Mahdi SadeghiBakhi

Mahdi SadeghiBakhi

Auto-generated profile, based on publicly available information

Mahdi SadeghiBakhi

Department of Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
2 May 2022 in IEEE Journal of Translational Engineering in Health and Medicine
Verified
Journal Article
Open access
MSMehdi Sadeghibakhi
Mehdi Sadeghibakhi
HPHamidreza Pourreza
Hamidreza Pourreza
HMHamidreza Mahyar
Hamidreza Mahyar
Objective: Multiple Sclerosis (MS) is an autoimmune and demyelinating disease that leads to lesions in the central nervous system. This disease can be tracked and diagnosed using Magnetic Resonance Imaging (MRI). A multitude of multimodality automatic biomedical approaches are used to segment lesions that are not beneficial for patients in terms of cost, time, and usability. The authors of the present paper propose a method employing just one modality (FLAIR image) to segment MS lesions accurately. Methods: A patch-based Convolutional Neural Network (CNN) is designed, inspired by 3D-ResNet and spatial-channel attention module, to segment MS lesions. The proposed method consists of three stages: (1) the Contrast-Limited Adaptive Histogram Equalization (CLAHE) is applied to the original images and concatenated to the extracted edges to create 4D images; (2) the patches of size 80 × 80 × 80 × 2 are randomly selected from the 4D images; and (3) the extracted patches are passed into an attention-based CNN which is used to segment the lesions. Finally, the proposed method was compared to previous studies of the same dataset. Results: The current study evaluates the model with a test set of ISIB challenge data. Experimental results illustrate that the proposed approach significantly surpasses existing methods of Dice similarity and Absolute Volume Difference while the proposed method uses just one modality (FLAIR) to segment the lesions. Conclusions: The authors have introduced an automated approach to segment the lesions, which is based on, at most, two modalities as an input. The proposed architecture comprises convolution, deconvolution, and an SCA-VoxRes module as an attention module. The results show, that the proposed method outperforms well compared to other methods.

28 October 2024 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Neda RojhaniNeda Rojhani
Neda Rojhani
MSMahdi SadeghiBakhi
Mahdi SadeghiBakhi
Marco PassafiumeMarco Passafiume
Marco Passafiume
Alessandro CidronaliAlessandro Cidronali
Alessandro Cidronali
George ShakerGeorge Shaker
George Shaker
In low-altitude airspace surveillance, distinguishing between birds and drones is crucial due to their overlapping radar signatures. Radar, the preferred technology for long-range surveillance, struggles with this differentiation. To address this, our study introduces an unsupervised deep-learning method utilizing real radar data from birds and UAVs. This approach starts with data cleaning and up-sampling using Synthetic Minority Over-sampling Technique (SMOTE) to manage dataset imbalance. We integrate Principal Component Analysis (PCA) with deep learning to reduce the feature set efficiently. This integration minimizes computational demands while retaining essential information for precise clustering, enhancing real-world applicability. A Deep Clustering Network (DCN) exploits the reduced-dimensional space created by PCA to identify distinct signal clusters for birds and drones, optimized for radar surveillance without relying on predefined labels. A deep neural network maps data into a cluster-friendly hidden space, designed for radar signal analysis. The model’s effectiveness, with an average Normalized Mutual Information (NMI) score of 0.878 through K-fold cross-validation, underscores the innovative potential of combining PCA with unsupervised learning. This method overcomes traditional radar techniques’ limitations, offering a scalable and efficient solution for surveillance scenarios.

20 November 2024 in IEEE Open Journal of Instrumentation and Measurement
Verified
Journal Article
Open access
SGSara Naseri Golestani
Sara Naseri Golestani
MSMahdi SadeghiBakhi
Mahdi SadeghiBakhi
KMKing Fai Ma
King Fai Ma
Henry LeungHenry Leung
Henry Leung
Environmental monitoring is essential for understanding and mitigating the impact of human activities on the planet, as well as for developing effective strategies for sustainable development and conservation. Accurate object detection in aerial images is crucial for environmental monitoring and surveillance using Unmanned Aerial Vehicles (UAVs). However, existing methods, including Mask R-CNN and YOLO, struggle to detect small and medium-sized objects from UAV sensors, limiting their usability for UAV surveillance. We propose Hydra-Mask-RCNN (HMRCNN), a multitask learning network that enhances detection precision for small and medium-sized objects in aerial images. By integrating Adaptive Branching Network (ABN) with HydraNet, HMRCNN improves feature extraction and object detection capabilities. Evaluations on MS-COCO, Aerial-Cars, VisDrone, and Plastic in river datasets show significant improvements in average recall (AR) compared to baseline models, including Mask R-CNN and YOLO. Our approach has important implications for environmental monitoring, enabling more accurate detection of objects relevant to transportation, security, traffic, pollution, and infrastructure management. With the growing use of UAVs in environmental surveillance, HMRCNN offers a valuable tool for enhancing environmental measurement and assessment capabilities. Our method improves detection performance by over 6% on UAV datasets, making it a valuable contribution to the field as the commercial UAV market is expected to grow from $25 billion to $50 billion in the next decade.

23 February 2022
Verified
Conference Paper
Closed access
MSMehdi SadeghiBakhi
Mehdi SadeghiBakhi
SKSeyed Majid Khorashadizadeh
Seyed Majid Khorashadizadeh
RBReza Behboodi
Reza Behboodi
ALAli Mohammad Latif
Ali Mohammad Latif
This paper proposes an Unbiased Variable Windows Size Impulse noise filter (UVWS) using a genetic algorithm to effectively restore the corrupted images with high or slight noise densities. The method consists of three stages. First, all pixels are classified into noisy and noise-free categories based on their intensities. In the second stage, the noisy pixels are pushed into a descending priority list the priority associated with each pixel is the number of noise-free pixels in the neighbor’s local window. Finally, for each pixel in the list, a local weighted average is calculated so that the corresponding weight for each neighbor is optimized by the genetic algorithm (GA). The performance of the proposed method is evaluated on several benchmark images and compared with four methods from the literature. The results show that the proposed method performs better in terms of visual quality and PSNR especially when the noise density is very high.

28 October 2021
Verified
Conference Paper
Closed access
SKSeyed Majid Khorashadizadeh
Seyed Majid Khorashadizadeh
MSMehdi SadeghiBakhi
Mehdi SadeghiBakhi
FSFatemeh Seifishahpar
Fatemeh Seifishahpar
ALAli Mohammad Latif
Ali Mohammad Latif
Our approach to no-reference image quality assessment (IQA) is grounded on the assumption that natural scenes have certain statistical properties which are altered in the presence of distortion. Therefore, by measuring this statistic one can recognize the distortion affecting the image and provide a no-reference (NR) IQA. In this paper, we extract local entropy and standard deviation from non-overlapping 8 × 8 blocks in the image and its gradient version from 2 scales. Extracting features from gradient images can help to better distinguishing blur and noise effects on images. Having extracted local measures, we aggregate them by finding the parameters of a Gaussian mixture model fitted on these local measures. Finally, our quality metric is achieved via a Neural Network machine learning tool, and its performance is evaluated on a standard LIVE database. The experimental results point out that our proposed features not only can identify the type of distortion but also are consistent with the DMOS in subjective assessment in terms of the correlation coefficient.