Faculty Profile

About

Dr H N Suma is the Professor in the Department of Medical Electronics, BMSCE, Bangalore. She heads CIME (Center for Innovation in Medical Electronics). She is the Member of BOG, BMSCE. CEO of Center for Innovation, Incubation & Entrepreneurship (CIIE) and also Chief coordinator for Student satellite Project, BMSCE. She holds a UG Degree in Electronics & Communication from MCE, Hassan. Her PG Degree is in Bio-Medical Instrumentation from SJCE, Mysore. She holds a PhD from Mysore University. Her PhD thesis title was “Pattern Recognition Techniques for Regionalizing the Activity Patterns of the Human Brain using functional Magnetic Resonance Imaging (fMRI) data”. She has 30 publications to her credit in international and national journals and conferences. She has undertaken collaborative projects with National & International Institutions/ Hospitals: Biomedical Engineering school-Stanford University, FOETH-Oxford University, IISc, KIMSH, Raman Research Institute, NIMHANS to name a few. She has executed two funded projects and a consultancy project with FOETH-Oxford University. She is the Principal Investigator for two funded projects from DST (Development of portable digital X-Ray machine) and VGST and a consultancy project (Development of an automated ophthalmic KIOSK) in collaboration with NTU and TTSH, Singapore. Her Research Interests are: Medical Imaging, Brain Mapping, Brain Warping, Neural Networks and Pattern recognition.

Education

• Ph D - Neoroimaging - Medical Image processing
  Mysore University
  Passed Year: 2010 | Program Type: PartTime
• M Tech - Biomedical Instrumentation
  Mysore University
  Passed Year: 1994 | Program Type: FullTime
• B E - Electronics & Communication
  Mysore University
  Passed Year: 1988 | Program Type: FullTime

Selected Publications

• Journal | Published On : 18-04-2019
  S Guruprasad, MZ Kurian, HN Suma
  "PROBABILITY RANDOM INDEX BASED CLUSTERING FOR SEGMENTATION OF PET-CT IMAGES", Biomedical Engineering: Applications, Basis and Communications Abstract:Medical image segmentation is a vital process in medical diagnosis and evaluation of tumor response to therapy. Current segmentation methods works only on single modality image like positron emission tomography has low resolution and gives only functional information; Computed Tomography has low contrast and provides structural information. This paper focus on segmentation of multimodality PET-CT image. In recent days PET-CT is advanced multimodal imaging equipment, which gives both functional and anatomical information in a single image. Probability random index is a new methodology adopted to segment the portion of an image, which is most essential for determining the actual intricacies involved in the portion of a body. The clustering is another methodology used to group similar pixel locations into a single group based on unpredictable random values of an image.
  Weblink
• Conference | Published On : 08-07-2018
  Deepthi Badarinath, S Chaitra, Neha Bharill, Muhammad Tanveer, Mukesh Prasad, HN Suma, Abhishek M Appaji, Anand Vinekar
  "Study of Clinical Staging and Classification of Retinal Images for Retinopathy of Prematurity (ROP) Screening", International Joint Conference on Neural Networks (IJCNN) Abstract: Retinopathy of Prematurity (ROP) is a disease which requires immediate precautionary measures to prevent blindness in the infants, and this condition is prevalent in premature babies in all the underdeveloped, developing, and in the developed countries as well. This paper proposes a tool by which the stage and zones of Retinopathy of Prematurity in infants can be diagnosed easily. This tool takes the input from the Retcam and detects the stage, zone, and gives a rating of 1 to 9 for classifying the severity of the disease in the infants. This is achieved by extracting the optic disc, marking the ridge, and the distance of the optic nerve. This tool can be easily used by nurses and paramedics, unlike the existing technologies which require the guidance of a specialist to come to a conclusion.
  Weblink
• Conference | Published On : 14-12-2015
  S Guruprasad, MZ Kurian, HN Suma
  "Fusion of CT and PET medical images using hybrid algorithm DWT-DCT-PCA", 2nd International Conference on Information Science and Security (ICISS) Abstract:The successful diagnosis of a disease depends on the accuracy of the image obtained from medical imaging modalities. Medical image fusion acts as a 'life saving tool'-thus it has emerged as a promising research field in recent years. The objective of medical imaging is to acquire a high resolution image with more information for the sake of diagnostic purposes. This paper proposes a hybrid fusion algorithm for multimodality medical images. There are two type of modalities one is 'Anatomy', which gives structural details of body parts, such as X-ray, CT, MRI, and other 'Physiology and Metabolism', it gives the information about functional details of cell activity in the organ, such as SPECT, PET. Structure without function is a corpse and function without structure is a ghost. Therefore, both of the Anatomy, Physiology and Metabolism images are investigated. So, this work makes fusion of CT and PET images
  Weblink
• Conference | Published On : 12-06-2015
  I V Accamma, H N Suma, M Dakshayini
  "A Genetic algorithm based feature selection technique for classification of multiple-subject fMRI data", IEEE International Advance Computing Conference (IACC) Abstract: Functional Magnetic Resonance Imaging (fMRI) is a neuroimaging technique used to capture images of brain activity. These images have high spatial resolution and hence are very high dimensional. Each scan consists of more than one hundred thousand voxels. All of the scanned voxels are not activated for every stimulus. Therefore, finding the informative voxels with respect to stimulus becomes a prerequisite for any machine learning solution using fMRI data. The specific problem attempted to be solved in this paper is that of decoding cognitive states from multiple-subject fMRI data. Decoding multiple-subject data is challenging owing to the difference in the shape and size of the brain of different subjects. A Genetic algorithm based technique is proposed here for selection of voxels that capture commonality across subjects. Some popular feature selection techniques are compared against Genetic algorithms.
  Weblink
• Journal | Published On : 05-11-2007
  H N Suma, S Murali
  "Principal Component Analysis for Analysis and Classification of fMRI Activation Maps", IJCSNS International Journal of Computer Science and Network Security, VOL.7 No.11, November 2007. Abstract:Principal Component Analysis (PCA) a standard method for creating uncorrelated variables from best-fitting linear combinations of the variables in the raw depth data extracted using Statistical Parametric mapping (SPM). This approach is equivalent to finding an orthogonal basis such that the projection onto each successive vector (or\“principal component”) is of maximal variance (and uncorrelated with each previous vector). The templates comprising of principal components represent individual activity. These are then fed to the back propagation training algorithm. The trained network is capable of classifying the test pattern into the corresponding defined class.
  Weblink

Other Information

Convener: CIME (Center for Innovation in Medical Electronics).
Chief Convener: Center for Innovation, Incubation & Entrepreneurship (CIIE)
Programme Director and SPOC: Student satellite Project, BMSCE
TT Board Representation: Melton Foundation, BMSCE
Ex- Member of BOG, BMSCE.
Member of Academic Council, SIT, Tumkur
Member of Academic Council, DSCE, Bangalore
Member of BOS, Dr AIT, Bangalore
Chairman Library committee, BMSCE
Doctoral committee member - NIMHANS, Bangalore
Doctoral committee member - BNMIT, Bangalore
Doctoral committee member - UVCE, Bangalore

Download Resume