A New Framework for Precise Identification of Prostatic Adenocarcinoma

Abstract

Prostate cancer, which is also known as prostatic adenocarcinoma, is an unconstrained growth of epithelial cells in the prostate and has become one of the leading causes of cancer-related death worldwide. The survival of patients with prostate cancer relies on detection at an early, treatable stage. In this paper, we introduce a new comprehensive framework to precisely differentiate between malignant and benign prostate cancer. This framework proposes a noninvasive computer-aided diagnosis system that integrates two imaging modalities of MR (diffusion-weighted (DW) and T2-weighted (T2W)). For the first time, it utilizes the combination of functional features represented by apparent diffusion coefficient (ADC) maps estimated from DW-MRI for the whole prostate in combination with texture features with its first- and second-order representations, extracted from T2W-MRIs of the whole prostate, and shape features represented by spherical harmonics constructed for the lesion inside the prostate and integrated with PSA screening results. The dataset presented in the paper includes 80 biopsy confirmed patients, with a mean age of 65.7 years (43 benign prostatic hyperplasia, 37 prostatic carcinomas). Experiments were conducted using different well-known machine learning approaches including support vector machines (SVM), random forests (RF), decision trees (DT), and linear discriminant analysis (LDA) classification models to study the impact of different feature sets that lead to better identification of prostatic adenocarcinoma. Using a leave-one-out cross-validation approach, the diagnostic results obtained using the SVM classification model along with the combined feature set after applying feature selection (88.75% accuracy, 81.08% sensitivity, 95.35% specificity, and 0.8821 AUC) indicated that the system's performance, after integrating and reducing different types of feature sets, obtained an enhanced diagnostic performance compared with each individual feature set and other machine learning classifiers. In addition, the developed diagnostic system provided consistent diagnostic performance using 10-fold and 5-fold cross-validation approaches, which confirms the reliability, generalization ability, and robustness of the developed system.

Keywords: MRI; PSA; computer-aided diagnosis; functional features; prostate cancer; shape features; texture analysis.

Figure 1

The proposed framework for early detection of prostatic adenocarcinoma.

Figure 2

Calculations of voxel-wise apparent diffusion coefficients (ADC) for PCa and the cumulative distribution functions (CDFs) at different b-values from b100 to b1400.

Figure 3

CDFs of ADC values for a benign case (solid) vs. a malignant case (dotted) for ADC maps obtained using different b-values from b100 to b1400. Note that region index indicates the different regions where the ADC values within the same range falls into.

Figure 4

Illustrative examples of prostatic texture differences showing high gray level heterogeneity in four different malignant cases (first row) and low gray level heterogeneity in four different benign cases (second row).

Figure 5

First-order textural features extraction.

Figure 6

Second-order GLCM textural features extraction, where the central voxel of interest is shown in blue and the 26-neighbors are shown in red. The spatial relationship in the neighborhood block is obtained at different angles of zero, $\frac{\mathsf{\pi }}{2}$, $\frac{\mathsf{\pi }}{4}$, and $\frac{3\mathsf{\pi }}{4}$.

Figure 7

Second-order GLRLM textural features extraction, where the central voxel of interest is shown in blue and the 26-neighbors are shown in red. The spatial relationship is investigated to detect groups of sequential horizontal or vertical voxels with the same gray level.

Figure 8

Visualization 3D shape differences between four malignant cases in the first row, and four benign cases in the second row.

Figure 9

Reconstruction errors differences at different spherical harmonics (SH 01, 10, 50, 70, 85) between a malignant case and a benign case.

Figure 10

Performance metrics for evaluation of the proposed framework.

Figure 11

ROC curves of (a) SVM comparing various feature sets using leave-one-out cross validation, (b) different classifiers comparison using FS7 along with leave-one-out cross validation, (c) different classifiers comparison using FS7 along with 5-fold cross validation, and (d) comparison of classifiers using FS7 along with 10-fold cross validation.