Fully Automated Tumor Segmentation from Ultrasound Images by Choosing Dynamic Thresholding

Islam, Md. Musfiqul; Mostafiz, Md. Tawsif; Mujaddeed, Seemab-Al-

IUT Repository Home
→
Electrical and Electronics Engineering (EEE)
→
Thesis
→
Undergraduate
→
2022
→
View Item

dc.contributor.author	Islam, Md. Musfiqul
dc.contributor.author	Mostafiz, Md. Tawsif
dc.contributor.author	Mujaddeed, Seemab-Al-
dc.date.accessioned	2023-01-05T08:39:50Z
dc.date.available	2023-01-05T08:39:50Z
dc.date.issued	2022-05-30
dc.identifier.citation	[1] Center for Disease Control and Prevention. Cancer among women. Cancer PreventionandControl website. www.cdc.gov/cancer/dcpc/data/women.htm. Published January 2, 2013. AccessedOctober 7, 2013 [2]International Agency for Research on Cancer. Breast cancer incidence, mortality andprevalenceWorldwide in 2008. GLOBOCAN website.globocan.iarc.fr/Pages/fact_sheets_cancer.asp.PublishedJuly 10, 2013. Accessed October 7, 2013 [3] R. L. Siegel, K. D. Miller and A. Jemal, "Cancer statistics, 2016," CA Cancer J Clin, vol. 66, no.1, pp. 7-30, 2016. [4] C.M. Sehgal, S.P. Weinstein, P.H. Arger, E.F. Conant, A review of breast ultrasound, J.Mammary Gland Biol. Neoplasia 11 (2006) 113–123. [5] J.G. Bosch, S.C. Mitchell, B.P. Lelieveldt, F. Nijland, O. Kamp, M. Sonka, J.H. Reiber,Automatic segmentation of echocardiographic sequences by active appearance motion models, IEEETrans. Med. Imaging 21 (2002) 1374–1383. [6] Kisslo J, Firek B, Ota T, Kang DH, Fleishman CE, Stetten G, Li J, Ohazama CJ, AdamsD,Landolfo C, Ryan T, von Ramm O. Realtime volumetric echocardiography: The technologyandthepossibilities. Echocardiography 2000;17:773–779. [7] T. Chan and L. Vese, "Active contours without edges," in IEEE transactions on imageprocessing10(2), 2001, pp. 266-277. [8] Active Contours Without Edges \| Sanjay Chaudhary - Academia.edu[9] Md. Anisur Rahman Farazy, “Incidence of Breast Cancer in Bangladesh,” Health Care, vol. 3,issue 3, pp. 53-54, October, 2015. [10] American Cancer Society, in Cancer Facts and Figures, 2019. [11] Siegel RL, Miller KD & Jemal A, “Cancer Statistics, 2019,” CA Cancer J Clin, vol. 69, issue1,pp. 7 – 34, 2019. [12] Ultrasound Imaging FDA. (https://www.fda.gov/radiation-emitting-products/medicalimaging/ultrasound-imaging) (accessed May 1,2022) [13] Propagation of Sound Waves (https://www.pasco.com/products/guides/sound-waves) (accessedApril 27,2022) 40 [14] Instrumentation_Electronics/transducer/2011/07.(http://www.instrumentationtoday.com/piezoelectric-transducer/2011/07) (accessed May 1,2022) [15] Carstensen, E. L. (1976). Interaction of Ultrasound with Tissues. Ultrasound in Medicine, 517–517. [16] Interaction_of_Ultrasound_Waves_with_Tissue.(https://eechocardiography.com/page/page.php?UID=1427121051) (accessed May 5,2022) [17] B. D. Fornage, “Ultrasound of the breast,” Ultrasound Quart., vol. 11, no. 1, pp. 1–39, 1993. [18] A. Stavos, D. Thickman, C. Rapp, M. Dennis, S. Parker, and S. G.A., “Solid breast modules: Useofsonography to distinguish between benign and malignant lesions,” Radiology, vol. 196, pp.123–134,1995. [19] V. Jackson, “Management of solid breast modules: What is the role of sonography? Radiology, vol. 196, pp. 14–15, 1995. [20] P. Arger,C. Sehgal, E. Conant, J. Zuckerman, S. Rowling, and J. Patton, “Interreader variabilityandpredictive value of is descriptions ofsolid masses: Pilotstudy,” Acad. Radiol., vol. 8, pp. 335–342, 2001[21] K. Horsch, M. L. Giger, L. A. Venta, and C. J. Vyborny, “Automatic segmentation of breast lesions onultrasound,” Med. Phys., vol. 28, no.8, pp. 1652–1659, Aug. 2001. [22] ——, “Computerized diagnosis of breast lesions on ultrasound,” Med. Phys., vol. 29, no. 2, pp. 157–164, Feb. 2002. [23] K. Horsch, M. L. Giger, C. J. Vyborny, and L. A. Venta, “Performance of computer-aided diagnosisin the interpretation of lesions on breast sonography,” Acad. Radiol., vol. 11, no. 3, pp. 272–280, Mar. 2004. [24] K. Drukker, M. L. Giger, K. Horsch, C. J. Kupinski, M. A. Vyborny, and E. B. Mendelson, “Computerized lesion detection on breast ultrasound,” Med. Phys., vol. 29, no. 7, pp. 1438–1446, Jul. 2002. [25] K. Drukker, M. L. Giger, C. J. Vyborny, and E. B. Mendelson, “Computerized detectionandclassification of cancer on breast ultrasound,” Acad. Radiol., vol. 11, no. 5, pp. 526–535, May2004. [26] Rodrigues, Paulo Sergio (2017), “Breast Ultrasound Image”, Mendeley Data, V1, DOI: 10.17632/wmy84gzngw.1 [27] Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A. Dataset of breast ultrasound images. Datain Brief. 2020 Feb;28:104863. DOI: 10.1016/j.dib.2019.104863. [28] Image Processing with Python. [29] Articles:“Watershed_Algorithm_and_its_application”. 41 (https://www.aegissofttech.com/articles/watershed-algorithm-and-limitations.html) (accessed May 5,2022) [30] Olivier Rousseau and Yves Bourgault, "Heart segmentation with an iterative Chan-Vesealgorithm," University of Ottawa, Ontario , 2009. [31] Fan, M., & Lee, T. C. M. (2015). Variants of seeded region growing. IET Image Processing, 9(6), 478–485. doi:10.1049/iet-ipr.2014.0490 [32] Medixant, RadiAnt DICOM Viewer, (2018). (www.radiantviewer.com) (accessed May5,2022)[33] Śmieszny, Fast Photo Crop, 2013. (https://apps.microsoft.com/store/detail/fast-photo- crop/9WZDNCRDNVPV?hl=ar-eg&gl=EG (accessed May 3,2022) [34] Al-Dhabyani, W., Gomaa, M., Khaled, H., & Fahmy, A. (2019). Dataset of Breast UltrasoundImages. Data in Brief, 104863. doi:10.1016/j.dib.2019.10486 [35] Diagnostics of pregnancy Pregnant woman getting ultrasound from doctor UltrasoundStockPhoto.(https://media.istockphoto.com/photos/diagnostics-of-pregnancy-picture-id123824128) (accessed May 5,2022) [36] ‘Roshni's Physics E-Portfolio’. (https://sites.google.com/site/roshnisphysicseportfolio/sound-waves) (accessed May 5,2022) [37] Fastest Anesthesia & Intensive Care & Emergency Medicine Insight Engine. (https://aneskey.com/ultrasound-basics-2/#ch02ref1) (accessed May 2,2022) [38] Ultrasound Theory Module_FAMUS.(http://famus.org.uk/modules/ultrasound-theory-module)(accessed April 29,2022) [39] “Ultrasonic Materials Ideal for today’s highest- performance transducers_ datasheet ultrasonicmetarials-10997 by Entegris’ POCO Materials are ideal for several high- technologyindustries.” [40] Yao, Guilin. (2017). A Survey on Pre-Processing in Image Matting. Journal of ComputerScience and Technology. 32. 122-138. 10.1007/s11390-017-1709-z. [41] #007 OpenCV projects – Image segmentation with Watershed algorithm. 42 [42] Al-Dhabyani, W., Gomaa, M., Khaled, H., & Fahmy, A. (2019). Dataset of Breast Ultrasound Images. Data in Brief, 104863. [43] “Ming Tang, Yasin Kaymaz, Brandon L Logeman, Stephen Eichhorn, Zhengzheng S Liang, CatherineDulac, Timothy B Sackton, Evaluating single-cell cluster stability using the Jaccard similarityindex, Bioinformatics, Volume 37, Issue 15, 1 August 2021, Pages 2212–2214”	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/1630
dc.description	Supervised by Prof. Dr. Md. Taslim Reza, Department of Electrical and Electronic Engineering(EEE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Electrical and Electronic Engineering, 2022.	en_US
dc.description.abstract	The main fortitude of diagnostic ultrasound are its ability to reveal the mechanical compositionofanatomy, the dynamic mobility of organs and instant details of bloodcirculation. Breast ultrasoundimaging is congenital, radiation-free, and convenient. Automatic breast ultrasound (BUS) imagesegmentation is difficult in clinicalpractice but vital for cancer diagnosis and medication planning. Speckle noises and attenuated artifacts are prominent in ultrasound images. Speckles obscureaspects that are essential for diagnosis and evaluation. Due to low contrast, automatically findingareas of interest (ROIs) and inaccurate tumor boundaries in breast ultrasound images (BUS), automatically segmenting breast tumors from ultrasound remains a challenge. The majorityofultrasound image segmentation algorithms are centered on region growing or active contours. These are semi- automatic segmenting methods in which seed points or preliminary contours haveto be identified manually. This thesis presents a fully automated tumor segmentationfromUltrasound Images by choosing dynamic thresholding. This framework also includes selectionof anautomated threshold value for watershed method. The area and boundary error metrics are usedtoevaluate the performance of the proposed completely automatic segmentation method on a BUSdatabase. Our proposed method is more accurate and reliable in the segmentation of BUSimagesthan the fully automated method recently proposed.	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Electrical and Electronic Engineering(EEE), Islamic University of Technology(IUT),	en_US
dc.subject	Image Segmentation, Watershed Method, Active Contour Method, Seed Region Growing Method, Ultrasound	en_US
dc.title	Fully Automated Tumor Segmentation from Ultrasound Images by Choosing Dynamic Thresholding	en_US
dc.type	Thesis	en_US