Automated Prostate Gland Segmentation Based on an Unsupervised Fuzzy C-Means Clustering Technique Using Multispectral T1w and T2w MR Imaging

Leonardo Rundo,Carmelo Militello,Salvatore Vitabile,Giancarlo Mauri,Maria Gilardi,Antonio Garufi,Giorgio Russo

doi:10.3390/info8020049

Abstract

Prostate imaging analysis is difficult in diagnosis, therapy, and staging of prostate cancer. In clinical practice, Magnetic Resonance Imaging (MRI) is increasingly used thanks to its morphologic and functional capabilities. However, manual detection and delineation of prostate gland on multispectral MRI data is currently a time-expensive and operator-dependent procedure. Efficient computer-assisted segmentation approaches are not yet able to address these issues, but rather have the potential to do so. In this paper, a novel automatic prostate MR image segmentation method based on the Fuzzy C-Means (FCM) clustering algorithm, which enables multispectral T1-weighted (T1w) and T2-weighted (T2w) MRI anatomical data processing, is proposed. This approach, using an unsupervised Machine Learning technique, helps to segment the prostate gland effectively. A total of 21 patients with suspicion of prostate cancer were enrolled in this study. Volume-based metrics, spatial overlap-based metrics and spatial distance-based metrics were used to quantitatively evaluate the accuracy of the obtained segmentation results with respect to the gold-standard boundaries delineated manually by an expert radiologist. The proposed multispectral segmentation method was compared with the same processing pipeline applied on either T2w or T1w MR images alone. The multispectral approach considerably outperforms the monoparametric ones, achieving an average Dice Similarity Coefficient 90.77 ± 1.75, with respect to 81.90 ± 6.49 and 82.55 ± 4.93 by processing T2w and T1w imaging alone, respectively. Combining T2w and T1w MR image structural information significantly enhances prostate gland segmentation by exploiting the uniform gray appearance of the prostate on T1w MRI.

Highlights

Prostate cancer is the most frequently diagnosed cancer in men aside from skin cancer, and 180,890 new cases of prostate cancer have been expected in the US during 2016 [1,2]
To evaluate the accuracy of the proposed segmentation method, several metrics were calculated by comparing the automatically segmented prostate gland Region of Interest (ROI) against the manually contoured ones by anby experienced radiologist
The results achieved by the proposed proposed segmentation segmentation approach on multispectral T1w and T2w co-registered MR images were compared by applying the same processing pipeline on the corresponding corresponding monoparametric monoparametric T2w

Summary

Introduction

Prostate cancer is the most frequently diagnosed cancer in men aside from skin cancer, and 180,890 new cases of prostate cancer have been expected in the US during 2016 [1,2]. Prostate imaging is still a critical and challenging issue in diagnosis, therapy, and staging of prostate cancer (PCa). In [4], MRI-guided biopsy showed a high detection rate of clinically significant PCa in patients with persisting cancer suspicion, after a previous negative systematic TRUS-guided biopsy, which represents the gold-standard for diagnosis of prostate cancer [5]. MRI scanning before a biopsy can serve as a triage test in men with raised serum Prostate-Specific Antigen (PSA) levels, in order to select those for biopsy with significant cancer that requires treatment [6]. Klein et al [7] presented an automatic method, based on non-rigid registration of a set of pre-labeled atlas images, for delineating the prostate in 3D MR scans. The Dice Similarity Coefficient (DSC), to quantify the overlap between the automatic and manual segmentations, and the shortest

Objectives

Methods

Results

Discussion

Conclusion