Eben Sophia Paul
@karunya.edu
Assistant Professor
Karunya Deemed University
EDUCATION
Ph. D - Medical image processing
RESEARCH INTERESTS
Medical image processing
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Michel Ashick A, Eben Sophia P, Stewart Kirubakaran S, and Narmadha D
IEEE
This work uses machine learning to predict how well metal oxide nanoparticles (MONPs) will deliver anticancer medications in a novel attempt to transform nanomedicine. In order to determine the ideal metal oxide nanoparticles (MONPs) for efficient anticancer drug delivery, this project explores a variety of machine learning techniques. Using an extensive dataset that includes toxicity profiles, drug transport efficiency assessments, and MONP physicochemical properties, the research examines the predictive power of many machine learning techniques. By means of rigorous validation procedures and careful experimentation, the research aims to identify the most effective models for precisely forecasting the optimal MONPs for anticancer medication delivery. Through comparative evaluations of several algorithms, the study seeks to offer important insights into the best methods for this crucial application. The results of this study have the potential to significantly advance the area of nanomedicine by enabling the logical design and selection of MONPs for enhanced anticancer drug delivery, thereby contributing to the ongoing efforts in combating cancer with precision and efficacy.
J. Anitha, P. Eben Sophia, Le Hoang Son, and Victor Hugo C. de Albuquerque
Elsevier BV
P. Eben Sophia and J. Anitha
Inderscience Publishers
J. Anitha, P. Eben Sophia, and D. Jude Hemanth
Springer Singapore
Paul Eben Sophia and Jude Anitha
Informa UK Limited
ABSTRACT Context-based compression plays a vital role in digital communication systems, since a particular region alone can be preserved using high bit rate and the other regions can be compressed using low bit rate compressions. Such methods are of great interest in tele-radiology applications requiring large storage. This paper presents an enhanced method for compression of medical images using wavelet transformation, normalization, and prediction. The compression method can be tuned to reproduce a good quality image close to the original image for the selected contextual area. Initially, the image undergoes 2D wavelet transform to obtain the approximate and the detailed coefficients. To ease the process of prediction, normalization is done for each sub-band separately, followed by mask-based prediction of the normalized coefficients. Finally, the prediction error coefficients are entropy-encoded using arithmetic coding technique. The proposed algorithm utilizes prediction as well as transformation to achieve a better compression along with good quality. The performance of the proposed system is compared with JPEG2000 and other conventional and contextual compression algorithms. The results show better performance quantitatively and visually.
P. Eben Sophia and J. Anitha
Wiley
Contextual compression is an essential part of any medical image compression since it facilitates no loss of diagnostic information. Although there are many techniques available for contextual image compression still there is a need for developing an efficient and optimized technique which would produce good quality images at lower bit rates. This article presents an efficient contextual compression algorithm using wavelet and contourlet transforms to capture the fine details of the image, along with directional information to produce good quality at high Compression Ratio (CR). The 2D discrete wavelet transform, which uses the simplest Daubechies wavelets, db1, or haar wavelet, is chosen and used to get the subband coefficients. The approximate coefficients of the higher subbands undergo contourlet transform employing length N ladder filters for capturing the directional information of the subbands at different scale and orientations. An optimized approach is used for predicting the quantized and the normalized subband coefficients resulting in improved compression performance. The proposed contextual compression approach was evaluated for its performance in terms of CR, Peak Signal to Noise Ratio, Feature SIMilarity index, Structure SIMilarity Index, and Universal quality (Q) after reconstruction. The results clarify the efficiency of the proposed method over other compression techniques.
P. Eben Sophia and J. Anitha
IOS Press
Low bit rate compression approach has been proposed for easy transmission of medical image from one place to another. Contourlet transform technique is used for obtaining multi directional subbands and for capturing the fine details of the image. Transformed coefficients are then normalized using a mathematical approach for each subbands, followed by quantization and encoding. Arithmetic coding techniques are used for entropy encoding. Experimental results shows that the visual quality as well as the compression ratio of the reconstructed image is high compared to the existing wavelet based compression technique at low bit rates. Contextual compression is well supported for such conditions where the unwanted regions are compressed lossy, but with good visual quality. The result of the proposed method shows better compression performance with good visual quality at low bit rates.
P. Eben Sophia and J. Anitha
Springer Singapore
P. Eben Sophia and J. Anitha
Inderscience Publishers
Transmission of medical images from one place to another is an important part of telemedicine applications. Raw medical images take huge time for transmission which makes telemedicine process tedious and impractical. When subjected to compression either there will be a loss of data or size will not be reduced much. One way to overcome this problem is to allow some loss of data so that the size is reduced and also diagnostically important parts remains unaffected. This is the process behind region-based compression. Critical analysis has been done on the advances in the compression techniques developed till now and their perspectives in the field of telemedicine. Emphasis is laid on region-based compression a technique which paves the way for efficient and effective compression of medical images. The review also covers the scope of future research along with suitable solution to improve the performance of compression algorithms for telemedicine.
P. Eben Sophia and J. Anitha
IEEE
There is an increasing demand for transmitting medical images for telemedicine application. These medical images are rich in radiological information and the file sizes associated with it are also large. Medical images such as MRI (Magnetic Resonance Imaging) produce human body pictures in digital form and they produce excessive amount of data. So compression is necessary for storage and transmission purpose. Image compression enhances the performance of any digital system by reducing the time and cost with or without reduction in image quality. The algorithms used in this paper utilize Region Of Interest (ROI) based compression which again increases the compression ratio compared to the traditional block based methods. The results of 3 different classical algorithms with and without ROI are compared and the results are reported. ROI is coded with good fidelity than NROI and also incorporates progressive transmission. Distortion rates and compression rates are evaluated for all images and the results are compared.
D. Jackuline Moni and P. Eben Sophia
IEEE
A configurable multiplier optimized for low power and high speed operations and which can be configured either for single 16-bit multiplication operation, single 8-bit multiplication or twin parallel 8-bit multiplication is designed. The output product can be truncated to further decrease power consumption and increase speed by sacrificing a bit of output precision. Furthermore, the proposed multiplier maintains an acceptable output quality with enough accuracy when truncation is performed. Thus it provides a flexible arithmetic capacity and a tradeoff between output precision and power consumption. The approach also dynamically detects the input range of multipliers and disables the switching operation of the non effective ranges. Thus the ineffective circuitry can be efficiently deactivated, thereby reducing power consumption and increasing the speed of operation. Thus the proposed multiplier outperforms the conventional multiplier in terms of power and speed efficiencies.
RECENT SCHOLAR PUBLICATIONS
MOST CITED SCHOLAR PUBLICATIONS
Publications
1. P. Eben Sophia, J. Anitha. (2019) “Performance enhanced Ripplet transform based compression method for medical images”, Journal of the International Measurement Confederation, DOI: 10.1016/j.. [Impact factor: 5.13]
2. P. Eben Sophia, J. Anitha. (2017) “A hybrid contextual compression technique using wavelet and contourlet transforms with PSO optimized prediction”, International journal of imaging systems and technology. DOI: 10.1002/ [Impact factor: 2.2]
3. P. Eben Sophia, J. Anitha. (2017) “Contextual MRI image compression using normalized Wavelet-transform coefficients and prediction”, IETE Journal of Research. DOI 10.1080/03772063.2017.1309998. [Impact factor: 1.877]
4. P. Eben Sophia, J. Anitha. (2016) “Contourlet transform based sub-band normalization for region based medical image compression” Intelligent Decision Technologies, Vol. 1, Preprint: 1-7. DOI 10.3233/IDT-160265. [Scopus Indexed]
5. P. Eben Sophia, J. Anitha. (2016) “Enhanced method of using contourlet transform for Medical image compression”, International Journal of Advanced Intelligence Paradigms, Accepted. [Scopus Indexed]
6. P. Eben Sophia, J. Anitha. (2015) “A systematic review on advances and perspectives of image compression in telemedicine” International Journal of Advanced Intelligence Paradigms, 7(2), 136-155. [Scopus Indexed]
INDUSTRY EXPERIENCE
1.5 years