Sarah Lindgren Belal1, May Sadik2, Reza Kaboteh2, Olof Enqvist3, Johannes Ulén4, Mads H Poulsen5, Jane Simonsen6, Poul F Høilund-Carlsen6, Lars Edenbrandt2, Elin Trägårdh7. 1. Department of Translational Medicine, Lund University, Malmö, Sweden. Electronic address: sarah.lindgren_belal@med.lu.se. 2. Department of Clinical Physiology, Sahlgrenska University Hospital, Göteorg, Sweden. 3. Department of Signals and Systems, Chalmers University of Technology, Göteborg, Sweden. 4. Eigenvision AB, Malmö, Sweden. 5. Department of Urology, Odense University Hospital, Odense, Denmark. 6. Department of Nuclear Medicine, Odense University Hospital, Odense, Denmark. 7. Department of Translational Medicine, Lund University, Malmö, Sweden; Wallenberg Center for Molecular Medicine, Lund University, Malmö, Sweden.
Abstract
PURPOSE: The aim of this study was to develop a deep learning-based method for segmentation of bones in CT scans and test its accuracy compared to manual delineation, as a first step in the creation of an automated PET/CT-based method for quantifying skeletal tumour burden. METHODS: Convolutional neural networks (CNNs) were trained to segment 49 bones using manual segmentations from 100 CT scans. After training, the CNN-based segmentation method was tested on 46 patients with prostate cancer, who had undergone 18F-choline-PET/CT and 18F-NaF PET/CT less than three weeks apart. Bone volumes were calculated from the segmentations. The network's performance was compared with manual segmentations of five bones made by an experienced physician. Accuracy of the spatial overlap between automated CNN-based and manual segmentations of these five bones was assessed using the Sørensen-Dice index (SDI). Reproducibility was evaluated applying the Bland-Altman method. RESULTS: The median (SD) volumes of the five selected bones were by CNN and manual segmentation: Th7 41 (3.8) and 36 (5.1), L3 76 (13) and 75 (9.2), sacrum 284 (40) and 283 (26), 7th rib 33 (3.9) and 31 (4.8), sternum 80 (11) and 72 (9.2), respectively. Median SDIs were 0.86 (Th7), 0.85 (L3), 0.88 (sacrum), 0.84 (7th rib) and 0.83 (sternum). The intraobserver volume difference was less with CNN-based than manual approach: Th7 2% and 14%, L3 7% and 8%, sacrum 1% and 3%, 7th rib 1% and 6%, sternum 3% and 5%, respectively. The average volume difference measured as ratio volume difference/mean volume between the two CNN-based segmentations was 5-6% for the vertebral column and ribs and ≤3% for other bones. CONCLUSION: The new deep learning-based method for automated segmentation of bones in CT scans provided highly accurate bone volumes in a fast and automated way and, thus, appears to be a valuable first step in the development of a clinical useful processing procedure providing reliable skeletal segmentation as a key part of quantification of skeletal metastases.
PURPOSE: The aim of this study was to develop a deep learning-based method for segmentation of bones in CT scans and test its accuracy compared to manual delineation, as a first step in the creation of an automated PET/CT-based method for quantifying skeletal tumour burden. METHODS: Convolutional neural networks (CNNs) were trained to segment 49 bones using manual segmentations from 100 CT scans. After training, the CNN-based segmentation method was tested on 46 patients with prostate cancer, who had undergone 18F-choline-PET/CT and 18F-NaF PET/CT less than three weeks apart. Bone volumes were calculated from the segmentations. The network's performance was compared with manual segmentations of five bones made by an experienced physician. Accuracy of the spatial overlap between automated CNN-based and manual segmentations of these five bones was assessed using the Sørensen-Dice index (SDI). Reproducibility was evaluated applying the Bland-Altman method. RESULTS: The median (SD) volumes of the five selected bones were by CNN and manual segmentation: Th7 41 (3.8) and 36 (5.1), L3 76 (13) and 75 (9.2), sacrum 284 (40) and 283 (26), 7th rib 33 (3.9) and 31 (4.8), sternum 80 (11) and 72 (9.2), respectively. Median SDIs were 0.86 (Th7), 0.85 (L3), 0.88 (sacrum), 0.84 (7th rib) and 0.83 (sternum). The intraobserver volume difference was less with CNN-based than manual approach: Th7 2% and 14%, L3 7% and 8%, sacrum 1% and 3%, 7th rib 1% and 6%, sternum 3% and 5%, respectively. The average volume difference measured as ratio volume difference/mean volume between the two CNN-based segmentations was 5-6% for the vertebral column and ribs and ≤3% for other bones. CONCLUSION: The new deep learning-based method for automated segmentation of bones in CT scans provided highly accurate bone volumes in a fast and automated way and, thus, appears to be a valuable first step in the development of a clinical useful processing procedure providing reliable skeletal segmentation as a key part of quantification of skeletal metastases.
Authors: Xiaofan Xiong; Brian J Smith; Stephen A Graves; John J Sunderland; Michael M Graham; Brandie A Gross; John M Buatti; Reinhard R Beichel Journal: Med Phys Date: 2022-01-19 Impact factor: 4.506
Authors: Hanna Sartor; David Minarik; Olof Enqvist; Johannes Ulén; Anders Wittrup; Maria Bjurberg; Elin Trägårdh Journal: Clin Transl Radiat Oncol Date: 2020-09-14
Authors: Maria E S Takahashi; Camila Mosci; Edna M Souza; Sérgio Q Brunetto; Cármino de Souza; Fernando V Pericole; Irene Lorand-Metze; Celso D Ramos Journal: Nucl Med Commun Date: 2020-04 Impact factor: 1.698