Browsing by Author "Basiri, Reza"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- ItemOpen AccessMethod for Optimizing Quantitative Temporal Lobe Epilepsy MR Imaging(2018-01-17) Basiri, Reza; Lebel, Robert Marc; Federico, Paolo; Agha-Khani, Yahya; Takele Zewdie, Ephrem; Frayne, Richard; Sotero Díaz, Roberto C.Many neurological disorders such as epilepsy rely on MRI for detection of structural abnormalities. However, the current clinical MRI methods are insufficient and insensitive in detection of subtle abnormalities. MRI quantitative T2 mapping is a promising quantitative medical imaging technique as it is highly sensitive to tissue composition. The conventional approach for T2 mapping assumes mono-exponential signal decay; however, this is rarely observed due to transmit field inhomogeneity and miscalibration at high field MRIs. The nonexponentially results in poor fits and a systematic bias in estimated decay rates. A recently proposed fitting method, called stimulated echo correction, uses the same input data but estimates the major confounds associated with mono-exponential fitting. Optimal accuracy and non-optimal precision is achieved in this method. My first aim was to develop a stimulated echo correction based method with fewer parameters and higher precision relative to the original one. The second aim was to implement this new method in order to better identify abnormal brain regions in temporal lobe epilepsy that were poorly visualized on standard images. I hypothesized that my improved stimulated echo correction with fewer parameters would provide more accurate and reliable transverse relaxometry imaging than does conventional or the original stimulated echo correction fitting methods, and would improve our ability to detect subtle irregularities associated with epilepsy. The new method was evaluated with simulated and in-vivo data, in which up to 27% reduction in variance in the new method compared to the original stimulated echo correction was observed. Moreover, the new method had greater reliability in categorizing abnormalities in hippocampal regions when compared with exponential and stimulated echo correction methods. I concluded that the new method is able to reduce the variance in T2 relaxometry from multi-echo spin echo sequences; therefore, this method can potentially help in detection of those lesser obvious hippocampus abnormalities.
- ItemOpen AccessProtocol for metadata and image collection at diabetic foot ulcer clinics: enabling research in wound analytics and deep learning(2024-01-29) Basiri, Reza; Manji, Karim; LeLievre, Philip M.; Toole, John; Kim, Faith; Khan, Shehroz S.; Popovic, Milos R.Abstract Background The escalating impact of diabetes and its complications, including diabetic foot ulcers (DFUs), presents global challenges in quality of life, economics, and resources, affecting around half a billion people. DFU healing is hindered by hyperglycemia-related issues and diverse diabetes-related physiological changes, necessitating ongoing personalized care. Artificial intelligence and clinical research strive to address these challenges by facilitating early detection and efficient treatments despite resource constraints. This study establishes a standardized framework for DFU data collection, introducing a dedicated case report form, a comprehensive dataset named Zivot with patient population clinical feature breakdowns and a baseline for DFU detection using this dataset and a UNet architecture. Results Following this protocol, we created the Zivot dataset consisting of 269 patients with active DFUs, and about 3700 RGB images and corresponding thermal and depth maps for the DFUs. The effectiveness of collecting a consistent and clean dataset was demonstrated using a bounding box prediction deep learning network that was constructed with EfficientNet as the feature extractor and UNet architecture. The network was trained on the Zivot dataset, and the evaluation metrics showed promising values of 0.79 and 0.86 for F1-score and mAP segmentation metrics. Conclusions This work and the Zivot database offer a foundation for further exploration of holistic and multimodal approaches to DFU research.