Quantification of uptake in pelvis F‐18 FLT PET‐CT images using a 3D localization and segmentation CNN
- 19 January 2022
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 49 (3) , 1585-1598
Abstract
Purpose: The purpose of this work was to develop and validate a deep convolutional neural network (CNN) approach for the automated pelvis segmentation in computed tomography (CT) scans to enable the quantification of active pelvic bone marrow by means of Fluorothymidine F‐18 (FLT) tracer uptake measurement in positron emission tomography (PET) scans. This quantification is a critical step in calculating bone marrow dose for radiopharmaceutical therapy clinical applications as well as external beam radiation doses.Methods: An approach for the combined localization and segmentation of the pelvis in CT volumes of varying sizes, ranging from full‐body to pelvis CT scans, was developed that utilizes a novel CNN architecture in combination with a random sampling strategy. The method was validated on 34 planning CT scans and 106 full‐body FLT PET‐CT scans using a cross‐validation strategy. Specifically, two different training and CNN application options were studied, quantitatively assessed, and statistically compared.Results: The proposed method was able to successfully locate and segment the pelvis in all test cases. On all data sets, an average Dice coefficient of 0.9396 0.0182 or better was achieved. The relative tracer uptake measurement error ranged between 0.065% and 0.204%. The proposed approach is time‐efficient and shows a reduction in runtime of up to 95% compared to a standard U‐Net‐based approach without a localization component.Conclusions: The proposed method enables the efficient calculation of FLT uptake in the pelvis. Thus, it represents a valuable tool to facilitate bone marrow preserving adaptive radiation therapy and radiopharmaceutical dose calculation. Furthermore, the method can be adapted to process other bone structures as well as organs.Keywords
Funding Information
- National Cancer Institute (U01CA140206)
This publication has 20 references indexed in Scilit:
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- Using [18F]Fluorothymidine Imaged With Positron Emission Tomography to Quantify and Reduce Hematologic Toxicity Due to Chemoradiation Therapy for Pelvic Cancer PatientsInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Marginal Space Deep Learning: Efficient Architecture for Volumetric Image ParsingIEEE Transactions on Medical Imaging, 2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- FACTS: Fully Automatic CT Segmentation of a Hip JointAnnals of Biomedical Engineering, 2014
- A methodology for incorporating functional bone marrow sparing in IMRT planning for pelvic radiation therapyRadiotherapy and Oncology, 2011
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006