Breast Cancer Segmentation Methods: Current Status and Future Potentials.
Journal
BioMed research international
ISSN: 2314-6141
Titre abrégé: Biomed Res Int
Pays: United States
ID NLM: 101600173
Informations de publication
Date de publication:
2021
2021
Historique:
received:
22
03
2021
revised:
14
05
2021
accepted:
11
06
2021
entrez:
2
8
2021
pubmed:
3
8
2021
medline:
23
9
2021
Statut:
epublish
Résumé
Early breast cancer detection is one of the most important issues that need to be addressed worldwide as it can help increase the survival rate of patients. Mammograms have been used to detect breast cancer in the early stages; if detected in the early stages, it can drastically reduce treatment costs. The detection of tumours in the breast depends on segmentation techniques. Segmentation plays a significant role in image analysis and includes detection, feature extraction, classification, and treatment. Segmentation helps physicians quantify the volume of tissue in the breast for treatment planning. In this work, we have grouped segmentation methods into three groups: classical segmentation that includes region-, threshold-, and edge-based segmentation; machine learning segmentation; and supervised and unsupervised and deep learning segmentation. The findings of our study revealed that region-based segmentation is frequently used for classical methods, and the most frequently used techniques are region growing. Further, a median filter is a robust tool for removing noise. Moreover, the MIAS database is frequently used in classical segmentation methods. Meanwhile, in machine learning segmentation, unsupervised machine learning methods are more frequently used, and U-Net is frequently used for mammogram image segmentation because it does not require many annotated images compared with other deep learning models. Furthermore, reviewed papers revealed that it is possible to train a deep learning model without performing any preprocessing or postprocessing and also showed that the U-Net model is frequently used for mammogram segmentation. The U-Net model is frequently used because it does not require many annotated images and also because of the presence of high-performance GPU computing, which makes it easy to train networks with more layers. Additionally, we identified mammograms and utilised widely used databases, wherein 3 and 28 are public and private databases, respectively.
Identifiants
pubmed: 34337066
doi: 10.1155/2021/9962109
pmc: PMC8321730
doi:
Types de publication
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
9962109Informations de copyright
Copyright © 2021 Epimack Michael et al.
Déclaration de conflit d'intérêts
The authors declare no conflict of interest.
Références
Comput Med Imaging Graph. 2001 Jan-Feb;25(1):47-59
pubmed: 11120407
Am Fam Physician. 2013 Feb 15;87(4):274-8
pubmed: 23418799
Acad Radiol. 2001 Mar;8(3):250-6
pubmed: 11249089
Med Phys. 2000 Jan;27(1):13-22
pubmed: 10659733
Comput Methods Programs Biomed. 2021 Mar;200:105913
pubmed: 33422854
Springerplus. 2015 Oct 12;4:591
pubmed: 26543726
Conf Proc IEEE Eng Med Biol Soc. 2004;2004:1814-7
pubmed: 17272061
AJR Am J Roentgenol. 2007 Jan;188(1):236-41
pubmed: 17179372
Annu Rev Biomed Eng. 2000;2:315-37
pubmed: 11701515
Radiology. 2004 Oct;233(1):255-65
pubmed: 15317954
Phys Med Biol. 2020 Feb 28;65(5):055005
pubmed: 31722327
Comput Methods Programs Biomed. 2013 May;110(2):150-9
pubmed: 23273502
Med Phys. 2010 Aug;37(8):4432-44
pubmed: 20879602
IEEE Trans Med Imaging. 2001 Dec;20(12):1275-84
pubmed: 11811827
Radiology. 2005 Aug;236(2):451-7
pubmed: 16040901
IEEE Trans Med Imaging. 2001 Dec;20(12):1209-14
pubmed: 11811821
Med Biol Eng Comput. 2016 Jul;54(7):1003-24
pubmed: 26546074
Conf Proc IEEE Eng Med Biol Soc. 2005;2005:6500-3
pubmed: 17281758
Med Phys. 1999 Aug;26(8):1642-54
pubmed: 10501064
Clin Obstet Gynecol. 2016 Dec;59(4):688-709
pubmed: 27741212
AJR Am J Roentgenol. 2016 Apr;206(4):883-90
pubmed: 26866649
Radiology. 2009 Jun;251(3):663-72
pubmed: 19366902
J Community Health. 2000 Jun;25(3):183-98
pubmed: 10868813
Diagnostics (Basel). 2020 Nov 23;10(11):
pubmed: 33238512
J Digit Imaging. 2012 Jun;25(3):377-86
pubmed: 21989574
J Radiol. 2009 Jun;90(6):747-51
pubmed: 19623131
Acad Radiol. 2001 Nov;8(11):1074-82
pubmed: 11721807
J Digit Imaging. 2017 Apr;30(2):172-184
pubmed: 27844218
BMC Med Imaging. 2014 Jun 24;14:23
pubmed: 24961885
Radiology. 2001 Apr;219(1):192-202
pubmed: 11274556
Comput Methods Programs Biomed. 2014 Apr;114(1):88-101
pubmed: 24513228
IEEE Trans Med Imaging. 2004 Sep;23(9):1129-40
pubmed: 15377122
J Digit Imaging. 2020 Aug;33(4):858-868
pubmed: 32206943
Med Image Anal. 2010 Apr;14(2):87-110
pubmed: 20071209
Adv Exp Med Biol. 2020;1213:59-72
pubmed: 32030663
Artif Intell Med. 2017 Jun;79:28-41
pubmed: 28606722
J Digit Imaging. 2015 Oct;28(5):613-25
pubmed: 25776767
J Med Syst. 2012 Oct;36(5):3051-61
pubmed: 21947904
Comput Math Methods Med. 2015;2015:891692
pubmed: 25737739
J Digit Imaging. 2015 Oct;28(5):604-12
pubmed: 25720749
CA Cancer J Clin. 2018 Nov;68(6):394-424
pubmed: 30207593
Int J Med Inform. 2018 Sep;117:44-54
pubmed: 30032964
J Digit Imaging. 2010 Oct;23(5):547-53
pubmed: 19756865
BMC Bioinformatics. 2020 Dec 9;21(Suppl 1):192
pubmed: 33297952
J Med Internet Res. 2019 Jul 26;21(7):e14464
pubmed: 31350843
Radiology. 2014 Jan;270(1):49-56
pubmed: 24354377