Navdeep Dahiya

Dr. Navdeep Dahiya

Georgia Institute of Technology, Atlanta, Georgia, USA
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 February 2019 in Medical Image Analysis
Verified
Journal Article
Closed access
HHHassan Al Hajj
Hassan Al Hajj
MLMathieu Lamard
Mathieu Lamard
PCPierre-Henri Conze
Pierre-Henri Conze
SRSoumali Roychowdhury
Soumali Roychowdhury
XHXiaowei Hu
Xiaowei Hu
GQGwenolé Quellec
Gwenolé Quellec

15 January 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Albert ComelliAlbert Comelli
Albert Comelli
Navdeep DahiyaNavdeep Dahiya
Navdeep Dahiya
Alessandro StefanoAlessandro Stefano
Alessandro Stefano
Federica VernuccioFederica Vernuccio
Federica Vernuccio
MPMarzia Portoghese
Marzia Portoghese
AYAnthony Yezzi
Anthony Yezzi
Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.

20 November 2020 in Biomedical Engineering Letters
Verified
Journal Article
Closed access
PDF file
Albert ComelliAlbert Comelli
Albert Comelli
Navdeep DahiyaNavdeep Dahiya
Navdeep Dahiya
Alessandro StefanoAlessandro Stefano
Alessandro Stefano
VBViviana Benfante
Viviana Benfante
GGGiovanni Gentile
Giovanni Gentile
Salvatore PastaSalvatore Pasta
Salvatore Pasta

9 August 2021 in Medical Physics
Verified
Journal Article
Closed access
PDF file
Navdeep DahiyaNavdeep Dahiya
Navdeep Dahiya
SASadegh R Alam
Sadegh R Alam
PZPengpeng Zhang
Pengpeng Zhang
SZSi‐Yuan Zhang
Si‐Yuan Zhang
TLTianfang Li
Tianfang Li
SNSaad Nadeem
Saad Nadeem

19 November 2020 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
Albert ComelliAlbert Comelli
Albert Comelli
CCClaudia Coronnello
Claudia Coronnello
Navdeep DahiyaNavdeep Dahiya
Navdeep Dahiya
Viviana BenfanteViviana Benfante
Viviana Benfante
Stefano PalmucciStefano Palmucci
Stefano Palmucci
Alessandro StefanoAlessandro Stefano
Alessandro Stefano
Background: The aim of this work is to identify an automatic, accurate, and fast deep learning segmentation approach, applied to the parenchyma, using a very small dataset of high-resolution computed tomography images of patients with idiopathic pulmonary fibrosis. In this way, we aim to enhance the methodology performed by healthcare operators in radiomics studies where operator-independent segmentation methods must be used to correctly identify the target and, consequently, the texture-based prediction model. Methods: Two deep learning models were investigated: (i) U-Net, already used in many biomedical image segmentation tasks, and (ii) E-Net, used for image segmentation tasks in self-driving cars, where hardware availability is limited and accurate segmentation is critical for user safety. Our small image dataset is composed of 42 studies of patients with idiopathic pulmonary fibrosis, of which only 32 were used for the training phase. We compared the performance of the two models in terms of the similarity of their segmentation outcome with the gold standard and in terms of their resources’ requirements. Results: E-Net can be used to obtain accurate (dice similarity coefficient = 95.90%), fast (20.32 s), and clinically acceptable segmentation of the lung region. Conclusions: We demonstrated that deep learning models can be efficiently applied to rapidly segment and quantify the parenchyma of patients with pulmonary fibrosis, without any radiologist supervision, in order to produce user-independent results.

7 March 2019 in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Verified
Journal Article
Closed access
Navdeep DahiyaNavdeep Dahiya
Navdeep Dahiya
AYA. Yezzi
A. Yezzi
MPM. Piccinelli
M. Piccinelli
EGE. Garcia
E. Garcia
Segmentation of epicardial and endocardial boundaries is a critical step in diagnosing cardiovascular function in heart patients. The manual tracing of organ contours in computed tomography angiography (CTA) slices is subjective, time-consuming and impractical in clinical setting. We propose a novel multidimensional automatic edge detection algorithm based on shape priors and principal component analysis (PCA). We have developed a highly customised parametric model for implicit representations of segmenting curves (3D) for left ventricle (LV), right ventricle (RV) and epicardium (Epi) used simultaneously to achieve myocardial segmentation. We have combined these representations in a region-based image modelling framework with high-level constraints enabling the modelling of complex cardiac anatomical structures to automatically guide the segmentation of endo/epicardial boundaries. Test results on 30 short-axis CTA datasets show robust segmentation with error (mean ±std mm) of (1.46 ±0.41), (2.06 ±0.65) and (2.88 ±0.59) for LV, RV and Epi, respectively.