A complementary scheme for automated detection of high-uptake regions on dedicated breast PET and whole-body PET/CT.
Breast cancer
Dedicated breast pet
Image processing
Whole-body PET/CT
Journal
Radiological physics and technology
ISSN: 1865-0341
Titre abrégé: Radiol Phys Technol
Pays: Japan
ID NLM: 101467995
Informations de publication
Date de publication:
Sep 2019
Sep 2019
Historique:
received:
10
01
2019
accepted:
17
05
2019
revised:
16
05
2019
pubmed:
28
5
2019
medline:
22
1
2020
entrez:
27
5
2019
Statut:
ppublish
Résumé
In this study, we aimed to develop a hybrid method for automated detection of high-uptake regions in the breast and axilla using dedicated breast positron-emission tomography (db PET) and whole-body PET/computed tomography (CT) images. In our proposed method, high-uptake regions in the breast and axilla were detected using db PET images and whole-body PET/CT images. In db PET images, high-uptake regions in the breast were detected using adaptive thresholding technique based on the noise characteristics. In whole-body PET/CT images, the region of the breast that includes the axilla was first extracted using CT images. Next, high-uptake regions in the extracted breast region were detected on the PET images. By integration of the results of the two types of PET images, a final candidate region was obtained. In the experiments, the accuracy of extracting the region of the breast and detection ability was evaluated using clinical data. As a result, all breast regions were extracted correctly. The sensitivity of detection was 0.765, and the number of false positive cases were 1.8, which was 30% better than those on whole-body PET/CT alone. These results suggested that the proposed method, combining the two types of PET images is effective for improving detection performance.
Identifiants
pubmed: 31129787
doi: 10.1007/s12194-019-00516-8
pii: 10.1007/s12194-019-00516-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
260-267Subventions
Organisme : Grant-in-Aid for Scientific Research on Innovative Areas
ID : 26108005
Références
IEEE Trans Med Imaging. 2000 Feb;19(2):115-26
pubmed: 10784283
J Nucl Med. 2003 Aug;44(8):1238-42
pubmed: 12902413
Med Phys. 2003 Aug;30(8):2040-51
pubmed: 12945970
Med Phys. 2007 Nov;34(11):4378-88
pubmed: 18072503
Comput Methods Programs Biomed. 2008 Dec;92(3):238-48
pubmed: 18514362
Med Phys. 2008 Dec;35(12):5253-62
pubmed: 19175084
Phys Med Biol. 2010 May 21;55(10):2917-39
pubmed: 20436235
J Digit Imaging. 2011 Jun;24(3):446-63
pubmed: 20508965
J Nucl Med. 2012 Oct;53(10):1534-42
pubmed: 22933819
Int J Comput Assist Radiol Surg. 2013 Jul;8(4):527-45
pubmed: 23054747
Int J Comput Assist Radiol Surg. 2014 Jan;9(1):59-69
pubmed: 23793722
J Nucl Med. 2014 Jul;55(7):1198-203
pubmed: 24812244
Ann Nucl Med. 2014 Jul;28(6):597-602
pubmed: 24878887
J Digit Imaging. 2015 Oct;28(5):613-25
pubmed: 25776767
Diagnostics (Basel). 2015 Mar 16;5(1):61-83
pubmed: 26854143
AJR Am J Roentgenol. 2016 Jun;206(6):1307-14
pubmed: 27058014
Med Phys. 2016 May;43(5):2261
pubmed: 27147338
Med Phys. 2016 Jun;43(6):2821-2827
pubmed: 27277030
Eur J Radiol. 2017 May;90:138-145
pubmed: 28583624
J Nucl Med. 1995 Oct;36(10):1836-9
pubmed: 7562051