Interactive Image Processing with AI (IIPAI)
This web application is a test platform for developing and interacting with AI-powered image processing tools for use in medical imaging, focusing on magnetic resonance imaging (MRI). Modern MRI machines commonly use AI methods to scan faster and produce images directly from the scanner with increased spatial resolution and signal-to-noise (SNR). There are also vendors who provide post-processing tools to denoise and/or increase spatial resolution (i.e., super-resolution) of existing images. These methods are powerful but can lead to unnatural-looking images, artifacts, and even hallucinations that can impact the radiologist's interpretation.
This web app demonstrates interactive AI tools that allow the user to adjust the amount of image enhancement on the fly, just as one would interact with zoom/pan or window/level settings on any medical imaging viewer. The degree of denoising and super-resolution can be independently adjusted to the reader's preference to accommodate a wide range of images with variable noise, resolution, and artifacts. The AI-enhanced images are smoothly connected to the source images, providing explainability and increasing confidence in diagnostic interpretation.
Click below to launch a live demo and experience this technology for yourself!
Enhancement Pad
The AI-powered enhancement is adjusted with this square widget, which independently controls the amount of denoising (DN) by moving up/down and the degree of super-resolution (SR) by moving left/right.
Video Demo
Click below to watch a short (2 min) video demonstration of this technology.
Learn More
This is an ongoing development project and no official release is available yet. Contact the author for more information and view other projects at https://deepimaging.org.
Data Sources
The images used in this demo are all publicly available from NCI's The Cancer Imaging Archive (TCIA). They are used here for demonstration purposes only.
Breast: Newitt, D. C., Partridge, S. C., Zhang, Z., Gibbs, J., Chenevert, T., Rosen, M., Bolan, P., Marques, H., Romanoff, J., Cimino, L., Joe, B. N., Umphrey, H., Ojeda-Fournier, H., Dogan, B., Oh, K. Y., Abe, H., Drukteinis, J., Esserman, L. J., & Hylton, N. M. (2021). ACRIN 6698/I-SPY2 Breast DWI [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/tcia.kk02-6d95
Brain: Bakas, S., Sako, C., Akbari, H., Bilello, M., Sotiras, A., Shukla, G., Rudie, J. D., Flores Santamaria, N., Fathi Kazerooni, A., Pati, S., Rathore, S., Mamourian, E., Ha, S. M., Parker, W., Doshi, J., Baid, U., Bergman, M., Binder, Z. A., Verma, R., … Davatzikos, C. (2021). Multi-parametric magnetic resonance imaging (mpMRI) scans for de novo Glioblastoma (GBM) patients from the University of Pennsylvania Health System (UPENN-GBM) (Version 2) [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/TCIA.709X-DN49
Prostate: Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N., & Huisman, H. (2017). SPIE-AAPM
Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N., & Huisman, H. (2017). SPIE-AAPM PROSTATEx Challenge Data (Version 2) [dataset]. The Cancer Imaging Archive. https://doi.org/10.7937/K9TCIA.2017.MURS5CL