Skip to main content

Detection of Tumour Based on Breast Tissue Categorization | Chapter 04 | Advances in Applied Science and Technology Vol. 4

Background: Breast cancer originates in breast tissue, which is made up of glands for milk production (lobules),  and  the  ducts  that  connect  lobules  to  the  nipple.  Breasts  contain  both  dense  tissue (glandular  tissue  and  connective  tissue,  together  known  as  fibro-glandular  tissue)  and  fatty  tissue. Fatty tissue appears dark on a mammogram, whereas fibro-glandular tissue appears as white. Despite the benefits of Computer Aided Detection (CAD), false detection of breast tumour is still a challenging issue with oncologist. A mammography is a non-invasive screening tool that uses low energy X-rays to show the pathology structure of breast tissue. Interpreting mammogram visually is a time consuming process  and  requires  a  great  deal  of  skill  and  experience. Earlier  Computer  Aided  Techniques emphasis detection of tumour in breast tissues rather than categorization of breast into Breast Imaging Report and Data System (BI-RADS) which is the medically understandable method of reporting.

Aim: The work centred on developing a CAD system which is capable of not only detecting but also categorizing breast tissue in line with BI-RADS scale.

Methodology: The acquired images were pre-processed to remove unwanted contents. Two stage medical procedural approach was designed to categorize thetissue in breast images into low dense (fatty) and high dense. Tumours in the low dense breasts were segmented, and then classified as normal,  benign  and  malignant.  The  developed  system  was  evaluated  using  sensitivity,  specificity, false positive reduction, false negative reduction and overall performance.

Results: The  developed  CAD  achieved  90.65%  sensitivity,  73.59%  specificity,  0.02  positive reduction, 0.04 false negative reduction and 85.71% overall performance.

Conclusion: The  false  positive  reduction  result  obtained  shows  that  false  detection  has  been minimized as a result of categorization procedure of the breast tissue in mammograms. This article has  reported  breast  tumour  detection  from  breast  tissue  categorisation  using  Medical  procedural approach.  The  developed  system  assisted  in  identification  of  suspicious  mammograms  and identification  of  dense  and  fatty  breasts.  The  classification  of  the  segmented  mammogram  into normal,  benign  and  malignant  achieved  a  better  false  positive  reduction  (0.02)  andfalse  negative reduction  (0.04)  and  thus  provided  an  improved  method  for  detection  and  classification  of  breast tumour in terms of overall performance.

Author(s) Details

Temilola Morufat Adepoju
Department of Computer Science and Engineering, Faculty of Engineering & Technology, LAUTECH, Nigeria.

John Adedapo Ojo
Department of Electronic and Electrical Engineering, Faculty of Engineering & Technology, LAUTECH, Nigeria.

Elijah Olusayo Omidiora
Department of Computer Science and Engineering, Faculty of Engineering & Technology, LAUTECH, Nigeria.

Bello Temitope Olugbenga
Department of Radiology, Faculty of Health Sciences, LAUTECH, Nigeria.


Comments

Popular posts from this blog

Consensus Summit: Lipids and Cardiovascular Health in the Nigerian Population | Chapter 09 | Current Trends in Food Science Vol. 1

Aims: To issue a consensus statement on Lipids and Cardiovascular Health and the impact of their interrelationship in Nigerian Population. Study Design: Experts from a range of relevant disciplines, deliberated on different aspects of Lipids and Cardiovascular Health in the Nigerian Population at a Summit. Place and Duration of Study: The Summit was held in April 2016 at the Nigerian Institute of Medical Research. Methodology: Presentations were made on central themes after which expert participants split into four different groups to consider the questions relevant to different sub themes of the title. Consensus was arrived at, from presentations of groups at plenary. Conclusion: With the increase in the prevalence of NCDs, especially Cardiovascular Disease in Nigeria, and the documented evidence of deleterious effects of lipids, the expert panel called for an urgent need to advocate for the general public and health professionals to make heart-friendly

A Review on Gongronema latifolium, an Extremely Useful Plant with Great Prospects | Chapter 11 | Recent Advances in Biological Research Vol. 3

Gongronema latifolium is a plant that has a wide range of nutritional and ethnomedical uses in different tropical African communities. Scientific reports on the chemical composition and bioactivity (anti-inflammatory, antimicrobial, antidiabetic, antioxidant, anticancer and allelopathic properties) of the plant material by different authors are discussed in this review. Future prospects of the plant extracts in the areas of herbal formulations, food preservation, alcoholic fermentation and beer production, drug discovery and allelopathy are also highlighted. Author   Details: Olugbenga Morebise Faculty of Basic Medical Sciences, All Saints University School of Medicine, Roseau, Commonwealth of Dominica. Read full article: http://bp.bookpi.org/index.php/bpi/catalog/view/50/403/433-1 View Volume: https://doi.org/10.9734/bpi/rabr/v3

An Overview of Ultrasonic Technology and Its Applications in Food Processing, Preservation and Quality Control | Chapter 03 | Current Research in Science and Technology Vol. 3

Ultrasound is one of the emerging technologies that were developed to minimize processing, maximize quality and ensure the safety of food products. In recent years, ultrasound technology has been used as an alternative processing option to conventional thermal approaches. Although Ultrasonication methods have been used for years in research and diagnostics, major advances have been made in the last decade. The applications for which high power ultrasound can be used range from existing processes that are enhanced by the retrofitting of high power ultrasonic technology, to the development of processes up to now not possible with conventional energy sources. The present paper reviews the generation, principle mechanism, properties, process parameters, applications, merits and demerits and future trends of the ultrasound technology in the food processing. Author(s) Details Er. Bogala Madhu Department of Processing and Food Engineering, College of Technology and Engineering, MP