Hierarchical Clustering-based Segmentation (HCS) Aided Interpretation of Multi-parametric MR Images of the Prostate

SELVAN, Arul (2017). Hierarchical Clustering-based Segmentation (HCS) Aided Interpretation of Multi-parametric MR Images of the Prostate. In: Image-Guided Therapies Network+ Meeting, Town Hall, Sheffield, 10 March 2017. (Unpublished)

PDF (Poster)
Image_Guided_Therapies_Poster.pdf - Accepted Version
Creative Commons Attribution No Derivatives.

Download (1MB) | Preview
Official URL: http://www.image-guided-therapies.ac.uk/event/epsr...
Related URLs:


BACKGROUND: Tissue abnormality is usually related to a dissimilar part of an otherwise homogeneous image. Choosing the optimal post processing threshold value can be difficult because the image composition may vary depending on the acquisition parameters and the type of tissue. Hierarchical Clustering-based Segmentation (HCS) is an approach to Computer Aided Monitoring (CAM) that enables a user to define a region of interest and the process generates a hierarchy of segmentation results to highlight the varied dissimilarities that might be present. HCS allows the user to derive the maximum benefit from the computational capability (perception) of the machine while at the same time, enabling them to incorporate their own interpretation in the appropriate place. This achieves a complementary synthesis of both computer and human strengths [1]. Aim of the Study: HCS PROCESS AS AN AID TO DIAGNOSIS IN mpMRI OF PROSTATE To evaluate HCS process as semi-quantitative analytical tool, to complement radiologist's interpretation of mpMR images of prostate METHOD: In prostate cancer, the leaky characteristics of the tumour angiogenesis, is demonstrated in DCE-MRI by the early rapid high enhancement just after the administration of contrast medium followed immediately by a relatively rapid decline. In comparison there will be a lower and continuously increasing enhancement for normal tissues. The above characteristics can be demonstrated by the quantitative measurement of signal enhancement in DCE-MRI with time i.e. Time Intensity Curve (TIC). The characteristic shape of the TIC (Figure 2) may be used for supporting diagnosis. Within the user defined ROI, the HCS process is applied to the DCE-MRI temporal frame of a slice of interest identified by the user. For qualitative analysis, for dissimilar regions, HCS process provides following (Fig. 3A, B) heat map, regions coloured as per their TIC types and correlation with T2 regions. For quantitative analysis, parametric image of the time intensity curves of the contrast wash-in, wash-out process are plotted for suspicious regions confirmed by user (Fig. 3C).

Item Type: Conference or Workshop Item (Poster)
Uncontrolled Keywords: mpMRI, Multi parametric Magnetic Resonance Imaging, Prostate, T1 Weighted, T2 Weighted, Dynamic Contrast Enhanced, DCE-MRI
Research Institute, Centre or Group - Does NOT include content added after October 2018: Materials and Engineering Research Institute > Modelling Research Centre > Microsystems and Machine Vision Laboratory
Departments - Does NOT include content added after October 2018: Faculty of Science, Technology and Arts > Department of Engineering and Mathematics
Depositing User: Arul Selvan
Date Deposited: 20 Apr 2017 11:20
Last Modified: 18 Mar 2021 16:05
URI: https://shura.shu.ac.uk/id/eprint/15392

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics