Tissue-specific and Interpretable Sub-segmentation of Whole Tumour Burden on CT Images by Unsupervised Fuzzy Clustering

May 1, 2020

This is the first method for Computed Tomography tissue-specific image segmentation of whole tumours. In particular, our computational framework based on unsupervised fuzzy clustering techniques sub-segments tumour lesions into hypo-dense (cystic/necrotic), hyper-dense (calcified), and intermediately dense (soft tissue) tumour components. The results obtained on ovarian and renal cancer are accurate and reliable.

Tissue-specific and Interpretable Sub-segmentation of Whole Tumour Burden on CT Images by Unsupervised Fuzzy Clustering
Connect

Connect with us

The Mark Foundation Institute for Integrated Cancer Medicine (MFICM) at the University of Cambridge aims to revolutionise cancer care by affecting patients along their treatment pathway.

Find out more

Connect