2. INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 2
Name of the Candidate : A S Hepsi Ajibah
Reference No. : 22141550
Affiliation (for PT Scholars) : GKM college of Engineering and Technology,
Chennai
Name of the Proposed Supervisor : Dr. Heltin Genitha C
Affiliation : St, Joseph’s college of Engineering,
Chennai
3. INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 3
Sl.No. Degree Specialisation
University/
Institute
Year of
Passing
Marks
(%/CGPA)
1 B.E Computer Science
Tagore Engineering
college,
Rathinamanagalam.
2016 6.8 CGPA
2 M.E Computer Science
Valliammai
Engineering college,
Kattamgalathur.
2018 8.01 CGPA
4. INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 4
Sl.
No.
Designation Organisation From To
Years of
Experience
1
Assistant
Professor
GKM college of
Engineering and
Technology
20-09-21
Till
date
Total Years of Experience – Nil
5. INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 5
Sl.
No.
Title of the
Paper
Authors
Name of the
Journal
Year,Volume,
Issue
Impact Factor as
per Clarivites
1
Remote
monitoring of
power quality
analyzer using
cost effective
webserver
module.
A S Hepsi Ajibah,
Chenthamarai
Selvam,
Hijo Joy,
B Vanathi
International
journal of
innovative
research in
computer and
communication
engineering.
2018, Volume 6,
Issue 3
Note: Papers published till 30.11.2021 only will be considered
6. Nowadays skin lesions have several anatomical and causative factors, which are associated with numerous skin-
related pigmentary disorders
To make the diagnosis easier and accurate the computer aided diagnosis system(CAD) is used.
CAD uses Deep Learning algorithms to forecast the illness from dermatoscopic images improves the diagnosis
process to distinguish between the potential complications
a novel DL based model is used to summarize the characteristics of skin lesions and the status of image
technology, to predict the type of the lesion.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 6
7. The proposed research on CAD systems for Multiple skin disorder aims to:
Provide cost effective, safe and timely diagnosis of orthopedic diseases.
Collect the dataset from the clinical imaging tool dermatoscopy
Preprocess the image to increase the image quality by using enhanced filters for classification and
segmentation.
To detect the disease feature selection and extraction are the crucial steps.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 7
8. Author &Year Title Algorithms Used Advantages
Mohd Mohsin Ali
(2022)
An Automated and Efficient Deep
Learning based Classification of
Multiple Skin Disorders from Skin
Lesion Images
Neural Network Classifier
Having Multiple Numbers Of
Layers With Different
Functionalities
The experimental
consequences are encouraging
indicating a classification
accuracy of 98%, signifying
the possible use for much
computer-vision based similar
biomedical application.
Reza Ahmadi Mehr
Ali Ameri
(2022 DEC)
Skin Cancer Detection Based on Deep
Learning
deep convolutional neural
networks (CNNs) have
achieved excellent
performance in automated
skin cancer classification with
accuracy similar to that of
dermatologists.
On a dataset of 57536
dermoscopic images, the
proposed approach achieved
an accuracy of 89.3% in the
discrimination of 4 major skin
conditions and 94.5% in the
classification of benign vs.
malignant lesions.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION
8
9. Author &Year Title Aspect Covered Summary
Bin Zhang, Xue
Zhou,Yichen Luo, Hao
Zhang, HuayongYang, Jien
Ma & Liang Ma
Opportunities and Challenges:
Classification of Skin Disease
Based on Deep Learning
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 9
10. The preprocessing of medical images is not done with enhanced filters.
Explore the possibility of automatically extracting the lesion area for more detailed
classification is not present.
Two stage U-net strategy is used to segment and detect the disease.
The further refinement and accuracy is needed in delineating the disease without the
experienced surgeon’s help.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 10
11. To detect the orthopedic disease CAD uses ultrasound images, based on patient movement
and equipment restrictions, some artefacts make identification of these ultrasound pictures
problematic.
Some preprocessing approaches are required to increase image quality for classification and
segmentation while maintaining pixels of interest.
Initially input dataset is preprocessed using Enhanced Wiener filter and Butterworth filtering
methods for image denoising and image enhancement respectively
The data structure for classification is formed by these pixels, which includes image features.
As a result feature selection and extraction are the crucial step in the diagnostic system’s
categorization process.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 11
12. This proposes a three –stage image segmentation method using U-Net and Iterative Random
forest classifier(IFRC) for efficient detection of orthopedic diseases in Ultrasound images.
Feature extraction is performed by transform based analysis.
Using Principal component analysis, the resulting characteristics are finally decreased to
ideal subset.
Performance parameters such as accuracy, specificity, sensitivity and dice score of new
method will be compared with the traditional method.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 12
13. Image preprocessing steps divided into two processes.
To enhance the noise free image by using enhance wiener filter
To enhance frequency domain image using Butterworth filtering.
Then three stage segmentation strategy for ultrasonic images.
Feature extraction and feature selection process are analyzed using transformation based
analyzer and principal component analysis.
To classify the image by using Iterative Random Forest classifier(IFRC).
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 13
14. INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 14
Image
Dataset
Image
Preprocessing
Three stage
Segmentation
Feature Extraction
and Feature Selection
Classification
15. For first time we proposed a third stage segmentation strategy for ultrasonic
images, demonstrating that it outperforms a single stage U-Net by dividing the task
down into three smaller challenges.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 15
16. Vedpal Singh, Irraivan Elamvazuthi, Varun Jeoti, John George and Dileep Kumar, Universiti Teknologi Petronas, Bandar Seri Iskandar,
Perak Darul Ridzuan, Malaysia, Research Imaging Centre, University of Malaya, Malaysia, Computer aided diagnosis (cad) tool for the
analysis of calcaneofibular ligament using ultrasonographic images, ARPN Journal of Engineering and Applied Science, VOL. 11, NO.
14, JULY 2016.
Yang Guo and Chen Chen, First Affiliated Hospital of Xiamen University, Xiamen 361000, China Correspondence should be addressed
to Yang Guo; g20041116@xmu.edu.cn Received 9 September 2021; Revised 30 October 2021; Accepted 1 November 2021; Published
22 November 2021, An Orthopedic Auxiliary Diagnosis System Based on Image Recognition Technology.
Carlo V. Cannistraci, Franco M. Montevecchi and Massimo Alessio, Department of Mechanics, Politecnico di Torino, Turin, Italy
2CMP Group, Microsoft Research, Politecnico di Torino, Turin, Italy 3Proteome Biochemistry, San Raffaele Scientific Institute, Milan,
Italy, Median-modified Wiener filter provides efficient denoising, preserving spot edge and morphology in 2-DE image processing,
August 10, 2009.
Junying Chen, Feng Li, Yixuan Fu, Qun Liu, and Jiajun Huang Guangzhou Key Laboratory of Robotics and Intelligent Software School
of Software Engineering, South China University of Technology, A Study of Image Segmentation Algorithms Combined with Different
Image Preprocessing Methods for Thyroid Ultrasound Images.
Alexander Blankstein, Department of Orthopedics, Sheba Medical Center, University of Tel Aviv School of Medicine, 16 Kehilat Bavel
St., Ramat Hasharon 47322, Israel, Ultrasound in the diagnosis of clinical orthopedics: The orthopedic stethoscope, February 11,2016.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 16
17. Ultrasonic images of orthopedic disease
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 17