Prostate cancer segmentation with simultaneous estimation of Markov random field parameters and class

Prostate cancer detection and segmentation on MRI using non-local mask R-CNN with histopathological ground truth

BACKGROUND

Automatic detection and segmentation of intraprostatic lesions (ILs) on preoperative multiparametric-magnetic resonance images (mp-MRI) can improve clinical workflow efficiency and enhance the diagnostic accuracy of prostate cancer and is an essential step in dominant intraprostatic lesion boost.

PURPOSE

The goal is to improve the detection and segmentation accuracy of 3D ILs in MRI by a proposed a deep learning (DL)-based algorithm with histopathological ground truth.

METHODS

This retrospective study included 262 patients with in vivo prostate biparametric MRI (bp-MRI) scans and were divided into three cohorts based on their data analysis and annotation. Histopathological ground truth was established by using histopathology images as delineation reference standard on cohort 1, which consisted of 64 patients and was randomly split into 20 training, 12 validation, and 32 testing patients. Cohort 2 consisted of 158 patients with bp-MRI based lesion delineation, and was randomly split into 104 training, 15 validation, and 39 testing patients. Cohort 3 consisted of 40 unannotated patients, used in semi-supervised learning. We proposed a non-local Mask R-CNN and boosted its performance by applying different training techniques. The performance of non-local Mask R-CNN was compared with baseline Mask R-CNN, 3D U-Net and an experienced radiologist's delineation and was evaluated by detection rate, dice similarity coefficient (DSC), sensitivity, and Hausdorff Distance (HD).

RESULTS

The independent testing set consists of 32 patients with histopathological ground truth. With the training technique maximizing detection rate, the non-local Mask R-CNN achieved 80.5% and 94.7% detection rate; 0.548 and 0.604 DSC; 5.72 and 6.36 95 HD (mm); 0.613 and 0.580 sensitivity for ILs of all Gleason Grade groups (GGGs) and clinically significant ILs (GGG > 2), which outperformed baseline Mask R-CNN and 3D U-Net. For clinically significant ILs, the model segmentation accuracy was significantly higher than that of the experienced radiologist involved in the study, who achieved 0.512 DSC (p = 0.04), 8.21 (p = 0.041) 95 HD (mm), and 0.398 (p = 0.001) sensitivity.

CONCLUSION

The proposed DL model achieved state-of-art performance and has the potential to help improve radiotherapy treatment planning and noninvasive prostate cancer diagnosis.

Attention-guided multi-scale learning network for automatic prostate and tumor segmentation on MRI

BACKGROUND AND OBJECTIVE

Image-guided clinical diagnosis can be achieved by automatically and accurately segmenting prostate and prostatic cancer in male pelvic magnetic resonance imaging (MRI) images. For accurate tumor removal, the location, number, and size of prostate cancer are crucial, especially in surgical patients. The morphological differences between the prostate and tumor regions are small, the size of the tumor is uncertain, the boundary between the tumor and surrounding tissue is blurred, and the classification that separates the normal region from the tumor is uneven. Therefore, segmenting prostate and tumor on MRI images is challenging.

METHODS

This study offers a new prostate and prostatic cancer segmentation network based on double branch attention driven multi-scale learning for MRI. To begin, the dual branch structure provides two input images with different scales for feature coding, as well as a multi-scale attention module that collects details from different scales. The features of the double branch structure are then entered into the built feature fusion module to get more complete context information. Finally, to give a more precise learning representation, each stage is built using a deep supervision mechanism.

RESULTS

The results of our proposed network's prostate and tumor segmentation on a variety of male pelvic MRI data sets show that it outperforms existing techniques. For prostate and prostatic cancer MRI segmentation, the dice similarity coefficient (DSC) values were 91.65% and 84.39%, respectively.

CONCLUSIONS

Our method maintains high correlation and consistency between automatic segmentation results and expert manual segmentation results. Accurate automatic segmentation of prostate and prostate cancer has important clinical significance.

Prostate cancer segmentation from MRI by a multistream fusion encoder

BACKGROUND

Targeted prostate biopsy guided by multiparametric magnetic resonance imaging (mpMRI) detects more clinically significant lesions than conventional systemic biopsy. Lesion segmentation is required for planning MRI-targeted biopsies. The requirement for integrating image features available in T2-weighted and diffusion-weighted images poses a challenge in prostate lesion segmentation from mpMRI.

PURPOSE

A flexible and efficient multistream fusion encoder is proposed in this work to facilitate the multiscale fusion of features from multiple imaging streams. A patch-based loss function is introduced to improve the accuracy in segmenting small lesions.

METHODS

The proposed multistream encoder fuses features extracted in the three imaging streams at each layer of the network, thereby allowing improved feature maps to propagate downstream and benefit segmentation performance. The fusion is achieved through a spatial attention map generated by optimally weighting the contribution of the convolution outputs from each stream. This design provides flexibility for the network to highlight image modalities according to their relative influence on the segmentation performance. The encoder also performs multiscale integration by highlighting the input feature maps (low-level features) with the spatial attention maps generated from convolution outputs (high-level features). The Dice similarity coefficient (DSC), serving as a cost function, is less sensitive to incorrect segmentation for small lesions. We address this issue by introducing a patch-based loss function that provides an average of the DSCs obtained from local image patches. This local average DSC is equally sensitive to large and small lesions, as the patch-based DSCs associated with small and large lesions have equal weights in this average DSC.

RESULTS

The framework was evaluated in 931 sets of images acquired in several clinical studies at two centers in Hong Kong and the United Kingdom. In particular, the training, validation, and test sets contain 615, 144, and 172 sets of images, respectively. The proposed framework outperformed single-stream networks and three recently proposed multistream networks, attaining F1 scores of 82.2 and 87.6% in the lesion and patient levels, respectively. The average inference time for an axial image was 11.8 ms.

CONCLUSION

The accuracy and efficiency afforded by the proposed framework would accelerate the MRI interpretation workflow of MRI-targeted biopsy and focal therapies.

Deep learning-based dominant index lesion segmentation for MR-guided radiation therapy of prostate cancer

BACKGROUND

Dose escalation radiotherapy enables increased control of prostate cancer (PCa) but requires segmentation of dominant index lesions (DIL). This motivates the development of automated methods for fast, accurate, and consistent segmentation of PCa DIL.

PURPOSE

To construct and validate a model for deep-learning-based automatic segmentation of PCa DIL defined by Gleason score (GS) ≥3+4 from MR images applied to MR-guided radiation therapy. Validate generalizability of constructed models across scanner and acquisition differences.

METHODS

Five deep-learning networks were evaluated on apparent diffusion coefficient (ADC) MRI from 500 lesions in 365 patients arising from internal training Dataset 1 (156 lesions in 125 patients, 1.5Tesla GE MR with endorectal coil), testing using Dataset 1 (35 lesions in 26 patients), external ProstateX Dataset 2 (299 lesions in 204 patients, 3Tesla Siemens MR), and internal inter-rater Dataset 3 (10 lesions in 10 patients, 3Tesla Philips MR). The five networks include: multiple resolution residually connected network (MRRN) and MRRN regularized in training with deep supervision implemented into the last convolutional block (MRRN-DS), Unet, Unet++, ResUnet, and fast panoptic segmentation (FPSnet) as well as fast panoptic segmentation with smoothed labels (FPSnet-SL). Models were evaluated by volumetric DIL segmentation accuracy using Dice similarity coefficient (DSC) and the balanced F1 measure of detection accuracy, as a function of lesion aggressiveness and size (Dataset 1 and 2), and accuracy with respect to two-raters (on Dataset 3). Upon acceptance for publication segmentation models will be made available in an open-source GitHub repository.

RESULTS

In general, MRRN-DS more accurately segmented tumors than other methods on the testing datasets. MRRN-DS significantly outperformed ResUnet in Dataset2 (DSC of 0.54 vs. 0.44, p < 0.001) and the Unet++ in Dataset3 (DSC of 0.45 vs. p = 0.04). FPSnet-SL was similarly accurate as MRRN-DS in Dataset2 (p = 0.30), but MRRN-DS significantly outperformed FPSnet and FPSnet-SL in both Dataset1 (0.60 vs. 0.51 [p = 0.01] and 0.54 [p = 0.049] respectively) and Dataset3 (0.45 vs. 0.06 [p = 0.002] and 0.24 [p = 0.004] respectively). Finally, MRRN-DS produced slightly higher agreement with experienced radiologist than two radiologists in Dataset 3 (DSC of 0.45 vs. 0.41).

CONCLUSIONS

MRRN-DS was generalizable to different MR testing datasets acquired using different scanners. It produced slightly higher agreement with an experienced radiologist than that between two radiologists. Finally, MRRN-DS more accurately segmented aggressive lesions, which are generally candidates for radiative dose ablation.

A novel approach for automatic segmentation of prostate and its lesion regions on magnetic resonance imaging

Objective

To develop an accurate and automatic segmentation model based on convolution neural network to segment the prostate and its lesion regions.

Methods

Of all 180 subjects, 122 healthy individuals and 58 patients with prostate cancer were included. For each subject, all slices of the prostate were comprised in the DWIs. A novel DCNN is proposed to automatically segment the prostate and its lesion regions. This model is inspired by the U-Net model with the encoding-decoding path as the backbone, importing dense block, attention mechanism techniques, and group norm-Atrous Spatial Pyramidal Pooling. Data augmentation was used to avoid overfitting in training. In the experimental phase, the data set was randomly divided into a training (70%), testing set (30%). four-fold cross-validation methods were used to obtain results for each metric.

Results

The proposed model achieved in terms of Iou, Dice score, accuracy, sensitivity, 95% Hausdorff Distance, 86.82%,93.90%, 94.11%, 93.8%,7.84 for the prostate, 79.2%, 89.51%, 88.43%,89.31%,8.39 for lesion region in segmentation. Compared to the state-of-the-art models, FCN, U-Net, U-Net++, and ResU-Net, the segmentation model achieved more promising results.

Conclusion

The proposed model yielded excellent performance in accurate and automatic segmentation of the prostate and lesion regions, revealing that the novel deep convolutional neural network could be used in clinical disease treatment and diagnosis.

Comparative Analysis of the Performance of Complex Texture Clustering Driven by Computational Intelligence Methods Using Multiple Clustering Models

Traditional texture cluster algorithms are frequently used in engineering; however, despite their widespread application, these algorithms continue to suffer from drawbacks including excessive complexity and limited universality. This study will focus primarily on the analysis of the performance of a number of different texture clustering algorithms. In addition, the performance of traditional texture classification algorithms will be compared in terms of image size, clustering number, running time, and accuracy. Finally, the performance boundaries of various algorithms will be determined in order to determine where future improvements to these algorithms should be concentrated. In the experiment, some traditional clustering algorithms are used as comparative tools for performance analysis. The qualitative and quantitative data both show that there is a significant difference in performance between the different algorithms. It is only possible to achieve better performance by selecting the appropriate algorithm based on the characteristics of the texture image.

Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods

Prostate cancer represents today the most typical example of a pathology whose diagnosis requires multiparametric imaging, a strategy where multiple imaging techniques are combined to reach an acceptable diagnostic performance. However, the reviewing, weighing and coupling of multiple images not only places additional burden on the radiologist, it also complicates the reviewing process. Prostate cancer imaging has therefore been an important target for the development of computer-aided diagnostic (CAD) tools. In this survey, we discuss the advances in CAD for prostate cancer over the last decades with special attention to the deep-learning techniques that have been designed in the last few years. Moreover, we elaborate and compare the methods employed to deliver the CAD output to the operator for further medical decision making.

Applications of Artificial Intelligence to Prostate Multiparametric MRI (mpMRI): Current and Emerging Trends

Prostate carcinoma is one of the most prevalent cancers worldwide. Multiparametric magnetic resonance imaging (mpMRI) is a non-invasive tool that can improve prostate lesion detection, classification, and volume quantification. Machine learning (ML), a branch of artificial intelligence, can rapidly and accurately analyze mpMRI images. ML could provide better standardization and consistency in identifying prostate lesions and enhance prostate carcinoma management. This review summarizes ML applications to prostate mpMRI and focuses on prostate organ segmentation, lesion detection and segmentation, and lesion characterization. A literature search was conducted to find studies that have applied ML methods to prostate mpMRI. To date, prostate organ segmentation and volume approximation have been well executed using various ML techniques. Prostate lesion detection and segmentation are much more challenging tasks for ML and were attempted in several studies. They largely remain unsolved problems due to data scarcity and the limitations of current ML algorithms. By contrast, prostate lesion characterization has been successfully completed in several studies because of better data availability. Overall, ML is well situated to become a tool that enhances radiologists' accuracy and speed.

Segmentation of the Prostatic Gland and the Intraprostatic Lesions on Multiparametic Magnetic Resonance Imaging Using Mask Region-Based Convolutional Neural Networks

Purpose

Accurate delineation of the prostate gland and intraprostatic lesions (ILs) is essential for prostate cancer dose-escalated radiation therapy. The aim of this study was to develop a sophisticated deep neural network approach to magnetic resonance image analysis that will help IL detection and delineation for clinicians.

Methods and Materials

We trained and evaluated mask region-based convolutional neural networks to perform the prostate gland and IL segmentation. There were 2 cohorts in this study: 78 public patients (cohort 1) and 42 private patients from our institution (cohort 2). Prostate gland segmentation was performed using T2-weighted images (T2WIs), although IL segmentation was performed using T2WIs and coregistered apparent diffusion coefficient maps with prostate patches cropped out. The IL segmentation model was extended to select 5 highly suspicious volumetric lesions within the entire prostate.

Results

The mask region-based convolutional neural networks model was able to segment the prostate with dice similarity coefficient (DSC) of 0.88 ± 0.04, 0.86 ± 0.04, and 0.82 ± 0.05; sensitivity (Sens.) of 0.93, 0.95, and 0.95; and specificity (Spec.) of 0.98, 0.85, and 0.90. However, ILs were segmented with DSC of 0.62 ± 0.17, 0.59 ± 0.14, and 0.38 ± 0.19; Sens. of 0.55 ± 0.30, 0.63 ± 0.28, and 0.22 ± 0.24; and Spec. of 0.974 ± 0.010, 0.964 ± 0.015, and 0.972 ± 0.015 in public validation/public testing/private testing patients when trained with patients from cohort 1 only. When trained with patients from both cohorts, the values were as follows: DSC of 0.64 ± 0.11, 0.56 ± 0.15, and 0.46 ± 0.15; Sens. of 0.57 ± 0.23, 0.50 ± 0.28, and 0.33 ± 0.17; and Spec. of 0.980 ± 0.009, 0.969 ± 0.016, and 0.977 ± 0.013.

Conclusions

Our research framework is able to perform as an end-to-end system that automatically segmented the prostate gland and identified and delineated highly suspicious ILs within the entire prostate. Therefore, this system demonstrated the potential for assisting the clinicians in tumor delineation.

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.

MPCaD: a multi-scale radiomics-driven framework for automated prostate cancer localization and detection

Background

Quantitative radiomic features provide a plethora of minable data extracted from multi-parametric magnetic resonance imaging (MP-MRI) which can be used for accurate detection and localization of prostate cancer. While most cancer detection algorithms utilize either voxel-based or region-based feature models, the complexity of prostate tumour phenotype in MP-MRI requires a more sophisticated framework to better leverage available data and exploit a priori knowledge in the field.

Methods

In this paper, we present MPCaD, a novel Multi-scale radiomics-driven framework for Prostate Cancer Detection and localization which leverages radiomic feature models at different scales as well as incorporates a priori knowledge of the field. Tumour candidate localization is first performed using a statistical texture distinctiveness strategy that leverages a voxel-resolution feature model to localize tumour candidate regions. Tumour region classification via a region-resolution feature model is then performed to identify tumour regions. Both voxel-resolution and region-resolution feature models are built upon and extracted from six different MP-MRI modalities. Finally, a conditional random field framework that is driven by voxel-resolution relative ADC features is used to further refine the localization of the tumour regions in the peripheral zone to improve the accuracy of the results.

Results

The proposed framework is evaluated using clinical prostate MP-MRI data from 30 patients, and results demonstrate that the proposed framework exhibits enhanced separability of cancerous and healthy tissue, as well as outperforms individual quantitative radiomics models for prostate cancer detection.

Conclusion

Quantitative radiomic features extracted from MP-MRI of prostate can be utilized to detect and localize prostate cancer.

Development of a measure for evaluating lesion-wise performance of CAD algorithms in the context of mpMRI detection of prostate cancer

PURPOSE

Computer-aided detection/diagnosis (CAD) of prostate cancer (PCa) on multiparametric MRI (mpMRI) is an active area of research. In the literature, the performance of predictive models trained to detect PCa on mpMRI has typically been reported in terms of voxel-wise measures such as sensitivity and specificity and/or area under the receiver operating curve (AUC). However, it is unclear whether models that score higher by these measures are actually superior. Here, we propose a novel method for lesion identification as well as novel measures that assess the quality of the detected lesions.

METHODS

A total of 46 axial MRI slices of interest from 34 patients and the associated histopathologic ground truths were used to develop and to characterize the proposed measures. The proposed lesion-wise score s_ℓ is based on the Jaccard similarity index with modifications that emphasize the overlap and colocalization of predicted lesions with ground truth lesions. Thresholding of s_ℓ allowed for the sensitivity and specificity of lesion detection to be assessed, while the proposed lesion-summary score s_σ is a weighted average of s_ℓ s that provides a single summary statistic of lesion detection performance. The proposed measures were used to compare the lesion detection performance of a predictive model vs that of a radiologist on the same data set. The measures were also used to evaluate the degree to which viewing the cancer prediction improved diagnostic accuracy.

RESULTS

The lesion-wise score qualitatively reflected the goodness of predicted lesions over a wide range of values (s_ℓ = 0.1 to s_ℓ = 0.8) and was found to encompass a larger range of values than the Dice coefficient did over the same range of prediction qualities (0-0.9 vs 0-0.75). The lesion-summary score was shown to vary linearly with voxel-wise sensitivity and quadratically with voxel-wise specificity and correlated well with voxel-wise AUC (ρ = 0.68) and the Dice coefficient (ρ = 0.88). Radiologist performance was found to be significantly improved after viewing the model-generated cancer prediction maps as quantified by both s_σ (P = 0.01) and DSC (P = 0.04), with improvements in both lesion detection sensitivity and specificity.

CONCLUSION

The proposed measures allow for the assessment of lesion detection performance, which is most relevant in a clinical setting and would not be possible to do with voxel-wise measures alone.

Automatic Prostate Cancer Segmentation Using Kinetic Analysis in Dynamic Contrast-Enhanced MRI

BACKGROUND

Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) provides functional information on the microcirculation in tissues by analyzing the enhancement kinetics which can be used as biomarkers for prostate lesions detection and characterization.

OBJECTIVE

The purpose of this study is to investigate spatiotemporal patterns of tumors by extracting semi-quantitative as well as wavelet-based features, both extracted from pixel-based time-signal intensity curves to segment prostate lesions on prostate DCE-MRI.

METHODS

Quantitative dynamic contrast-enhanced MRI data were acquired on 22 patients. Optimal features selected by forward selection are used for the segmentation of prostate lesions by applying fuzzy c-means (FCM) clustering. The images were reviewed by an expert radiologist and manual segmentation performed as the ground truth.

RESULTS

Empirical results indicate that fuzzy c-mean classifier can achieve better results in terms of sensitivity, specificity when semi-quantitative features were considered versus wavelet kinetic features for lesion segmentation (Sensitivity of 87.58% and 75.62%, respectively) and (Specificity of 89.85% and 68.89 %, respectively).

CONCLUSION

The proposed segmentation algorithm in this work can potentially be implemented for automatic prostate lesion detection in a computer aided diagnosis scheme and combined with morphologic features to increase diagnostic credibility.

Discriminative Scale Learning (DiScrn): Applications to Prostate Cancer Detection from MRI and Needle Biopsies

There has been recent substantial interest in extracting sub-visual features from medical images for improved disease characterization compared to what might be achievable via visual inspection alone. Features such as Haralick and Gabor can provide a multi-scale representation of the original image by extracting measurements across differently sized neighborhoods. While these multi-scale features are effective, on large-scale digital pathological images, the process of extracting these features is computationally expensive. Moreover for different problems, different scales and neighborhood sizes may be more or less important and thus a large number of features extracted might end up being redundant. In this paper, we present a Discriminative Scale learning (DiScrn) approach that attempts to automatically identify the distinctive scales at which features are able to best separate cancerous from non-cancerous regions on both radiologic and digital pathology tissue images. To evaluate the efficacy of our approach, our approach was employed to detect presence and extent of prostate cancer on a total of 60 MRI and digitized histopathology images. Compared to a multi-scale feature analysis approach invoking features across all scales, DiScrn achieved 66% computational efficiency while also achieving comparable or even better classifier performance.

Liver Ultrasound Image Segmentation Using Region-Difference Filters

In this paper, region-difference filters for the segmentation of liver ultrasound (US) images are proposed. Region-difference filters evaluate maximum difference of the average of two regions of the window around the center pixel. Implementing the filters on the whole image gives region-difference image. This image is then converted into binary image and morphologically operated for segmenting the desired lesion from the ultrasound image. The proposed method is compared with the maximum a posteriori-Markov random field (MAP-MRF), Chan-Vese active contour method (CV-ACM), and active contour region-scalable fitting energy (RSFE) methods. MATLAB code available online for the RSFE method is used for comparison whereas MAP-MRF and CV-ACM methods are coded in MATLAB by authors. Since no comparison is available on common database for the performance of the three methods, therefore, performance comparison of the three methods and proposed method was done on liver US images obtained from PGIMER, Chandigarh, India and from online resource. A radiologist blindly analyzed segmentation results of the 4 methods implemented on 56 images and had selected the segmentation result obtained from the proposed method as best for 46 test US images. For the remaining 10 US images, the proposed method performance was very near to the other three segmentation methods. The proposed segmentation method obtained the overall accuracy of 99.32% in comparison to the overall accuracy of 85.9, 98.71, and 68.21% obtained by MAP-MRF, CV-ACM, and RSFE methods, respectively. Computational time taken by the proposed method is 5.05 s compared to the time of 26.44, 24.82, and 28.36 s taken by MAP-MRF, CV-ACM, and RSFE methods, respectively.

Connecting Markov random fields and active contour models: application to gland segmentation and classification

We introduce a Markov random field (MRF)-driven region-based active contour model (MaRACel) for histological image segmentation. This Bayesian segmentation method combines a region-based active contour (RAC) with an MRF. State-of-the-art RAC models assume that every spatial location in the image is statistically independent, thereby ignoring valuable contextual information among spatial locations. To address this shortcoming, we incorporate an MRF prior into energy term of the RAC. This requires a formulation of the Markov prior consistent with the continuous variational framework characteristic of active contours; consequently, we introduce a continuous analog to the discrete Potts model. Based on the automated segmentation boundary of glands by MaRACel model, explicit shape descriptors are then employed to distinguish prostate glands belonging to Gleason patterns 3 (G3) and 4 (G4). To demonstrate the effectiveness of MaRACel, we compare its performance to the popular models proposed by Chan and Vese (CV) and Rousson and Deriche (RD) with respect to the following tasks: (1) the segmentation of prostatic acini (glands) and (2) the differentiation of G3 and G4 glands. On almost 600 prostate biopsy needle images, MaRACel was shown to have higher average dice coefficients, overlap ratios, sensitivities, specificities, and positive predictive values both in terms of segmentation accuracy and ability to discriminate between G3 and G4 glands compared to the CV and RD models.

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

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

Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases

BACKGROUND

With a wide array of multi-modal, multi-protocol, and multi-scale biomedical data being routinely acquired for disease characterization, there is a pressing need for quantitative tools to combine these varied channels of information. The goal of these integrated predictors is to combine these varied sources of information, while improving on the predictive ability of any individual modality. A number of application-specific data fusion methods have been previously proposed in the literature which have attempted to reconcile the differences in dimensionalities and length scales across different modalities. Our objective in this paper was to help identify metholodological choices that need to be made in order to build a data fusion technique, as it is not always clear which strategy is optimal for a particular problem. As a comprehensive review of all possible data fusion methods was outside the scope of this paper, we have focused on fusion approaches that employ dimensionality reduction (DR).

METHODS

In this work, we quantitatively evaluate 4 non-overlapping existing instantiations of DR-based data fusion, within 3 different biomedical applications comprising over 100 studies. These instantiations utilized different knowledge representation and knowledge fusion methods, allowing us to examine the interplay of these modules in the context of data fusion. The use cases considered in this work involve the integration of (a) radiomics features from T2w MRI with peak area features from MR spectroscopy for identification of prostate cancer in vivo, (b) histomorphometric features (quantitative features extracted from histopathology) with protein mass spectrometry features for predicting 5 year biochemical recurrence in prostate cancer patients, and (c) volumetric measurements on T1w MRI with protein expression features to discriminate between patients with and without Alzheimers' Disease.

RESULTS AND CONCLUSIONS

Our preliminary results in these specific use cases indicated that the use of kernel representations in conjunction with DR-based fusion may be most effective, as a weighted multi-kernel-based DR approach resulted in the highest area under the ROC curve of over 0.8. By contrast non-optimized DR-based representation and fusion methods yielded the worst predictive performance across all 3 applications. Our results suggest that when the individual modalities demonstrate relatively poor discriminability, many of the data fusion methods may not yield accurate, discriminatory representations either. In summary, to outperform the predictive ability of individual modalities, methodological choices for data fusion must explicitly account for the sparsity of and noise in the feature space.

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.

Combined PET/MR: The Real Work Has Just Started. Summary Report of the Third International Workshop on PET/MR Imaging; February 17-21, 2014, Tübingen, Germany

This paper summarises the proceedings and discussions at the third annual workshop held in Tübingen, Germany, dedicated to the advancement of the technical, scientific and clinical applications of combined PET/MRI systems in humans. Two days of basic scientific and technical instructions with "hands-on" tutorials were followed by 3 days of invited presentations from active researchers in this and associated fields augmented by round-table discussions and dialogue boards with specific themes. These included the use of PET/MRI in paediatric oncology and in adult neurology, oncology and cardiology, the development of multi-parametric analyses, and efforts to standardise PET/MRI examinations to allow pooling of data for evaluating the technology. A poll taken on the final day demonstrated that over 50 % of those present felt that while PET/MRI technology underwent an inevitable slump after its much-anticipated initial launch, it was now entering a period of slow, progressive development, with new key applications emerging. In particular, researchers are focusing on exploiting the complementary nature of the physiological (PET) and biochemical (MRI/MRS) data within the morphological framework (MRI) that these devices can provide. Much of the discussion was summed up on the final day when one speaker commented on the state of PET/MRI: "the real work has just started".

A Learning-Based CT Prostate Segmentation Method via Joint Transductive Feature Selection and Regression

In1 recent years, there has been a great interest in prostate segmentation, which is a important and challenging task for CT image guided radiotherapy. In this paper, a learning-based segmentation method via joint transductive feature selection and transductive regression is presented, which incorporates the physician's simple manual specification (only taking a few seconds), to aid accurate segmentation, especially for the case with large irregular prostate motion. More specifically, for the current treatment image, experienced physician is first allowed to manually assign the labels for a small subset of prostate and non-prostate voxels, especially in the first and last slices of the prostate regions. Then, the proposed method follows the two step: in prostate-likelihood estimation step, two novel algorithms: tLasso and wLapRLS, will be sequentially employed for transductive feature selection and transductive regression, respectively, aiming to generate the prostate-likelihood map. In multi-atlases based label fusion step, the final segmentation result will be obtained according to the corresponding prostate-likelihood map and the previous images of the same patient. The proposed method has been substantially evaluated on a real prostate CT dataset including 24 patients with 330 CT images, and compared with several state-of-the-art methods. Experimental results show that the proposed method outperforms the state-of-the-arts in terms of higher Dice ratio, higher true positive fraction, and lower centroid distances. Also, the results demonstrate that simple manual specification can help improve the segmentation performance, which is clinically feasible in real practice.

MAPS: A Quantitative Radiomics Approach for Prostate Cancer Detection

This paper presents a quantitative radiomics feature model for performing prostate cancer detection using multiparametric MRI (mpMRI). It incorporates a novel tumor candidate identification algorithm to efficiently and thoroughly identify the regions of concern and constructs a comprehensive radiomics feature model to detect tumorous regions. In contrast to conventional automated classification schemes, this radiomics-based feature model aims to ground its decisions in a way that can be interpreted and understood by the diagnostician. This is done by grouping features into high-level feature categories which are already used by radiologists to diagnose prostate cancer: Morphology, Asymmetry, Physiology, and Size (MAPS), using biomarkers inspired by the PI-RADS guidelines for performing structured reporting on prostate MRI. Clinical mpMRI data were collected from 13 men with histology-confirmed prostate cancer and labeled by an experienced radiologist. These annotated data were used to train classifiers using the proposed radiomics-driven feature model in order to evaluate the classification performance. The preliminary experimental results indicated that the proposed model outperformed each of its constituent feature groups as well as a comparable conventional mpMRI feature model. A further validation of the proposed algorithm will be conducted using a larger dataset as future work.

Multiparametric MRI prostate cancer analysis via a hybrid morphological-textural model

Multiparametric MRI has shown considerable promise as a diagnostic tool for prostate cancer grading. Diffusion-weighted MRI (DWI) has shown particularly strong potential for improving the delineation between cancerous and healthy tissue in the prostate gland. Current automated diagnostic methods using multiparametric MRI, however, tend to either use low-level features, which are difficult to interpret by radiologists and clinicians, or use highly subjective heuristic methods. We propose a novel strategy comprising a tumor candidate identification scheme and a hybrid textural-morphological feature model for delineating between cancerous and non-cancerous tumor candidates in the prostate gland via multiparametric MRI. Experimental results using clinical multiparametric MRI datasets show that the proposed strategy has strong potential as a diagnostic tool to aid radiologists and clinicians identify and detect prostate cancer more efficiently and effectively.

Combined unsupervised-supervised classification of multiparametric PET/MRI data: application to prostate cancer

Multiparametric medical imaging data can be large and are often complex. Machine learning algorithms can assist in image interpretation when reliable training data exist. In most cases, however, knowledge about ground truth (e.g. histology) and thus training data is limited, which makes application of machine learning algorithms difficult. The purpose of this study was to design and implement a learning algorithm for classification of multidimensional medical imaging data that is robust and accurate even with limited prior knowledge and that allows for generalization and application to unseen data. Local prostate cancer was chosen as a model for application and validation. 16 patients underwent combined simultaneous [(11) C]-choline positron emission tomography (PET)/MRI. The following imaging parameters were acquired: T2 signal intensities, apparent diffusion coefficients, parameters Ktrans and Kep from dynamic contrast-enhanced MRI, and PET standardized uptake values (SUVs). A spatially constrained fuzzy c-means algorithm (sFCM) was applied to the single datasets and the resulting labeled data were used for training of a support vector machine (SVM) classifier. Accuracy and false positive and false negative rates of the proposed algorithm were determined in comparison with manual tumor delineation. For five of the 16 patients rates were also determined in comparison with the histopathological standard of reference. The combined sFCM/SVM algorithm proposed in this study revealed reliable classification results consistent with the histopathological reference standard and comparable to those of manual tumor delineation. sFCM/SVM generally performed better than unsupervised sFCM alone. We observed an improvement in accuracy with increasing number of imaging parameters used for clustering and SVM training. In particular, including PET SUVs as an additional parameter markedly improved classification results. A variety of applications are conceivable, especially for imaging of tissues without easily available histopathological correlation.

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.

Computer-aided analysis of prostate multiparametric MR images: an unsupervised fusion-based approach

OBJECTIVE

The aim of this study is to provide an automatic framework for computer-aided analysis of multiparametric magnetic resonance (mp-MR) images of prostate.

METHOD

We introduce a novel method for the unsupervised analysis of the images. An evidential C-means classifier was adapted for use with a segmentation scheme to address multisource data and to manage conflicts and redundancy.

RESULTS

Experiments were conducted using data from 15 patients. The evaluation protocol consisted in evaluating the method abilities to classify prostate tissues, showing the same behaviour on the mp-MR images, into homogeneous classes. As the actual diagnosis was available, thanks to the correlation with histopathological findings, the assessment focused on the ability to segment cancer foci. The method exhibited global sensitivity and specificity of 70 and 88 %, respectively.

CONCLUSION

The preliminary results obtained by these initial experiments showed that the method can be applied in clinical routine practice to help making decision especially for practitioners with limited experience in prostate MRI analysis.

Automatic lung tumor segmentation on PET/CT images using fuzzy Markov random field model

The combination of positron emission tomography (PET) and CT images provides complementary functional and anatomical information of human tissues and it has been used for better tumor volume definition of lung cancer. This paper proposed a robust method for automatic lung tumor segmentation on PET/CT images. The new method is based on fuzzy Markov random field (MRF) model. The combination of PET and CT image information is achieved by using a proper joint posterior probability distribution of observed features in the fuzzy MRF model which performs better than the commonly used Gaussian joint distribution. In this study, the PET and CT simulation images of 7 non-small cell lung cancer (NSCLC) patients were used to evaluate the proposed method. Tumor segmentations with the proposed method and manual method by an experienced radiation oncologist on the fused images were performed, respectively. Segmentation results obtained with the two methods were similar and Dice's similarity coefficient (DSC) was 0.85 ± 0.013. It has been shown that effective and automatic segmentations can be achieved with this method for lung tumors which locate near other organs with similar intensities in PET and CT images, such as when the tumors extend into chest wall or mediastinum.

Multi-modality functional image guided dose escalation in the presence of uncertainties

BACKGROUND AND PURPOSE

In order to increase local tumour control by radiotherapy without increasing toxicity, it appears promising to harness functional imaging (FI) to guide dose to sub-volumes of the target with a high tumour load and perhaps de-escalate dose to low risk volumes, in order to maximise the efficiency of the deposited radiation dose.

METHODS AND MATERIALS

A number of problems have to be solved to make focal dose escalation (FDE) efficient and safe: (1) how to combine ambiguous information from multiple imaging modalities; (2) how to take into account uncertainties of FI based tissue classification; (3) how to account for geometric uncertainties in treatment delivery; (4) how to add complementary FI modalities to an existing scheme. A generic optimisation concept addresses these points and is explicitly designed for clinical efficacy and for lowering the implementation threshold to FI-guided FDE. It combines classic tumour control probability modelling with a multi-variate logistic regression model of FI accuracy and an uncomplicated robust optimisation method.

RESULTS

Its key elements are (1) that dose is deposited optimally when it achieves equivalent expected effect everywhere in the target volume and (2) that one needs to cap the certainty about the absence of tumour anywhere in the target region. For illustration, an example of a PET/MR-guided FDE in prostate cancer is given.

CONCLUSIONS

FDE can be safeguarded against FI uncertainties, at the price of a limit on the sensible dose escalation.

Prostate focal peripheral zone lesions: characterization at multiparametric MR imaging--influence of a computer-aided diagnosis system

PURPOSE

To assess the impact of a computer-aided diagnosis (CAD) system in the characterization of focal prostate lesions at multiparametric magnetic resonance (MR) imaging.

MATERIALS AND METHODS

Formal institutional review board approval was not required. Thirty consecutive 1.5-T multiparametric MR imaging studies (with T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced imaging) obtained before radical prostatectomy in patients between September 2008 and February 2010 were reviewed. Twelve readers assessed the likelihood of malignancy of 88 predefined peripheral zone lesions by using a five-level (level, 0-4) subjective score (SS) in reading session 1. This was repeated 5 weeks later in reading session 2. The CAD results were then disclosed, and in reading session 3, the readers could amend the scores assigned during reading session 2. Diagnostic accuracy was assessed by using a receiver operating characteristic (ROC) regression model and was quantified with the area under the ROC curve (AUC).

RESULTS

Mean AUCs were significantly lower for less experienced (<1 year) readers (P < .02 for all sessions). Seven readers improved their performance between reading sessions 1 and 2, and 12 readers improved their performance between sessions 2 and 3. The mean AUCs for reading session 1 (83.0%; 95% confidence interval [CI]: 77.9%, 88.0%) and reading session 2 (84.1%; 95% CI: 78.1%, 88.7%) were not significantly different (P = .76). Although the mean AUC for reading session 3 (87.2%; 95% CI: 81.0%, 92.0%) was higher than that for session 2, the difference was not significant (P = .08). For an SS positivity threshold of 3, the specificity of reading session 2 (79.0%; 95% CI: 71.1%, 86.4%) was not significantly different from that of session 1 (78.7%; 95% CI: 70.5%, 86.8%) but was significantly lower than that of session 3 (86.2%; 95% CI: 77.1%, 93.1%; P < .03). The sensitivity of reading session 2 (68.4%; 95% CI: 57.5%, 77.7%) was significantly higher than that of session 1 (64.0%; 95% CI: 52.9%, 73.9%; P = .003) but was not significantly different from that of session 3 (71.4%; 95% CI: 58.3%, 82.7%).

CONCLUSION

A CAD system may improve the characterization of prostate lesions at multiparametric MR imaging by increasing reading specificity.

Cross-device automated prostate cancer localization with multiparametric MRI

Prostate cancer localization using supervised classification techniques has aroused considerable interest in medical imaging community in recent years. However, it is crucial to have an accurate training data set for supervised classification techniques. Since different devices with, e.g., different protocols and/or field strengths cause different intensity profiles, each device/protocol must have an accompanying training data set, which is very costly to obtain. It is highly desirable to adapt the existing classifier(s) trained for one device/protocol to help classify data coming from another device/protocol. In this paper, we propose a novel method that has the ability to design classifiers obtained from one imaging protocol and/or MRI device to be used on a data set from another protocol and/or imaging device. As an example problem, we consider prostate cancer localization with multiparametric MRI. We show that simple normalization techniques such as z-score are not sufficient for cross-device automated cancer localization. On the other hand, the method we have originally developed based on relative intensity allows us to successfully use a classifier obtained from one device to be applied on a test patient imaged with another device. Proposed method also allows us to employ T2-weighted MR images directly instead of an additional step to normalize T2-weighted images usually performed in an ad hoc manner when T2 maps are not available. To demonstrate the effectiveness of the proposed method, we use a multiparametric MRI data set acquired from 18 biopsy-confirmed cancer patients with two separate scanners: 1) 1.5-T (Excite HD) GE and 2) 1.5-T (Achieva) Philips Healthcare scanners. A comprehensive visual, quantitative, and statistical analysis of the results show that methods we have developed allow us to: 1) perform cross-device automated classification and 2) use T2-weighted images without an ad hoc subject-specific normalization.

PCG-cut: graph driven segmentation of the prostate central gland

Prostate cancer is the most abundant cancer in men, with over 200,000 expected new cases and around 28,000 deaths in 2012 in the US alone. In this study, the segmentation results for the prostate central gland (PCG) in MR scans are presented. The aim of this research study is to apply a graph-based algorithm to automated segmentation (i.e. delineation) of organ limits for the prostate central gland. The ultimate goal is to apply automated segmentation approach to facilitate efficient MR-guided biopsy and radiation treatment planning. The automated segmentation algorithm used is graph-driven based on a spherical template. Therefore, rays are sent through the surface points of a polyhedron to sample the graph's nodes. After graph construction--which only requires the center of the polyhedron defined by the user and located inside the prostate center gland--the minimal cost closed set on the graph is computed via a polynomial time s-t-cut, which results in the segmentation of the prostate center gland's boundaries and volume. The algorithm has been realized as a C++ module within the medical research platform MeVisLab and the ground truth of the central gland boundaries were manually extracted by clinical experts (interventional radiologists) with several years of experience in prostate treatment. For evaluation the automated segmentations of the proposed scheme have been compared with the manual segmentations, yielding an average Dice Similarity Coefficient (DSC) of 78.94 ± 10.85%.

Statistical Learning Algorithm for in situ and invasive breast carcinoma segmentation

Dynamic Contrast Enhanced MRI (DCE-MRI) has proven to be a highly sensitive imaging modality in diagnosing breast cancers. However, analyzing the DCE-MRI is time-consuming and prone to errors due to the large volume of data. Mathematical models to quantify contrast perfusion, such as the black box methods and pharmacokinetic analysis, are inaccurate, sensitive to noise and depend on a large number of external factors such as imaging parameters, patient physiology, arterial input function, and fitting algorithms, leading to inaccurate diagnosis. In this paper, we have developed a novel Statistical Learning Algorithm for Tumor Segmentation (SLATS) based on Hidden Markov Models to auto-segment regions of angiogenesis, corresponding to tumor. The SLATS algorithm has been trained to identify voxels belonging to the tumor class using the time-intensity curve, first and second derivatives of the intensity curves ("velocity" and "acceleration" respectively) and a composite vector consisting of a concatenation of the intensity, velocity and acceleration vectors. The results of SLATS trained for the four vectors has been shown for 22 Invasive Ductal Carcinoma (IDC) and 19 Ductal Carcinoma In Situ (DCIS) cases. The SLATS trained for the velocity tuple shows the best performance in delineating the tumors when compared with the segmentation performed by an expert radiologist and the output of a commercially available software, CADstream.

Multi-kernel graph embedding for detection, Gleason grading of prostate cancer via MRI/MRS

Even though 1 in 6 men in the US, in their lifetime are expected to be diagnosed with prostate cancer (CaP), only 1 in 37 is expected to die on account of it. Consequently, among many men diagnosed with CaP, there has been a recent trend to resort to active surveillance (wait and watch) if diagnosed with a lower Gleason score on biopsy, as opposed to seeking immediate treatment. Some researchers have recently identified imaging markers for low and high grade CaP on multi-parametric (MP) magnetic resonance (MR) imaging (such as T2 weighted MR imaging (T2w MRI) and MR spectroscopy (MRS)). In this paper, we present a novel computerized decision support system (DSS), called Semi Supervised Multi Kernel Graph Embedding (SeSMiK-GE), that quantitatively combines structural, and metabolic imaging data for distinguishing (a) benign versus cancerous, and (b) high- versus low-Gleason grade CaP regions from in vivo MP-MRI. A total of 29 1.5Tesla endorectal pre-operative in vivo MP MRI (T2w MRI, MRS) studies from patients undergoing radical prostatectomy were considered in this study. Ground truth for evaluation of the SeSMiK-GE classifier was obtained via annotation of disease extent on the pre-operative imaging by visually correlating the MRI to the ex vivo whole mount histologic specimens. The SeSMiK-GE framework comprises of three main modules: (1) multi-kernel learning, (2) semi-supervised learning, and (3) dimensionality reduction, which are leveraged for the construction of an integrated low dimensional representation of the different imaging and non-imaging MRI protocols. Hierarchical classifiers for diagnosis and Gleason grading of CaP are then constructed within this unified low dimensional representation. Step 1 of the hierarchical classifier employs a random forest classifier in conjunction with the SeSMiK-GE based data representation and a probabilistic pairwise Markov Random Field algorithm (which allows for imposition of local spatial constraints) to yield a voxel based classification of CaP presence. The CaP region of interest identified in Step 1 is then subsequently classified as either high or low Gleason grade CaP in Step 2. Comparing SeSMiK-GE with unimodal T2w MRI, MRS classifiers and a commonly used feature concatenation (COD) strategy, yielded areas (AUC) under the receiver operative curve (ROC) of (a) 0.89±0.09 (SeSMiK), 0.54±0.18 (T2w MRI), 0.61±0.20 (MRS), and 0.64±0.23 (COD) for distinguishing benign from CaP regions, and (b) 0.84±0.07 (SeSMiK),0.54±0.13 (MRI), 0.59±0.19 (MRS), and 0.62±0.18 (COD) for distinguishing high and low grade CaP using a leave one out cross-validation strategy, all evaluations being performed on a per voxel basis. Our results suggest that following further rigorous validation, SeSMiK-GE could be developed into a powerful diagnostic and prognostic tool for detection and grading of CaP in vivo and in helping to determine the appropriate treatment option. Identifying low grade disease in vivo might allow CaP patients to opt for active surveillance rather than immediately opt for aggressive therapy such as radical prostatectomy.

Class-specific weighting for Markov random field estimation: application to medical image segmentation

Many estimation tasks require Bayesian classifiers capable of adjusting their performance (e.g. sensitivity/specificity). In situations where the optimal classification decision can be identified by an exhaustive search over all possible classes, means for adjusting classifier performance, such as probability thresholding or weighting the a posteriori probabilities, are well established. Unfortunately, analogous methods compatible with Markov random fields (i.e. large collections of dependent random variables) are noticeably absent from the literature. Consequently, most Markov random field (MRF) based classification systems typically restrict their performance to a single, static operating point (i.e. a paired sensitivity/specificity). To address this deficiency, we previously introduced an extension of maximum posterior marginals (MPM) estimation that allows certain classes to be weighted more heavily than others, thus providing a means for varying classifier performance. However, this extension is not appropriate for the more popular maximum a posteriori (MAP) estimation. Thus, a strategy for varying the performance of MAP estimators is still needed. Such a strategy is essential for several reasons: (1) the MAP cost function may be more appropriate in certain classification tasks than the MPM cost function, (2) the literature provides a surfeit of MAP estimation implementations, several of which are considerably faster than the typical Markov Chain Monte Carlo methods used for MPM, and (3) MAP estimation is used far more often than MPM. Consequently, in this paper we introduce multiplicative weighted MAP (MWMAP) estimation-achieved via the incorporation of multiplicative weights into the MAP cost function-which allows certain classes to be preferred over others. This creates a natural bias for specific classes, and consequently a means for adjusting classifier performance. Similarly, we show how this multiplicative weighting strategy can be applied to the MPM cost function (in place of the strategy we presented previously), yielding multiplicative weighted MPM (MWMPM) estimation. Furthermore, we describe how MWMAP and MWMPM can be implemented using adaptations of current estimation strategies such as iterated conditional modes and MPM Monte Carlo. To illustrate these implementations, we first integrate them into two separate MRF-based classification systems for detecting carcinoma of the prostate (CaP) on (1) digitized histological sections from radical prostatectomies and (2) T2-weighted 4 Tesla ex vivo prostate MRI. To highlight the extensibility of MWMAP and MWMPM to estimation tasks involving more than two classes, we also incorporate these estimation criteria into a MRF-based classifier used to segment synthetic brain MR images. In the context of these tasks, we show how our novel estimation criteria can be used to arbitrarily adjust the sensitivities of these systems, yielding receiver operator characteristic curves (and surfaces).

A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images

Prostate segmentation is a challenging task, and the challenges significantly differ from one imaging modality to another. Low contrast, speckle, micro-calcifications and imaging artifacts like shadow poses serious challenges to accurate prostate segmentation in transrectal ultrasound (TRUS) images. However in magnetic resonance (MR) images, superior soft tissue contrast highlights large variability in shape, size and texture information inside the prostate. In contrast poor soft tissue contrast between prostate and surrounding tissues in computed tomography (CT) images pose a challenge in accurate prostate segmentation. This article reviews the methods developed for prostate gland segmentation TRUS, MR and CT images, the three primary imaging modalities that aids prostate cancer diagnosis and treatment. The objective of this work is to study the key similarities and differences among the different methods, highlighting their strengths and weaknesses in order to assist in the choice of an appropriate segmentation methodology. We define a new taxonomy for prostate segmentation strategies that allows first to group the algorithms and then to point out the main advantages and drawbacks of each strategy. We provide a comprehensive description of the existing methods in all TRUS, MR and CT modalities, highlighting their key-points and features. Finally, a discussion on choosing the most appropriate segmentation strategy for a given imaging modality is provided. A quantitative comparison of the results as reported in literature is also presented.

3D ultrasound image segmentation using wavelet support vector machines

PURPOSE

Transrectal ultrasound (TRUS) imaging is clinically used in prostate biopsy and therapy. Segmentation of the prostate on TRUS images has many applications. In this study, a three-dimensional (3D) segmentation method for TRUS images of the prostate is presented for 3D ultrasound-guided biopsy.

METHODS

This segmentation method utilizes a statistical shape, texture information, and intensity profiles. A set of wavelet support vector machines (W-SVMs) is applied to the images at various subregions of the prostate. The W-SVMs are trained to adaptively capture the features of the ultrasound images in order to differentiate the prostate and nonprostate tissue. This method consists of a set of wavelet transforms for extraction of prostate texture features and a kernel-based support vector machine to classify the textures. The voxels around the surface of the prostate are labeled in sagittal, coronal, and transverse planes. The weight functions are defined for each labeled voxel on each plane and on the model at each region. In the 3D segmentation procedure, the intensity profiles around the boundary between the tentatively labeled prostate and nonprostate tissue are compared to the prostate model. Consequently, the surfaces are modified based on the model intensity profiles. The segmented prostate is updated and compared to the shape model. These two steps are repeated until they converge. Manual segmentation of the prostate serves as the gold standard and a variety of methods are used to evaluate the performance of the segmentation method.

RESULTS

The results from 40 TRUS image volumes of 20 patients show that the Dice overlap ratio is 90.3% ± 2.3% and that the sensitivity is 87.7% ± 4.9%.

CONCLUSIONS

The proposed method provides a useful tool in our 3D ultrasound image-guided prostate biopsy and can also be applied to other applications in the prostate.

Prostate cancer localization using multiparametric MRI based on semi-supervised techniques with automated seed initialization

In this paper, we propose a novel and efficient semisupervised technique for automated prostate cancer localization using multiparametric magnetic resonance imaging (MRI). This method can be used in guiding biopsy, surgery, and therapy. We systematically present a new segmentation technique by developing a multiparametric graph based random walker (RW) algorithm with automated seed initialization to perform prostate cancer segmentation using multiparametric MRI. RW algorithm has proved to be accurate and fast in segmentation applications; however it requires a set of (user provided) seed points in order to perform segmentation. In this study, we first developed a novel RW method, which can be used with multiparametric MR images and then devised alternative methods that can determine seed points in an automated manner using discriminative classifiers such as support vector machines (SVM). Proposed RW method with automated seed initialization is able to produce improved segmentation results by assigning more weights to the images with more discriminative power.We applied the proposed method to a multiparametric dataset obtained from biopsy confirmed prostate cancer patients. Proposed method produces a sensitivity/ specificity rate of 0.76 and 0.86, respectively. Both visual, quantitative as well as statistical results are presented to show the significant performance improvements. Fisher sign test is used to demonstrate the statistical significance of our results by achieving p-values less than 0.05. This method outperforms available RW and SVM based methods by achieving a high specificity rate while not reducing sensitivity.

Multimodal wavelet embedding representation for data combination (MaWERiC): integrating magnetic resonance imaging and spectroscopy for prostate cancer detection

Recently, both Magnetic Resonance (MR) Imaging (MRI) and Spectroscopy (MRS) have emerged as promising tools for detection of prostate cancer (CaP). However, due to the inherent dimensionality differences in MR imaging and spectral information, quantitative integration of T(2) weighted MRI (T(2)w MRI) and MRS for improved CaP detection has been a major challenge. In this paper, we present a novel computerized decision support system called multimodal wavelet embedding representation for data combination (MaWERiC) that employs, (i) wavelet theory to extract 171 Haar wavelet features from MRS and 54 Gabor features from T(2)w MRI, (ii) dimensionality reduction to individually project wavelet features from MRS and T(2)w MRI into a common reduced Eigen vector space, and (iii), a random forest classifier for automated prostate cancer detection on a per voxel basis from combined 1.5 T in vivo MRI and MRS. A total of 36 1.5 T endorectal in vivo T(2)w MRI and MRS patient studies were evaluated per voxel by MaWERiC using a three-fold cross validation approach over 25 iterations. Ground truth for evaluation of results was obtained by an expert radiologist annotations of prostate cancer on a per voxel basis who compared each MRI section with corresponding ex vivo wholemount histology sections with the disease extent mapped out on histology. Results suggest that MaWERiC based MRS T(2)w meta-classifier (mean AUC, μ = 0.89 ± 0.02) significantly outperformed (i) a T(2)w MRI (using wavelet texture features) classifier (μ = 0.55 ± 0.02), (ii) a MRS (using metabolite ratios) classifier (μ = 0.77 ± 0.03), (iii) a decision fusion classifier obtained by combining individual T(2)w MRI and MRS classifier outputs (μ = 0.85 ± 0.03), and (iv) a data combination method involving a combination of metabolic MRS and MR signal intensity features (μ = 0.66 ± 0.02).

Automatic computer-aided detection of prostate cancer based on multiparametric magnetic resonance image analysis

In this paper, a fully automatic computer-aided detection (CAD) method is proposed for the detection of prostate cancer. The CAD method consists of multiple sequential steps in order to detect locations that are suspicious for prostate cancer. In the initial stage, a voxel classification is performed using a Hessian-based blob detection algorithm at multiple scales on an apparent diffusion coefficient map. Next, a parametric multi-object segmentation method is applied and the resulting segmentation is used as a mask to restrict the candidate detection to the prostate. The remaining candidates are characterized by performing histogram analysis on multiparametric MR images. The resulting feature set is summarized into a malignancy likelihood by a supervised classifier in a two-stage classification approach. The detection performance for prostate cancer was tested on a screening population of 200 consecutive patients and evaluated using the free response operating characteristic methodology. The results show that the CAD method obtained sensitivities of 0.41, 0.65 and 0.74 at false positive (FP) levels of 1, 3 and 5 per patient, respectively. In conclusion, this study showed that it is feasible to automatically detect prostate cancer at a FP rate lower than systematic biopsy. The CAD method may assist the radiologist to detect prostate cancer locations and could potentially guide biopsy towards the most aggressive part of the tumour.

3D Prostate Segmentation of Ultrasound Images Combining Longitudinal Image Registration and Machine Learning

We developed a three-dimensional (3D) segmentation method for transrectal ultrasound (TRUS) images, which is based on longitudinal image registration and machine learning. Using longitudinal images of each individual patient, we register previously acquired images to the new images of the same subject. Three orthogonal Gabor filter banks were used to extract texture features from each registered image. Patient-specific Gabor features from the registered images are used to train kernel support vector machines (KSVMs) and then to segment the newly acquired prostate image. The segmentation method was tested in TRUS data from five patients. The average surface distance between our and manual segmentation is 1.18 ± 0.31 mm, indicating that our automatic segmentation method based on longitudinal image registration is feasible for segmenting the prostate in TRUS images.

A Molecular Image-directed, 3D Ultrasound-guided Biopsy System for the Prostate

Systematic transrectal ultrasound (TRUS)-guided biopsy is the standard method for a definitive diagnosis of prostate cancer. However, this biopsy approach uses two-dimensional (2D) ultrasound images to guide biopsy and can miss up to 30% of prostate cancers. We are developing a molecular image-directed, three-dimensional (3D) ultrasound image-guided biopsy system for improved detection of prostate cancer. The system consists of a 3D mechanical localization system and software workstation for image segmentation, registration, and biopsy planning. In order to plan biopsy in a 3D prostate, we developed an automatic segmentation method based wavelet transform. In order to incorporate PET/CT images into ultrasound-guided biopsy, we developed image registration methods to fuse TRUS and PET/CT images. The segmentation method was tested in ten patients with a DICE overlap ratio of 92.4% ± 1.1 %. The registration method has been tested in phantoms. The biopsy system was tested in prostate phantoms and 3D ultrasound images were acquired from two human patients. We are integrating the system for PET/CT directed, 3D ultrasound-guided, targeted biopsy in human patients.

Pathologic validation of a model based on diffusion-weighted imaging and dynamic contrast-enhanced magnetic resonance imaging for tumor delineation in the prostate peripheral zone

PURPOSE

For focal boost strategies in the prostate, the robustness of magnetic resonance imaging-based tumor delineations needs to be improved. To this end we developed a statistical model that predicts tumor presence on a voxel level (2.5×2.5×2.5 mm3) inside the peripheral zone. Furthermore, we show how this model can be used to derive a valuable input for radiotherapy treatment planning.

METHODS AND MATERIALS

The model was created on 87 radiotherapy patients. For the validation of the voxelwise performance of the model, an independent group of 12 prostatectomy patients was used. After model validation, the model was stratified to create three different risk levels for tumor presence: gross tumor volume (GTV), high-risk clinical target volume (CTV), and low-risk CTV.

RESULTS

The model gave an area under the receiver operating characteristic curve of 0.70 for the prediction of tumor presence in the prostatectomy group. When the registration error between magnetic resonance images and pathologic delineation was taken into account, the area under the curve further improved to 0.89. We propose that model outcome values with a high positive predictive value can be used to define the GTV. Model outcome values with a high negative predictive value can be used to define low-risk CTV regions. The intermediate outcome values can be used to define a high-risk CTV.

CONCLUSIONS

We developed a logistic regression with a high diagnostic performance for voxelwise prediction of tumor presence. The model output can be used to define different risk levels for tumor presence, which in turn could serve as an input for dose planning. In this way the robustness of tumor delineations for focal boost therapy can be greatly improved.