Diffusion-weighted magnetic resonance imaging during radiotherapy of locally advanced cervical cancer – treatment response assessment using different segmentation methods

Abstract

(2015) Diffusion-weighted magnetic resonance imaging during radiotherapy of locally advanced cervical cancer -treatment response assessment using different segmentation methods, Acta Oncologica, 54:9, 1535Oncologica, 54:9, -1542 AbstrAct background. Diffusion-weighted magnetic resonance imaging (DW-MRI) and the derived apparent diffusion coefficient (ADC) value has potential for monitoring tumor response to radiotherapy (RT). Method used for segmentation of volumes with reduced diffusion will influence both volume size and observed distribution of ADC values. This study evaluates: 1) different segmentation methods; and 2) how they affect assessment of tumor ADC value during RT. Material and methods. Eleven patients with locally advanced cervical cancer underwent MRI three times during their RT: prior to start of RT (PRERT), two weeks into external beam RT (WK2RT) and one week prior to brachytherapy (PREBT). Volumes on DW-MRI were segmented using three semi-automatic segmentation methods: "cluster analysis", "relative signal intensity (SD4)" and "region growing". Segmented volumes were compared to the gross tumor volume (GTV) identified on T2-weighted MR images using the Jaccard similarity index (JSI). ADC values from segmented volumes were compared and changes of ADC values during therapy were evaluated. results. Significant difference between the four volumes (GTV, DWI cluster , DWI SD4 and DWI region ) was found (p  0.01), and the volumes changed significantly during treatment (p  0.01). There was a significant difference in JSI among segmentation methods at time of PRERT (p  0.016) with region growing having the lowest JSI GTV (mean sd: 0.35  0.1), followed by the SD4 method (mean sd: 0.50  0.1) and clustering (mean sd: 0.52  0.3). There was no significant difference in mean ADC value compared at same treatment time. Mean tumor ADC value increased significantly (p  0.01) for all methods across treatment time. conclusion. Among the three semi-automatic segmentations of hyper-intense intensities on DW-MR images implemented, cluster analysis and relative signal thresholding had the greatest similarity to the clinical tumor volume. Evaluation of mean ADC value did not depend on segmentation method.

Concordance of FDG PET/CT metabolic tumour volume versus DW-MRI functional tumour volume with T2-weighted anatomical tumour volume in cervical cancer

“…The choice of imaging modality used in tumour contouring or segmentation technique can result in varying derived tumour volume [ 16 , 28 , 29 ]. There is no consensus of the methodology of tumour segmentation using DW-MRI or ADC values.…”

“…A recent study has shown that K-means clustering using both S 0 and ADC is a promising method for reliable delineation of heterogeneous tumours in patients with metastatic gastrointestinal stromal tumours [ 25 ]. The relative signal intensity [ 31 ] and region growing [ 32 ] methods are alternative segmentation techniques which were described to have limitations related to their dependence on b -value and acquisition method for DW-MRI images, and sensitivity to signal-to-noise ratio [ 16 ].…”

“…Additional DW-MRI has been demonstrated in the literature to outperform T2W imaging alone in depicting local recurrence and differentiating it from post-treatment changes such as fibrosis [ 12 – 14 ]. The use of ADC for measuring target volumes with different tissue characteristics for dose prescription in image-guided adaptive brachytherapy [ 15 ] and various segmentation methods with DW-MRI [ 16 ] have also been studied. However, further investigation in its clinical application to radiotherapy treatment planning is warranted.…”

Autodelineation of cervical cancers using multiparametric magnetic resonance imaging and machine learning

“…Most studies, as recently reviewed by Ghose et al [11], focus on delineating organs at risk, or use the manual delineation from treatment planning to autodelineate tumours in images acquired during treatment using registration algorithms [12]. Methods proposed for identifying tumours in the cervix tend to have a high degree of manual interaction [11,13].…”

Cluster analysis of dynamic contrast enhanced MRI reveals tumor subregions related to locoregional relapse for cervical cancer patients

“…The K-means algorithm is fast and robust, and is appropriate for large data sets, consisting of thousands to millions of voxels [8]. K-means clustering and similar methods may be used in segmenting MR images of the brain [9], but have also been utilized for segmentation of cervical cancers [10]. In a previous study, we used K-means analysis of Tofts parameter maps to identify a voxel cluster associated with treatment outcome [11].…”