Automated 3-dimensional segmentation of pelvic lymph nodes in magnetic resonance images
- PMID: 22047383
- DOI: 10.1118/1.3654162
Automated 3-dimensional segmentation of pelvic lymph nodes in magnetic resonance images
Abstract
Purpose: Computer aided diagnosis (CAD) of lymph node metastases may help reduce reading time and improve interpretation of the large amount of image data in a 3-D pelvic MRI exam. The purpose of this study was to develop an algorithm for automated segmentation of pelvic lymph nodes from a single seed point, as part of a CAD system for the classification of normal vs metastatic lymph nodes, and to evaluate its performance compared to other algorithms.
Methods: The authors' database consisted of pelvic MR images of 146 consecutive patients, acquired between January 2008 and April 2010. Each dataset included four different MR sequences, acquired after infusion of a lymph node specific contrast medium based on ultrasmall superparamagnetic particles of iron oxide. All data sets were analyzed by two expert readers who, reading in consensus, annotated and manually segmented the lymph nodes. The authors compared four segmentation algorithms: confidence connected region growing (CCRG), extended CCRG (ECC), graph cut segmentation (GCS), and a segmentation method based on a parametric shape and appearance model (PSAM). The methods were ranked based on spatial overlap with the manual segmentations, and based on diagnostic accuracy in a CAD system, with the experts' annotations as reference standard.
Results: A total of 2347 manually annotated lymph nodes were included in the analysis, of which 566 contained a metastasis. The mean spatial overlap (Dice similarity coefficient) was: 0.35 (CCRG), 0.57 (ECC), 0.44 (GCS), and 0.46 (PSAM). When combined with the classification system, the area under the ROC curve was: 0.805 (CCRG), 0.890 (ECC), 0.807 (GCS), 0.891 (PSAM), and 0.935 (manual segmentation).
Conclusions: We identified two segmentation methods, ECC and PSAM, that achieve a high diagnostic accuracy when used in conjunction with a CAD system for classification of normal vs metastatic lymph nodes. The manual segmentations still achieve the highest diagnostic accuracy.
Similar articles
-
Spatially varying accuracy and reproducibility of prostate segmentation in magnetic resonance images using manual and semiautomated methods.Med Phys. 2014 Nov;41(11):113503. doi: 10.1118/1.4899182. Med Phys. 2014. PMID: 25370674
-
Metastases in normal-sized pelvic lymph nodes: detection with diffusion-weighted MR imaging.Radiology. 2014 Oct;273(1):125-35. doi: 10.1148/radiol.14132921. Epub 2014 Jun 2. Radiology. 2014. PMID: 24893049 Clinical Trial.
-
Ultrasmall superparamagnetic particles of iron oxide allow for the detection of metastases in normal sized pelvic lymph nodes of patients with bladder and/or prostate cancer.Eur J Cancer. 2013 Feb;49(3):616-24. doi: 10.1016/j.ejca.2012.09.034. Epub 2012 Oct 18. Eur J Cancer. 2013. PMID: 23084842
-
Computer-aided lymph node segmentation in volumetric CT data.Med Phys. 2012 Sep;39(9):5419-28. doi: 10.1118/1.4742845. Med Phys. 2012. PMID: 22957609 Free PMC article.
-
MR contrast agents in lymph node imaging.Eur J Radiol. 2006 Jun;58(3):375-82. doi: 10.1016/j.ejrad.2005.12.044. Epub 2006 Feb 7. Eur J Radiol. 2006. PMID: 16464554 Review.
Cited by
-
The accuracy of artificial intelligence deformed nodal structures in cervical online cone-beam-based adaptive radiotherapy.Phys Imaging Radiat Oncol. 2024 Feb 8;29:100546. doi: 10.1016/j.phro.2024.100546. eCollection 2024 Jan. Phys Imaging Radiat Oncol. 2024. PMID: 38369990 Free PMC article.
-
Utility of diffusion weighted imaging-based radiomics nomogram to predict pelvic lymph nodes metastasis in prostate cancer.BMC Med Imaging. 2022 Nov 4;22(1):190. doi: 10.1186/s12880-022-00905-3. BMC Med Imaging. 2022. PMID: 36333664 Free PMC article.
-
Development and validation of the 3D U-Net algorithm for segmentation of pelvic lymph nodes on diffusion-weighted images.BMC Med Imaging. 2021 Nov 13;21(1):170. doi: 10.1186/s12880-021-00703-3. BMC Med Imaging. 2021. PMID: 34774001 Free PMC article.
-
Deep learning-based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: A multicentre study.EBioMedicine. 2020 Jun;56:102780. doi: 10.1016/j.ebiom.2020.102780. Epub 2020 Jun 5. EBioMedicine. 2020. PMID: 32512507 Free PMC article.
-
Classifying Neck Lymph Nodes of Head and Neck Squamous Cell Carcinoma in MRI Images with Radiomic Features.J Digit Imaging. 2020 Jun;33(3):613-618. doi: 10.1007/s10278-019-00309-w. J Digit Imaging. 2020. PMID: 31950301 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
Miscellaneous