N
Nikhil Kumar Tomar
Publications - 14
Citations - 308
Nikhil Kumar Tomar is an academic researcher. The author has contributed to research in topics: Segmentation & Deep learning. The author has an hindex of 3, co-authored 14 publications receiving 65 citations.
Papers
More filters
Journal ArticleDOI
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
Debesh Jha,Sharib Ali,Nikhil Kumar Tomar,Håvard D. Johansen,Dag Johansen,Jens Rittscher,Michael Riegler,Pål Halvorsen +7 more
TL;DR: A comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimise miss-detection rates.
Book ChapterDOI
DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation
Nikhil Kumar Tomar,Debesh Jha,Sharib Ali,Håvard D. Johansen,Dag Johansen,Michael Riegler,Pål Halvorsen +6 more
TL;DR: In this paper, a dual decoder attention network was proposed for segmentation of colorectal polyps, which achieved a dice coefficient of 0.7874, mIoU 0.7010, recall 0.7987, and precision of precision 0.8577, demonstrating the generalization ability of the model.
Posted Content
FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation.
Nikhil Kumar Tomar,Debesh Jha,Michael Riegler,Håvard D. Johansen,Dag Johansen,Jens Rittscher,Pål Halvorsen,Sharib Ali +7 more
TL;DR: In this article, a novel architecture called feedback attention network (FANet) is proposed to unify the previous epoch mask with the feature map of the current training epoch, which is then used to provide a hard attention to the learnt feature maps at different convolutional layers.
Proceedings ArticleDOI
NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy
Debesh Jha,Nikhil Kumar Tomar,Sharib Ali,Michael Riegler,Håvard D. Johansen,Dag Johansen,Thomas de Lange,Pål Halvorsen +7 more
TL;DR: NanoNet as mentioned in this paper proposes a novel architecture for the segmentation of video capsule endoscopy and colonoscopy images, which allows real-time performance and has higher segmentation accuracy compared to other more complex ones.
Proceedings ArticleDOI
Exploring Deep Learning Methods for Real-Time Surgical Instrument Segmentation in Laparoscopy
Debesh Jha,Sharib Ali,Nikhil Kumar Tomar,Michael Riegler,Dag Johansen,Håvard D. Johansen,Pål Halvorsen +6 more
TL;DR: In this paper, a dual decoder attention network (DDANet) was proposed for the automated segmentation of surgical instruments in laparoscopy, which achieved a dice coefficient of 0.8739 and mean intersection over union of 1.8183 for the Robust Medical Instrument Segmentation (ROBUST-MIS) Challenge 2019 dataset.