Abstract
Tumor segmentation is a crucial but difficult task in treatment planning and follow-up of cancerous patients. The challenge of automating the tumor segmentation has recently received a lot of attention, but the potential of utilizing hybrid positron emission tomography (PET)/magnetic resonance imaging (MRI), a novel and promising imaging modality in oncology, is still under-explored. Recent approaches have either relied on manual user input and/or performed the segmentation patient-by-patient, whereas a fully unsupervised segmentation framework that exploits the available information from all patients is still lacking.We present an unsupervised across-patients supervoxel-based clustering framework for lung tumor segmentation in hybrid PET/MRI. The method consists of two steps: First, each patient is represented by a set of PET/MRI supervoxel-features. Then the data points from all patients are transformed and clustered on a population level into tumor and non-tumor supervoxels. The proposed framework is tested on the scans of 18 non-small cell lung cancer patients with a total of 19 tumors and evaluated with respect to manual delineations provided by clinicians. Experiments study the performance of several commonly used clustering algorithms within the framework and provide analysis of (i) the effect of tumor size, (ii) the segmentation errors, (iii) the benefit of across-patient clustering, and (iv) the noise robustness.The proposed framework detected 15 out of 19 tumors in an unsupervised manner. Moreover, performance increased considerably by segmenting across patients, with the mean dice score increasing from 0.169±0.295 (patient-by-patient) to 0.470±0.308 (across-patients). Results demonstrate that both spectral clustering and Manhattan hierarchical clustering have the potential to segment tumors in PET/MRI with a low number of missed tumors and a low number of false-positives, but that spectral clustering seems to be more robust to noise.
Highlights
Medical imaging is today an integrated part of diagnostics and treatment planning of cancer patients
A more recent advancement in hybrid radiologic imaging is the positron emission tomography (PET)/magnetic resonance imaging (MRI) scanner, in which the anatomical information is obtained from MRI instead of computed tomography (CT)
Today there exists a large range of methods for tumor segmentation in established modalities such as PET, CT, MRI and hybrid PET/CT (Foster et al, 2014; Moghbel, Mashohor, Mahmud, & Saripan, 2018; Wadhwa, Bhardwaj, & Verma, 2019; Ju et al, 2015), while the use of hybrid PET/MRI is less explored
Summary
Medical imaging is today an integrated part of diagnostics and treatment planning of cancer patients. The potential of hybrid PET/MRI is still being investigated and remains an open question (Ehman et al, 2017) This includes its potential in the important task of lung tumor segmentation,. But inherently difficult, part of the treatment planning and follow-up of these cancerous patients is the process of isolating the tumor volume in medical images (Sauwen et al, 2016) Today, this tumor segmentation is commonly performed manu ally in a slice-by-slice manner. We aim to contribute to the recent line of work in order to further investigate the potential of PET/MRI for unsupervised lung tumor segmentation. A novel unsupervised lung tumor segmentation framework that can utilize information across patients in PET/MRI images.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
