Multi-scale dyadic filter modulation based enhancement and classification of medical images
- PDF / 2,983,083 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 7 Downloads / 142 Views
Multi-scale dyadic filter modulation based enhancement and classification of medical images Ankit Vidyarthi 1 Received: 31 May 2019 / Revised: 28 June 2020 / Accepted: 13 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
For the last many decades, the research is towards the classification of medical images in the early phase of its detection. But, the task becomes challenging due to the absence of the color information, like in natural scene images, and low illumination. In this paper, a multiscale spectral approach is proposed for the classification of medical images. The proposed approach uses a dyadic filter bank extended to six scales for simultaneous modulation of the frequency and amplitude signal of the medical image. The modulated signal strength is used for enhancing the contrast of the image as a preprocessing step. The 32 bin spectral histogram is used to fetch the features using different modulation components at each scale of the dyadic filter bank. The proposed method has experimented with two medical imaging databases - one is malignant Brain tumor MRI scans collected from SMS medical college Jaipur. The second database is from the TCIA data repository having three datasets of LungCT and Brain MRI. These datasets have experimented with SVM using a quadratic kernel function. The experimental results show that the proposed approach fetches better textural information as compared with traditional texture analysis methods. Based on the analysis of the experimentation results, it is recommended that the use of the spectral features gives better early detection of the abnormalities for medical imaging datasets. Keywords Filter bank . Image enhancement . Amplitude- Frequency modulation . Medical imaging . Classification
1 Introduction Image classification is one of the promising areas of research to provide the most appropriate label to unseen samples. This becomes even more complex and challenging when working
* Ankit Vidyarthi [email protected]
1
Department of Computer Science Engineering & Information Technology, Jaypee Institute of Information Technology, Noida, Uttar Pradesh 201309, India
Multimedia Tools and Applications
with medical images having low illumination like MRI, CT scan, Ultrasound, and X-ray images. In addition, the absence of color information results in a challenge for visual analytics in medical images. In multi-class classification problems of medical images, the extraction of features from low illuminated images is a field of research. Due to the absence of color parameter, irregular shape, size, and location of the abnormality region; literature suggests the use of texture analysis for feature extraction. But the analysis of the texture information becomes complicated due to low illumination. Various theories in texture analysis found the use of enhancement of the medical images as a pre-processing step for texture feature extraction. Image enhancement is one of the pre-processing steps where the quality of the image is impr
Data Loading...
