Return to search

Development of computer-based algorithms for unsupervised assessment of radiotherapy contouring

INTRODUCTION: Despite the advances in radiotherapy treatment delivery, target volume delineation remains one of the greatest sources of error in the radiotherapy delivery process, which can lead to poor tumour control probability and impact clinical outcome. Contouring assessments are performed to ensure high quality of target volume definition in clinical trials but this can be subjective and labour-intensive. This project addresses the hypothesis that computational segmentation techniques, with a given prior, can be used to develop an image-based tumour delineation process for contour assessments. This thesis focuses on the exploration of the segmentation techniques to develop an automated method for generating reference delineations in the setting of advanced lung cancer. The novelty of this project is in the use of the initial clinician outline as a prior for image segmentation. METHODS: Automated segmentation processes were developed for stage II and III non-small cell lung cancer using the IDEAL-CRT clinical trial dataset. Marker-controlled watershed segmentation, two active contour approaches (edge- and region-based) and graph-cut applied on superpixels were explored. k-nearest neighbour (k-NN) classification of tumour from normal tissues based on texture features was also investigated. RESULTS: 63 cases were used for development and training. Segmentation and classification performance were evaluated on an independent test set of 16 cases. Edge-based active contour segmentation achieved highest Dice similarity coefficient of 0.80 ± 0.06, followed by graphcut at 0.76 ± 0.06, watershed at 0.72 ± 0.08 and region-based active contour at 0.71 ± 0.07, with mean computational times of 192 ± 102 sec, 834 ± 438 sec, 21 ± 5 sec and 45 ± 18 sec per case respectively. Errors in accuracy of irregularly shaped lesions and segmentation leakages at the mediastinum were observed. In the distinction of tumour and non-tumour regions, misclassification errors of 14.5% and 15.5% were achieved using 16- and 8-pixel regions of interest (ROIs) respectively. Higher misclassification errors of 24.7% and 26.9% for 16- and 8-pixel ROIs were obtained in the analysis of the tumour boundary. CONCLUSIONS: Conventional image-based segmentation techniques with the application of priors are useful in automatic segmentation of tumours, although further developments are required to improve their performance. Texture classification can be useful in distinguishing tumour from non-tumour tissue, but the segmentation task at the tumour boundary is more difficult. Future work with deep-learning segmentation approaches need to be explored.

Identiferoai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:763765
Date January 2019
CreatorsYang, Huiqi
ContributorsJena, Raj ; Hoskin, Peter
PublisherUniversity of Cambridge
Source SetsEthos UK
Detected LanguageEnglish
TypeElectronic Thesis or Dissertation
Sourcehttps://www.repository.cam.ac.uk/handle/1810/284463

Page generated in 0.0015 seconds