Automatic FDG-PET-based tumor and metastatic lymph node segmentation in cervical cancer
(2014) Medical Imaging 2014: Image Processing In Progress in Biomedical Optics and Imaging - Proceedings of SPIE 9034.- Abstract
Treatment of cervical cancer, one of the three most commonly diagnosed cancers worldwide, often relies on delineations of the tumour and metastases based on PET imaging using the contrast agent 18F-Fluorodeoxyglucose (FDG). We present a robust automatic algorithm for segmenting the gross tumour volume (GTV) and metastatic lymph nodes in such images. As the cervix is located next to the bladder and FDG is washed out through the urine, the PET-positive GTV and the bladder cannot be easily separated. Our processing pipeline starts with a histogram-based region of interest detection followed by level set segmentation. After that, morphological image operations combined with clustering, region growing, and nearest neighbour labelling allow... (More)
Treatment of cervical cancer, one of the three most commonly diagnosed cancers worldwide, often relies on delineations of the tumour and metastases based on PET imaging using the contrast agent 18F-Fluorodeoxyglucose (FDG). We present a robust automatic algorithm for segmenting the gross tumour volume (GTV) and metastatic lymph nodes in such images. As the cervix is located next to the bladder and FDG is washed out through the urine, the PET-positive GTV and the bladder cannot be easily separated. Our processing pipeline starts with a histogram-based region of interest detection followed by level set segmentation. After that, morphological image operations combined with clustering, region growing, and nearest neighbour labelling allow to remove the bladder and to identify the tumour and metastatic lymph nodes. The proposed method was applied to 125 patients and no failure could be detected by visual inspection. We compared our segmentations with results from manual delineations of corresponding MR and CT images, showing that the detected GTV lays at least 97.5% within the MR/CT delineations. We conclude that the algorithm has a very high potential for substituting the tedious manual delineation of PET positive areas.
(Less)
- author
- Arbonès, Dídac R. ; Jensen, Henrik G. ; Loft, Annika ; Munck Af Rosenschöld, Per LU ; Hansen, Anders Elias ; Igel, Christian and Darkner, Sune
- publishing date
- 2014-01-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Cervix cancer, PET, Segmentation, Tumor delineation
- host publication
- Medical Imaging 2014 : Image Processing - Image Processing
- series title
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE
- volume
- 9034
- article number
- 903441
- publisher
- SPIE
- conference name
- Medical Imaging 2014: Image Processing
- conference location
- San Diego, CA, United States
- conference dates
- 2014-02-16 - 2014-02-18
- external identifiers
-
- scopus:84902094498
- ISSN
- 1605-7422
- ISBN
- 9780819498274
- DOI
- 10.1117/12.2042909
- language
- English
- LU publication?
- no
- id
- 9e6969b7-082a-4eab-9b6c-4583183e638c
- date added to LUP
- 2020-07-28 08:48:29
- date last changed
- 2023-07-20 08:31:44
@inproceedings{9e6969b7-082a-4eab-9b6c-4583183e638c, abstract = {{<p>Treatment of cervical cancer, one of the three most commonly diagnosed cancers worldwide, often relies on delineations of the tumour and metastases based on PET imaging using the contrast agent 18F-Fluorodeoxyglucose (FDG). We present a robust automatic algorithm for segmenting the gross tumour volume (GTV) and metastatic lymph nodes in such images. As the cervix is located next to the bladder and FDG is washed out through the urine, the PET-positive GTV and the bladder cannot be easily separated. Our processing pipeline starts with a histogram-based region of interest detection followed by level set segmentation. After that, morphological image operations combined with clustering, region growing, and nearest neighbour labelling allow to remove the bladder and to identify the tumour and metastatic lymph nodes. The proposed method was applied to 125 patients and no failure could be detected by visual inspection. We compared our segmentations with results from manual delineations of corresponding MR and CT images, showing that the detected GTV lays at least 97.5% within the MR/CT delineations. We conclude that the algorithm has a very high potential for substituting the tedious manual delineation of PET positive areas.</p>}}, author = {{Arbonès, Dídac R. and Jensen, Henrik G. and Loft, Annika and Munck Af Rosenschöld, Per and Hansen, Anders Elias and Igel, Christian and Darkner, Sune}}, booktitle = {{Medical Imaging 2014 : Image Processing}}, isbn = {{9780819498274}}, issn = {{1605-7422}}, keywords = {{Cervix cancer; PET; Segmentation; Tumor delineation}}, language = {{eng}}, month = {{01}}, publisher = {{SPIE}}, series = {{Progress in Biomedical Optics and Imaging - Proceedings of SPIE}}, title = {{Automatic FDG-PET-based tumor and metastatic lymph node segmentation in cervical cancer}}, url = {{http://dx.doi.org/10.1117/12.2042909}}, doi = {{10.1117/12.2042909}}, volume = {{9034}}, year = {{2014}}, }