Sepand AliMadadSoltani

Education

• GPA: 15.31/20
• Courses: Magnetic Resonance Imaging, Segmentation & Registration, Artificial Intelligence in Medical Imaging, Image Reconstruction & Inverse Problems
  
• €10,000 Excellence Scholarship awarded for excellent academic background
  

• Concentration: Biomedical Engineering
• GPA: 16.33/20
• Courses: Statistical Pattern Recognition, Signals & Systems, C Programming, Engineering Math, Engineering Probability

Research Experience

• Built an automatic carotid-artery segmentation pipeline on MR angiography in Python
• Implemented a Markov chain Monte Carlo Bayesian inference algorithm for partial volume correction
• Achieved lower quantification bias than alternative methods (MAPE 13% vs 24% and 37%)
• Collaborated with Paris-Saclay to independently validate the method and demonstrate reusability
• Performed realistic Monte Carlo PET simulations to support and strengthen evaluation outcomes
• Developed new tools and improved existing ones for efficient processing of PET and MRI data in C and Python

• Developed a Python-based medical image analysis software, from scratch utilizing VTK and PyQt libraries
• Implemented multiple interactive tools (ruler, shapes, and text insertion tools)
• Developed an image processing algorithm for detecting tissue boundaries
• Designed a smart interactive scissor tool for fast, semi-automatic tissue segmentation
• Enabled users to import custom plugins to extend the functionality of the software based on their needs
• Successfully shipped the software for Linux and Windows operating systems

Skills

• Programming: Python, C, C++, CMake, Bash, QML
• Software and Tools: GNU/Linux, Git, FMRIB FSL, 3D Slicer, TPCCLIB
• Libraries: Tensorflow, PyTorch, NumPy, pandas, scikit-learn, Matplotlib, ITK, VTK, Qt, PyQt
• Languages: English (fluent, TOEFL score:101/120), French (Intermediate), Persian (Native)

Work Experience

• Designed and developed a modern interface using the Qt Framework's QML language
• Built and optimized backend logic in C++ to handle large volumes of data efficiently

• Created a Python-based medical analysis software focusing on user-friendliness and user experience
• Designed and implemented a workflow user interface and logic for designing custom pipelines using the Qt framework
• Worked with a team of engineers to integrate various machine learning algorithms into the workflow
• Designed and integrated a medical image visualizer using VTK
• Integrated multiple visualization tools and utilities such as colormaps, image thresholding and interactive segmentation

• Implemented smart presence detection and remote-control support for the monitor stand in Valiasr Street Museum

Projects

• Implemented the network based on a paper using the Tensorflow library in Python
• Synthesized images of Persian text of different variety
• Applied data augmentation techniques such as rotating, translating, adding distortion, and adding noise to images
• Successfully trained the model for both languages using the self-made synthesized Persian dataset and public English datasets
• Achieved +85% accuracy for both languages

• Pre-processed and processed raw fMRI and MRI data from the ADNI database using the FSL library to extract time-series data to calculate functional connectivity maps of the subjects' brains
• Studied the previous works on this subject to find the gap
• Experimented with RCNN & CNN networks using Tensorflow to extract temporal and spatial features from images
• Gained hands-on experience with image pre-processing, neural network architecture, and deep learning principles
• Although a full model was not achieved, a lot of experience and insight were gained into medical imaging and deep learning concepts

• Implemented brain extraction from structural reference MR image
• Implemented fMRI pre-processing including motion correction, slice timing correction, spatial smoothing, and co-registration
• Implemented atlas-based ROI time-series extraction
• Enabled parallel processing to accelerate computation for large datasets
• Utilized the program for processing fMRI data from the ADNI dataset

• Developed a custom 2D graphics renderer completely from scratch using the OpenGL graphics API in C++
• Implemented user input handling, navigatable menus, and text rendering capabilities to the engine
• Designed and implemented the game of Tetris using the said engine in Object Oriented C++