Functional MR Imaging of Prostate Cancer

Outcome prediction of SSTR-RADS-3A and SSTR-RADS-3B lesions in patients with neuroendocrine tumors based on 68Ga-DOTATATE PET/MR

PURPOSE

Somatostatin receptor (SSTR)-targeted PET imaging has emerged as a common approach to evaluating those patients with well-differentiated neuroendocrine tumors (NETs). The SSTR reporting and data system (SSTR-RADS) version 1.0 provides a means of categorizing lesions from 1 to 5 according to the likelihood of NET involvement, with SSTR-RADS-3A (soft-tissue) and SSTR-RADS-3B (bone) lesions being those suggestive of but without definitive NET involvement. The goal of the present study was to assess the ability of 68Ga-DOTATATE PET/MR imaging data to predict outcomes for indeterminate SSTR-RADS-3A and 3B lesions.

METHODS

NET patients with indeterminate SSTR-RADS-3A or SSTR-RADS-3B lesions who underwent 68Ga-DOTATATE PET/MR imaging from April 2020 through August 2023 were retrospectively evaluated. All patients underwent follow-up through December 2023 (median, 17 months; (3-31 months)), with imaging follow-up or biopsy findings ultimately being used to classify lesions as malignant or benign. Lesion maximum standardized uptake value (SUVmax) along with minimum and mean apparent diffusion coefficient (ADCmin and ADCmean) values were measured and assessed for correlations with outcomes on follow-up.

RESULTS

In total, 33 indeterminate SSTR-RADS-3 lesions from 22 patients (19 SSTR-RADS-3A and 14 SSTR-RADS-3B) were identified based upon baseline 68Ga-DOTATATE PET/MR findings. Over the course of follow-up, 16 of these lesions (48.5%) were found to exhibit true NET positivity, including 9 SSTR-RADS-3A and 7 SSTR-RADS-3B lesions. For SSTR-RADS-3A lymph nodes, a diameter larger than 0.7 cm and an ADCmin of 779 × 10-6mm2/s or lower were identified as being more likely to be associated with metastatic lesions. Significant differences in ADCmin and ADCmean were identified when comparing metastatic and non-metastatic SSTR-RADS-3B bone lesions (P < 0.05), with these parameters offering a high predictive ability (AUC = 0.94, AUC = 0.86).

CONCLUSION

Both diameter and ADCmin can aid in the accurate identification of the nature of lesions associated with SSTR-RADS-3A lymph nodes, whereas ADCmin and ADCmean values can inform the accurate interpretation of SSTR-RADS-3B bone lesions.

A machine learning radiomics model based on bpMRI to predict bone metastasis in newly diagnosed prostate cancer patients

OBJECTIVES

To develop and evaluate a machine learning radiomics model based on biparametric magnetic resonance imaging MRI (bpMRI) to predict bone metastasis (BM) status in newly diagnosed prostate cancer (PCa) patients.

METHODS

We retrospectively analyzed bpMRI scans of PCa patients from multiple centers between January 2016 and October 2021. 348 PCa patients were recruited from two institutions for this study. The first institution contributed 284 patients, stratified and randomly divided into training and internal validation cohorts at a 7:3 ratio. The remaining 64 patients were sourced from the second institution and comprised the external validation cohort. Radiomics features were extracted from axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) tumor regions. We developed the radiomics prediction model for BM in the training cohort and validated it in the internal and external validation cohorts. As a benchmark, we trained the logistic regression model with lasso feature reduction (LFR-LRM) in the training cohort and further compared it with Naive Bayes, eXtreme Gradient Boosting (XGboost), Random Forest (RF), GBDT, SVM, Adaboost, and KNN algorithms and validated in both the internal and external cohorts. The performance of several predictive models was assessed by receiver operating characteristic (ROC).

RESULTS

The LFR-LRM model achieved an area under the receiver operating characteristic curve (AUC) of 0.89 (95% CI: 0.822-0.974) and an accuracy of 0.828 (95% CI: 0.713-0.911). The AUC and accuracy in external validation were 0.866 (95% CI: 0.784-0.948) and 0.769 (95% CI: 0.648-0.864), respectively. The RF and XGBoost models outperformed the LFR-LRM, with AUCs of 0.907 (95% CI: 0.863-0.949) and 0.928 (95% CI: 0.882-0.974) and accuracies of 0.831 (95% CI: 0.727-0.907) and 0.884 (95% CI: 0.792-0.946). External validation for these models yielded AUCs and accuracies of 0.911 (95% CI: 0.861-0.966), 0.921 (95% CI: 0.889-0.953), and 0.846 (95% CI: 0.735-0.923) and 0.876 (95% CI: 0.771-0.945), respectively.

CONCLUSIONS

The XGboost machine learning model is more accurate than LFR-LRM for predicting BM in patients with newly confirmed PCa.

Endothelin-axis antagonism enhances tumor perfusion in pancreatic cancer

Delivery of therapeutic agents in pancreatic cancer (PC) is impaired due to its hypovascular and desmoplastic tumor microenvironment. The Endothelin (ET)-axis is the major regulator of vasomotor tone under physiological conditions and is highly upregulated in multiple cancers. We investigated the effect of dual endothelin receptor antagonist bosentan on perfusion and macromolecular transport in a PC cell-fibroblast co-implantation tumor model using Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI). Following bosentan treatment, the contrast enhancement ratio and wash-in rates in tumors were two- and nine times higher, respectively, compared to the controls, whereas the time to peak was significantly shorter (7.29 ± 1.29 min v/s 22.08 ± 5.88 min; p = 0.04). Importantly, these effects were tumor selective as the magnitudes of change for these parameters were much lower in muscles. Bosentan treatment also reduced desmoplasia and improved intratumoral distribution of high molecular weight FITC-dextran. Overall, these findings support that targeting the ET-axis can serve as a potential strategy to selectively enhance tumor perfusion and improve the delivery of therapeutic agents in pancreatic tumors.

Identification and functional analysis of LncRNA-XIST ceRNA network in prostate cancer

BACKGROUND

Long non-coding RNAs (lncRNAs) play a functional role in the progression of prostate cancer (PCa). However, the molecular mechanism, expression, or function of the lncRNA XIST in PCa is not well understood. Therefore, the major goal of this study was to investigate the involvement of XIST in PCa.

METHODS

We used the The Cancer Genome Atlas (TCGA) database to conduct a pan-cancer bioinformatics analysis of XIST and identified that it may play an important role in prostate cancer. This finding was verified using clinical samples and in vitro assays. Finally, we constructed an XIST ceRNA network for prostate cancer.

RESULTS

Our in vitro and in vivo results showed that the XIST gene expression level was higher in PCa derived cells and tissues compared to that in normal cells and tissues. XIST gene expression level was positively correlated with the invasion and proliferation of tumour cells. Furthermore, the downregulation of XIST inhibited the growth of subcutaneous 22Rv1 xenografts in nude mice. In addition, we constructed a XIST ceRNA network. Consistent with previous studies, we found that the role of XIST is mediated through via sponges, such as miRNA -96-5p, miRNA -153-3p, and miRNA-182-5p.

CONCLUSION

High expression level of XIST can lead to enhanced carcinogenicity in PCa. Therefore, XIST has the potential to be used as a prognostic marker and may become a new research focus for the treatment of PCa.

Synthetic correlated diffusion imaging hyperintensity delineates clinically significant prostate cancer

Prostate cancer (PCa) is the second most common cancer in men worldwide and the most frequently diagnosed cancer among men in more developed countries. The prognosis of PCa is excellent if detected at an early stage, making early screening crucial for detection and treatment. In recent years, a new form of diffusion magnetic resonance imaging called correlated diffusion imaging (CDI) was introduced, and preliminary results show promise as a screening tool for PCa. In the largest study of its kind, we investigate the relationship between PCa presence and a new variant of CDI we term synthetic correlated diffusion imaging (CDI\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^s$$\end{document}s), as well as its performance for PCa delineation compared to current standard MRI techniques [T2-weighted (T2w) imaging, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) imaging] across a cohort of 200 patient cases. Statistical analyses reveal that hyperintensity in CDI\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^s$$\end{document}s is a strong indicator of PCa presence and achieves strong delineation of clinically significant cancerous tissue compared to T2w, DWI, and DCE. These results suggest that CDI\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^s$$\end{document}s hyperintensity may be a powerful biomarker for the presence of PCa, and may have a clinical impact as a diagnostic aid for improving PCa screening.

To Determine the Diagnostic Accuracy of Diffusion-Weighted Imaging in the Diagnosis of Prostate Carcinoma Taking Histopathology As the Gold Standard

Introduction Carcinoma of the prostate is the most common malignancy among males. Serum prostate-specific antigen (PSA) levels and digital rectal examination (DRE) are the initial investigations for the detection of prostate cancer. In recent years, some investigators have used color Doppler ultrasound and diffusion-weighted imaging (DWI) for the diagnosis of prostate cancer and avoided invasive and painful investigation, i.e., biopsy. The purpose of the study is to determine the validity of DWI in detecting prostatic cancer taking histopathology as the gold standard. Material and methods This cross-sectional study was conducted prospectively in the radiology department of a tertiary care hospital from January 1, 2019, to December 31, 2020. This study was approved by the Departmental Research Committee. A total of 272 male patients were included in our study who have elevated PSA levels (>4.0 ng/ml) with symptoms of hematuria and urinary retention. All included subjects were sent to the radiology department for DWI imaging. The DWI imaging was analyzed for prostate cancer and the results were correlated with histopathological diagnosis. Results The average age of patients was 50.28±9.93 years. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of DWI in the diagnoses of prostate cancer were 86.7%, 87.8%, 75.8%, 93.8%, and 87.5%, respectively. Conclusion DWI is an informative and non-invasive imaging modality with high diagnostic accuracy for the diagnosis of prostate carcinoma.

Imaging of Neuroendocrine Prostatic Carcinoma

Neuroendocrine prostate cancer (NEPC) is an aggressive subtype of prostate cancer that typically has a high metastatic potential and poor prognosis in comparison to the adenocarcinoma subtype. Although it can arise de novo, NEPC much more commonly occurs as a mechanism of treatment resistance during therapy for conventional prostatic adenocarcinoma, the latter is also termed as castration-resistant prostate cancer (CRPC). The incidence of NEPC increases after hormonal therapy and they represent a challenge, both in the radiological and pathological diagnosis, as well as in the clinical management. This article provides a comprehensive imaging review of prostatic neuroendocrine tumors.

Fatty Acid Metabolism Reprogramming in Advanced Prostate Cancer

Prostate cancer (PCa) is a carcinoma in which fatty acids are abundant. Fatty acid metabolism is rewired during PCa development. Although PCa can be treated with hormone therapy, after prolonged treatment, castration-resistant prostate cancer can develop and can lead to increased mortality. Changes to fatty acid metabolism occur systemically and locally in prostate cancer patients, and understanding these changes may lead to individualized treatments, especially in advanced, castration-resistant prostate cancers. The fatty acid metabolic changes are not merely reflective of oncogenic activity, but in many cases, these represent a critical factor in cancer initiation and development. In this review, we analyzed the literature regarding systemic changes to fatty acid metabolism in PCa patients and how these changes relate to obesity, diet, circulating metabolites, and peri-prostatic adipose tissue. We also analyzed cellular fatty acid metabolism in prostate cancer, including fatty acid uptake, de novo lipogenesis, fatty acid elongation, and oxidation. This review broadens our view of fatty acid switches in PCa and presents potential candidates for PCa treatment and diagnosis.

Precise Identification of Prostate Cancer from DWI Using Transfer Learning

Background and Objective: The use of computer-aided detection (CAD) systems can help radiologists make objective decisions and reduce the dependence on invasive techniques. In this study, a CAD system that detects and identifies prostate cancer from diffusion-weighted imaging (DWI) is developed. Methods: The proposed system first uses non-negative matrix factorization (NMF) to integrate three different types of features for the accurate segmentation of prostate regions. Then, discriminatory features in the form of apparent diffusion coefficient (ADC) volumes are estimated from the segmented regions. The ADC maps that constitute these volumes are labeled by a radiologist to identify the ADC maps with malignant or benign tumors. Finally, transfer learning is used to fine-tune two different previously-trained convolutional neural network (CNN) models (AlexNet and VGGNet) for detecting and identifying prostate cancer. Results: Multiple experiments were conducted to evaluate the accuracy of different CNN models using DWI datasets acquired at nine distinct b-values that included both high and low b-values. The average accuracy of AlexNet at the nine b-values was 89.2±1.5% with average sensitivity and specificity of 87.5±2.3% and 90.9±1.9%. These results improved with the use of the deeper CNN model (VGGNet). The average accuracy of VGGNet was 91.2±1.3% with sensitivity and specificity of 91.7±1.7% and 90.1±2.8%. Conclusions: The results of the conducted experiments emphasize the feasibility and accuracy of the developed system and the improvement of this accuracy using the deeper CNN.

Can mean ADC value and ADC ratio of benign prostate tissue to prostate cancer assist in the prediction of clinically significant prostate cancer within the PI-RADSv2 scoring system?

Background

The aim of this study is to investigate whether quantitative DW metrics can provide additive value to the reliable categorization of lesions within existing PI-RADSv2 guidelines. Fifty-eight patients with clinically suspicious prostate cancer who underwent PR examination, PSA serum levels, sextant TRUS-guided biopsies, and bi-parametric MR imaging were included in the study.

Results

Sixty-six lesions were detected by histopathological analysis of surgical specimens. The mean ADC values were significantly lower in tumor than non-tumor tissue. The mean ADC value inversely correlated with Gleason score of tumors with a significant p value < 0.001.Conversely, a positive relationship was found between the ADC ratio (ADC of benign prostatic tissue to prostate cancer) and the pathologic Gleason score with a significant elevation of the ADC ratio along with an increase of the pathologic Gleason score (p < 0.001). ROC curves constructed for the tumor ADC and ADC ratio helped to distinguish pathologically aggressive (Gleason score ≥ 7) from non-aggressive (Gleason score ≤ 6) tumors and to correlate it with PIRADSv2 scoring to predict the presence of clinically significant PCA (PIRADSv2 DW ≥ 4). The ability of the tumor ADC and ADC ratio to predict highly aggressive tumors (GS> 7) was high (AUC for ADC and ADC ratio, 0.946 and 0.897; p = 0.014 and 0.039, respectively). The ADC cut-off value for GS ≥ 7 was < 0.7725 and for GS ≤ 6 was > 0.8620 with sensitivity and specificity 97 and 94%. The cutoff ADC ratio for predicting (GS > 7) was 1.42 and for GS ≤ 6 was > 1.320 with sensitivity and specificity 97 and 92%. By applying this ADC ratio cut-off value the sensitivity and specificity of reader 1 for correct categorization of PIRADSv2 DW > 4 increased from 90 and 68% to 95 and 90% and that of reader 2 increased from 94 and 88% to 97 and 92%, respectively.

Conclusion

Estimation of DW metrics (ADC and ADC ratio between benign prostatic tissue and prostate cancer) allow the non-invasive assessment of biological aggressiveness of prostate cancer and allow reliable application of the PIRADSv2 scoring to determine clinically significant cancer (DW score > 4) which may contribute in planning initial treatment strategies.

Doctor, a patient is on the phone asking about the endorectal coil!

The question referred to in the title of this article is a relatively common situation when performing prostate MRI in some healthcare settings. Moreover, the answer is not always straightforward. The decisions on type of receiver coil for prostate MRI and whether or not an endorectal coil (ERC) should be used is based on several factors. These relate to the patient (e.g., body habitus, presence of metallic devices in the pelvis), the focus of the exam (diagnosis, staging, recurrence), and characteristics of the MRI system (e.g., magnetic field strength and hardware components including coil design and number of elements/channels available in the surface coil). Historically, the combined use of an ERC and a surface coil was the optimal combination for maximizing the signal-to-noise ratio (SNR), particularly for low-strength magnetic fields (1.5T). However, there are several disadvantages associated with the use of an ERC, and several studies have advocated equivalent clinical performance of modern MRI systems for diagnosis and staging of prostate cancer (PCa), either with ERC or surface alone. Accordingly, there is a wide variation in the precise imaging technique across institutions. This article focuses on the most relevant aspects of the decision of whether to use an ERC for PCa MR imaging.

A Hybrid End-to-End Approach Integrating Conditional Random Fields into CNNs for Prostate Cancer Detection on MRI

Prostate Cancer (PCa) is the most common oncological disease in Western men. Even though a growing effort has been carried out by the scientific community in recent years, accurate and reliable automated PCa detection methods on multiparametric Magnetic Resonance Imaging (mpMRI) are still a compelling issue. In this work, a Deep Neural Network architecture is developed for the task of classifying clinically significant PCa on non-contrast-enhanced MR images. In particular, we propose the use of Conditional Random Fields as a Recurrent Neural Network (CRF-RNN) to enhance the classification performance of XmasNet, a Convolutional Neural Network (CNN) architecture specifically tailored to the PROSTATEx17 Challenge. The devised approach builds a hybrid end-to-end trainable network, CRF-XmasNet, composed of an initial CNN component performing feature extraction and a CRF-based probabilistic graphical model component for structured prediction, without the need for two separate training procedures. Experimental results show the suitability of this method in terms of classification accuracy and training time, even though the high-variability of the observed results must be reduced before transferring the resulting architecture to a clinical environment. Interestingly, the use of CRFs as a separate postprocessing method achieves significantly lower performance with respect to the proposed hybrid end-to-end approach. The proposed hybrid end-to-end CRF-RNN approach yields excellent peak performance for all the CNN architectures taken into account, but it shows a high-variability, thus requiring future investigation on the integration of CRFs into a CNN.

The value of MR textural analysis in prostate cancer

Current diagnosis and treatment stratification of patients with suspected prostate cancer relies on a combination of histological and magnetic resonance imaging (MRI) findings. The aim of this article is to provide a brief overview of prostate pathological grading as well as the relevant aspects of multiparametric (MRI) mpMRI, before indicating the potential that magnetic resonance textural analysis (MRTA) offers within prostate cancer. A review of the evidence base on MRTA in prostate cancer will enable discussion of the utility of this field while also indicating recommendations to future research. Radiomic textural analysis allows the assessment of spatial inter-relationships between pixels within an image by use of mathematical methods. First-order textural analysis is better understood and may have more clinical validity than higher-order textural features. Textural features extracted from apparent diffusion coefficient maps have shown the most potential for clinical utility in MRTA of prostate cancers. Future studies should aim to integrate machine learning techniques to better represent the role of MRTA in prostate cancer clinical practice. Nomenclature should be used to reduce misidentification between first-order and second-order energy and entropy. Automated methods of segmentation should be encouraged in order to reduce problems associated with inclusion of normal tissue within regions of interest. The retrospective and small-scale nature of most published studies, make it difficult to draw meaningful conclusions. Future larger prospective studies are required to validate the textural features indicated to have potential in characterisation and/or diagnosis of prostate cancer before translation into routine clinical practice.

Diagnostic performance of diffusion-weighted imaging for prostate cancer: Peripheral zone versus transition zone

OBJECTIVES

Diffusion-weighted imaging (DWI) has been shown to be an important component of multiparametric magnetic resonance imaging (mpMRI). We compared performance of DWI for detection of prostate cancer (PCa) in peripheral zone (PZ) and transition zone (TZ) of prostate.

MATERIALS AND METHODS

We reviewed data of 460 subjects who underwent preoperative 3.0-Tesla mpMRI and subsequently radical prostatectomy. Level of suspicion for PCa was graded using 5-grade Likert-scale from DWI. Topographic analyses were performed for location of tumor foci at each surgical specimen. Among those with DWI grade ≥ III, we analyzed concordance rate on the location of radiologic and pathologic index lesions between DWI and surgical specimens.

RESULTS

Among 460 patients, 351 (76.3%) patients showed suspicious DWI lesions (57.5% in PZ, 42.5% in TZ). Multivariates regression analyses revealed significant associations between high DWI grade and adverse pathologic outcomes including pathologic stage, Gleason score, tumor volume and extracapsular extension (all p < 0.05). Overall concordance rates between DWI and surgical specimen were 75.8%, significantly higher in PZ than TZ (82.2% vs. 67.1% p = 0.002). Such concordance rate showed a positive linear association with increase in DWI grading (p < 0.001). Among 109 patients with DWI grade I-II, 28 (25.7%) harbored high grade disease (pathologic Gleason score ≥ 4 + 3).

CONCLUSIONS

DWI detects tumors in PZ of prostate more accurately than those in TZ. Such accuracy of DWI was shown to be more evident with higher DWI grade. Meanwhile, a negative DWI did not guarantee absence of high grade PCa.

Detecting prostate cancer and prostatic calcifications using advanced magnetic resonance imaging

Prostate cancer and prostatic calcifications have a high incidence in elderly men. We aimed to investigate the diagnostic capabilities of susceptibility-weighted imaging in detecting prostate cancer and prostatic calcifications. A total number of 156 men, including 34 with prostate cancer and 122 with benign prostate were enrolled in this study. Computed tomography, conventional magnetic resonance imaging, diffusion-weighted imaging, and susceptibility-weighted imaging were performed on all the patients. One hundred and twelve prostatic calcifications were detected in 87 patients. The sensitivities and specificities of the conventional magnetic resonance imaging, apparent diffusion coefficient, and susceptibility-filtered phase images in detecting prostate cancer and prostatic calcifications were calculated. McNemar's Chi-square test was used to compare the differences in sensitivities and specificities between the techniques. The results showed that the sensitivity and specificity of susceptibility-filtered phase images in detecting prostatic cancer were greater than that of conventional magnetic resonance imaging and apparent diffusion coefficient (P < 0.05). In addition, the sensitivity and specificity of susceptibility-filtered phase images in detecting prostatic calcifications were comparable to that of computed tomography and greater than that of conventional magnetic resonance imaging and apparent diffusion coefficient (P < 0.05). Given the high incidence of susceptibility-weighted imaging (SWI) abnormality in prostate cancer, we conclude that susceptibility-weighted imaging is more sensitive and specific than conventional magnetic resonance imaging, diffusion-weighted imaging, and computed tomography in detecting prostate cancer. Furthermore, susceptibility-weighted imaging can identify prostatic calcifications similar to computed tomography, and it is much better than conventional magnetic resonance imaging and diffusion-weighted imaging.

Prostate cancer detection using quantitative T2 and T2 -weighted imaging: The effects of 5-alpha-reductase inhibitors in men on active surveillance

BACKGROUND

T₂ -weighted imaging (T₂ -WI) information has been used in a qualitative manner in the assessment of prostate cancer. Quantitative derivatives (T₂ relaxation time) can be generated from T₂ -WI. These outputs may be useful in helping to discriminate clinically significant prostate cancer from background signal.

PURPOSE/HYPOTHESIS

To investigate changes in quantitative T₂ parameters in lesions and noncancerous tissue of men on active surveillance for prostate cancer taking dutasteride 0.5 mg or placebo daily for 6 months.

STUDY TYPE

Retrospective.

POPULATION/SUBJECTS

Forty men randomized to 6 months of daily dutasteride (n = 20) or placebo (n = 20).

FIELD STRENGTH/SEQUENCE

Multiparametric 3T MRI at baseline and 6 months. This included a multiecho MR sequence for quantification of the T₂ relaxation times, in three regions of interest (index lesion, noncancerous peripheral [PZ] and transitional [TZ] zones). A synthetic signal contrast (T₂ Q contrast) between lesion and noncancerous tissue was assessed using quantitative T₂ values. Signal contrast was calculated using the T₂ -weighted sequence (T₂ W contrast).

ASSESSMENT

Two radiologists reviewed the scans in consensus according to Prostate Imaging Reporting and Data System (PI-RADS v. 2) guidelines.

STATISTICAL TESTS

Wilcoxon and Mann-Whitney U-tests, Spearman's correlation.

RESULTS

When compared to noncancerous tissue, shorter T₂ values were observed within lesions at baseline (83.5 and 80.5 msec) and 6 months (81.5 and 81.9 msec) in the placebo and dutasteride arm, respectively. No significant differences for T₂ W contrast at baseline and after 6 months were observed, both in the placebo (0.40 [0.29-0.49] vs. 0.43 [0.25-0.49]; P = 0.881) and dutasteride arm (0.35 [0.24-0.47] vs. 0.37 [0.22-0.44]; P = 0.668). There was a significant, positive correlation between the T₂ Q contrast and the T₂ W contrast values (r = 0.786; P < 0.001).

DATA CONCLUSION

The exposure to antiandrogen therapy did not significantly influence the T₂ contrast or the T₂ relaxation values in men on active surveillance for prostate cancer.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1646-1653.

Measurement of serum isoform [-2]proPSA derivatives shows superior accuracy to magnetic resonance imaging in the diagnosis of prostate cancer in patients with a total prostate-specific antigen level of 2-10 ng/ml

OBJECTIVE

More accurate diagnostic procedures for prostate cancer are needed to avoid unnecessary biopsy due to the low specificity of prostate-specific antigen (PSA). Recent studies showed that the percentage of serum isoform [-2]proPSA (p2PSA) to free PSA (%p2PSA), the Prostate Health Index (PHI) and magnetic resonance imaging (MRI) were more accurate than PSA. The aim of this study was to test the accuracy of %p2PSA, PHI and MRI in discriminating patients with and without prostate cancer.

MATERIALS AND METHODS

The subjects were 50 consecutive men with a PSA level of 2.0-10.0 ng/ml, who underwent prostate biopsy from October 2012 to July 2014. These patients underwent multiparametric MRI before biopsy, and their serum samples were measured for PSA, free PSA and p2PSA. The sensitivity, specificity and accuracy of PHI, %p2PSA and MRI were compared with PSA in the diagnosis of biopsy-confirmed prostate cancer.

RESULTS

In a univariate analysis, %p2PSA [area under the curve (AUC): 0.811] and PHI (AUC 0.795) were more accurate than MRI (AUC: 0.583) and PSA (AUC: 0.554) for prostate cancer detection. At 60% sensitivity, the specificity of PHI (76.5%) was higher than that of MRI (52.9%). For significant cancer detection, %p2PSA (AUC: 0.745), PHI (AUC: 0.791) and MRI (AUC: 0.739) were marginally more accurate than PSA (AUC: 0.696). At 85% sensitivity, the specificity of MRI (62.1%) was higher than that of PHI (34.5%).

CONCLUSION

PHI and %p2PSA can be used for screening the general population and MRI can be used for detection of significant cancer in patients suspected, from screening tests, of having prostate cancer.

Predicting prostate tumour location from multiparametric MRI using Gaussian kernel support vector machines: a preliminary study

The performance of a support vector machine (SVM) algorithm was investigated to predict prostate tumour location using multi-parametric MRI (mpMRI) data. The purpose was to obtain information of prostate tumour location for the implementation of bio-focused radiotherapy. In vivo mpMRI data were collected from 16 patients prior to radical prostatectomy. Sequences included T2-weighted imaging, diffusion-weighted imaging and dynamic contrast enhanced imaging. In vivo mpMRI was registered with 'ground truth' histology, using ex vivo MRI as an intermediate registration step to improve accuracy. Prostate contours were delineated by a radiation oncologist and tumours were annotated on histology by a pathologist. Five patients with minimal imaging artefacts were selected for this study. A Gaussian kernel SVM was trained and tested on different patient data subsets. Parameters were optimised using leave-oneout cross validation. Signal intensities of mpMRI were used as features and histology annotations as true labels. Prediction accuracy, as well as area under the curve (AUC) of the receiver operating characteristics (ROC) curve, were used to assess performance. Results demonstrated the prediction accuracy ranged from 70.4 to 87.1% and AUC of ROC ranged from 0.81 to 0.94. Additional investigations showed the apparent diffusion coefficient map from diffusion weighted imaging was the most important imaging modality for predicting tumour location. Future work will incorporate additional patient data into the framework to increase the sensitivity and specificity of the model, and will be extended to incorporate predictions of biological characteristics of the tumour which will be used in bio-focused radiotherapy optimisation.

Clinical Imaging of Tumor Metabolism with ¹H Magnetic Resonance Spectroscopy

Magnetic resonance spectroscopy (MRS) is a noninvasive functional technique to evaluate the biochemical behavior of human tissues. This property has been widely used in assessment and therapy monitoring of brain tumors. MRS studies can be implemented outside the brain, with successful and promising results in the evaluation of prostate and breast cancer, although still with limited reproducibility. As a result of technical improvements, malignancies of the musculoskeletal system and abdominopelvic organs can benefit from the molecular information that MRS provides. The technical challenges and main applications in oncology of (1)H MRS in a clinical setting are the focus of this review.

Role of multiparametric MRI in the diagnosis of prostate cancer: update

Prostate cancer is the most common malignancy of the male gender. The role of magnetic resonance imaging has evolved very rapidly over the years to be currently recognized as a fundamental tool in the diagnosis, treatment and follow-up of prostate cancer.

MR Imaging of the Prostate Gland

This article discusses MR imaging of the normal prostate and of disease conditions of the prostate including prostatitis, cystic lesions, amyloidosis, calculi, hematospermia, benign prostatic hyperplasia, and malignancy.

Computer-aided diagnosis: detection and localization of prostate cancer within the peripheral zone

We propose a methodology for prostate cancer detection and localization within the peripheral zone based on combining multiple segmentation techniques. We extract four image features using Gaussian and median filters. Subsequently, we use each image feature separately to generate binary segmentations. Finally, we take the intersection of all four binary segmentations, incorporating a model of the peripheral zone, and perform erosion to remove small false-positive regions. The initial evaluation of this method is based on 275 MRI images from 37 patients, and 86% of the slices were classified correctly with 87% and 86% sensitivity and specificity achieved, respectively. This paper makes two contributions: firstly, a novel computer-aided diagnosis approach, which is based on combining multiple segmentation techniques using only a small number of simple image features, and secondly, the development of the proposed method and its application in prostate cancer detection and localization using a single MRI modality with the results comparable with the state-of-the-art multimodality and advanced computer vision methods in the literature. Copyright © 2015 John Wiley & Sons, Ltd.

Multiparametric MRI for prostate cancer detection: Preliminary results on quantitative analysis of dynamic contrast enhanced imaging, diffusion-weighted imaging and spectroscopy imaging

INTRODUCTION

Early promising data suggest that combined use of both morphological and functional MRI (multi-parametric MR, mpMRI) including MRSI, DWI and DCE may be of additional value for prostate cancer localization and its local staging. The objective of this paper is to evaluate the diagnostic performance of mpMRI in the detection of prostate cancer.

METHODS

Thirty-one consecutive male patients were screened to be enrolled in a single center prospective observational study. All eligible patients underwent multi-parametric MRI and TRUS (Trans Rectal Ultra Sound) guided prostate biopsies. A register, approved by the Institutional Ethics Committee, included patients enrolled in this study. All patients who decided to undergo the MRI examination signed an explicit informed consensus. MRI data were aligned on a common spatial grid and several functional parameters (perfusion, diffusion and metabolic parameters) were computed. Statistical analysis was conducted in order to compare mpMRI with biopsy-based analysis.

RESULTS

Statistically significant differences between median values in high Gleason score (≥5) and low Gleason score (<5) to Wilcox on rank sum test were obtained for MRSI parameters and for plasma fraction (Tofts model) of DCE-MRI. The area under curve obtained with ROC analysis showed that the best-performing single-parameter was vp (plasma fraction of Tofts model), while the best parameters combination to discriminate the area with high Gleason score were (Cho+Cr)/Cit and Cho+Cr. Linear Discrimination Analysis showed that the best results were obtained considering the linear combination of all MRSI parameters and the linear combination of all features (perfusion, diffusion and metabolic parameters).

CONCLUSIONS

In conclusion, our findings showed that by combining morphological MRI, DWI, DCE-MRI and MRSI, an increase in sensitivity and specificity correlated to biopsy Gleason grade could be obtained. Furthermore, morphological and functional MRI could have a diagnostic role in patients with prostate cancer, identifying those patients who will have a negative work-up and those patients at high risk for a high Gleason score cancer of the prostate.

Post-treated prostate cancer: normal findings and signs of local relapse on multiparametric magnetic resonance imaging

The use of multiparametric magnetic resonance imaging (mp-MRI) for prostate cancer has increased over recent years, mainly for detection, staging, and active surveillance. However, suspicion of recurrence in the set of biochemical failure is becoming a significant reason for clinicians to request mp-MRI. Radiologists should be able to recognize the normal post-treatment MRI findings. Fibrosis and atrophic remnant seminal vesicles after prostatectomy are often found and must be differentiated from local relapse. Moreover, brachytherapy, external beam radiotherapy, cryosurgery, and hormonal therapy tend to diffusely decrease the signal intensity of the peripheral zone on T2-weighted images (T2WI) due to the loss of water content, consequently mimicking tumor and hemorrhage. The combination of T2WI and functional studies like diffusion-weighted imaging and dynamic contrast-enhanced improves the identification of local relapse. Tumor recurrence tends to restrict on diffusion images and avidly enhances after contrast administration either within or outside the gland. The authors provide a pictorial review of the normal findings and the signs of local tumor relapse after radical prostatectomy, external beam radiotherapy, brachytherapy, cryosurgery, and hormonal therapy.

Validating multiparametric MRI for diagnosis and monitoring of prostate cancer in patients for active surveillance

PURPOSE

To compare multiparametric magnetic resonance imaging (mpMRI) with transrectal ultrasound-guided prostate biopsy (TRUS-bx) for the diagnosis and monitoring of small-volume prostate cancer (PCa) in patients on active surveillance (AS).

METHODS

In a retrospective cross-sectional validation study, 100 patients on AS for PCa underwent a systematic 12-core TRUS-bx (the gold standard) as well as mpMRI, on either a 1.5 or 3 Tesla scanner (32 and 68 patients, respectively). Three pathologists reported biopsy histology separately. A single, experienced radiologist scored mpMRI scans using the PI-RADS system. We compared left- and right-sided PI-RADS scores of the peripheral zone with TRUS-bx results of the relevant prostate lobe. We then estimated the specificity and sensitivity of mpMRI in diagnosing low-grade low-risk PCa in our AS cohort.

RESULTS

The sensitivity of mpMRI was 37% (95% CI 28-47%) and specificity was 85% (CI 76-92%) for cancer. The negative predictive value was 51% (CI 44-60%), and the positive predictive value was 76% (CI 62-87%). The positive and negative likelihood ratios were 2.5 and 0.7, respectively.

CONCLUSION

Because of its low specificity and low negative predictive value, mpMRI is not suitable for diagnosing low-grade small-volume PCa. However, because of a specificity of 85% and a negative likelihood ratio of 0.7, mpMRI may be useful for follow-up of previously TRUS-bx diagnosed patients who are on AS.

Zone-specific logistic regression models improve classification of prostate cancer on multi-parametric MRI

OBJECTIVES

To assess the interchangeability of zone-specific (peripheral-zone (PZ) and transition-zone (TZ)) multiparametric-MRI (mp-MRI) logistic-regression (LR) models for classification of prostate cancer.

METHODS

Two hundred and thirty-one patients (70 TZ training-cohort; 76 PZ training-cohort; 85 TZ temporal validation-cohort) underwent mp-MRI and transperineal-template-prostate-mapping biopsy. PZ and TZ uni/multi-variate mp-MRI LR-models for classification of significant cancer (any cancer-core-length (CCL) with Gleason > 3 + 3 or any grade with CCL ≥ 4 mm) were derived from the respective cohorts and validated within the same zone by leave-one-out analysis. Inter-zonal performance was tested by applying TZ models to the PZ training-cohort and vice-versa. Classification performance of TZ models for TZ cancer was further assessed in the TZ validation-cohort. ROC area-under-curve (ROC-AUC) analysis was used to compare models.

RESULTS

The univariate parameters with the best classification performance were the normalised T2 signal (T2nSI) within the TZ (ROC-AUC = 0.77) and normalized early contrast-enhanced T1 signal (DCE-nSI) within the PZ (ROC-AUC = 0.79). Performance was not significantly improved by bi-variate/tri-variate modelling. PZ models that contained DCE-nSI performed poorly in classification of TZ cancer. The TZ model based solely on maximum-enhancement poorly classified PZ cancer.

CONCLUSION

LR-models dependent on DCE-MRI parameters alone are not interchangable between prostatic zones; however, models based exclusively on T2 and/or ADC are more robust for inter-zonal application.

KEY POINTS

• The ADC and T2-nSI of benign/cancer PZ are higher than benign/cancer TZ. • DCE parameters are significantly different between benign PZ and TZ, but not between cancerous PZ and TZ. • Diagnostic models containing contrast enhancement parameters have reduced performance when applied across zones.

Multiparametric-MRI in diagnosis of prostate cancer

Multiparametric-magnetic resonance imaging (mp-MRI) has shown promising results in diagnosis, localization, risk stratification and staging of clinically significant prostate cancer. It has also opened up opportunities for focal treatment of prostate cancer. Combinations of T2-weighted imaging, diffusion imaging, perfusion (dynamic contrast-enhanced imaging) and spectroscopic imaging have been used in mp-MRI assessment of prostate cancer, but T2 morphologic assessment and functional assessment by diffusion imaging remains the mainstay for prostate cancer diagnosis on mp-MRI. Because assessment on mp-MRI can be subjective, use of the newly developed standardized reporting Prostate Imaging and Reporting Archiving Data System scoring system and education of specialist radiologists are essential for accurate interpretation. This review focuses on the present status of mp-MRI in prostate cancer and its evolving role in the management of prostate cancer.

Interpretation and reporting multiparametric prostate MRI: a primer for residents and novices

Multiparametric MRI has developed as a tool for prostate cancer lesion detection, characterization, staging, surveillance, and imaging of local recurrence. Given the disease frequency and the growing importance of imaging, as reliance on PSA declines, radiologists involved in prostate MRI imaging must become proficient with the fundamentals of multiparametric prostate MRI (T2WI, DWI, DCE-MRI, and MR spectroscopy). Interpretation and reporting must yield accuracy, consistency, and add value to clinical care. This review provides a primer to novices and trainees learning about multiparametric prostate MRI. MRI technique is presented along with the use of particular MRI sequences. Relevant prostate anatomy is outlined and imaging features of prostate cancer with staging are discussed. Finally structured reporting is introduced, and some limitations of prostate MRI are discussed.

Dynamic contrast-enhanced MRI for the detection of prostate cancer: meta-analysis

OBJECTIVE

The purpose of this study was to systematically review and meta-analyze dynamic contrast-enhanced MRI (DCE-MRI) for the detection of prostate cancer in comparison with standard evaluation with T2-weighted imaging.

MATERIALS AND METHODS

A PubMed electronic database search for the terms "dynamic contrast-enhanced," "prostate," and "MRI" was completed for articles up to September 17, 2013. All included studies had histopathologic correlation. Two by two contingency data were constructed for each study. A binormal bayesian ROC model was used to estimate and compare sensitivity, specificity, and AUC among eligible modalities.

RESULTS

Both DCE-MRI (0.82-0.86) and diffusion-weighted MRI (DWI) (0.84-0.88) yielded significantly better AUC than T2-weighted imaging (0.68-0.77). Moreover, partial AUC for the combination of DCE-MRI, DWI, and T2-weighted imaging was improved significantly (0.111; 0.103-0.119) when compared with DCE-MRI alone (0.079; 0.072-0.085) and T2-weighted imaging alone (0.079; 0.074-0.084) but not DWI alone (0.099; 0.091-0.108). Sensitivity and specificity were similar among the four modalities.

CONCLUSION

DCE-MRI improves AUC of tumor detection overall compared with T2-weighted imaging alone. Methods for DCE-MRI analysis require standardization, but visual analysis performs similar to semiquantitative methods. A two-parameter approach using DCE-MRI and T2-weighted imaging or DWI and T2-weighted imaging may be sufficient, and the latter may be more favorable for most routine prostate cancer imaging.

Symmetry based prostate cancer detection

OBJECTIVE

To retrospectively assess the value of left and right half symmetry analysis in prostate T2 weighted images (T2WI) for improving prostate cancer (PCa) screening.

METHODS

T2WI and other data of a total of 66 males were collected; the control group and cancer group had 33 patients each. Thresholding geometric active contours algorithm was used for prostate region segmentation, and the measure of local reflectional symmetry algorithm was applied to extract the longitudinal symmetry axes. After that, cross-correlation coefficients (CCs) of the left and right halves of each prostate were obtained.

RESULTS

Data analysis showed that the mean and variance of the value of the left and right half CCs of prostate T2WI in the cancer group and control group were 0.73 ± 0.05 and 0.82 ± 0.06, respectively. The area under the receiver operating characteristic curve was 0.87, and the specificity and the sensitivity were 91% and 70%, respectively. The p < 0.001 indicated that the value of CCs of the prostates between the two groups was significantly different.

CONCLUSION

The symmetry in T2WI is a potential useful index for PCa screening and has a potential value for PCa detection and localizations of tumours for biopsy.

ADVANCES IN KNOWLEDGE

Texture bilateral symmetry of prostate T2WI is employed to screen the suspected prostate tumour.

Computer-Aided Detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review

Prostate cancer is the second most diagnosed cancer of men all over the world. In the last few decades, new imaging techniques based on Magnetic Resonance Imaging (MRI) have been developed to improve diagnosis. In practise, diagnosis can be affected by multiple factors such as observer variability and visibility and complexity of the lesions. In this regard, computer-aided detection and computer-aided diagnosis systems have been designed to help radiologists in their clinical practice. Research on computer-aided systems specifically focused for prostate cancer is a young technology and has been part of a dynamic field of research for the last 10 years. This survey aims to provide a comprehensive review of the state-of-the-art in this lapse of time, focusing on the different stages composing the work-flow of a computer-aided system. We also provide a comparison between studies and a discussion about the potential avenues for future research. In addition, this paper presents a new public online dataset which is made available to the research community with the aim of providing a common evaluation framework to overcome some of the current limitations identified in this survey.

Logistic regression model for diagnosis of transition zone prostate cancer on multi-parametric MRI

OBJECTIVES

We aimed to develop logistic regression (LR) models for classifying prostate cancer within the transition zone on multi-parametric magnetic resonance imaging (mp-MRI).

METHODS

One hundred and fifty-five patients (training cohort, 70 patients; temporal validation cohort, 85 patients) underwent mp-MRI and transperineal-template-prostate-mapping (TPM) biopsy. Positive cores were classified by cancer definitions: (1) any-cancer; (2) definition-1 [≥Gleason 4 + 3 or ≥ 6 mm cancer core length (CCL)] [high risk significant]; and (3) definition-2 (≥Gleason 3 + 4 or ≥ 4 mm CCL) cancer [intermediate-high risk significant]. For each, logistic-regression mp-MRI models were derived from the training cohort and validated internally and with the temporal cohort. Sensitivity/specificity and the area under the receiver operating characteristic (ROC-AUC) curve were calculated. LR model performance was compared to radiologists' performance.

RESULTS

Twenty-eight of 70 patients from the training cohort, and 25/85 patients from the temporal validation cohort had significant cancer on TPM. The ROC-AUC of the LR model for classification of cancer was 0.73/0.67 at internal/temporal validation. The radiologist A/B ROC-AUC was 0.65/0.74 (temporal cohort). For patients scored by radiologists as Prostate Imaging Reporting and Data System (Pi-RADS) score 3, sensitivity/specificity of radiologist A 'best guess' and LR model was 0.14/0.54 and 0.71/0.61, respectively; and radiologist B 'best guess' and LR model was 0.40/0.34 and 0.50/0.76, respectively.

CONCLUSIONS

LR models can improve classification of Pi-RADS score 3 lesions similar to experienced radiologists.

KEY POINTS

• MRI helps find prostate cancer in the anterior of the gland • Logistic regression models based on mp-MRI can classify prostate cancer • Computers can help confirm cancer in areas doctors are uncertain about.

High-resolution diffusion-weighted imaging of the prostate

OBJECTIVE

The purpose of this study was to evaluate the effect of increasing the spatial resolution of the prostate DWI protocol on image quality and lesion conspicuity.

SUBJECTS AND METHODS

Twenty-nine patients with biopsy-proven prostate cancer undergoing MRI examinations were imaged with two diffusion-weighted imaging (DWI) protocols: current standard clinical protocol (6.7 mm(3) voxels) and a new high-resolution protocol (3.1 mm(3) voxels). Diffusion-weighted images were independently and subjectively scored on lesion conspicuity, internal architecture definition, and overall image quality by two radiologists. Average apparent diffusion coefficient (ADC) values were measured in normal tissue and cancerous lesions on both sequences. Reader scores and ADC and contrast values were compared between the two protocols. Cancer ADC values were correlated with Gleason scores.

RESULTS

The signal-to-noise ratio of the new high-resolution DWI protocol was 40% lower than that of the standard protocol. The reader scores were higher by 0.73 (range, 0.29-1.16) grades, or 19% (range, 7-32%), on average, for the new protocol, indicating better image quality. The average ADC values were 8% higher with the new protocol, with ADC contrast values between cancer and normal prostate unchanged. There was marginally significant correlation of cancer ADC values with Gleason scores (p = 0.05, r ≈ -0.36).

CONCLUSION

We showed that for DWI of the prostate at 3-7 mm(3) voxel sizes the benefits of higher spatial resolution outweigh the effects of reduced signal-to-noise and contrast-to-noise ratios, potentially improving the sensitivity to small or sparse prostate cancers. Radiologists can consider using higher-spatial-resolution DWI sequences in their practices.

Imaging and intervention in prostate cancer: Current perspectives and future trends

Prostate cancer is the commonest malignancy in men that causes significant morbidity and mortality worldwide. Screening by digital rectal examination (DRE) and serum prostate-specific antigen (PSA) is used despite its limitations. Gray-scale transrectal ultrasound (TRUS), used to guide multiple random prostatic biopsies, misses up to 20% cancers and frequently underestimates the grade of malignancy. Increasing the number of biopsy cores marginally increases the yield. Evolving techniques of real-time ultrasound elastography (RTE) and contrast-enhanced ultrasound (CEUS) are being investigated to better detect and improve the yield by allowing “targeted” biopsies. Last decade has witnessed rapid developments in magnetic resonance imaging (MRI) for improved management of prostate cancer. In addition to the anatomical information, it is capable of providing functional information through diffusion-weighted imaging (DWI), magnetic resonance spectroscopy (MRS), and dynamic contrast-enhanced (DCE) MRI. Multi-parametric MRI has the potential to exclude a significant cancer in majority of cases. Inclusion of MRI before prostatic biopsy can reduce the invasiveness of the procedure by limiting the number of cores needed to make a diagnosis and support watchful waiting in others. It is made possible by targeted biopsies as opposed to random. With the availability of minimally invasive therapeutic modalities like high-intensity focused ultrasound (HIFU) and interstitial laser therapy, detecting early cancer is even more relevant today. [18F]--fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸FDG PET/CT) has no role in the initial evaluation of prostate cancer. Choline PET has been recently found to be more useful. Fluoride-PET has a higher sensitivity and resolution than a conventional radionuclide bone scan in detecting skeletal metastases.

Prostate cancer: role of pretreatment multiparametric 3-T MRI in predicting biochemical recurrence after radical prostatectomy

OBJECTIVE

The purpose of this study is to retrospectively investigate whether pretreatment multiparametric MRI findings can predict biochemical recurrence in patients who underwent radical prostatectomy (RP) for localized prostate cancer.

MATERIALS AND METHODS

In this study, 282 patients with biopsy-proven prostate cancer who received RP underwent pretreatment MRI using a phased-array coil at 3 T, including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced MRI (DCE-MRI). MRI variables included apparent tumor presence on combined imaging sequences, extracapsular extension, and tumor size on DWI or DCE-MRI. Clinical variables included baseline prostate-specific antigen (PSA) level, clinical stage, and Gleason score at biopsy. The relationship between clinical and imaging variables and biochemical recurrence was evaluated using Cox regression analysis.

RESULTS

After a median follow-up of 26 months, biochemical recurrence developed in 61 patients (22%). Univariate analysis revealed that all the imaging and clinical variables were significantly associated with biochemical recurrence (p < 0.01). On multivariate analysis, however, baseline PSA level (p = 0.002), Gleason score at biopsy (p = 0.024), and apparent tumor presence on combined T2WI, DWI, and DCE-MRI (p = 0.047) were the only significant independent predictors of biochemical recurrence. Of the independent predictors, apparent tumor presence on combined T2WI, DWI, and DCE-MRI showed the highest hazard ratio (2.38) compared with baseline PSA level (hazard ratio, 1.05) and Gleason score at biopsy (hazard ratio, 1.34).

CONCLUSION

The apparent tumor presence on combined T2WI, DWI, and DCE-MRI of pretreatment MRI is an independent predictor of biochemical recurrence after RP. This finding may be used to construct a predictive model for biochemical recurrence after surgery.

Incremental learning with SVM for multimodal classification of prostatic adenocarcinoma

Robust detection of prostatic cancer is a challenge due to the multitude of variants and their representation in MR images. We propose a pattern recognition system with an incremental learning ensemble algorithm using support vector machines (SVM) tackling this problem employing multimodal MR images and a texture-based information strategy. The proposed system integrates anatomic, texture, and functional features. The data set was preprocessed using B-Spline interpolation, bias field correction and intensity standardization. First- and second-order angular independent statistical approaches and rotation invariant local phase quantization (RI-LPQ) were utilized to quantify texture information. An incremental learning ensemble SVM was implemented to suit working conditions in medical applications and to improve effectiveness and robustness of the system. The probability estimation of cancer structures was calculated using SVM and the corresponding optimization was carried out with a heuristic method together with a 3-fold cross-validation methodology. We achieved an average sensitivity of 0.844 ± 0.068 and a specificity of 0.780 ± 0.038, which yielded superior or similar performance to current state of the art using a total database of only 41 slices from twelve patients with histological confirmed information, including cancerous, unhealthy non-cancerous and healthy prostate tissue. Our results show the feasibility of an ensemble SVM being able to learn additional information from new data while preserving previously acquired knowledge and preventing unlearning. The use of texture descriptors provides more salient discriminative patterns than the functional information used. Furthermore, the system improves selection of information, efficiency and robustness of the classification. The generated probability map enables radiologists to have a lower variability in diagnosis, decrease false negative rates and reduce the time to recognize and delineate structures in the prostate.