Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44929

ADVANCED LOGISTIC REGRESSION FOR DETECTING THE BRAIN TUMOUR CELLS

KOWSHIKA A, SHOBANA M, KAVITHA M S

Abstract

A single person's brain MRI scan will often include many slices spanning the 3D anatomical image. Accordingly, brain tumour segmentation from MR images is a difficult and time-consuming manual process. Additionally, avoiding biopsy and facilitating a more secure diagnosis, automated brain tumour categorization using an MRI scan is non-invasive. Researchers have put in a lot of time and energy since the turn of the millennium and the late '90s to develop a system for automatically segmenting and classifying brain tumours. Therefore, there is a wealth of literature on the topic, much of it devoted to various approaches to segmentation such as region growth, conventional machine learning, and deep learning. In a similar vein, other tasks involving brain tumour classification by histological type have been carried out, with outstanding performance outcomes produced. Noise is removed and colour is removed from the MRI pictures before they are converted to grayscale. Finally, a logistic regression is utilised for determining the types for testing images, with a success rate of 98%. This proposed scheme is provided for getting the stroke and tumour cells in details without any noise.

Keywords

Logistic Regression, Machine Learning, Artificial intelligence, Two Models, True positive

Full Text

PDF

References

?>