Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing
Abstract High-resolution peripheral quantitative computed tomography (HR-pQCT) is an emerging in vivo imaging modality for quantification of bone microarchitecture. However, extraction of quantitative microarchitectural parameters from HR-pQCT images requires an accurate segmentation of the image. T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-27350-0 |
| _version_ | 1797958658091384832 |
|---|---|
| author | Nathan J. Neeteson Bryce A. Besler Danielle E. Whittier Steven K. Boyd |
| author_facet | Nathan J. Neeteson Bryce A. Besler Danielle E. Whittier Steven K. Boyd |
| author_sort | Nathan J. Neeteson |
| collection | DOAJ |
| description | Abstract High-resolution peripheral quantitative computed tomography (HR-pQCT) is an emerging in vivo imaging modality for quantification of bone microarchitecture. However, extraction of quantitative microarchitectural parameters from HR-pQCT images requires an accurate segmentation of the image. The current standard protocol using semi-automated contouring for HR-pQCT image segmentation is laborious, introduces inter-operator biases into research data, and poses a barrier to streamlined clinical implementation. In this work, we propose and validate a fully automated algorithm for segmentation of HR-pQCT radius and tibia images. A multi-slice 2D U-Net produces initial segmentation predictions, which are post-processed via a sequence of traditional morphological image filters. The U-Net was trained on a large dataset containing 1822 images from 896 unique participants. Predicted segmentations were compared to reference segmentations on a disjoint dataset containing 386 images from 190 unique participants, and 156 pairs of repeated images were used to compare the precision of the novel and current protocols. The agreement of morphological parameters obtained using the predicted segmentation relative to the reference standard was excellent (R2 between 0.938 and > 0.999). Precision was significantly improved for several outputs, most notably cortical porosity. This novel and robust algorithm for automated segmentation will increase the feasibility of using HR-pQCT in research and clinical settings. |
| first_indexed | 2024-04-11T00:23:05Z |
| format | Article |
| id | doaj.art-932dd58ca8dd4c638fb0eca91b72fe02 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T00:23:05Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-932dd58ca8dd4c638fb0eca91b72fe022023-01-08T12:12:23ZengNature PortfolioScientific Reports2045-23222023-01-0113111610.1038/s41598-022-27350-0Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processingNathan J. Neeteson0Bryce A. Besler1Danielle E. Whittier2Steven K. Boyd3McCaig Institute for Bone and Joint Health and Department of Radiology, University of CalgaryMcCaig Institute for Bone and Joint Health and Department of Radiology, University of CalgaryMcCaig Institute for Bone and Joint Health and Department of Radiology, University of CalgaryMcCaig Institute for Bone and Joint Health and Department of Radiology, University of CalgaryAbstract High-resolution peripheral quantitative computed tomography (HR-pQCT) is an emerging in vivo imaging modality for quantification of bone microarchitecture. However, extraction of quantitative microarchitectural parameters from HR-pQCT images requires an accurate segmentation of the image. The current standard protocol using semi-automated contouring for HR-pQCT image segmentation is laborious, introduces inter-operator biases into research data, and poses a barrier to streamlined clinical implementation. In this work, we propose and validate a fully automated algorithm for segmentation of HR-pQCT radius and tibia images. A multi-slice 2D U-Net produces initial segmentation predictions, which are post-processed via a sequence of traditional morphological image filters. The U-Net was trained on a large dataset containing 1822 images from 896 unique participants. Predicted segmentations were compared to reference segmentations on a disjoint dataset containing 386 images from 190 unique participants, and 156 pairs of repeated images were used to compare the precision of the novel and current protocols. The agreement of morphological parameters obtained using the predicted segmentation relative to the reference standard was excellent (R2 between 0.938 and > 0.999). Precision was significantly improved for several outputs, most notably cortical porosity. This novel and robust algorithm for automated segmentation will increase the feasibility of using HR-pQCT in research and clinical settings.https://doi.org/10.1038/s41598-022-27350-0 |
| spellingShingle | Nathan J. Neeteson Bryce A. Besler Danielle E. Whittier Steven K. Boyd Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing Scientific Reports |
| title | Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing |
| title_full | Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing |
| title_fullStr | Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing |
| title_full_unstemmed | Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing |
| title_short | Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing |
| title_sort | automatic segmentation of trabecular and cortical compartments in hr pqct images using an embedding predicting u net and morphological post processing |
| url | https://doi.org/10.1038/s41598-022-27350-0 |
| work_keys_str_mv | AT nathanjneeteson automaticsegmentationoftrabecularandcorticalcompartmentsinhrpqctimagesusinganembeddingpredictingunetandmorphologicalpostprocessing AT bryceabesler automaticsegmentationoftrabecularandcorticalcompartmentsinhrpqctimagesusinganembeddingpredictingunetandmorphologicalpostprocessing AT danielleewhittier automaticsegmentationoftrabecularandcorticalcompartmentsinhrpqctimagesusinganembeddingpredictingunetandmorphologicalpostprocessing AT stevenkboyd automaticsegmentationoftrabecularandcorticalcompartmentsinhrpqctimagesusinganembeddingpredictingunetandmorphologicalpostprocessing |