Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images

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.

Association of bone mineral density with bone texture attributes extracted using routine magnetic resonance imaging

OBJECTIVE

Dual-energy X-ray absorptiometry (DXA)-derived bone mineral density (BMD) often fails to predict fragility fractures. Quantitative textural analysis using magnetic resonance imaging (MRI) may potentially yield useful radiomic features to predict fractures. We aimed to investigate the correlation between BMD and texture attributes (TAs) extracted from MRI scans and the interobserver reproducibility of the analysis.

METHODS

Forty-nine volunteers underwent lumbar spine 1.5-T MRI and DXA. Three-dimensional (3-D) gray-level co-occurrence matrices were measured from routine sagittal T2 fast spin-echo images using the IBEX software. Twenty-two TAs were extracted from 3-D segmented L3 vertebrae. The estimated concordance coefficient was calculated using linear regression analysis. A Pearson correlation coefficient analysis was performed to evaluate the correlation between BMD and the TAs. Interobserver reproducibility was assessed with the concordance coefficient described by Lin.

RESULTS

The results revealed a fair-to-moderate significant correlation between BMD and 13 TAs (r=-0.20 to 0.39; p<0.05). Eight TAs (autocorrelation, energy, homogeneity 1, homogeneity 1.1, maximum probability, sum average, sum variance, and inverse difference normalized) negatively correlated with BMD (r=-0.20 to -0.38; p<0.05), whereas five TAs (dissimilarity, difference entropy, entropy, sum entropy, and information measure corr 1) positively correlated with BMD (r=0.29-0.39; p<0.05). The interobserver agreement was almost perfect for all significant TAs (95% confidence interval, 0.92-1.00; p<0.05).

CONCLUSION

Specific TAs could be reliably extracted from routine MRI and correlated with BMD. Our results encourage future evaluation of the potential usefulness of quantitative texture measurements from MRI scans for predicting fragility fractures.

A Transfer Learning Approach for Malignant Prostate Lesion Detection on Multiparametric MRI

Purpose:

In prostate focal therapy, it is important to accurately localize malignant lesions in order to increase biological effect of the tumor region while achieving a reduction in dose to noncancerous tissue. In this work, we proposed a transfer learning–based deep learning approach, for classification of prostate lesions in multiparametric magnetic resonance imaging images.

Methods:

Magnetic resonance imaging images were preprocessed to remove bias artifact and normalize the data. Two state-of-the-art deep convolutional neural network models, InceptionV3 and VGG-16, were pretrained on ImageNet data set and retuned on the multiparametric magnetic resonance imaging data set. As lesion appearances differ by the prostate zone that it resides in, separate models were trained. Ensembling was performed on each prostate zone to improve area under the curve. In addition, the predictions from lesions on each prostate zone were scaled separately to increase the area under the curve for all lesions combined.

Results:

The models were tuned to produce the highest area under the curve on validation data set. When it was applied to the unseen test data set, the transferred InceptionV3 model achieved an area under the curve of 0.81 and the transferred VGG-16 model achieved an area under the curve of 0.83. This was the third best score among the 72 methods from 33 participating groups in ProstateX competition.

Conclusion:

The transfer learning approach is a promising method for prostate cancer detection on multiparametric magnetic resonance imaging images. Features learned from ImageNet data set can be useful for medical images.

Prostate Cancer Detection using Deep Convolutional Neural Networks

Prostate cancer is one of the most common forms of cancer and the third leading cause of cancer death in North America. As an integrated part of computer-aided detection (CAD) tools, diffusion-weighted magnetic resonance imaging (DWI) has been intensively studied for accurate detection of prostate cancer. With deep convolutional neural networks (CNNs) significant success in computer vision tasks such as object detection and segmentation, different CNN architectures are increasingly investigated in medical imaging research community as promising solutions for designing more accurate CAD tools for cancer detection. In this work, we developed and implemented an automated CNN-based pipeline for detection of clinically significant prostate cancer (PCa) for a given axial DWI image and for each patient. DWI images of 427 patients were used as the dataset, which contained 175 patients with PCa and 252 patients without PCa. To measure the performance of the proposed pipeline, a test set of 108 (out of 427) patients were set aside and not used in the training phase. The proposed pipeline achieved area under the receiver operating characteristic curve (AUC) of 0.87 (95[Formula: see text] Confidence Interval (CI): 0.84-0.90) and 0.84 (95[Formula: see text] CI: 0.76-0.91) at slice level and patient level, respectively.

Artificial intelligence and neural networks in urology: current clinical applications

INTRODUCTION

As we enter the era of "big data," an increasing amount of complex health-care data will become available. These data are often redundant, "noisy," and characterized by wide variability. In order to offer a precise and transversal view of a clinical scenario the artificial intelligence (AI) with machine learning (ML) algorithms and Artificial neuron networks (ANNs) process were adopted, with a promising wide diffusion in the near future. The present work aims to provide a comprehensive and critical overview of the current and potential applications of AI and ANNs in urology.

EVIDENCE ACQUISITION

A non-systematic review of the literature was performed by screening Medline, PubMed, the Cochrane Database, and Embase to detect pertinent studies regarding the application of AI and ANN in Urology.

EVIDENCE SYNTHESIS

The main application of AI in urology is the field of genitourinary cancers. Focusing on prostate cancer, AI was applied for the prediction of prostate biopsy results. For bladder cancer, the prediction of recurrence-free probability and diagnostic evaluation were analysed with ML algorithms. For kidney and testis cancer, anecdotal experiences were reported for staging and prediction of diseases recurrence. More recently, AI has been applied in non-oncological diseases like stones and functional urology.

CONCLUSIONS

AI technologies are growing their role in health care; but, up to now, their "real-life" implementation remains limited. However, in the near future, the potential of AI-driven era could change the clinical practice in Urology, improving overall patient outcomes.

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features

Microscopic biopsy images are coloured in nature because pathologists use the haematoxylin and eosin chemical colour dyes for biopsy examinations. In this study, biopsy images are used for histological grading and the analysis of benign and malignant prostate tissues. The following PCa grades are analysed in the present study: benign, grade 3, grade 4, and grade 5. Biopsy imaging has become increasingly important for the clinical assessment of PCa. In order to analyse and classify the histological grades of prostate carcinomas, pixel-based colour moment descriptor (PCMD) and gray-level co-occurrence matrix (GLCM) methods were used to extract the most significant features for multilayer perceptron (MLP) neural network classification. Haar wavelet transformation was carried out to extract GLCM texture features, and colour features were extracted from RGB (red/green/blue) colour images of prostate tissues. The MANOVA statistical test was performed to select significant features based on F-values and P-values using the R programming language. We obtained an average highest accuracy of 92.7% using level-1 wavelet texture and colour features. The MLP classifier performed well, and our study shows promising results based on multi-feature classification of histological sections of prostate carcinomas.

Novel imaging techniques of rectal cancer: what do radiomics and radiogenomics have to offer? A literature review

INTRODUCTION

As computational capabilities have advanced, radiologists and their collaborators have looked for novel ways to analyze diagnostic images. This has resulted in the development of radiomics and radiogenomics as new fields in medical imaging. Radiomics and radiogenomics may change the practice of medicine, particularly for patients with colorectal cancer. Radiomics corresponds to the extraction and analysis of numerous quantitative imaging features from conventional imaging modalities in correlation with several endpoints, including the prediction of pathology, genomics, therapeutic response, and clinical outcome. In radiogenomics, qualitative and/or quantitative imaging features are extracted and correlated with genetic profiles of the imaged tissue. Thus far, several studies have evaluated the use of radiomics and radiogenomics in patients with colorectal cancer; however, there are challenges to be overcome before its routine implementation including challenges related to sample size, model design and interpretability, and the lack of robust multicenter validation set.

MATERIAL AND METHODS

In this article, we will review the concepts of radiomics and radiogenomics and their potential applications in rectal cancer.

CONCLUSION

Radiologists should be aware of the basic concepts, benefits, pitfalls, and limitations of new radiomic and radiogenomics techniques to achieve a balanced interpretation of the results.

Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet

Multi-parametric MRI (mp-MRI) is considered the best non-invasive imaging modality for diagnosing prostate cancer (PCa). However, mp-MRI for PCa diagnosis is currently limited by the qualitative or semi-quantitative interpretation criteria, leading to inter-reader variability and a suboptimal ability to assess lesion aggressiveness. Convolutional neural networks (CNNs) are a powerful method to automatically learn the discriminative features for various tasks, including cancer detection. We propose a novel multi-class CNN, FocalNet, to jointly detect PCa lesions and predict their aggressiveness using Gleason score (GS). FocalNet characterizes lesion aggressiveness and fully utilizes distinctive knowledge from mp-MRI. We collected a prostate mp-MRI dataset from 417 patients who underwent 3T mp-MRI exams prior to robotic-assisted laparoscopic prostatectomy. FocalNet was trained and evaluated in this large study cohort with fivefold cross validation. In the free-response receiver operating characteristics (FROC) analysis for lesion detection, FocalNet achieved 89.7% and 87.9% sensitivity for index lesions and clinically significant lesions at one false positive per patient, respectively. For the GS classification, evaluated by the receiver operating characteristics (ROC) analysis, FocalNet received the area under the curve of 0.81 and 0.79 for the classifications of clinically significant PCa (GS ≥ 3 + 4) and PCa with GS ≥ 4 + 3, respectively. With the comparison to the prospective performance of radiologists using the current diagnostic guideline, FocalNet demonstrated comparable detection sensitivity for index lesions and clinically significant lesions, only 3.4% and 1.5% lower than highly experienced radiologists without statistical significance.

PI-RADS 3 Lesions: Role of Prostate MRI Texture Analysis in the Identification of Prostate Cancer

PURPOSE

To determine the diagnostic performance of texture analysis of prostate MRI for the diagnosis of prostate cancer among Prostate Imaging Reporting and Data System (PI-RADS) 3 lesions.

MATERIALS AND METHODS

Forty-three patients with at least 1 PI-RADS 3 lesion on prostate MRI performed between June 2016 and January 2019 were retrospectively included. Reference standard was pathological analysis of radical prostatectomy specimens or MRI-targeted biopsies. Texture analysis extraction of target lesions was performed on axial T2-weighted images and apparent diffusion coefficient (ADC) maps using a radiomic software. Lesions were categorized as prostate cancer (Gleason score [GS] ≥ 6), and no prostate cancer. Statistical analysis was performed using the generalized linear model (GLM) regression and the discriminant analysis (DA). AUROC with 95% confidence intervals were calculated to assess the diagnostic performance of standalone features and predictive models for the diagnosis of prostate cancer (GS ≥ 6) and clinically-significant prostate cancer (GS ≥ 7).

RESULTS

The analysis of 46 PI-RADS 3 lesions (ie, 27 [58.7%] no prostate cancers; 19 [41.3%] prostate cancers) revealed 9 and 6 independent texture parameters significantly correlated with the final histopathological results on T2-weighted and ADC maps images, respectively. The resulting GLM and DA predictive models for the diagnosis of prostate cancer yielded an AUROC of 0.775 and 0.779 on T2-weighted images or 0.815 and 0.821 on ADC maps images. For the diagnosis of clinically-significant prostate cancer, the resulting GLM and DA predictive models for the diagnosis of prostate cancer yielded an AUROC of 0.769 and 0.817 on T2-weighted images or 0.749 and 0.744 on ADC maps images.

CONCLUSION

Texture analysis of PI-RADS 3 lesions on T2-weighted and ADC maps images helps identifying prostate cancer. The good diagnostic performance of the combination of multiple radiomic features for the diagnosis of prostate cancer may help predicting lesions where aggressive management may be warranted.

MRI-derived radiomics: methodology and clinical applications in the field of pelvic oncology

Personalized medicine aims at offering optimized treatment options and improved survival for cancer patients based on individual variability. The success of precision medicine depends on robust biomarkers. Recently, the requirement for improved non-biologic biomarkers that reflect tumor biology has emerged and there has been a growing interest in the automatic extraction of quantitative features from medical images, denoted as radiomics. Radiomics as a methodological approach can be applied to any image and most studies have focused on PET, CT, ultrasound, and MRI. Here, we aim to present an overview of the radiomics workflow as well as the major challenges with special emphasis on the use of multiparametric MRI datasets. We then reviewed recent studies on radiomics in the field of pelvic oncology including prostate, cervical, and colorectal cancer.

Current status of artificial intelligence applications in urology and their potential to influence clinical practice

OBJECTIVE

To investigate the applications of artificial intelligence (AI) in diagnosis, treatment and outcome predictionin urologic diseases and evaluate its advantages over traditional models and methods.

MATERIALS AND METHODS

A literature search was performed after PROSPERO registration (CRD42018103701) and in compliance with Preferred Reported Items for Systematic Reviews and Meta-Analyses (PRISMA) methods. Articles between 1994 and 2018 using the search terms "urology", "artificial intelligence", "machine learning" were included and categorized by the application of AI in urology. Review articles, editorial comments, articles with no full-text access, and nonurologic studies were excluded.

RESULTS

Initial search yielded 231 articles, but after excluding duplicates and following full-text review and examination of article references, only 111 articles were included in the final analysis. AI applications in urology include: utilizing radiomic imaging or ultrasonic echo data to improve or automate cancer detection or outcome prediction, utilizing digitized tissue specimen images to automate detection of cancer on pathology slides, and combining patient clinical data, biomarkers, or gene expression to assist disease diagnosis or outcome prediction. Some studies employed AI to plan brachytherapy and radiation treatments while others used video based or robotic automated performance metrics to objectively evaluate surgical skill. Compared to conventional statistical analysis, 71.8% of studies concluded that AI is superior in diagnosis and outcome prediction.

CONCLUSION

AI has been widely adopted in urology. Compared to conventional statistics AI approaches are more accurate in prediction and more explorative for analyzing large data cohorts. With an increasing library of patient data accessible to clinicians, AI may help facilitate evidence-based and individualized patient care.

Radiologic-Radiomic Machine Learning Models for Differentiation of Benign and Malignant Solid Renal Masses: Comparison With Expert-Level Radiologists

OBJECTIVE. The objective of our study was to compare the performance of radiologicradiomic machine learning (ML) models and expert-level radiologists for differentiation of benign and malignant solid renal masses using contrast-enhanced CT examinations. MATERIALS AND METHODS. This retrospective study included a cohort of 254 renal cell carcinomas (RCCs) (190 clear cell RCCs [ccRCCs], 38 chromophobe RCCs [chrRCCs], and 26 papillary RCCs [pRCCs]), 26 fat-poor angioleiomyolipomas, and 10 oncocytomas with preoperative CT examinations. Lesions identified by four expert-level radiologists (> 3000 genitourinary CT and MRI studies) were manually segmented for radiologicradiomic analysis. Disease-specific support vector machine radiologic-radiomic ML models for classification of renal masses were trained and validated using a 10-fold cross-validation. Performance values for the expert-level radiologists and radiologic-radiomic ML models were compared using the McNemar test. RESULTS. The performance values for the four radiologists were as follows: sensitivity of 73.7-96.8% (median, 84.5%; variance, 122.7%) and specificity of 48.4-71.9% (median, 61.8%; variance, 161.6%) for differentiating ccRCCs from pRCCs and chrRCCs; sensitivity of 73.7-96.8% (median, 84.5%; variance, 122.7%) and specificity of 52.8-88.9% for differentiating ccRCCs from fat-poor angioleiomyolipomas and oncocytomas (median, 80.6%; variance, 269.1%); and sensitivity of 28.1-60.9% (median, 84.5%; variance, 122.7%) and specificity of 75.0-88.9% for differentiating pRCCs and chrRCCs from fat-poor angioleiomyolipomas and oncocytomas (median, 50.0%; variance, 191.1%). After a 10-fold cross-validation, the radiologic-radiomic ML model yielded the following performance values for differentiating ccRCCs from pRCCs and chrRCCs, ccRCCs from fat-poor angioleiomyolipomas and oncocytomas, and pRCCs and chrRCCs from fat-poor angioleiomyolipomas and oncocytomas: a sensitivity of 90.0%, 86.3%, and 73.4% and a specificity of 89.1%, 83.3%, and 91.7%, respectively. CONCLUSION. Expert-level radiologists had obviously large variances in performance for differentiating benign from malignant solid renal masses. Radiologic-radiomic ML can be a potential way to improve interreader concordance and performance.

Computed Tomography-Derived Radiomic Metrics Can Identify Responders to Immunotherapy in Ovarian Cancer

PURPOSE

To determine if radiomic measures of tumor heterogeneity derived from baseline contrast-enhanced computed tomography (CE-CT) are associated with durable clinical benefit and time to off-treatment in patients with recurrent ovarian cancer (OC) enrolled in prospective immunotherapeutic trials.

MATERIALS AND METHODS

This retrospective study included 75 patients with recurrent OC who were enrolled in prospective immunotherapeutic trials (n = 74) or treated off-label (n = 1) and had baseline CE-CT scans. Disease burden (total tumor volume, number of disease sites), radiomic measures of intertumor heterogeneity (cluster-site entropy, cluster-site dissimilarity), and intratumor heterogeneity of the largest lesion (Haralick texture features) were computed. Associations of clinical, conventional imaging, and radiomic measures with durable clinical benefit and time to off-treatment were examined.

RESULTS

In univariable analysis, fewer disease sites, lower intertumor heterogeneity (lower cluster-site entropy, lower cluster-site dissimilarity), and lower intratumor heterogeneity of the largest lesion (higher energy) were significantly associated with durable clinical benefit (P ≤ .031). More disease sites, presence of pleural disease and/or distant metastases, higher intertumor heterogeneity (higher cluster-site entropy, higher cluster-site dissimilarity), and higher intratumor heterogeneity of the largest lesion (higher Contrast_{largest-lesion}) were significantly associated with shorter time to off-treatment (P ≤ .034). In multivariable analysis, higher Energy_{largest-lesion} (indicator of lower intratumor heterogeneity; P = .006; odds ratio, 1.41) and fewer disease sites (P = .003; odds ratio, 1.64) remained significant indicators of durable clinical benefit (multivariable model C-index, 0.821). Higher cluster-site dissimilarity (indicator of higher intertumor heterogeneity) was a modest but single independent indicator of shorter time to off-treatment (P = .004; hazard ratio, 1.19; C-index, 0.6).

CONCLUSION

Fewer disease sites and lower intra- and intertumor heterogeneity modeled from the baseline CE-CT may indicate better response of OC to immunotherapy.

Automatic stratification of prostate tumour aggressiveness using multiparametric MRI: a horizontal comparison of texture features

Background: Previous studies have identified apparent diffusion coefficient (ADC) from diffusion-weighted imaging (DWI) can stratify prostate cancer into high- and low-grade disease (HG and LG, respectively). In this study, we consider the improvement of incorporating texture features (TFs) from T2-weighted (T2w) multiparametric magnetic resonance imaging (mpMRI) relative to mpMRI alone to predict HG and LG disease. Material and methods: In vivo mpMRI was acquired from 30 patients prior to radical prostatectomy. Sequences included T2w imaging, DWI and dynamic contrast enhanced (DCE) MRI. In vivo mpMRI data were co-registered with 'ground truth' histology. Tumours were delineated on the histology with Gleason scores (GSs) and classed as HG if GS ≥ 4 + 3, or LG if GS ≤ 3 + 4. Texture features based on three statistical families, namely the grey-level co-occurrence matrix (GLCM), grey-level run length matrix (GLRLM) and the grey-level size zone matrix (GLSZM), were computed from T2w images. Logistic regression models were trained using different feature subsets to classify each lesion as either HG or LG. To avoid overfitting, fivefold cross validation was applied on feature selection, model training and performance evaluation. Performance of all models generated was evaluated using the area under the curve (AUC) method. Results: Consistent with previous studies, ADC was found to discriminate between HG and LG with an AUC of 0.76. Of the three statistical TF families, GLCM (plus select mpMRI features including ADC) scored the highest AUC (0.84) with GLRLM plus mpMRI similarly performing well (AUC  =  0.82). When all TFs were considered in combination, an AUC of 0.91 (95% confidence interval 0.87-0.95) was achieved. Conclusions: Incorporating T2w TFs significantly improved model performance for classifying prostate tumour aggressiveness. This result, however, requires further validation in a larger patient cohort.

The Promise of Digital Biopsy for the Prediction of Tumor Molecular Features and Clinical Outcomes Associated With Immunotherapy

Immunotherapy by immune checkpoint inhibitors has emerged as an effective treatment for a slight proportion of patients with aggressive tumors. Currently, some molecular determinants, such as the expression of the programmed cell death ligand-1 (PD-L1) or the tumor mutational burden (TMB) have been used in the clinical practice as predictive biomarkers, although they fail in consistency, applicability, or reliability to precisely identify the responding patients mainly because of their spatial intratumoral heterogeneity. Therefore, new biomarkers for early prediction of patient response to immunotherapy, that could integrate several approaches, are eagerly sought. Novel methods of quantitative image analysis (such as radiomics or pathomics) might offer a comprehensive approach providing spatial and temporal information from macroscopic imaging features potentially predictive of underlying molecular drivers, tumor-immune microenvironment, tumor-related prognosis, and clinical outcome (in terms of response or toxicity) following immunotherapy. Preliminary results from radiomics and pathomics analysis have demonstrated their ability to correlate image features with PD-L1 tumor expression, high CD3 cell infiltration or CD8 cell expression, or to produce an image signature concordant with gene expression. Furthermore, the predictive power of radiomics and pathomics can be improved by combining information from other modalities, such as blood values or molecular features, leading to increase the accuracy of these models. Thus, “digital biopsy,” which could be defined by non-invasive and non-consuming digital techniques provided by radiomics and pathomics, may have the potential to allow for personalized approach for cancer patients treated with immunotherapy.

Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization

Purpose

To develop and validate a classifier system for prediction of prostate cancer (PCa) Gleason score (GS) using radiomics and texture features of T₂-weighted imaging (T₂w), diffusion weighted imaging (DWI) acquired using high b values, and T₂-mapping (T₂).

Methods

T₂w, DWI (12 b values, 0–2000 s/mm²), and T₂ data sets of 62 patients with histologically confirmed PCa were acquired at 3T using surface array coils. The DWI data sets were post-processed using monoexponential and kurtosis models, while T₂w was standardized to a common scale. Local statistics and 8 different radiomics/texture descriptors were utilized at different configurations to extract a total of 7105 unique per-tumor features. Regularized logistic regression with implicit feature selection and leave pair out cross validation was used to discriminate tumors with 3+3 vs >3+3 GS.

Results

In total, 100 PCa lesions were analysed, of those 20 and 80 had GS of 3+3 and >3+3, respectively. The best model performance was obtained by selecting the top 1% features of T₂w, ADC_m and K with ROC AUC of 0.88 (95% CI of 0.82–0.95). Features from T₂ mapping provided little added value. The most useful texture features were based on the gray-level co-occurrence matrix, Gabor transform, and Zernike moments.

Conclusion

Texture feature analysis of DWI, post-processed using monoexponential and kurtosis models, and T₂w demonstrated good classification performance for GS of PCa. In multisequence setting, the optimal radiomics based texture extraction methods and parameters differed between different image types.

Repeatability of Multiparametric Prostate MRI Radiomics Features

In this study we assessed the repeatability of radiomics features on small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI). The premise of radiomics is that quantitative image-based features can serve as biomarkers for detecting and characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics features under various preprocessing and extraction configurations including various image normalization schemes, different image pre-filtering, and different bin widths for image discretization. Although we found many radiomics features and preprocessing combinations with high repeatability (Intraclass Correlation Coefficient > 0.85), our results indicate that overall the repeatability is highly sensitive to the processing parameters. Neither image normalization, using a variety of approaches, nor the use of pre-filtering options resulted in consistent improvements in repeatability. We urge caution when interpreting radiomics features and advise paying close attention to the processing configuration details of reported results. Furthermore, we advocate reporting all processing details in radiomics studies and strongly recommend the use of open source implementations.

Computed Tomography-based Radiomics for Risk Stratification in Prostate Cancer

PURPOSE

To explore the role of Computed tomography (CT)-based radiomics features in prostate cancer risk stratification.

METHODS AND MATERIALS

The study population consisted of 506 patients with prostate cancer collected from a clinically annotated database. After applying exclusion criteria, 342 patients were included in the final analysis. CT-based radiomics features were extracted from planning CT scans for prostate gland-only structure, and machine learning was used to train models for Gleason score (GS) and risk group (RG) classifications. Repeated cross-validation was used. The discriminatory performance of the developed models was assessed using receiver operating characteristic area under the curve (AUC) analysis.

RESULTS

Classifiers using CT-based radiomics features distinguished between GS ≤ 6 versus GS ≥ 7 with AUC = 0.90 and GS 7(3 + 4) versus GS 7(4 + 3) with AUC = 0.98. Developed classifiers also showed excellent performance in distinguishing low versus high RG (AUC = 0.96) and low versus intermediate RG (AUC = 1.00), but poorer performance was observed for GS 7 versus GS > 7 (AUC = 0.69). An overall modest performance was observed for validation on holdout data sets with the highest AUC of 0.75 for classifiers of low versus high RG and an AUC of 0.70 for GS 7 versus GS > 7.

CONCLUSIONS

Our results show that radiomics features from routinely acquired planning CT scans could provide insights into prostate cancer aggressiveness in a noninvasive manner. Assessing models on training data sets, the classifiers were especially accurate in discerning high-risk from low-risk patients and in classifying GS 7 versus GS > 7 and GS 7(3 + 4) versus G7(4 + 3); however, classifiers were less adept at distinguishing high RG versus intermediate RG. External validation and prospective studies are warranted to verify the presented findings. These findings could potentially guide targeted radiation therapy strategies in radical intent radiation therapy for prostate cancer.

Radiomics: an Introductory Guide to What It May Foretell

PURPOSE OF REVIEW

To briefly review the radiomics concept, its applications, and challenges in oncology in the era of precision medicine.

RECENT FINDINGS

Over the last 5 years, more than 500 studies have evaluated the role of radiomics to predict tumor diagnosis, genetic pattern, tumor response to therapy, and survival in multiple cancers. This new post-processing method is aimed at extracting multiple quantitative features from the image and converting them into mineable data. Radiomics models developed have shown promising results and may play a role in the near future in the daily patient management especially to assess tumor heterogeneity acting as a whole tumor virtual biopsy. For now, radiomics is limited by its lack of standardization; future challenges will be to provide robust and reproducible metrics extracted from large multicenter databases.

Radiomics and radiogenomics of prostate cancer

Radiomics and radiogenomics are attractive research topics in prostate cancer. Radiomics mainly focuses on extraction of quantitative information from medical imaging, whereas radiogenomics aims to correlate these imaging features to genomic data. The purpose of this review is to provide a brief overview summarizing recent progress in the application of radiomics-based approaches in prostate cancer and to discuss the potential role of radiogenomics in prostate cancer.

Unenhanced CT Texture Analysis of Clear Cell Renal Cell Carcinomas: A Machine Learning-Based Study for Predicting Histopathologic Nuclear Grade

OBJECTIVE. The purpose of this study is to investigate the predictive performance of machine learning (ML)-based unenhanced CT texture analysis in distinguishing low (grades I and II) and high (grades III and IV) nuclear grade clear cell renal cell carcinomas (RCCs). MATERIALS AND METHODS. For this retrospective study, 81 patients with clear cell RCC (56 high and 25 low nuclear grade) were included from a public database. Using 2D manual segmentation, 744 texture features were extracted from unenhanced CT images. Dimension reduction was done in three consecutive steps: reproducibility analysis by two radiologists, collinearity analysis, and feature selection. Models were created using artificial neural network (ANN) and binary logistic regression, with and without synthetic minority oversampling technique (SMOTE), and were validated using 10-fold cross-validation. The reference standard was histopathologic nuclear grade (low vs high). RESULTS. Dimension reduction steps yielded five texture features for the ANN and six for the logistic regression algorithm. None of clinical variables was selected. ANN alone and ANN with SMOTE correctly classified 81.5% and 70.5%, respectively, of clear cell RCCs, with AUC values of 0.714 and 0.702, respectively. The logistic regression algorithm alone and with SMOTE correctly classified 75.3% and 62.5%, respectively, of the tumors, with AUC values of 0.656 and 0.666, respectively. The ANN performed better than the logistic regression (p < 0.05). No statistically significant difference was present between the model performances created with and without SMOTE (p > 0.05). CONCLUSION. ML-based unenhanced CT texture analysis using ANN can be a promising noninvasive method in predicting the nuclear grade of clear cell RCCs.

Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma

BACKGROUND & AIMS

Microvascular invasion (MVI) impairs surgical outcomes in patients with hepatocellular carcinoma (HCC). As there is no single highly reliable factor to preoperatively predict MVI, we developed a computational approach integrating large-scale clinical and imaging modalities, especially radiomic features from contrast-enhanced CT, to predict MVI and clinical outcomes in patients with HCC.

METHODS

In total, 495 surgically resected patients were retrospectively included. MVI-related radiomic scores (R-scores) were built from 7,260 radiomic features in 6 target volumes. Six R-scores, 15 clinical factors, and 12 radiographic scores were integrated into a predictive model, the radiographic-radiomic (RR) model, with multivariate logistic regression.

RESULTS

Radiomics related to tumor size and intratumoral heterogeneity were the top-ranked MVI predicting features. The related R-scores showed significant differences according to MVI status (p <0.001). Regression analysis identified 8 MVI risk factors, including 5 radiographic features and an R-score. The R-score (odds ratio [OR] 2.34) was less important than tumor capsule (OR 5.12), tumor margin (OR4.20), and peritumoral enhancement (OR 3.03). The RR model using these predictors achieved an area under the curve (AUC) of 0.909 in training/validation and 0.889 in the test set. Progression-free survival (PFS) and overall survival (OS) were significantly different between the RR-predicted MVI-absent and MVI-present groups (median PFS: 49.5 vs. 12.9 months; median OS: 76.3 vs. 47.3 months). RR-computed MVI probability, histologic MVI, tumor size, and Edmondson-Steiner grade were independently associated with disease-specific recurrence and mortality.

CONCLUSIONS

The computational approach, integrating large-scale clinico-radiologic and radiomic features, demonstrates good performance for predicting MVI and clinical outcomes. However, radiomics with current CT imaging analysis protocols do not provide statistically significant added value to radiographic scores.

LAY SUMMARY

The most effective treatment for hepatocellular carcinoma (HCC) is surgical removal of the tumor but often recurrence occurs, partly due to the presence of microvascular invasion (MVI). Lacking a single highly reliable factor able to preoperatively predict MVI, we developed a computational approach to predict MVI and the long-term clinical outcome of patients with HCC. In particular, the added value of radiomics, a newly emerging form of radiography, was comprehensively investigated. This computational method can enhance the communication with the patient about the likely success of the treatment and guide clinical management, with the aim of finding drugs that reduce the risk of recurrence.

Clinically significant prostate cancer detection on MRI: A radiomic shape features study

PURPOSE

Prostate multiparametric MRI (mpMRI) is the imaging modality of choice for detecting clinically significant prostate cancer (csPCa). Among various parameters, lesion maximum diameter and volume are currently considered of value to increase diagnostic accuracy. Quantitative radiomics allows for the extraction of more advanced shape features. Our aim was to assess which shape features derived from MRI index lesions correlate with csPCa presence.

MATERIALS AND METHODS

We retrospectively enrolled 75 consecutive subjects, who underwent mpMRI on a 3 T scanner, divided based on MRI index lesion Gleason Score in a csPCa group (GS > 3 + 4, n = 41) and a non-csPCa one (n = 34). Ten shape features were extracted both from axial T2-weighted and ADC maps images, after lesion tridimensional segmentation. Univariable and multivariable logistic analysis were used to evaluate the relationship between shape features and csPCa. Diagnostic performance was assessed measuring the area under the curve of the receiver operating characteristic (ROC) analysis. Diagnostic accuracy, sensitivity, and specificity were determined using the best cut-off on each ROC. A P value < 0.05 was considered statistically significant.

RESULTS

Univariable analysis demonstrated that almost every shape feature was statistically significant between csPCa e non-csPCa groups. However, multivariable analysis revealed that the parameter defined as surface area to volume ratio (SAVR), especially when extracted from ADC maps is the strongest independent predictor of csPCa among tested shape features.

CONCLUSION

The radiomic shape feature SAVR, extracted from ADC maps after index lesion segmentation, appears as a promising tool for csPCa detection.

A predictive nomogram for individualized recurrence stratification of bladder cancer using multiparametric MRI and clinical risk factors

BACKGROUND

Preoperative prediction of bladder cancer (BCa) recurrence risk is critical for individualized clinical management of BCa patients.

PURPOSE

To develop and validate a nomogram based on radiomics and clinical predictors for personalized prediction of the first 2 years (TFTY) recurrence risk.

STUDY TYPE

Retrospective.

POPULATION

Preoperative MRI datasets of 71 BCa patients (34 recurrent) were collected, and divided into training (n = 50) and validation cohorts (n = 21).

FIELD STRENGTH/SEQUENCE

3.0T MRI/T₂ -weighted (T₂ W), multi-b-value diffusion-weighted (DW), and dynamic contrast-enhanced (DCE) sequences.

ASSESSMENT

Radiomics features were extracted from the T₂ W, DW, apparent diffusion coefficient, and DCE images. A Rad_Score model was constructed using the support vector machine-based recursive feature elimination approach and a logistic regression model. Combined with the important clinical factors, including age, gender, grade, and muscle-invasive status (MIS) of the archived lesion, tumor size and number, surgery, and image signs like stalk and submucosal linear enhancement, a radiomics-clinical nomogram was developed, and its performance was evaluated in the training and the validation cohorts. The potential clinical usefulness was analyzed by the decision curve.

STATISTICAL TESTS

Univariate and multivariate analyses were performed to explore the independent predictors for BCa recurrence prediction.

RESULTS

Of the 1872 features, the 32 with the highest area under the curve (AUC) of receiver operating characteristic were selected for the Rad_Score calculation. The nomogram developed by two independent predictors, MIS and Rad_Score, showed good performance in the training (accuracy 88%, AUC 0.915, P << 0.01) and validation cohorts (accuracy 80.95%, AUC 0.838, P = 0.009). The decision curve exhibited when the risk threshold was larger than 0.3, more benefit was observed by using the radiomics-clinical nomogram than using the radiomics or clinical model alone.

DATA CONCLUSION

The proposed radiomics-clinical nomogram has potential in the preoperative prediction of TFTY BCa recurrence.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;50:1893-1904.

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1- or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary based on differing acquisition protocols between institutions. We present the first empirical study of benchmarking five different radiomic feature families in terms of both reproducibility and discriminability in a multisite setting, specifically, for identifying prostate tumors in the peripheral zone on MRI. Our cohort comprised 147 patient T2-weighted MRI datasets from four different sites, all of which are first preprocessed to correct for acquisition-related artifacts such as bias field, differing voxel resolutions, and intensity drift (nonstandardness). About 406 three-dimensional voxel-wise radiomic features from five different families (gray, Haralick, gradient, Laws, and Gabor) were evaluated in a cross-site setting to determine (a) how reproducible they are within a relatively homogeneous nontumor tissue region and (b) how well they could discriminate tumor regions from nontumor regions. Our results demonstrate that a majority of the popular Haralick features are reproducible in over 99% of all cross-site comparisons, as well as achieve excellent cross-site discriminability (classification accuracy of ≈ 0.8 ). By contrast, a majority of Laws features are highly variable across sites (reproducible in < 75 % of all cross-site comparisons) as well as resulting in low cross-site classifier accuracies ( < 0.6 ), likely due to a large number of noisy filter responses that can be extracted. These trends suggest that only a subset of radiomic features and associated parameters may be both reproducible and discriminable enough for use within machine learning classifier schemes.

Computational Approaches in Theranostics: Mining and Predicting Cancer Data

The ability to understand the complexity of cancer-related data has been prompted by the applications of (1) computer and data sciences, including data mining, predictive analytics, machine learning, and artificial intelligence, and (2) advances in imaging technology and probe development. Computational modelling and simulation are systematic and cost-effective tools able to identify important temporal/spatial patterns (and relationships), characterize distinct molecular features of cancer states, and address other relevant aspects, including tumor detection and heterogeneity, progression and metastasis, and drug resistance. These approaches have provided invaluable insights for improving the experimental design of therapeutic delivery systems and for increasing the translational value of the results obtained from early and preclinical studies. The big question is: Could cancer theranostics be determined and controlled in silico? This review describes the recent progress in the development of computational models and methods used to facilitate research on the molecular basis of cancer and on the respective diagnosis and optimized treatment, with particular emphasis on the design and optimization of theranostic systems. The current role of computational approaches is providing innovative, incremental, and complementary data-driven solutions for the prediction, simplification, and characterization of cancer and intrinsic mechanisms, and to promote new data-intensive, accurate diagnostics and therapeutics.

Multiparametric MRI and radiomics in prostate cancer: a review

Multiparametric MRI (mpMRI) is an imaging modality that combines anatomical MR imaging with one or more functional MRI sequences. It has become a versatile tool for detecting and characterising prostate cancer (PCa). The traditional role of mpMRI was confined to PCa staging, but due to the advanced imaging techniques, its role has expanded to various stages in clinical practises including tumour detection, disease monitor during active surveillance and sequential imaging for patient follow-up. Meanwhile, with the growing speed of data generation and the increasing volume of imaging data, it is highly demanded to apply computerised methods to process mpMRI data and extract useful information. Hence quantitative analysis for imaging data using radiomics has become an emerging paradigm. The application of radiomics approaches in prostate cancer has not only enabled automatic localisation of the disease but also provided a non-invasive solution to assess tumour biology (e.g. aggressiveness and the presence of hypoxia). This article reviews mpMRI and its expanding role in PCa detection, staging and patient management. Following that, an overview of prostate radiomics will be provided, with a special focus on its current applications as well as its future directions.

Objective risk stratification of prostate cancer using machine learning and radiomics applied to multiparametric magnetic resonance images

Multiparametric magnetic resonance imaging (mpMRI) has become increasingly important for the clinical assessment of prostate cancer (PCa), but its interpretation is generally variable due to its relatively subjective nature. Radiomics and classification methods have shown potential for improving the accuracy and objectivity of mpMRI-based PCa assessment. However, these studies are limited to a small number of classification methods, evaluation using the AUC score only, and a non-rigorous assessment of all possible combinations of radiomics and classification methods. This paper presents a systematic and rigorous framework comprised of classification, cross-validation and statistical analyses that was developed to identify the best performing classifier for PCa risk stratification based on mpMRI-derived radiomic features derived from a sizeable cohort. This classifier performed well in an independent validation set, including performing better than PI-RADS v2 in some aspects, indicating the value of objectively interpreting mpMRI images using radiomics and classification methods for PCa risk assessment.

An Intelligent Clinical Decision Support System for Preoperative Prediction of Lymph Node Metastasis in Gastric Cancer

PURPOSE

The aim of this study was to develop and validate a computational clinical decision support system (DSS) on the basis of CT radiomics features for the prediction of lymph node (LN) metastasis in gastric cancer (GC) using machine learning-based analysis.

METHODS

Clinicopathologic and CT imaging data were retrospectively collected from 490 patients who were diagnosed with GC between January 2002 and December 2016. Radiomics features were extracted from venous-phase CT images. Relevant features were selected, ranked, and modeled using a support vector machine classifier in 326 training and validation data sets. A model test was performed independently in a test set (n = 164). Finally, a head-to-head comparison of the diagnostic performance of the DSS and that of the conventional staging criterion was performed.

RESULTS

Two hundred ninety-seven of the 490 patients examined had histopathologic evidence of LN metastasis, yielding a 60.6% metastatic rate. The area under the curve for predicting LN+ was 0.824 (95% confidence interval, 0.804-0.847) for the DSS in the training and validation data and 0.764 (95% confidence interval, 0.699-0.833) in the test data. The calibration plots showed good concordance between the predicted and observed probability of LN+ using the DSS approach. The DSS was better able to predict LN metastasis than the conventional staging criterion in the training and validation data (accuracy 76.4% versus 63.5%) and in the test data (accuracy 71.3% versus 63.2%) CONCLUSIONS: A DSS based on 13 "worrisome" radiomics features appears to be a promising tool for the preoperative prediction of LN status in patients with GC.

Radiomics-based machine learning methods for isocitrate dehydrogenase genotype prediction of diffuse gliomas

Purpose

Reliable and accurate predictive models are necessary to drive the success of radiomics. Our aim was to identify the optimal radiomics-based machine learning method for isocitrate dehydrogenase (IDH) genotype prediction in diffuse gliomas.

Methods

Eight classical machine learning methods were evaluated in terms of their stability and performance for pre-operative IDH genotype prediction. A total of 126 patients were enrolled for analysis. Overall, 704 radiomic features extracted from the pre-operative MRI images were analyzed. The patients were randomly assigned to either the training set or the validation set at a ratio of 2:1. Feature selection and classification model training were done using the training set, whereas the predictive performance and stability of the model were independently assessed using the validation set.

Results

Random Forest (RF) showed high predictive performance (accuracy 0.885 ± 0.041, AUC 0.931 ± 0.036), whereas neural network (NN) (accuracy 0.829 ± 0.064, AUC 0.878 ± 0.052) and flexible discriminant analysis (FDA) (accuracy 0.851 ± 0.049, AUC 0.875 ± 0.057) displayed low predictive performance. With regard to stability, RF also showed high robustness against data perturbation (relative standard deviations, RSD 3.87%).

Conclusions

RF is a promising machine learning method in predicting IDH genotype. Development of an accurate and reliable model can assist in the initial diagnostic evaluation and treatment planning for diffuse glioma patients.

Electronic supplementary material

The online version of this article (10.1007/s00432-018-2787-1) contains supplementary material, which is available to authorized users.

Assessment of prostate cancer prognostic Gleason grade group using zonal-specific features extracted from biparametric MRI using a KNN classifier

Purpose

To automatically assess the aggressiveness of prostate cancer (PCa) lesions using zonal‐specific image features extracted from diffusion weighted imaging (DWI) and T2W MRI.

Methods

Region of interest was extracted from DWI (peripheral zone) and T2W MRI (transitional zone and anterior fibromuscular stroma) around the center of 112 PCa lesions from 99 patients. Image histogram and texture features, 38 in total, were used together with a k‐nearest neighbor classifier to classify lesions into their respective prognostic Grade Group (GG) (proposed by the International Society of Urological Pathology 2014 consensus conference). A semi‐exhaustive feature search was performed (1–6 features in each feature set) and validated using threefold stratified cross validation in a one‐versus‐rest classification setup.

Results

Classifying PCa lesions into GGs resulted in AUC of 0.87, 0.88, 0.96, 0.98, and 0.91 for GG1, GG2, GG1 + 2, GG3, and GG4 + 5 for the peripheral zone, respectively. The results for transitional zone and anterior fibromuscular stroma were AUC of 0.85, 0.89, 0.83, 0.94, and 0.86 for GG1, GG2, GG1 + 2, GG3, and GG4 + 5, respectively.

CONCLUSION

This study showed promising results with reasonable AUC values for classification of all GG indicating that zonal‐specific imaging features from DWI and T2W MRI can be used to differentiate between PCa lesions of various aggressiveness.

Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer

OBJECTIVE

To develop different radiomic models based on the magnetic resonance imaging (MRI) radiomic features and machine learning methods to predict early intensity-modulated radiation therapy (IMRT) response, Gleason scores (GS) and prostate cancer (Pca) stages.

METHODS

Thirty-three Pca patients were included. All patients underwent pre- and post-IMRT T2-weighted (T2 W) and apparent diffusing coefficient (ADC) MRI. IMRT response was calculated in terms of changes in the ADC value, and patients were divided as responders and non-responders. A wide range of radiomic features from different feature sets were extracted from all T2 W and ADC images. Univariate radiomic analysis was performed to find highly correlated radiomic features with IMRT response, and a paired t test was used to find significant features between responders and non-responders. To find high predictive radiomic models, tenfold cross-validation as the criterion for feature selection and classification was applied on the pre-, post- and delta IMRT radiomic features, and area under the curve (AUC) of receiver operating characteristics was calculated as model performance value.

RESULTS

Of 33 patients, 15 patients (45%) were found as responders. Univariate analysis showed 20 highly correlated radiomic features with IMRT response (20 ADC and 20 T2). Two and fifteen T2 and ADC radiomic features were found as significant (P-value ≤ 0.05) features between responders and non-responders, respectively. Several cross-combined predictive radiomic models were obtained, and post-T2 radiomic models were found as high predictive models (AUC 0.632) followed by pre-ADC (AUC 0.626) and pre-T2 (AUC 0.61). For GS prediction, T2 W radiomic models were found as more predictive (mean AUC 0.739) rather than ADC models (mean AUC 0.70), while for stage prediction, ADC models had higher prediction performance (mean AUC 0.675).

CONCLUSIONS

Radiomic models developed by MR image features and machine learning approaches are noninvasive and easy methods for personalized prostate cancer diagnosis and therapy.

Predicting Gleason Score of Prostate Cancer Patients Using Radiomic Analysis

Purpose: Use of quantitative imaging features and encoding the intra-tumoral heterogeneity from multi-parametric magnetic resonance imaging (mpMRI) for the prediction of Gleason score is gaining attention as a non-invasive biomarker for prostate cancer (PCa). This study tested the hypothesis that radiomic features, extracted from mpMRI, could predict the Gleason score pattern of patients with PCa. Methods: This analysis included T2-weighted (T2-WI) and apparent diffusion coefficient (ADC, computed from diffusion-weighted imaging) scans of 99 PCa patients from The Cancer Imaging Archive (TCIA). A total of 41 radiomic features were calculated from a local tumor sub-volume (i.e., regions of interest) that is determined by a centroid coordinate of PCa volume, grouped based on their Gleason score patterns. Kruskal-Wallis and Spearman's rank correlation tests were used to identify features related to Gleason score groups. Random forest (RF) classifier model was used to predict Gleason score groups and identify the most important signature among the 41 radiomic features. Results: Gleason score groups could be discriminated based on zone size percentage, large zone size emphasis and zone size non-uniformity values (p < 0.05). These features also showed a significant correlation between radiomic features and Gleason score groups with a correlation value of -0.35, 0.32, 0.42 for the large zone size emphasis, zone size non-uniformity and zone size percentage, respectively (corrected p < 0.05). RF classifier model achieved an average of the area under the curves of the receiver operating characteristic (ROC) of 83.40, 72.71, and 77.35% to predict Gleason score groups (G1) = 6; 6 < (G2) < (3 + 4) and (G3) ≥ 4 + 3, respectively. Conclusion: Our results suggest that the radiomic features can be used as a non-invasive biomarker to predict the Gleason score of the PCa patients.

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.

Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

Although cancer often is referred to as "a disease of the genes," it is indisputable that the (epi)genetic properties of individual cancer cells are highly variable, even within the same tumor. Hence, preexisting resistant clones will emerge and proliferate after therapeutic selection that targets sensitive clones. Herein, the authors propose that quantitative image analytics, known as "radiomics," can be used to quantify and characterize this heterogeneity. Virtually every patient with cancer is imaged radiologically. Radiomics is predicated on the beliefs that these images reflect underlying pathophysiologies, and that they can be converted into mineable data for improved diagnosis, prognosis, prediction, and therapy monitoring. In the last decade, the radiomics of cancer has grown from a few laboratories to a worldwide enterprise. During this growth, radiomics has established a convention, wherein a large set of annotated image features (1-2000 features) are extracted from segmented regions of interest and used to build classifier models to separate individual patients into their appropriate class (eg, indolent vs aggressive disease). An extension of this conventional radiomics is the application of "deep learning," wherein convolutional neural networks can be used to detect the most informative regions and features without human intervention. A further extension of radiomics involves automatically segmenting informative subregions ("habitats") within tumors, which can be linked to underlying tumor pathophysiology. The goal of the radiomics enterprise is to provide informed decision support for the practice of precision oncology.

An annotated test-retest collection of prostate multiparametric MRI

Multiparametric Magnetic Resonance Imaging (mpMRI) is widely used for characterizing prostate cancer. Standard of care use of mpMRI in clinic relies on visual interpretation of the images by an expert. mpMRI is also increasingly used as a quantitative imaging biomarker of the disease. Little is known about repeatability of such quantitative measurements, and no test-retest datasets have been available publicly to support investigation of the technical characteristics of the MRI-based quantification in the prostate. Here we present an mpMRI dataset consisting of baseline and repeat prostate MRI exams for 15 subjects, manually annotated to define regions corresponding to lesions and anatomical structures, and accompanied by region-based measurements. This dataset aims to support further investigation of the repeatability of mpMRI-derived quantitative prostate measurements, study of the robustness and reliability of the automated analysis approaches, and to support development and validation of new image analysis techniques. The manuscript can also serve as an example of the use of DICOM for standardized encoding of the image annotation and quantification results.

Automatic Detection of Prostate Tumor Habitats using Diffusion MRI

A procedure for identification of optimal Apparent Diffusion Coefficient (ADC) thresholds for automatic delineation of prostatic lesions with restricted diffusion at differing risk for cancer was developed. The relationship between the size of the identified Volumes of Interest (VOIs) and Gleason Score (GS) was evaluated. Patients with multiparametric (mp)MRI, acquired prior to radical prostatectomy (RP) (n = 18), mpMRI-ultrasound fused (MRI-US) (n = 21) or template biopsies (n = 139) were analyzed. A search algorithm, spanning ADC thresholds in 50 µm²/s increments, determined VOIs that were matched to RP tumor nodules. Three ADC thresholds for both peripheral zone (PZ) and transition zone (TZ) were identified for estimation of VOIs at low, intermediate, and high risk of prostate cancer. The determined ADC thresholds for low, intermediate and high risk in PZ/TZ were: 900/800; 1100/850; and 1300/1050 µm²/s. The correlation coefficients between the size of the high/intermediate/low risk VOIs and GS in the three cohorts were 0.771/0.778/0.369, 0.561/0.457/0.355 and 0.423/0.441/0.36 (p < 0.05). Low risk VOIs mapped all RP lesions; area under the curve (AUC) for intermediate risk VOIs to discriminate GS6 vs GS ≥ 7 was 0.852; for high risk VOIs to discriminate GS6,7 vs GS ≥ 8 was 0.952. In conclusion, the automatically delineated volumes in the prostate with restricted diffusion were found to strongly correlate with cancer aggressiveness.

PROSTATEx Challenges for computerized classification of prostate lesions from multiparametric magnetic resonance images

Grand challenges stimulate advances within the medical imaging research community; within a competitive yet friendly environment, they allow for a direct comparison of algorithms through a well-defined, centralized infrastructure. The tasks of the two-part PROSTATEx Challenges (the PROSTATEx Challenge and the PROSTATEx-2 Challenge) are (1) the computerized classification of clinically significant prostate lesions and (2) the computerized determination of Gleason Grade Group in prostate cancer, both based on multiparametric magnetic resonance images. The challenges incorporate well-vetted cases for training and testing, a centralized performance assessment process to evaluate results, and an established infrastructure for case dissemination, communication, and result submission. In the PROSTATEx Challenge, 32 groups apply their computerized methods (71 methods total) to 208 prostate lesions in the test set. The area under the receiver operating characteristic curve for these methods in the task of differentiating between lesions that are and are not clinically significant ranged from 0.45 to 0.87; statistically significant differences in performance among the top-performing methods, however, are not observed. In the PROSTATEx-2 Challenge, 21 groups apply their computerized methods (43 methods total) to 70 prostate lesions in the test set. When compared with the reference standard, the quadratic-weighted kappa values for these methods in the task of assigning a five-point Gleason Grade Group to each lesion range from - 0.24 to 0.27; superiority to random guessing can be established for only two methods. When approached with a sense of commitment and scientific rigor, challenges foster interest in the designated task and encourage innovation in the field.