Math helps. This project is dedicated for problems handled by math and software which arise while cancer treatment. Math support starts from interpretation and filtering of tomography data, followed by multiple tasks of screening and visualization, distance-area-volume estimation, optimization of parameters for gamma-knives, modeling and prototyping.
Main directions of development are quantitative and statistical analysis; machine learning for tumor recognition automation. aidScans solution is presented for scanner constructors and cancer researchers attention.
Educate yourself in the problem-specific IT-questions. Take a look on materials gathered on this site to see how you can (help) fight oncology diseases.
Visualization, quantitative analysis and simulation (computer modeling) customized by your research to check results, confirm hypothesis, process observation data, create interactive illustration for your research etc. You may see some practical example of mentioned techniques implemented in aidScans solution.
Well, you already know that getting device working is serious challenge. Software components are making this challenge beatable. The solutions are available starting from basic software data viewing and visualization and up to back-projection, signal filtering, artifacts preventing, auto-segmentation algorithms and 3D+ modeling, quantitative estimations and statistical analysis.
The process of device data interpretation starting from signals and going to images and from images to 3D, 4D, 5D visual models or estimation of ones means number of algorithms. The software framework is available for you. The application lets you getting your algorithm working as component of solid solution, demonstrating it effectiveness, purposes and optimization value.
The key mission of the project is availability and quality increase of health-care to people. The project is focused on reducing cancer treatment costs by automation software, which leads to resource usage optimization and mass solution deployments.
The project gathers materials about:
- Data gathering (mechanics, energy selection, geometry defined by scanner maker)
- Reconstruction (by measured discreet data, scalable raster model reconstructed)
- Filtering (noise, smoothing, contrast)
- Post-reconstruction processing: anti-artifact methods (more advanced filtering) and image normalization (rotation, scaling)
- Volumetric modeling and visualization
- Segmentation and vectorization (subparts selection, contours selection)
- Estimation of distances, area, volume
- Tumor growth modeling
- Optimization of trajectories of gamma-rays