Welcome


I am Research Scholar in the Department of Computer Science & Engineering, Indian Institute of Technology Roorkee, INDIA supervised by Prof. Balasubramanian Raman.


Research Interests
  1. Biomedical Image Processing
  2. Computer Vision
  3. Machine Learning
  4. Deep Learning

Following my interests, I tries to work in the domain of Breast (mammograms and sonograms) lesions delineation and classification that could bring betterment in the lives of women. Breast cancer is the second most deadly disease across womanhood. It is one of the growing fields of medical image analysis which stresses upon the automatic recognition of breast lumps and cysts. 
Various modalities have been adapted to diagnose and analyse breast lesions. Mammograms, Ultrasound (sonograms), PET/CT images and MRI are some of such droplets from a big sea of medical image categories.


Medical Image Segmentation

Image segmentation is a commonly used technique in digital image processing and analysis to partition an image into multiple parts or regions, often based on the characteristics of the pixels in the image. Image segmentation could involve separating foreground from background, or clustering regions of pixels based on similarities in color or shape. It is the most fundamental process which could be applied to an image. The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Therefore, segmenting an image into its representative objects is assumed to be the initial step.


Medical Image Classification

Image Classification refers to a process in computer vision that can classify an image according to its visual content. It is considered as an important step in automatic lesion delineation processes. It refers to the task of seamlessly extracting the objects from the visual raster image. When followed by segmentation, it proves to be an advantage for CAD. In the case of breast lesion classification, only two class classification can be taken care of. But in special cases BIRADS (Breast Imaging-Reporting and Data System)classification system is also followed. Explained below is the two most cancerous carcinoma's that occur in the form of benign and malignant breast cancers types in women.


Research Publications
  • Ridhi Arora and Balasubramanian Raman, A Deep Neural CNN Model with CRF for Breast Mass Segmentation in Mammograms, Accepted for publication in the 29th European Signal Processing Conference (EUSIPCO 2021) , May 2021, Dublin, Ireland. [Accepted]
  • Rishabh Mamgain, Balasubramanian Raman and Ridhi Arora, Re-calibrated Attention-based Deep Learning Technique for Dermoscopic Lesion Segmentation, 9th International Conference on Pattern Recognition and Machine Intelligence (PReMI 2021), 2021. [Communicated]
  • Ridhi Arora, Balasubramanian Raman, Kritagya Nayyar and Ruchi Awasthi, Automated Skin Lesion Segmentation using Attention-based Deep Convolutional Neural Network, Biomedical Signal Processing & Control (Elsevier),Vol. 65, 102358, 2021. [Published]
  • Ridhi Arora and Balasubramanian Raman, BUS-Net: Breast Tumor Detection Network for Ultrasound Images using Bi-directional ConvLSTM and Dense Residual Connections, Journal of Digital Imaging (Springer), 2021. [Communicated]
  • Ridhi Arora and Balasubramanian Raman, Deep Feature Extraction and Feature Fusion for the Region of Interest in Breast Histopathology, IEEE Journal of Biomedical and Health Informatics, 2021. [Under Review]
  • Ridhi Arora, Prateek Kumar Rai and Balasubramanian Raman, Deep Feature–based Automatic Classification of Mammograms, Medical & Biological Engineering & Computing (Springer), Vol. 58, No. 6, pp. 1199-1211, 2020. [Published]
  • Rahul Kumar, Ridhi Arora, Vipul Bansal, Vinodh J Sahayasheela, Himanshu Buckchash, Javed Imran, Narayanan Narayanan, Ganesh N Pandian and Balasubramanian Raman, Accurate prediction of COVID-19 using chest X-ray images through deep feature learning model with SMOTE and machine learning classifiers, medRxiv, 2020. [Preprint]
  • Ridhi Arora, Vipul Bansal, Himanshu Buckchash, Rahul Kumar, Vinodh J Sahayasheela, Narayanan Narayanan, Ganesh N Pandian and Balasubramanian Raman, AI-based Diagnosis of COVID-19 Patients Using X-ray Scans with Stochastic Ensemble of CNNs, TechRxiv, 2020. [Preprint]

Awards and Recognition
  • Registration support from CSE Department, IIT Roorkee to present my work entitled "A Deep Neural CNN Model with CRF for Breast Mass Segmentation in Mammograms" in the 29th European Signal Processing Conference (EUSIPCO 2021), Dublin, Ireland.  
  • Cleared Japanese Language Course for beginners at Indian Technology Roorkee (IITR).
  • Travel support from CSE Department, IIT Roorkee to attend the 11th Indian Conference on ‘Computer Vision, Graphics and Image Processing’ (ICVGIP 2018) at IIIT Hyderabad, India in December 2018. 
  • Receiving PhD scholarship by Ministry of Human Resource and Development (MHRD), Government of INDIA, (March 2017 - till date).
  • Received Rs. 72000 annually as TEQIP Scholarship in Masters.
  • Qualified Graduate Aptitude Test in Engineering (GATE 2016) conducted at the national level in India.
  • Qualified Haryana Teacher Eligibility Test (HTET 2016).
  • Secured 2nd position (SILVER MEDAL) in ALL INDIA SCIENCE OLYMPIAD.


Breast Mass Dataset (mammogram and sonogram)

To access the dataset, feel free to contact me at: rarora[AT]cs[DOT]iitr[DOT]ac[DOT]in