Suman Sedai

Suman Sedai

Auto-generated profile, based on publicly available information

Suman Sedai

IBM Research - Australia

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2018
Verified
Conference Paper
Closed access
DMDwarikanath Mahapatra
Dwarikanath Mahapatra
BABhavna Josephine Antony
Bhavna Josephine Antony
SSSuman Sedai
Suman Sedai
RGRahil Garnavi
Rahil Garnavi
Conventional approaches to image registration consist of time consuming iterative methods. Most current deep learning (DL) based registration methods extract deep features to use in an iterative setting. We propose an end-to-end DL method for registering multimodal images. Our approach uses generative adversarial networks (GANs) that eliminates the need for time consuming iterative methods, and directly generates the registered image with the deformation field. Appropriate constraints in the GAN cost function produce accurately registered images in less than a second. Experiments demonstrate their accuracy for multimodal retinal and cardiac MR image registration.

10 October 2019
Verified
Book Chapter
Closed access
PDF file
SSSuman Sedai
Suman Sedai
BABhavna Josephine Antony
Bhavna Josephine Antony
RRRavneet Rai
Ravneet Rai
KJKatie Jones
Katie Jones
HIHiroshi Ishikawa
Hiroshi Ishikawa
RGRahil Garnavi
Rahil Garnavi

4 September 2017
Verified
Book Chapter
Closed access
PDF file
SSSuman Sedai
Suman Sedai
DMDwarikanath Mahapatra
Dwarikanath Mahapatra
SHSajini Hewavitharanage
Sajini Hewavitharanage
SMStefan Maetschke
Stefan Maetschke
RGRahil Garnavi
Rahil Garnavi

14 September 2018
Verified
Book Chapter
Closed access
PDF file
SSSuman Sedai
Suman Sedai
BABhavna Josephine Antony
Bhavna Josephine Antony
DMDwarikanath Mahapatra
Dwarikanath Mahapatra
RGRahil Garnavi
Rahil Garnavi

1 July 2017 in IBM Journal of Research and Development
Verified
Journal Article
Closed access
BBB. Bozorgtabar
B. Bozorgtabar
SSS. Sedai
S. Sedai
PRP. K. Roy
P. K. Roy
RGR. Garnavi
R. Garnavi

1 April 2017
Verified
Conference Paper
Closed access
SSSuman Sedai
Suman Sedai
RTRuwan Tennakoon
Ruwan Tennakoon
PRPallab Roy
Pallab Roy
KCKhoa Cao
Khoa Cao
RGRahil Garnavi
Rahil Garnavi
The fovea is one of the most important anatomical landmarks in the eye and its localization is required in automated analysis of retinal diseases due to its role in sharp central vision. In this paper, we propose a two-stage deep learning framework for accurate segmentation of the fovea in retinal colour fundus images. In the first stage, coarse segmentation is performed to localize the fovea in the fundus image. The location information from the first stage is then used to perform fine-grained segmentation of the fovea region in the second stage. The proposed method performs end-to-end pixelwise segmentation by creating a deep learning model based on fully convolutional neural networks, which does not require the prior knowledge of the location of other retinal structures such as optic disc (OD) and vasculature geometry. We demonstrate the effectiveness of our method on a dataset with 400 retinal images with average localization error of 14 ± 7 pixels.