A
Abhijit Guha Roy
Researcher at Ludwig Maximilian University of Munich
Publications - 63
Citations - 3018
Abhijit Guha Roy is an academic researcher from Ludwig Maximilian University of Munich. The author has contributed to research in topics: Segmentation & Convolutional neural network. The author has an hindex of 20, co-authored 58 publications receiving 1708 citations. Previous affiliations of Abhijit Guha Roy include Indian Institute of Technology Kharagpur & Technische Universität München.
Papers
More filters
Journal ArticleDOI
ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks.
Abhijit Guha Roy,Sailesh Conjeti,Sri Phani Krishna Karri,Debdoot Sheet,Amin Katouzian,Christian Wachinger,Nassir Navab +6 more
TL;DR: A new fully convolutional deep architecture, termed ReLayNet, is proposed for end-to-end segmentation of retinal layers and fluid masses in eye OCT scans, validated on a publicly available benchmark dataset with comparisons against five state-of-the-art segmentation methods.
Book ChapterDOI
Concurrent Spatial and Channel ‘Squeeze & Excitation’ in Fully Convolutional Networks
TL;DR: In this paper, three variants of squeeze and excitation (SE) modules are introduced for image segmentation, i.e., squeezing spatially and exciting channel-wise (cSE), squeezing channelwise and exciting spatially (sSE), and concurrent spatial and channel squeeze & excitation(scSE).
Journal ArticleDOI
Recalibrating Fully Convolutional Networks With Spatial and Channel “Squeeze and Excitation” Blocks
TL;DR: This paper effectively incorporate the recently proposed “squeeze and excitation” (SE) modules for channel recalibration for image classification in three state-of-the-art F-CNNs and demonstrates a consistent improvement of segmentation accuracy on three challenging benchmark datasets.
Posted Content
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks
TL;DR: This paper introduces three variants of SE modules for image segmentation, and effectively incorporates these SE modules within three different state-of-the-art F-CNNs (DenseNet, SD-Net, U-Net) and observes consistent improvement of performance across all architectures, while minimally effecting model complexity.
Journal ArticleDOI
QuickNAT: A fully convolutional network for quick and accurate segmentation of neuroanatomy.
Abhijit Guha Roy,Sailesh Conjeti,Sailesh Conjeti,Nassir Navab,Nassir Navab,Christian Wachinger,Alzheimer’s Disease Neuroimaging Initiative +6 more
TL;DR: QuickNAT, a fully convolutional, densely connected neural network that segments a MRI brain scan in 20 s, is introduced and achieves superior segmentation accuracy and reliability in comparison to state‐of‐the‐art methods, while being orders of magnitude faster.