Hershey, Pennsylvania
New York, New YorkBeijing, China
Identification and Segmentation of Medical Images by Using Marker-Controlled Watershed Transformation Algorithm, XAI, and ML

Identification and Segmentation of Medical Images by Using Marker-Controlled Watershed Transformation Algorithm, XAI, and ML

Tahamina Yesmin (Haldia Institute of Management, India) and Pinaki Pratim Acharjya (Haldia Institute of Technology, India)
Copyright: © 2023 |Pages: 19
DOI: 10.4018/978-1-6684-7524-9.ch003
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

To make human life easy and compact, XAI has developed a lot with more innovations and contributed its own share. To make a suitable treatment while diagnosed with brain tumour, one needs to classify the tumour and detect it in a proper way where the explained result is most important. With the help of different analysis processes where marker-based approaches can help in proper segmentation and noise reduction analysis, numerous imaging modalities exist for tumour detection that are utilized to identify tumours in the brain. One of the most important issues of XAI system is medical diagnosis through ML in medical image processing. In this chapter, the authors present a modified marker-controlled watershed transformation approach to detect brain tumour with XAI and machine learning approaches. They include CNN and data augmentation algorithms. Image pre-processing takes the main area to detect and diagnose disease and diagnose properly. The statistical measurements have been introduced to get the mathematical abstractions of different approaches for result analysis.
Chapter Preview
Top

Literature Review

J. Welina, et.al, (2022), Introduce a XAI in an indispensable component while implementing AI as clinical equipment’s on medical care related works. This paper explains some doubtful questions related to field ML and existing XAI methods by conducting clinical requirements ground and systematic evaluation to answers the questions with clinical image explanations and computational works. Author proposed XAI algorithm on brain tumor. This work sheds light into the reducing of risk factors lies of directly applying XAI methods on some models (Jin, W., et.al 2022).

H.M. Das, et.al, (2022), presents an overview of XAI which is used in deep learning based medical analysis. More 220 papers on medical image analysis XAI techniques has surveyed and a framework of XAI criteria is introduced and categorized according to the framework and anatomical location. Mainly the paper focused on current critique on XAI, evaluation of XAI and future perspective of XAI (Bas, H.M., et.al, 2022).

Suganyadevi, S., (2021), introduceda model clinical picture handling techniques and examination, basic data and cutting-edge approaches with profound learning. The paper presents research on clinical picture handling as well as to characterize and execute the key rules that are distinguished and tended to. Through CNN network model additionally the paper enlightened the present status of the craftsmanship in light of the new logical writing which might be valuable to radiologists around the world (Suganyadevi, S., 2021).

Complete Chapter List

Search this Book:
Reset