Computerized characterization of prostate cancer by fractal analysis in MR images

Prediction of prostate cancer grade using fractal analysis of perfusion MRI: retrospective proof-of-principle study

OBJECTIVES

Multiparametric MRI has high diagnostic accuracy for detecting prostate cancer, but non-invasive prediction of tumor grade remains challenging. Characterizing tumor perfusion by exploiting the fractal nature of vascular anatomy might elucidate the aggressive potential of a tumor. This study introduces the concept of fractal analysis for characterizing prostate cancer perfusion and reports about its usefulness for non-invasive prediction of tumor grade.

METHODS

We retrospectively analyzed the openly available PROSTATEx dataset with 112 cancer foci in 99 patients. In all patients, histological grading groups specified by the International Society of Urological Pathology (ISUP) were obtained from in-bore MRI-guided biopsy. Fractal analysis of dynamic contrast-enhanced perfusion MRI sequences was performed, yielding fractal dimension (FD) as quantitative descriptor. Two-class and multiclass diagnostic accuracy was analyzed using area under the curve (AUC) receiver operating characteristic analysis, and optimal FD cutoffs were established. Additionally, we compared fractal analysis to conventional apparent diffusion coefficient (ADC) measurements.

RESULTS

Fractal analysis of perfusion allowed accurate differentiation of non-significant (group 1) and clinically significant (groups 2-5) cancer with a sensitivity of 91% (confidence interval [CI]: 83-96%) and a specificity of 86% (CI: 73-94%). FD correlated linearly with ISUP groups (r² = 0.874, p < 0.001). Significant groupwise differences were obtained between low, intermediate, and high ISUP group 1-4 (p ≤ 0.001) but not group 5 tumors. Fractal analysis of perfusion was significantly more reliable than ADC in predicting non-significant and clinically significant cancer (AUC_FD = 0.97 versus AUC_ADC = 0.77, p < 0.001).

CONCLUSION

Fractal analysis of perfusion MRI accurately predicts prostate cancer grading in low-, intermediate-, and high-, but not highest-grade, tumors.

KEY POINTS

• In 112 prostate carcinomas, fractal analysis of MR perfusion imaging accurately differentiated low-, intermediate-, and high-grade cancer (ISUP grade groups 1-4). • Fractal analysis detected clinically significant prostate cancer with a sensitivity of 91% (83-96%) and a specificity of 86% (73-94%). • Fractal dimension of perfusion at the tumor margin may provide an imaging biomarker to predict prostate cancer grading.

Computer-Aided Diagnosis in Multiparametric MRI of the Prostate: An Open-Access Online Tool for Lesion Classification with High Accuracy

Computer-aided diagnosis (CADx) approaches could help to objectify reporting on prostate mpMRI, but their use in many cases is hampered due to common-built algorithms that are not publicly available. The aim of this study was to develop an open-access CADx algorithm with high accuracy for classification of suspicious lesions in mpMRI of the prostate. This retrospective study was approved by the local ethics commission, with waiver of informed consent. A total of 124 patients with 195 reported lesions were included. All patients received mpMRI of the prostate between 2014 and 2017, and transrectal ultrasound (TRUS)-guided and targeted biopsy within a time period of 30 days. Histopathology of the biopsy cores served as a standard of reference. Acquired imaging parameters included the size of the lesion, signal intensity (T2w images), diffusion restriction, prostate volume, and several dynamic parameters along with the clinical parameters patient age and serum PSA level. Inter-reader agreement of the imaging parameters was assessed by calculating intraclass correlation coefficients. The dataset was stratified into a train set and test set (156 and 39 lesions in 100 and 24 patients, respectively). Using the above parameters, a CADx based on an Extreme Gradient Boosting algorithm was developed on the train set, and tested on the test set. Performance optimization was focused on maximizing the area under the Receiver Operating Characteristic curve (ROC_AUC). The algorithm was made publicly available on the internet. The CADx reached an ROC_AUC of 0.908 during training, and 0.913 during testing (p = 0.93). Additionally, established rule-in and rule-out criteria allowed classifying 35.8% of the malignant and 49.4% of the benign lesions with error rates of <2%. All imaging parameters featured excellent inter-reader agreement. This study presents an open-access CADx for classification of suspicious lesions in mpMRI of the prostate with high accuracy. Applying the provided rule-in and rule-out criteria might facilitate to further stratify the management of patients at risk.

Automated reference tissue normalization of T2-weighted MR images of the prostate using object recognition

Objectives

To develop and evaluate an automated method for prostate T2-weighted (T2W) image normalization using dual-reference (fat and muscle) tissue.

Materials and methods

Transverse T2W images from the publicly available PROMISE12 (N = 80) and PROSTATEx (N = 202) challenge datasets, and an in-house collected dataset (N = 60) were used. Aggregate channel features object detectors were trained to detect reference fat and muscle tissue regions, which were processed and utilized to normalize the 3D images by linear scaling. Mean prostate pseudo T2 values after normalization were compared to literature values. Inter-patient histogram intersections of voxel intensities in the prostate were compared between our approach, the original images, and other commonly used normalization methods. Healthy vs. malignant tissue classification performance was compared before and after normalization.

Results

The prostate pseudo T2 values of the three tested datasets (mean ± standard deviation = 78.49 ± 9.42, 79.69 ± 6.34 and 79.29 ± 6.30 ms) corresponded well to T2 values from literature (80 ± 34 ms). Our normalization approach resulted in significantly higher (p < 0.001) inter-patient histogram intersections (median = 0.746) than the original images (median = 0.417) and most other normalization methods. Healthy vs. malignant classification also improved significantly (p < 0.001) in peripheral (AUC 0.826 vs. 0.769) and transition (AUC 0.743 vs. 0.678) zones.

Conclusion

An automated dual-reference tissue normalization of T2W images could help improve the quantitative assessment of prostate cancer.

Electronic supplementary material

The online version of this article (10.1007/s10334-020-00871-3) contains supplementary material, which is available to authorized users.

Detection of Dominant Intra-prostatic Lesions in Patients With Prostate Cancer Using an Artificial Neural Network and MR Multi-modal Radiomics Analysis

Purpose: The aim of this study was to identify and rank discriminant radiomics features extracted from MR multi-modal images to construct an adaptive model for characterization of Dominant Intra-prostatic Lesions (DILs) from normal prostatic gland tissues (NT).

Methods and Materials: Two cohorts were retrospectively studied: Group A consisted of 98 patients and Group B 19 patients. Two image modalities were acquired using a 3.0T MR scanner: Axial T2 Weighted (T2W) and axial diffusion weighted (DW) imaging. A linear regression method was used to construct apparent diffusion coefficient (ADC) maps from DW images. DILs and the NT in the mirrored location were drawn on each modality. One hundred and sixty-eight radiomics features were extracted from DILs and NT. A Partial-Least-Squares-Correlation (PLSC) with one-way ANOVA along with bootstrapping ratio techniques were recruited to identify and rank the most discriminant latent variables. An artificial neural network (ANN) was constructed based on the optimal latent variable feature to classify the DILs and NTs. Nineteen patients were randomly chosen to test the contour variability effect on the radiomics analysis and the performance of the ANN. Finally, the trained ANN and a two dimension (2D) convolutional sampling method were combined and used to estimate DIL-NT probability map for two test cases.

Results: Among 168 radiomics-based latent variables, only the first four variables of each modality in the PLSC space were found to be significantly different between the DILs and NTs. Area Under Receiver Operating Characteristic (AUROC), Positive Predictive and Negative Predictive values (PPV and NPV) for the conventional method were 94%, 0.95, and 0.92, respectively. When the feature vector was randomly permuted 10,000 times, a very strong permutation-invariant efficiency (p < 0.0001) was achieved. The radiomic-based latent variables of the NTs and DILs showed no statistically significant differences (F_statistic < Fc = 4.11 with Confidence Level of 95% for all 8 variables) against contour variability. Dice coefficients between DIL-NT probability map and physician contours for the two test cases were 0.82 and 0.71, respectively.

Conclusion: This study demonstrates the high performance of combining radiomics information extracted from multimodal MR information such as T2WI and ADC maps, and adaptive models to detect DILs in patients with PCa.

A Deep Learning-Based Approach for the Detection and Localization of Prostate Cancer in T2 Magnetic Resonance Images

We address the problem of prostate lesion detection, localization, and segmentation in T2W magnetic resonance (MR) images. We train a deep convolutional encoder-decoder architecture to simultaneously segment the prostate, its anatomical structure, and the malignant lesions. To incorporate the 3D contextual spatial information provided by the MRI series, we propose a novel 3D sliding window approach, which preserves the 2D domain complexity while exploiting 3D information. Experiments on data from 19 patients provided for the public by the Initiative for Collaborative Computer Vision Benchmarking (I2CVB) show that our approach outperforms traditional pattern recognition and machine learning approaches by a significant margin. Particularly, for the task of cancer detection and localization, the system achieves an average AUC of 0.995, an accuracy of 0.894, and a recall of 0.928. The proposed mono-modal deep learning-based system performs comparably to other multi-modal MR-based systems. It could improve the performance of a radiologist in prostate cancer diagnosis and treatment planning.

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.

A review of the principles of texture analysis and its role in imaging of genitourinary neoplasms

Advances in the management of genitourinary neoplasms have resulted in a trend towards providing patients with personalized care. Texture analysis of medical images, is one of the tools that is being explored to provide information such as detection and characterization of tumors, determining their aggressiveness including grade and metastatic potential and for prediction of survival rates and risk of recurrence. In this article we review the basic principles of texture analysis and then detail its current role in imaging of individual neoplasms of the genitourinary system.

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.

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 inter-centre statistical scale standardisation for quantitatively evaluating prostate tissue on T2-weighted MRI

Magnetic resonance images (MRI) require intensity standardisation if they are used for the purpose of quantitative analysis as inherent variations in image intensity levels between different image sets are manifest due to technical factors. One approach is to standardise the image intensity values using a statistically applied biological reference tissue. The aim of this study is to compare the performance of differing candidate biological reference tissues for standardising T2WI intensity distributions. Fifty-one prostate cancer patients across two centres with different scanners were evaluated using the percentage interpatient coefficient of variation (%interCV) for four different biological references; femoral bone marrow, ischioanal fossa, obturator-internus muscle and bladder urine. The tissue with the highest reproducibility (lowest %interCV) in both centres was used for intensity standardisation of prostate T2WI using three different statistical measures (mean, Z-score, median + Interquartile Range). The performance of different standardisation methods was evaluated from the assessment of image intensity histograms and the percentage normalised root mean square error (%NRSME) of the healthy peripheral zone tissue. Ischioanal fossa as a reference tissue demonstrated the highest reproducibility with %interCV of 18.9 for centre1 and 11.2 for centre2. Using ischioanal fossa for statistical intensity standardisation and the median + Interquartile Range method demonstrated the lowest %NRMSE across centres for healthy peripheral zone tissues. This study demonstrates ischioanal fossa as a preferred reference tissue for standardising intensity values from T2WI of the prostate. Subsequent image standardisation using the median + Interquartile Range intensity of the reference tissue demonstrated a robust and reliable standardisation method for quantitative image assessment.

Magnetic resonance imaging (MRI)-based radiomics for prostate cancer radiotherapy

In radiotherapy (RT) of prostate cancer, dose escalation has been shown to reduce biochemical failure. Dose escalation only to determinate prostate tumor habitats has the potential to improve tumor control with less toxicity than when the entire prostate is dose escalated. Other issues in the treatment of the RT patient include the choice of the RT technique (hypo- or standard fractionation) and the use and length of concurrent/adjuvant androgen deprivation therapy (ADT). Up to 50% of high-risk men demonstrate biochemical failure suggesting that additional strategies for defining and treating patients based on improved risk stratification are required. The use of multiparametric MRI (mpMRI) is rapidly gaining momentum in the management of prostate cancer because of its improved diagnostic potential and its ability to combine functional and anatomical information. Currently, the Prostate Imaging, Reporting and Diagnosis System (PIRADS) is the standard of care for region of interest (ROI) identification and risk classification. However, PIRADS was not designed for 3D tumor volume delineation; there is a large degree of subjectivity and PIRADS does not accurately and reproducibly elucidate inter- and intra-lesional spatial heterogeneity. "Radiomics", as it refers to the extraction and analysis of large number of advanced quantitative radiological features from medical images using high throughput methods, is perfectly suited as an engine to effectively sift through the multiple series of prostate mpMRI sequences and quantify regions of interest. The radiomic efforts can be summarized in two main areas: (I) detection/segmentation of the suspicious lesion; and (II) assessment of the aggressiveness of prostate cancer. As related to RT, the goal of the latter is in particular to identify patients at high risk for metastatic disease; and the aim of the former is to identify and segment cancerous lesions and thus provide targets for radiation boost. The article is structured as follows: first, we describe the radiomic approach; and second, we discuss the radiomic pipeline as tailored for RT of prostate cancer. In this process we summarize the current efforts and progress in integrating mpMRI radiomics into the radiotherapeutic management of prostate cancer with emphasis placed on its role in treatment target definition, treatment plan strategizing, and prognostic assessment. The described concepts, methods and tools are not currently applicable to the radiation oncology practice outside of the research setting. More data are required in the form of clinical trials to assess the robustness of radiomics-based predictive models, and to maximize the efficacy of these models.

Computer aided diagnosis of prostate cancer: A texton based approach

PURPOSE

In this paper the authors propose a texton based prostate computer aided diagnosis approach which bypasses the typical feature extraction process such as filtering and convolution which can be computationally expensive. The study focuses the peripheral zone because 75% of prostate cancers start within this region and the majority of prostate cancers arising within this region are more aggressive than those arising in the transitional zone.

METHODS

For the model development, square patches were extracted at random locations from malignant and benign regions. Subsequently, extracted patches were aggregated and clustered using k-means clustering to generate textons that represent both regions. All textons together form a texton dictionary, which was used to construct a texton map for every peripheral zone in the training images. Based on the texton map, histogram models for each malignant and benign tissue samples were constructed and used as a feature vector to train our classifiers. In the testing phase, four machine learning algorithms were employed to classify each unknown sample tissue based on its corresponding feature vector.

RESULTS

The proposed method was tested on 418 T2-W MR images taken from 45 patients. Evaluation results show that the best three classifiers were Bayesian network (Az = 92.8% ± 5.9%), random forest (89.5% ± 7.1%), and k-NN (86.9% ± 7.5%). These results are comparable to the state-of-the-art in the literature.

CONCLUSIONS

The authors have developed a prostate computer aided diagnosis method based on textons using a single modality of T2-W MRI without the need for the typical feature extraction methods, such as filtering and convolution. The proposed method could form a solid basis for a multimodality magnetic resonance imaging based systems.

Automatic localization of cerebral cortical malformations using fractal analysis

Malformations of cortical development (MCDs) encompass a variety of brain disorders affecting the normal development and organization of the brain cortex. The relatively low incidence and the extreme heterogeneity of these disorders hamper the application of classical group level approaches for the detection of lesions. Here, we present a geometrical descriptor for a voxel level analysis based on fractal geometry, then define two similarity measures to detect the lesions at single subject level. The pipeline was applied to 15 normal children and nine pediatric patients affected by MCDs following two criteria, maximum accuracy (WACC) and minimization of false positives (FPR), and proved that our lesion detection algorithm is able to detect and locate abnormalities of the brain cortex with high specificity (WACC  =  85%, FPR  =  96%), sensitivity (WACC  =  83%, FPR  =  63%) and accuracy (WACC  =  85%, FPR  =  90%). The combination of global and local features proves to be effective, making the algorithm suitable for the detection of both focal and diffused malformations. Compared to other existing algorithms, this method shows higher accuracy and sensitivity.

Computer-aided Detection of Prostate Cancer with MRI: Technology and Applications

One in six men will develop prostate cancer in his lifetime. Early detection and accurate diagnosis of the disease can improve cancer survival and reduce treatment costs. Recently, imaging of prostate cancer has greatly advanced since the introduction of multiparametric magnetic resonance imaging (mp-MRI). Mp-MRI consists of T2-weighted sequences combined with functional sequences including dynamic contrast-enhanced MRI, diffusion-weighted MRI, and magnetic resonance spectroscopy imaging. Because of the big data and variations in imaging sequences, detection can be affected by multiple factors such as observer variability and visibility and complexity of the lesions. To improve quantitative assessment of the disease, various computer-aided detection systems have been designed to help radiologists in their clinical practice. This review paper presents an overview of literatures on computer-aided detection of prostate cancer with mp-MRI, which include the technology and its applications. The aim of the survey is threefold: an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application.

Prostate cancer radiomics and the promise of radiogenomics

Prostate cancer exhibits intra-tumoral heterogeneity that we hypothesize to be the leading confounding factor contributing to the underperformance of the current pre-treatment clinical-pathological and genomic assessment. These limitations impose an urgent need to develop better computational tools to identify men with low risk of prostate cancer versus others that may be at risk for developing metastatic cancer. The patient stratification will directly translate to patient treatments, wherein decisions regarding active surveillance or intensified therapy are made. Multiparametric MRI (mpMRI) provides the platform to investigate tumor heterogeneity by mapping the individual tumor habitats. We hypothesize that quantitative assessment (radiomics) of these habitats results in distinct combinations of descriptors that reveal regions with different physiologies and phenotypes. Radiogenomics, a discipline connecting tumor morphology described by radiomic and its genome described by the genomic data, has the potential to derive "radio phenotypes" that both correlate to and complement existing validated genomic risk stratification biomarkers. In this article we first describe the radiomic pipeline, tailored for analysis of prostate mpMRI, and in the process we introduce our particular implementations of radiomics modules. We also summarize the efforts in the radiomics field related to prostate cancer diagnosis and assessment of aggressiveness. Finally, we describe our results from radiogenomic analysis, based on mpMRI-Ultrasound (MRI-US) biopsies and discuss the potential of future applications of this technique. The mpMRI radiomics data indicate that the platform would significantly improve the biopsy targeting of prostate habitats through better recognition of indolent versus aggressive disease, thereby facilitating a more personalized approach to prostate cancer management. The expectation to non-invasively identify habitats with high probability of housing aggressive cancers would result in directed biopsies that are more informative and actionable. Conversely, providing evidence for lack of disease would reduce the incidence of non-informative biopsies. In radiotherapy of prostate cancer, dose escalation has been shown to reduce biochemical failure. Dose escalation only to determinate prostate habitats has the potential to improve tumor control with less toxicity than when the entire prostate is dose escalated.

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.

Fractal analysis of MRI data for the characterization of patients with schizophrenia and bipolar disorder

Fractal geometry can be used to analyze shape and patterns in brain images. With this study we use fractals to analyze T1 data of patients affected by schizophrenia or bipolar disorder, with the aim of distinguishing between healthy and pathological brains using the complexity of brain structure, in particular of grey matter, as a marker of disease. 39 healthy volunteers, 25 subjects affected by schizophrenia and 11 patients affected by bipolar disorder underwent an MRI session. We evaluated fractal dimension of the brain cortex and its substructures, calculated with an algorithm based on the box-count algorithm. We modified this algorithm, with the aim of avoiding the segmentation processing step and using all the information stored in the image grey levels. Moreover, to increase sensitivity to local structural changes, we computed a value of fractal dimension for each slice of the brain or of the particular structure. To have reference values in comparing healthy subjects with patients, we built a template by averaging fractal dimension values of the healthy volunteers data. Standard deviation was evaluated and used to create a confidence interval. We also performed a slice by slice t-test to assess the difference at slice level between the three groups. Consistent average fractal dimension values were found across all the structures in healthy controls, while in the pathological groups we found consistent differences, indicating a change in brain and structures complexity induced by these disorders.

A data-driven approach to prostate cancer detection from dynamic contrast enhanced MRI

Magnetic resonance imaging (MRI), particularly dynamic contrast enhanced (DCE) imaging, has shown great potential in prostate cancer diagnosis and staging. In the current practice of DCE-MRI, diagnosis is based on quantitative parameters extracted from the series of T1-weighted images acquired after the injection of a contrast agent. To calculate these parameters, a pharmacokinetic model is fitted to the T1-weighted intensities. Most models make simplistic assumptions about the perfusion process. Moreover, these models require accurate estimation of the arterial input function, which is challenging. In this work we propose a data-driven approach to characterization of the prostate tissue that uses the time series of DCE T1-weighted images without pharmacokinetic modeling. This approach uses a number of model-free empirical parameters and also the principal component analysis (PCA) of the normalized T1-weighted intensities, as features for cancer detection from DCE MRI. The optimal set of principal components is extracted with sparse regularized regression through least absolute shrinkage and selection operator (LASSO). A support vector machine classifier was used with leave-one-patient-out cross validation to determine the ability of this set of features in cancer detection. Our data is obtained from patients prior to radical prostatectomy and the results are validated based on histological evaluation of the extracted specimens. Our results, obtained on 449 tissue regions from 16 patients, show that the proposed data-driven features outperform the traditional pharmacokinetic parameters with an area under ROC of 0.86 for LASSO-isolated PCA parameters, compared to 0.78 for pharmacokinetic parameters. This shows that our novel approach to the analysis of DCE data has the potential to improve the multiparametric MRI protocol for prostate cancer detection.

Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice?

Background

Tumor spatial heterogeneity is an important prognostic factor, which may be reflected in medical images

Methods

Image texture analysis is an approach of quantifying heterogeneity that may not be appreciated by the naked eye. Different methods can be applied including statistical-, model-, and transform-based methods.

Results

Early evidence suggests that texture analysis has the potential to augment diagnosis and characterization as well as improve tumor staging and therapy response assessment in oncological practice.

Conclusion

This review provides an overview of the application of texture analysis with different imaging modalities, CT, MRI, and PET, to date and describes the technical challenges that have limited its widespread clinical implementation so far. With further efforts to refine its application, image texture analysis has the potential to develop into a valuable clinical tool for oncologic imaging.

Teaching Points

• Tumor spatial heterogeneity is an important prognostic factor.

• Image texture analysis is an approach of quantifying heterogeneity.

• Different methods can be applied, including statistical-, model-, and transform-based methods.

• Texture analysis could improve the diagnosis, tumor staging, and therapy response assessment.

Central gland and peripheral zone prostate tumors have significantly different quantitative imaging signatures on 3 Tesla endorectal, in vivo T2-weighted MR imagery

PURPOSE

To identify and evaluate textural quantitative imaging signatures (QISes) for tumors occurring within the central gland (CG) and peripheral zone (PZ) of the prostate, respectively, as seen on in vivo 3 Tesla (T) endorectal T2-weighted (T2w) MRI.

MATERIALS AND METHODS

This study used 22 preoperative prostate MRI data sets (16 PZ, 6 CG) acquired from men with confirmed prostate cancer (CaP) and scheduled for radical prostatectomy (RP). The prostate region-of-interest (ROI) was automatically delineated on T2w MRI, following which it was corrected for intensity-based acquisition artifacts. An expert pathologist manually delineated the dominant tumor regions on ex vivo sectioned and stained RP specimens as well as identified each of the studies as either a CG or PZ CaP. A nonlinear registration scheme was used to spatially align and then map CaP extent from the ex vivo RP sections onto the corresponding MRI slices. A total of 110 texture features were then extracted on a per-voxel basis from all T2w MRI data sets. An information theoretic feature selection procedure was then applied to identify QISes comprising T2w MRI textural features specific to CG and PZ CaP, respectively. The QISes for CG and PZ CaP were evaluated by means of Quadratic Discriminant Analysis (QDA) on a per-voxel basis against the ground truth for CaP on T2w MRI, mapped from corresponding histology.

RESULTS

The QDA classifier yielded an area under the Receiver Operating characteristic curve of 0.86 for the CG CaP studies, and 0.73 for the PZ CaP studies over 25 runs of randomized three-fold cross-validation. By comparison, the accuracy of the QDA classifier was significantly lower when (a) using all 110 texture features (with no feature selection applied), as well as (b) a randomly selected combination of texture features.

CONCLUSION

CG and PZ prostate cancers have significantly differing textural quantitative imaging signatures on T2w endorectal in vivo MRI.

Multiparametric MRI maps for detection and grading of dominant prostate tumors

PURPOSE

To develop an image-based technique capable of detection and grading of prostate cancer, which combines features extracted from multiparametric MRI into a single parameter map of cancer probability.

MATERIALS AND METHODS

A combination of features extracted from diffusion tensor MRI and dynamic contrast enhanced MRI was used to characterize biopsy samples from 29 patients. Support vector machines were used to separate the cancerous samples from normal biopsy samples and to compute a measure of cancer probability, presented in the form of a cancer colormap. The classification results were compared with the biopsy results and the classifier was tuned to provide the largest area under the receiver operating characteristic (ROC) curve. Based solely on the tuning of the classifier on the biopsy data, cancer colormaps were also created for whole-mount histopathology slices from four radical prostatectomy patients.

RESULTS

An area under ROC curve of 0.96 was obtained on the biopsy dataset and was validated by a "leave-one-patient-out" procedure. The proposed measure of cancer probability shows a positive correlation with Gleason score. The cancer colormaps created for the histopathology patients do display the dominant tumors. The colormap accuracy increases with measured tumor area and Gleason score.

CONCLUSION

Dynamic contrast enhanced imaging and diffusion tensor imaging, when used within the framework of supervised classification, can play a role in characterizing prostate cancer.

Feasibility of texture analysis for the assessment of biochemical changes in meniscal tissue on T1 maps calculated from delayed gadolinium-enhanced magnetic resonance imaging of cartilage data: comparison with conventional relaxation time measurements

OBJECTIVES

To (1) establish the feasibility of texture analysis for the in vivo assessment of biochemical changes in meniscal tissue on delayed gadolinium-enhanced magnetic resonance imaging of cartilage (dGEMRIC), and (2) compare textural with conventional T1 relaxation time measurements calculated from dGEMRIC data ("T1(Gd) relaxation times").

MATERIALS AND METHODS

We enrolled 10 asymptomatic volunteers (7 men and 3 women; mean age, 27.2 +/- 4.5 years), without a history of meniscus damage, in our study. MRI of the right knee was performed at 3.0 T. An isotropic, 3-dimensional (3D), double-echo steady-state sequences was used for morphologic evaluation, and a dual flip angle 3D gradient echo sequence was used for T1(Gd) mapping. All MRI scans were performed 90 minutes after injection of 0.2 mmol/kg of Gd-diethylenetriamine pentaacetic acid (DTPA), and subsequently, during application of a compressive force (50% of the body weight) in the axial direction. Regions of interest, covering the central portions of the posterior horn of the medial meniscus, were defined on 3 adjacent sagittal sections. Based on the relaxation time maps, mean T1(Gd), as well as the T1(Gd) texture features derived from the co-occurrence matrix (COC: Angular Second Moment, Entropy, Inverse Difference Moment) and wavelet transform (WAV: WavEnLL, WavEnHL, WavEnHH, WavEnLH), were calculated. Paired t tests were used to assess differences between baseline and compression, and intraclass correlation coefficients (ICC) were calculated to establish the intrarater reliability of the measurements.

RESULTS

Mean T1(Gd) (-67.3 ms, P = 0.011), Angular Second Moment (-0.0002, P = 0.009), Entropy (+0.033, P = 0.025), WavEnLL (+1011.16, P = 0.002), WavEnHL (+18.64, P = 0.012), and WavEnLH (+72.74, P = 0.035) differed significantly between baseline and compression. Intrarater reliability was substantial for mean T1(Gd) relaxation times (ICC = 0.99-1.0), and also for T1(Gd) co-occurrence matrix (ICC = 0.63-0.92) and WAV (ICC = 0.86-0.98) features.

CONCLUSIONS

Texture features extracted from T1 maps calculated from dGEMRIC data are feasible for the in vivo assessment of biochemical changes in the menisci, such as might be induced by mechanical loading. Thus, T1(Gd) texture features complement conventional relaxation time measurements. Further studies are necessary to determine whether the mechanical compression, or a prolonged Gd-DTPA uptake, or both, are responsible for the observed decrease in mean T1(Gd) relaxation times in the menisci.

Fractal dimension analysis of MDCT images for quantifying the morphological changes of the pulmonary artery tree in patients with pulmonary hypertension

Objective

The aim of this study was to use fractal dimension (FD) analysis on multidetector CT (MDCT) images for quantifying the morphological changes of the pulmonary artery tree in patients with pulmonary hypertension (PH).

Materials and Methods

Fourteen patients with PH and 17 patients without PH as controls were studied. All of the patients underwent contrast-enhanced helical CT and transthoracic echocardiography. The pulmonary artery trees were generated using post-processing software, and the FD and projected image area of the pulmonary artery trees were determined with ImageJ software in a personal computer. The FD, the projected image area and the pulmonary artery pressure (PAP) were statistically evaluated in the two groups.

Results

The FD, the projected image area and the PAP of the patients with PH were higher than those values of the patients without PH (p < 0.05, t-test). There was a high correlation of FD with the PAP (r = 0.82, p < 0.05, partial correlation analysis). There was a moderate correlation of FD with the projected image area (r = 0.49, p < 0.05, partial correlation analysis). There was a correlation of the PAP with the projected image area (r = 0.65, p < 0.05, Pearson correlation analysis).

Conclusion

The FD of the pulmonary arteries in the PH patients was significantly higher than that of the controls. There is a high correlation of FD with the PAP.

Texture-based classification of focal liver lesions on MRI at 3.0 Tesla: a feasibility study in cysts and hemangiomas

PURPOSE

To determine the feasibility of texture analysis for the classification of liver cysts and hemangiomas, on nonenhanced, zero-fill interpolated T1- and T2-weighted MR images.

MATERIALS AND METHODS

Forty-five patients (26 women and 19 men; mean age, 58.1 +/- 16.9 years) with liver cysts or hemangiomas were enrolled in the study. After exclusion of images with artifacts, T1-weighted images of 42 patients, and T2-weighted images of 39 patients, obtained at 3.0 Tesla (T), were available for further analysis. Texture features derived from the gray-level histogram, co-occurrence and run-length matrix, gradient, autoregressive model, and wavelet transform were calculated. Fisher, probability of classification error and average correlation (POE+ACC), and mutual information coefficients were used to extract subsets of optimized texture features. Linear discriminant analysis (LDA) in combination with k nearest neighbor (k-NN) classification, and k-means clustering, were used for lesion classification.

RESULTS

LDA/k-NN produced misclassification rates of 16-18% on T1-weighted, and 12-18% on T2-weighted images. K-means clustering yielded misclassification rates of 15-23% on T1-weighted, and 15-25% on T2-weighted images.

CONCLUSION

Texture-based classification of liver cysts and hemangiomas is feasible on zero-fill interpolated MR images obtained at 3.0T. Further studies are warranted to investigate the value of texture-based classification of other liver lesions, such as hepatocellular and cholangiocellular carcinoma, on MRI.