Quantitative and computational cancer imaging (QACCI) team focuses on design and development of quantitative multi-parametric MRI protocols incorporated with machine and deep learning techniques for generating specific and sensitive biomarkers for cancer detection and diagnosis. The imaging-computational approach is designed to build models that can predict patient- and tumor-specific pathological and genomics state. Most of the currently available computational methods are not generalizable and cannot be easily translated to clinical applications. Therefore, one of the main aims of this team is to explore and propose clinically-applicable computer-aided approaches for personalized surgical and treatment planning of patients with cancers in a collaborative platform, comprising of surgeons, oncologists, pathologists, radiologists, MR technologists, MRI physicists, and computational engineers. The mission of QACCI team is to advance clinical implementation of systematic computer-aided approaches for improving the confidence of healthcare providers in designing the most suitable diagnostic and treatment strategies for patients with cancers.

 

  • Design and development of Multi-parametric MRI protocols for diagnostic and treatment monitoring/planning purposes
  • Patient-specific imaging in brain tumors, head and neck, breast, prostate, liver, and gynecological cancers
  • Quantitative analytical methods based on artificial intelligence techniques and big/small data
  • Hamidreza Saligheh Rad, PhD (MRI Physicist)
  • Mohammadreza Ay, PhD (PET Physicist)
  • Hamidreza Haghighatkhah, MD (Radiologist)
  • Masoumeh Gity, MD (Radiologist)
  • Mehdi Zeinali Zadeh, MD (Neurosurgeon)
  • Guive Sharifi, MD (Neurosurgeon)
  • Farid Azmoodeh-Ardalan (Pathologist)
  • Mahyar Ghafouri, MD (Radiologist)
  • Morteza Sanei, MD (Radiologist)
  • Arvin Aryan, MD (Radiologist)
  • Leila Agha-Ghazvini, MD (Radiologist)
  • Maryam Rahmani, MD (Radiologist)
  • Niloofar Ayyoubi, MD (Radiologist)
  • Ahmad Ameri, MD (Oncologist)
  • Pedram Fadavi, MD (Oncologist)
  • Mostafa Farzin, MD (Oncologist)
  • Farhad Samiei, MD (Oncologist)
  • Kavous Firouz-Nia, MD (Radiologist)
  • Meysam Mohseni, MD (Neurosurgeon)
  • A novel multi-parametric (DWI/DSC-MRI) image fusion approach for accurate quantification of various regions in glioma brain tumors
  • Presentation of Non-Rigid Registration algorithm for Dynamic Contrast Enhanced Magneti Resounance Images (DCE-MRI ) in Ovary region based on pharmacokinetics parameters
  • Segmentation and classification of breast cancer tumors using quantitative DCE-MRI
  • Investigation of the competting/completing role of DWI-MRI vs. PET/CT in bone marrow metastatic breast cancer in pelvis region
  • Differentiation of Various Tumorous Regions in Multi-parametric MRI (DWI/PWI/T2/MRS) of Glioblastoma Multiforme Tumor Employing Multi-Variate Classification Methods
  • Determination of Glioma’s Target Volume For Conformal Radiotherapy and IMRT Treatment Planning Using Diffusion Tensor Magnetic Resonance Imaging
  • Investigation of Discriminative Role of Quantitative Diffusion Weighted MR Imaging and T2 in Complex Ovarian Masses
  • Presentation of Non-Rigid Registration algorithm for Dynamic Contrast Enhanced Magneti Resounance Images (DCE-MRI ) in Ovary region based on pharmacokinetics parameters
  • A study for the improvement of ability on detection and differentiation of Parotid Tumors by Multiparametric Analysis of Perfusion and Diffusion MR Images
  • Magnetic resonance grading of patients suspicious of prostate cancer, quantification of the MR ROI analysis and histology methods, and extention of these methods to other cancers
  • Comparing and evaluating the multiparametric MRI of prostate on pathological data in a clinical imaging center in Iran
  • Clinical Methodology for Quantification of Multi-Parametric Magnetic Resonance Imaging in Breast Cancer
  • Investigating the Role of Emerging MRI Methods (T2-relaxometry/ Intra-voxel Incoherent Motion) in Differentiation of Biopsy-Validated Tumorous Regions in Glioma Tumors
  • Quantitative Analysis of the Response of Glioma Tumor to Chemoradiotherapy Using Functional Map-Derived Diffusion MRI Biomarkers