Mohammadreza Zandehshahvar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammadreza Zandehshahvar has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Ali Adibi
Georgia Institute of Technology
5 shared publications Yashar Kiarashi
Department of Biomedical Informatics, Emory School of Medicine, 100 Woodruff Circle, Atlanta, Georgia30322, United States
3 shared publicationsHossein Maleki
School of Electrical and Computer Engineering, Georgia Institute of Technology, 778 Atlantic Drive NW, Atlanta, Georgia 30332, United States
2 shared publicationsMuliang Zhu
School of Electrical and Computer Engineering, Georgia Institute of Technology, 778 Atlantic Drive NW, Atlanta, Georgia30332, United States
2 shared publicationsAli Adibi
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
1 shared publicationCarlo N. De Cecco
Emory University
1 shared publication
Latest Publications
- Open Access
- 10 December 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (5) , 3930-3941
Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
To reduce the amount of required labeled data for lung disease severity classification from chest X-rays (CXRs) under class imbalance, this study applied deep active learning with a Bayesian Neural Network (BNN) approximation and weighted loss function. This retrospective study collected 2319 CXRs from 963 patients (mean age, 59.2 ± 16.6 years; 481 females) at Emory Healthcare affiliated hospitals between January and November 2020. All patients had clinically confirmed COVID-19. Each CXR was independently labeled by 3 to 6 board-certified radiologists as normal, moderate, or severe. A deep neural network with Monte Carlo Dropout was trained using active learning to classify disease severity. Various acquisition functions were used to iteratively select the most informative samples from an unlabeled pool. Performance was evaluated using accuracy, area under the receiver operating characteristic curve (AU-ROC), and area under the precision-recall curve (AU-PRC). Training time and acquisition time were recorded. Statistical analysis included descriptive metrics and performance comparisons across acquisition strategies. Least Confidence achieved 92.8% accuracy (AU-ROC, 0.95) in binary classification (normal vs. diseased) using 9.24% of the training data. In the multi-class setting, Mean STD achieved 70.5% accuracy (AU-ROC, 0.85) using 21.87% of the labeled data. These methods outperformed more complex and computationally expensive acquisition functions and significantly reduced labeling needs. Deep active learning with BNN approximation and weighted loss effectively reduces labeled data requirements while addressing class imbalance, maintaining or exceeding diagnostic performance.
- 10 December 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (5) , 3930-3941
Open AccessDeep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
To reduce the amount of required labeled data for lung disease severity classification from chest X-rays (CXRs) under class imbalance, this study applied deep active learning with a Bayesian Neural Network (BNN) approximation and weighted loss function. This retrospective study collected 2319 CXRs from 963 patients (mean age, 59.2 ± 16.6 years; 481 females) at Emory Healthcare affiliated hospitals between January and November 2020. All patients had clinically confirmed COVID-19. Each CXR was independently labeled by 3 to 6 board-certified radiologists as normal, moderate, or severe. A deep neural network with Monte Carlo Dropout was trained using active learning to classify disease severity. Various acquisition functions were used to iteratively select the most informative samples from an unlabeled pool. Performance was evaluated using accuracy, area under the receiver operating characteristic curve (AU-ROC), and area under the precision-recall curve (AU-PRC). Training time and acquisition time were recorded. Statistical analysis included descriptive metrics and performance comparisons across acquisition strategies. Least Confidence achieved 92.8% accuracy (AU-ROC, 0.95) in binary classification (normal vs. diseased) using 9.24% of the training data. In the multi-class setting, Mean STD achieved 70.5% accuracy (AU-ROC, 0.85) using 21.87% of the labeled data. These methods outperformed more complex and computationally expensive acquisition functions and significantly reduced labeling needs. Deep active learning with BNN approximation and weighted loss effectively reduces labeled data requirements while addressing class imbalance, maintaining or exceeding diagnostic performance.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Technology Letters
- Vol. 36 (4) , 215-218
Reducing Computation Complexity in Optimization of Nanophotonic Structures Using Pruning
Inverse design of complex nanophotonic devices is a very computation-consuming task. Deep-learning-based approaches can facilitate this process. However, due to the lack of solid knowledge about the underlying complexity of the input-output relation for a selected class of nanostructures, it is common to select an over-parameterized neural network (NN) for modeling this relation. We present a novel pruning method based on removing weak nodes and connections in the original NN to simplify the input-output relation without imposing significant error. In addition to reducing the model complexity computations, the pruned network can be used to find valuable insight into the physics of device operation. To show the efficacy of our approach, we use it for modeling and inverse design of two classes of nanostructures with different complexities.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Technology Letters
- Vol. 36 (4) , 215-218
Reducing Computation Complexity in Optimization of Nanophotonic Structures Using Pruning
Inverse design of complex nanophotonic devices is a very computation-consuming task. Deep-learning-based approaches can facilitate this process. However, due to the lack of solid knowledge about the underlying complexity of the input-output relation for a selected class of nanostructures, it is common to select an over-parameterized neural network (NN) for modeling this relation. We present a novel pruning method based on removing weak nodes and connections in the original NN to simplify the input-output relation without imposing significant error. In addition to reducing the model complexity computations, the pruned network can be used to find valuable insight into the physics of device operation. To show the efficacy of our approach, we use it for modeling and inverse design of two classes of nanostructures with different complexities.
- Open Access
- 31 January 2023
- Published by American Chemical Society (ACS) in ACS Photonics
- Vol. 10 (4) , 900-909
Metric Learning: Harnessing the Power of Machine Learning in Nanophotonics
- 31 January 2023
- Published by American Chemical Society (ACS) in ACS Photonics
- Vol. 10 (4) , 900-909
Open AccessMetric Learning: Harnessing the Power of Machine Learning in Nanophotonics
- Open Access
- 24 January 2022
- Published by American Chemical Society (ACS) in ACS Photonics
- Vol. 9 (2) , 714-721
Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
- 24 January 2022
- Published by American Chemical Society (ACS) in ACS Photonics
- Vol. 9 (2) , 714-721
Open AccessManifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
- 19 May 2021
- Published by Optica Publishing Group in Optics Letters
- Vol. 46 (11) , 2634-2637
Inverse design of photonic nanostructures using dimensionality reduction: reducing the computational complexity
In this Letter, we present a deep-learning-based method using neural networks (NNs) for inverse design of photonic nanostructures. We show that by using dimensionality reduction in both the design and the response spaces, the computational complexity of the inverse design algorithm is considerably reduced. As a proof of concept, we apply this method to design multi-layer thin-film structures composed of consecutive layers of two different dielectrics and compare the results using our techniques to those using conventional NNs.
- 19 May 2021
- Published by Optica Publishing Group in Optics Letters
- Vol. 46 (11) , 2634-2637
Inverse design of photonic nanostructures using dimensionality reduction: reducing the computational complexity
In this Letter, we present a deep-learning-based method using neural networks (NNs) for inverse design of photonic nanostructures. We show that by using dimensionality reduction in both the design and the response spaces, the computational complexity of the inverse design algorithm is considerably reduced. As a proof of concept, we apply this method to design multi-layer thin-film structures composed of consecutive layers of two different dielectrics and compare the results using our techniques to those using conventional NNs.
- Open Access
Toward Understanding COVID-19 Pneumonia: A Deep-learning-based Approach for Severity Analysis and Monitoring the Disease
We report a new approach using artificial intelligence to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with average area under curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in single patients and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in early stages. This will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.
Open AccessToward Understanding COVID-19 Pneumonia: A Deep-learning-based Approach for Severity Analysis and Monitoring the Disease
We report a new approach using artificial intelligence to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with average area under curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in single patients and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in early stages. This will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.