Keywords: Prostate, Prostate, radiomics, deep learning, Gleason score

Motivation: Gleason Score (GS) could only be obtained through biopsy or radical prostatectomy (RP), which might carry a multitude of complications and pose additional financial burdens and emotional strain.

Goal(s): To explore the predictive value of mixed model combined clinical features, radiomics features and deep learning features for GS.

Approach: The mixed model was constructed to classify grade group 0 (GG0) (benign), GG1, GG2, GG3, GG4 and GG5. DenseNet was used to establish the model.

Results: The mixed model had the best predictive ability, with Kw of 0.74 and relative accuracy of 0.76.

Impact: Clinicians could obtain GS without biopsy or surgery, which could avoid a lot of complications and financial burdens. Future studies could integrate automated VOI segmentation algorithm to optimize AI model.

Keywords: Prostate, Prostate

Motivation: Multiparametric MRI is highly sensitive for identifying clinically significant prostate cancer (csPCa), but has a poorer specificity, meaning many men undergo unnecessary prostate biopsies.

Goal(s): To evaluate whether artificial intelligence (AI) could improve the diagnostic accuracy of MRI compared to current clinical methods, including Likert score and PSA density (PSAd).

Approach: We carried out independent evaluation of a prostate MRI lesion classifier model using a large multisite and multivendor prostate MRI dataset (1,039 patients).

Results: The AI model matched the sensitivity and specificity of Likert score plus PSAd cut-offs on data similar to the training set, but did not generalise to other data.    

Impact: An infrastructure has been successfully established to allow robust and independent evaluation of prostate MRI lesion classification models to accelerate the development of such tools and to ensure adequate testing pre-deployment.

Keywords: Prostate, Diffusion/other diffusion imaging techniques, B0-inhomogeneity distortion correction

Motivation: The Jacobian intensity correction (JIC) of conventional EPI-distortion correction methods can conceal severe under-correction and even create false anatomical structure.

Goal(s): Demonstrate the shortcomings of JIC methods and present an alternative distortion-correction technique that obviates the need for a JIC.

Approach: Acquiring DWI images with opposite phase-encoding polarity at multiple b-values and normalizing prior to estimating tissue displacement eliminates the need to account for intensity scaling with the JIC. This approach, referred to as mRPG, was compared against conventional distortion correction methods.

Results: mRPG significantly improved the estimation and removal of spatial distortions compared to conventional methods.

Impact: Jacobian intensity correction (JIC) can generate misleading improvement of EPI distortion and create false structure in prostate diffusion images. Eliminating the JIC, by acquiring opposed-phase images at multiple b-values and normalizing prior to correction, results in improved EPI distortion correction.

Keywords: Prostate, Prostate, apparent diffusion coefficient; repetition time; diffusion-weighted imaging; magnetic resonance imaging; prostate cancer

Motivation: Assessing whether short repetition time (TR) diffusion-weighted imaging (DWI) surpasses conventional long TR DWI for prostate cancer detection.

Goal(s): To compare the image quality and diagnostic accuracy of short TR DWI to long TR DWI using a 3.0-Tesla MRI.

Approach: Twenty-five prostate cancer patients were imaged with both short (1850 ms) and long (6000 ms) TR DWI. We analyzed signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and apparent diffusion coefficient (ADC), with additional qualitative diagnostic assessments.

Results: Short TR DWI yielded higher CNR and visual scores with stable SNR, alongside robust ADC correlations, enhancing diagnostic performance notably for non-specialist readers.

Impact: Short repetition time diffusion-weighted imaging's improved prostate cancer detection could enhance diagnostic performance for non-specialist readers, influencing treatment and patient outcomes. It invites new magnetic resonance imaging research and may transform standard prostate cancer diagnostic protocols, reducing unnecessary invasive procedures.

Keywords: Prostate, Cancer

Motivation: A sensitive imaging method that distinguishes benign or low-grade prostate lesions from aggressive ones is one of the greatest needs in prostate cancer.

Goal(s): To develop new prostate DWI technique using a non-linear gradient (NLG) to improve the diagnostic accuracy of prostate cancer.

Approach: Using an NLG coil, we can circumvent the challenge of high b-value requirements by having a gradient with a high amplitude within a limited field of view, which applies to prostate imaging.

Results: We demonstrate feasibility of using an NLG for prostate imaging, after validation with a polyvinylpyrrolidone (PVP) phantom and testing SE and EPI sequences with prostate ADC-mapping.

Impact: To better diagnose prostate cancer with high sensitivity, we use an NLG insert coil. Using only one DWI and one non-diffusion image we showed comparable ADC maps to those produced using gold standard multi-shell linear gradient sequences.

Keywords: Radiomics, Radiomics, diffusion-weighted imaging (DWI), repeatability, magnetic resonance imaging (MRI)

Motivation: Typically, diffusion-weighted imaging (DWI) modelling is assumption-based using e.g. exponential models, but nonparametric (data-based) methods have not been explored. 

Goal(s): We propose a information-theoretic paradigm for DWI modelling which results in a novel radiomics for DWI of prostate cancer (PCa).

Approach: The proposed radiomics, EDDIE (entropy of divergence of DWI decay curve) is formulated as entropy of information lost from approximating a reference by DWI decay curves. It is subjected to classification of clinically significant and insignificant PCa using test-retest DWI datasets of 78 patients.

Results: EDDIE achieved an AUC score of 0.77 and an ICC (3,1) of 0.78 which indicates good repeatability. 

Impact: The proposed approach is nonparametric (assumption-free), interpretable (mathematically and physically meaningful) and complete (higher-order measurement). These may contribute towards more accurate and efficient DWI modelling. Besides, the associated novel radiomics could help ushering in more information-theoretic developments in this field. 

Keywords: Prostate, Prostate, Clinically Significant Prostate cancer,PSA density,PSA gray zone,PI-RADS v2.1

Motivation: It is crucial to improve the accuracy of detection of clinically significant prostate cancer (csPCa) within the PSA gray zone.

Goal(s): To combine PI-RADS v2.1 with prostate-specific antigen density(PSAD) derivatives to improve the predictive value of csPCa in the PSA gray zone.

Approach: Based on a dual-center study, logistic regression was used to analyze the predictive value of the multi-parameter combination on csPCa in the training group, the receiver operating characteristic curve(ROC) curves were used to evaluate the diagnostic performance, and conducting external validation.

Results: The area under curve (AUC) of combining of PI-RADS v2.1 and PSAD was the highest for predicting csPCa.

Impact: The dual-center study demonstrates combining of PI-RADS v2.1 and PSAD improved the predictive performance of csPCa in the PSA gray zone, and grouping PSAD with PI-RADS risk stratification can have more direct clinical applications.

Keywords: Prostate, Artifacts

Motivation: Clinically utilized diffusion weighted imaging (DWI), an essential part of prostate MRI, relies on echo planar imaging (EPI) and is prone to geometric distortion and signal loss due to susceptibility from rectal gas and metal hip prostheses.

Goal(s): To improve the robustness of prostate DWI in the setting of field inhomogeneities from hip prostheses and rectal gas.

Approach: Prospective study of 10 patients undergoing prostate MRI with diffusion prepped fast spin echo (FSE) sequence, as well as single-shot and multi-shot DW-EPI, comparing prostate measurements.

Results: We show feasibility of using a diffusion prepped FSE sequence in prostate MR with decreased distortion and artifact.

Impact: A diffusion prepped fast-spin echo sequence avoids distortion and signal loss from susceptibility artifacts seen with echo planar imaging, and is a feasible method to obtain robust diffusion weighted imaging of the prostate.

Keywords: Prostate, Prostate

Motivation: The diagnostic utility of whole tumor amide proton transfer–weighted (APTw) imaging analysis for predicting prostate cancer(PCa) has not been reported.

Goal(s): The purpose of this study was to evaluate the diagnostic performance of whole tumor APTw histogram analysis, for the depiction of PCa compared with multiparametric MRI with Prostate Imaging Reporting and Data System (PI-RADS) version 2.1. 

Approach: Diagnostic performance was assessed by ROC with AUC analysis. 

Results: We found that combining PI-RADS version 2.1 and APTw histogram achieved the best results in distinguishing  transition zone PCa from benign prostatic hyperplasia and peripheral zone PCa from chronic prostatitis.

Impact: Whole-tumor histogram analysis of APTw images improved the diagnostic performance of multiparametric MRI with PI-RADS version 2.1 in detecting prostate cancer in both the peripheral and transition zones.

Keywords: Prostate, Elastography, MRE, Lower Urinary Tract Symptoms, Shear Stiffness, LUTS

Motivation: There is a critical need for significant improvements in image-based assessment of the prostate in men with lower urinary tract symptoms (LUTS).

Goal(s): To develop non-invasive image-based biomarkers that will optimize clinical management of men with LUTS.

Approach: Quantify transition zone complex shear modulus (henceforth ‘stiffness’) with transperineal magnetic resonance elastography (pMRE) at 90Hz and 100Hz.

Results: Mean periurethral TZ stiffness increases with frequency (3.0clip_image006.png">0.4kPa).

Impact: Transperineal pMRE is technically feasible, generates volumetric whole prostate quantitative parametric maps that can differentiate zonal prostate anatomy. Periurethral TZ stiffness, measured with pMRE, may be a clinically useful biomarker for identifying discrete phenotypes of LUTS.

Keywords: Prostate, Prostate

Motivation: Accurate prediction of prostate cancer(PCa) bone metastases can be challenged by radiologists. The utility of APTw histogram methods for evaluating bone metastases involvement in PCa is still unclear.

Goal(s): The purpose of this study was to evaluate APTw-derived whole-tumor histogram analysis parameters in predicting PCa bone metastases. 

Approach: Diagnostic performance was evaluated using ROC analysis and the AUC comparisons were conducted using the DeLong method.

Results: Our preliminary research showed that whole-tumor histogram analysis of APTw images combined with clinical factors (tPSA, cT stage) showed good diagnosis efficiency in predicting PCa bone metastases while using ⁶⁸Ga-PSMA PET/CT as the reference standard. 

Impact: Our preliminary research showed that whole-tumor histogram analysis of APTw images combined with clinical factors(tPSA, T stage) showed good diagnosis efficiency in predicting prostate cancer bone metastases while using ⁶⁸Ga-PSMA PET/CT as the reference standard. 

Keywords: Prostate, Cancer, prostate cancer, brachytherapy, radiotherapy, MR spectroscopy

Motivation: Monitoring time-dependent effects of prostate brachy- and radiotherapy.

Goal(s): Assessment of prostate metabolic activity during and three months after the completion of brachy- and/or external beam radiotherapy. 

Approach: Single-voxel ¹H-MRS with a surface receiver coil. 

Results: It is demonstrated that the proposed ¹H-MRS approach is a useful tool for monitoring metabolic changes in prostate tissues treated with brachy- and/or external beam radiotherapy. We found reduction of citrate intensity close to the noise level to be the most reliable measure for identification of metabolic atrophy and response to therapy.

Impact: Single-voxel ¹H-MRS with a surface receiver coil is an effective method for monitoring the response of prostate tissues to brachy- and/or external beam radiotherapy. Good response to prostate radiotherapy might be characterized by low citrate intensity.

Keywords: Prostate, Prostate, Cancer, Hyperpolarized MR

Motivation: Monitoring the progression or response of advanced prostate metastases is a current clinical unmet need that is not reliably delineated with current CT and PET. 

Goal(s): Here, we developed a high-resolution whole abdominopelvic [1-¹³C]pyruvate HP MRI approach for the metabolic biomarker characterization of metastases in prostate cancer patients.

Approach: A variable-resolution imaging approach was used to provide high-resolution [1-¹³C]pyruvate, robust spatiotemporal denoising and B₁+ variation correction methods were used to quantify the rate-constant for the conversion of [1-¹³C]pyruvate to lactate, k_PL. 

Results: Improved conspicuity of [1-¹³C]pyruvate distribution and k_PL conversion maps of metastatic lesions were achieved with the new approach. 

Impact: The improvement in [1-¹³C]pyruvate resolution and clear delineation of highly metabolically active metastatic lesions in k_PL maps demonstrated the potential of [1-¹³C]pyruvate HP MRI in advanced prostate cancer.  

Keywords: Prostate, Hyperpolarized MR (Non-Gas), Prostate cancer, Preclinical models

Motivation: Diagnosis and treatment assessment of aggressive small cell neuroendocrine prostate cancer (SCNC) is challenging due to its admixture presence in conjunction with adenocarcinoma phenotype and differential response to treatments subjective to the metastatic sites.

Goal(s): This study aims to assess the therapeutic efficacy of platinum-based chemotherapy in preclinical SCNC metastatic models using patient derived xenografts.

Approach: Hyperpolarized ¹³C MRI was used to measure the apparent rate of change in glycolysis (k_PL) in PDX models of SCNC in metastatic sites.

Results: k_PL values clearly demonstrated a decrease upon treatment concordant to the change in tumor volume in both the liver and bone metastatic models.

Impact: k_PL, measured by hyperpolarized MRI, can be used to assess treatment efficacy yielding a non-invasive, potentially early biomarker readily translatable for use in patients with metastatic tumors for optimal therapeutic approaches.

Keywords: Prostate, Prostate, High-field MRI

Motivation: To better detect and delineate prostate cancer using ultrahigh field MRI.

Goal(s): To investigate if clinical prostate MRI at 7T using recent technological advances is feasible.

Approach: Prostate MRI was performed in 5 healthy volunteers using the latest generation of whole-body 7T MRI scanners incorporating enhanced gradient performance, advanced deep learning based image reconstruction and an 8Tx/16Rx torso array.

Results: High image quality with an unprecedented spatial resolution and a sharpness obtained at 7T outperformed those obtained at 3T even when time-matched sequences were acquired.

Impact: The preliminary data obtained from several volunteers provides a great encouragement to start clinical studies in prostate cancer patients.

Keywords: Prostate, Prostate, BPH, PCa

Motivation: Accurate interpretation of prostate MRI demands a high level of expertise and deep learning models for prostate cancer (PCa) detection often suffer from low specificity.

Goal(s): To explore the value of annotation of benign prostatic hyperplasia (BPH) to prostate cancer (PCa) detection.

Approach: We retrospectively collected 96 patients with PCa and 92 patients with BPH, all scanned with PI-RADS protocol. Two deep learning models were built: Model1 only detected PCa while Model2 simultaneously detected BPH and PCa.

Results: Model2 achieved superb performance with test AUC of 0.995, outperforming Model1 whose test AUC was 0.770.

Impact: Explicitly using the BPH label improved the performance of PCa detection significantly, implying multi-task deep learning models targeting multiple diseases are not only more in line with the needs of clinical applications, but can also bring about performance improvement.