Development of breast papillary index for diferentiation of benign and malignant lesions using ultrasound images

Hanh Pham, . and Raghavendra, U and Joel En, Wei Koh and Gudigar, Anjan and Wai Yee, Chan and Marlina Tanty, Ramli Hamid and Kartini, Rahmat and Farhana, Fadzli and Kwan Hoong, Ng and Chui Ping, Ooi and Ciaccio, Edward J. and Fujita, Hamido and Acharya, Rajendra U (2021) Development of breast papillary index for diferentiation of benign and malignant lesions using ultrasound images. Journal of Ambient Intelligence and Humanized Computing, 12 (2121). pp. 2121-2129. ISSN 1868-5137

[img] PDF
11669.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

Papillary breast lesions include a wide spectrum of pathologies ranging from benign to malignant. The word papillary originates from fnger-like projections, or papules, which are seen when these lesions are projected under a microscope. Papillary breast lesions have an array of radiological features at presentations; hence diferentiation between benign and malignant based on imaging features is challenging. Histopathological diagnosis is crucial for the distinction and further management of the lesions. Traditionally, tumor and ductal excision is the treatment of choice for malignant and atypical or benign papilloma with imaging discordance. However, current clinical practice guidance advocates complete surgical excision, even for asymptomatic and purely benign papillomas diagnosed on core needle biopsy, as they are highly associated with atypia and malignant upstage on subsequent surgery. Computer aided diagnosis (CAD) is a non-invasive method of diagnosing medical signals/images using advanced image processing followed by soft computing techniques. In this study, we have developed a non-invasive CAD system for diferentiating benign versus malignant papillary breast lesions using bi-dimensional empirical mode decomposition (BEMD) and the discrete cosine transform (DCT) followed by locality sensitive discriminant analysis (LSDA). The developed model is validated using a large collection of ultrasound images of papillary breast lesions, and achieved a maximum performance of 98.63% accuracy. We have also developed a breast papillary index, which may in the future be used as a substitute for the conventional soft computing techniques. The developed model can be utilized as a tool to assist radiologists in their routine clinical practice after validation with a larger database.

Item Type: Article
Uncontrolled Keywords: Papillary breast · Benign · Malignant · CAD · BEMD · DCT · LSDA · Classifcation · SVM
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 05 Jun 2021 09:59
Last Modified: 05 Jun 2021 09:59
URI: http://eprints.manipal.edu/id/eprint/156785

Actions (login required)

View Item View Item