Meysam Tavakoli

Dr. Meysam Tavakoli

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
20 April 2021 in IEEE Access
Verified
Journal Article
Open access
MTMeysam Tavakoli
Meysam Tavakoli
AMAlireza Mehdizadeh
Alireza Mehdizadeh
AAAfshin Aghayan
Afshin Aghayan
RSReza Pourreza Shahri
Reza Pourreza Shahri
TETim Ellis
Tim Ellis
JDJamshid Dehmeshki
Jamshid Dehmeshki
Detection of red lesions in color retinal images is a critical step to prevent the development of vision loss and blindness associated with diabetic retinopathy (DR). Microaneurysms (MAs) are the most frequently observed and are usually the first lesions to appear as a consequence of DR. Therefore, their detection is necessary for mass screening of DR. However, detecting these lesions is a challenging task because of the low image contrast, and the wide variation of imaging conditions. Recently, the emergence of computer-aided diagnosis systems offers promising approaches to detect these lesions for diagnostic purposes. In this paper we focus on developing unsupervised and supervised techniques to cope intelligently with the MAs detection problem. In the first step, the retinal images are preprocessed to remove background variation in order to achieve a high level of accuracy in the detection. In the main processing step, important landmarks such as the optic nerve head and retinal vessels are detected and masked using the Radon transform (RT) and multi-overlapping windows. Finally, the MAs are detected and numbered by using a combination of RT and a supervised support vector machine classifier. The method was tested on three publicly available datasets and a local database comprising a total of 749 images. Detection performance was evaluated using sensitivity, specificity, and FROC analysis. From the image analysis viewpoint, DR was detected with a sensitivity of 100% and a specificity of 93% on average across all of these databases. Moreover, from lesion-based analysis the proposed approach detected the MAs with sensitivity of 95.7% with an average of 7 false positives per image. These results compare favourably with the best of the published results to date.

20 December 2024 in Journal of Applied Clinical Medical Physics
Verified
Journal Article
Open access
ATAmin Talebi
Amin Talebi
ABAhmad Bitarafan‐Rajabi
Ahmad Bitarafan‐Rajabi
AAAzin Alizadeh‐Asl
Azin Alizadeh‐Asl
PSParisa Seilani
Parisa Seilani
BKBenyamin Khajetash
Benyamin Khajetash
MTMeysam Tavakoli
Meysam Tavakoli
Purpose: Cardiotoxicity is one of the major concerns in breast cancer treatment, significantly affecting patient outcomes. To improve the likelihood of favorable outcomes for breast cancer survivors, it is essential to carefully balance the potential advantages of treatment methods with the risks of harm to healthy tissues, including the heart. There is currently a lack of comprehensive, data‐driven evidence on effective risk stratification strategies. The aim of this study is to investigate the prediction of cardiotoxicity using machine learning methods combined with radiomics, clinical, and dosimetric features.Materials and methods: A cohort of 83 left‐sided breast cancer patients without a history of cardiac disease was examined. Two‐ and three‐dimensional echocardiography were performed before and after 6 months of treatment to evaluate cardiotoxicity. Cardiac dose‐volume histograms, demographic data, echocardiographic parameters, and ultrasound imaging radiomics features were collected for all patients. Toxicity modeling was developed with three feature selection methods and five classifiers in four separate groups (Dosimetric, Dosimetric + Demographic, Dosimetric + Demographic + Clinical, and Dosimetric + Demographic + Clinical + Imaging). The prediction performance of the models was validated using five‐fold cross‐validation and evaluated by AUCs.Results: 58% of patients showed cardiotoxicity 6 months after treatment. Mean left ventricular ejection fraction and Global longitudinal strain decreased significantly compared to pre‐treatment (p‐value < 0.001). After feature selection and prediction modeling, the Dosimetric, Dosimetric + Demographic, Dosimetric + Demographic + Clinical, Dosimetric + Demographic + Clinical + Imaging models showed prediction performance (AUC) up to 73%, 75%, 85%, and 97%, respectively.Conclusion: Incorporating clinical and imaging features along with dose descriptors are beneficial for predicting cardiotoxicity after radiotherapy.

1 November 2020 in Cell Reports Physical Science
Verified
Journal Article
Open access
MTMeysam Tavakoli
Meysam Tavakoli
SJSina Jazani
Sina Jazani
ISIoannis Sgouralis
Ioannis Sgouralis
WHWooseok Heo
Wooseok Heo
KIKunihiko Ishii
Kunihiko Ishii
SPSteve Presse
Steve Presse
Lifetimes of chemical species are typically estimated by either fitting time-correlated single-photon counting (TCSPC) histograms or phasor analysis from time-resolved photon arrivals. While both methods yield lifetimes in a computationally efficient manner, their performance is limited by choices made on the number of distinct chemical species contributing photons. However, the number of species is encoded in the photon arrival times collected for each illuminated spot and need not be set by hand a priori. Here, we propose a direct photon-by-photon analysis of data drawn from pulsed excitation experiments to infer, simultaneously and self-consistently, the number of species and their associated lifetimes from a few thousand photons. We do so by leveraging new mathematical tools within the Bayesian nonparametric. We benchmark our method for both simulated and experimental data for 1–4 species.

18 July 2023 in Biomedical Physics & Engineering Express
Verified
Journal Article
Closed access
BKBenyamin Khajetash
Benyamin Khajetash
ATAmin Talebi
Amin Talebi
ZBZahra Bagherpour
Zahra Bagherpour
SASamira Abbaspour
Samira Abbaspour
MTMeysam Tavakoli
Meysam Tavakoli
Multiple Sclerosis (MS) is the most common non-traumatic disabling disease in young people. The prediction active plaque has the potential to offer new biomarkers for assessing the activity of MS disease. Consequently it supports patient management in the clinical setting and trials. This study aims to investigate the predictive capability of radiomics features for identifying active plaques in these patients using T2 FLAIR (Fluid Attenuated Inversion Recovery) images. For this purpose, a dataset images from 82 patients with 122 lesions was analyzed. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) method. Six different classifier algorithms, namely K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), were employed for modeling. The models were evaluated using 5-fold cross-validation, and performance metrics including sensitivity, specificity, accuracy, area under the curve (AUC), and mean squared error were computed. A total of 107 radiomics features were extracted for each lesion, and 11 robust features were identified through the feature selection process. These features consisted of four shape features (elongation, flatness, major axis length, mesh volume), one first-order feature (energy), one Gray Level Co-occurrence Matrix feature (correlation), two Gray Level Run Length Matrix features (gray level non-uniformity, gray level non-uniformity normalized), and three Gray Level Size Zone Matrix features (low gray level zone emphasis, size zone non-uniformity, small area low gray level emphasis). The NB classifier demonstrated the best performance with an AUC, sensitivity, and specificity of 0.85, 0.82, and 0.66, respectively. The findings indicate the potential of radiomics features in predicting active MS plaques in T2 FLAIR images.

12 October 2023 in Journal of Applied Clinical Medical Physics
Verified
Journal Article
Open access
SASamaneh Abbasi
Samaneh Abbasi
AMAlireza Mehdizadeh
Alireza Mehdizadeh
HBHamid Reza Boveiri
Hamid Reza Boveiri
MSMohammad Amin Mosleh Shirazi
Mohammad Amin Mosleh Shirazi
RJReza Javidan
Reza Javidan
MTMeysam Tavakoli
Meysam Tavakoli
Multimodal image registration is a key for many clinical image‐guided interventions. However, it is a challenging task because of complicated and unknown relationships between different modalities. Currently, deep supervised learning is the state‐of‐theart method at which the registration is conducted in end‐to‐end manner and one‐shot. Therefore, a huge ground‐truth data is required to improve the results of deep neural networks for registration. Moreover, supervised methods may yield models that bias towards annotated structures. Here, to deal with above challenges, an alternative approach is using unsupervised learning models. In this study, we have designed a novel deep unsupervised Convolutional Neural Network (CNN)‐based model based on computer tomography/magnetic resonance (CT/MR) co‐registration of brain images in an affine manner. For this purpose, we created a dataset consisting of 1100 pairs of CT/MR slices from the brain of 110 neuropsychic patients with/without tumor. At the next step, 12 landmarks were selected by a well‐experienced radiologist and annotated on each slice resulting in the computation of series of metrics evaluation, target registration error (TRE), Dice similarity, Hausdorff, and Jaccard coefficients. The proposed method could register the multimodal images with TRE 9.89, Dice similarity 0.79, Hausdorff 7.15, and Jaccard 0.75 that are appreciable for clinical applications. Moreover, the approach registered the images in an acceptable time 203 ms and can be appreciable for clinical usage due to the short registration time and high accuracy. Here, the results illustrated that our proposed method achieved competitive performance against other related approaches from both reasonable computation time and the metrics evaluation.

24 April 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
BKBenyamin Khajetash
Benyamin Khajetash
SMseied rabi mehdi mahdavi
seied rabi mehdi mahdavi
ANAlireza Nikoofar
Alireza Nikoofar
LJLee Johnson
Lee Johnson
MTMeysam Tavakoli
Meysam Tavakoli
There are different side effects in radiotherapy of head and neck cancer (HNC) including xerostomia. The present study utilizes the addition of \(T_1\) and \(T_2\)-weighted Magnetic Resonance (MR) radiomic image features to typical Computed Tomography (CT)-based features and radiation dose-based characteristics and incorporates the evaluation and validation of individual and ensemble classifiers for prediction of early-onset xerostomia in radiotherapy of HNC. A total of 80 patients diagnosed with HNC were evaluated prospectively. The dataset was divided into two subsets: 70% for training and validation and 30% for testing. Stratified random sampling was used to ensure that the proportion of xerostomia cases was consistent across both subsets. This approach preserved the class balance and ensured a representative distribution of demographic, dosimetric, and radiomic features in both sets. MR and CT imaging, dosimetric, and demographic features of patients were used as model input data. Bilateral parotid radiomic features were extracted from CT, \(T_1\), and \(T_2\) weighted MR images. Pearson statistical tests were used for selection of features and Random Tree (RT), Neural Network (NN), Linear Support Vector Machine (LSVM) and Bayesian Network (BN) classifiers were evaluated. To prevent overfitting and data leakage, preprocessing was conducted. All features were normalized using the z-score technique, with the mean and standard deviation calculated from the training set and then applied to the test set. For the training dataset, the Synthetic Minority Oversampling Technique (SMOTE) was used to balance the minority class. The results suggest the extracted features from \(T_1\) weighted images have superior prediction ability compared to \(T_2\) weighted acquisitions. The RT and BN models based on \(T_1\) weighted images show better performance than those obtained with \(T_2\) weighted images. \(T_1\) weighted image-based analysis shows area under the curve (AUC) values for The RT and BN models of 0.90 and 0.84, respectively, while corresponding values obtained from \(T_2\) weighted images are 0.79 and 0.78 for RT and BN models respectively. Combined \(T_1\) weighted image-based models RT-BN, RT-LSVM-BN and RT-NN-LSVM-BN also show good performance having AUC values 0.97, 0.92, and 0.90, respectively. These results show that radiomic features from MR images obtained before radiotherapy can be used in addition to other metrics as personalized and unique biomarkers for prediction of early-onset xerostomia. Ensemble classifiers are more efficient than individual classifiers in prediction of early xerostomia.