview of the different types of prostatitis and possible imaging findings, highlighting abscesses as a severe complication. The most common congenital anomalies of the prostate are utricular cysts, whereas anomalies like aplasia, hypoplasia, and ectopia are rare disorders. Knowledge of indications for imaging and imaging appearance of these conditions may improve patient care and enhance differential diagnosis. KEY POINTS: · Current guidelines do not implement indications for mpMRI apart from prostate carcinoma.. · MRI can distinguish different anatomical phenotypes of prostatic enlargement.. · Prostatic artery embolization represents a valuable treatment option in cases of symptomatic benign prostatic enlargement.. · Different forms of prostatitis exist and may mimic prostate carcinoma in MRI.. · MRI can be used to evaluate anatomical prostate anomalies.. CITATION FORMAT: · Oerther B, Sigle A, Franiel T et al. More Than Detection of Adenocarcinoma - Indications and Findings in Prostate MRI in Benign Prostatic Disorders. Fortschr Röntgenstr 2022; 194: 481 - 490.

Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology.

Automatic prostate tumor segmentation is often unable to identify the lesion even if multi-parametric MRI data is used as input, and the segmentation output is difficult to verify due to the lack of clinically established ground truth images. In this work we use an explainable deep learning model to interpret the predictions of a convolutional neural network (CNN) for prostate tumor segmentation. The CNN uses a U-Net architecture which was trained on multi-parametric MRI data from 122 patients to automatically segment the prostate gland and prostate tumor lesions. In addition, co-registered ground truth data from whole mount histopathology images were available in 15 patients that were used as a test set during CNN testing. To be able to interpret the segmentation results of the CNN, heat maps were generated using the Gradient Weighted Class Activation Map (Grad-CAM) method. The CNN achieved a mean Dice Sorensen Coefficient 0.62 and 0.31 for the prostate gland and the tumor lesions -with the radiologist drawn ground truth and 0.32 with whole-mount histology ground truth for tumor lesions. Dice Sorensen Coefficient between CNN predictions and manual segmentations from MRI and histology data were not significantly different. In the prostate the Grad-CAM heat maps could differentiate between tumor and healthy prostate tissue, which indicates that the image information in the tumor was essential for the CNN segmentation.

Artificial Intelligence in Magnetic Resonance Imaging-based Prostate Cancer Diagnosis: Where Do We Stand in 2021?

CONTEXT: Men suspected of harboring prostate cancer (PCa) increasingly undergo multiparametric magnetic resonance imaging (mpMRI) and mpMRI-guided biopsy. The potential of mpMRI coupled to artificial intelligence (AI) methods to detect and classify PCa before decision-making requires investigation. OBJECTIVE: To review the literature for studies addressing the diagnostic performance of combined mpMRI and AI approaches to detect and classify PCa, and to provide selection criteria for relevant articles having clinical significance. EVIDENCE ACQUISITION: We performed a nonsystematic search of the English language literature using the PubMed-MEDLINE database up to October 30, 2020. We included all original studies addressing the diagnostic accuracy of mpMRI and AI to detect and classify PCa with histopathological analysis as a reference standard. EVIDENCE SYNTHESIS: Eleven studies assessed AI and mpMRI approaches for PCa detection and classification based on a ground truth that referred to the entire prostate either with radical prostatectomy specimens (RPS) or relocalization of positive systematic and/or targeted biopsy. Seven studies retrospectively annotated cancerous lesions onto mpMRI identified in whole-mount sections from RPS, three studies used a backward projection of histological prostate biopsy information, and one study used a combined cohort of both approaches. All studies cross-validated their data sets; only four used a test set and one a multisite validation scheme. Performance metrics for lesion detection ranged from 87.9% to 92% at a threshold specificity of 50%. The lesion classification accuracy of the algorithms was comparable to that of the Prostate Imaging-Reporting and Data System. CONCLUSIONS: For an algorithm to be implemented into radiological workflows and to be clinically applicable, it must be trained with a ground truth labeling that reflects histopathological information for the entire prostate and it must be externally validated. Lesion detection and classification performance metrics are promising but require prospective implementation and external validation for clinical significance. PATIENT SUMMARY: We reviewed the literature for studies on prostate cancer detection and classification using magnetic resonance imaging (MRI) and artificial intelligence algorithms. The main application is in supporting radiologists in interpreting MRI scans and improving the diagnostic performance, so that fewer unnecessary biopsies are carried out.

Quantitative Analysis of Diffusion Weighted Imaging May Improve Risk Stratification of Prostatic Transition Zone Lesions.

BACKGROUND/AIM: To investigate whether quantitative analysis of diffusion weighted images allows for improved risk stratification of transition zone lesions in prostate magnetic resonance imaging (MRI) evaluated according to PI-RADSv2.1 [Prostate Imaging Reporting and Data System, target variable: clinically significant prostate cancer (csPCa)]. PATIENTS AND METHODS: Consecutive patients with transition zone lesions in 3T prostate MRI were enrolled in the study. All lesions on MRI were histopathologically verified by transperineal MRI-TRUS fusion biopsy. Two blinded radiologists re-evaluated all lesions according to PI-RADSv2.1. A consensus reading was performed after reading of all cases. Additionally, mean apparent diffusion coefficient values (mADC) were derived from blinded lesion segmentation. ROC analysis was performed for PI-RADS categories and PI-RADS categories with separate subcategories and diffusion coefficient values (ADC). Data were examined for optimal mADC cut-off values that improve stratification of csPCa and benign lesions. RESULTS: Among 85 patients (mean age=66.2 years), 98 transition zone lesions were detected. Biopsy confirmed csPCa in 24/98 cases. Area under the curve (AUC) was 0.89/0.90 for reader 1, 0.92/0.91 for reader 2 and 0.92/0.91 for the consensus reading (5 category analysis/analysis with subcategories separately). Inter-reader agreement was substantial, with lower PI-RADS categories assigned by the more experienced reader (p<0.05). AUC for mADC alone was 0.81. When a cut-off threshold of 950 µm2/s mADC is used to downgrade PI-RADS 3 lesions to PI-RADS 2, biopsy could be avoided in all benign PI-RADS 3 cases. CONCLUSION: Quantitative analysis of diffusion weighted images may help avoid unnecessary biopsies of transition zone PI-RADS 3 lesions.