Artificial intelligence (AI) is finding an increasing number of applications in nuclear medicine and radiology. Deep learning models have been used to improve image quality, automate image segmentation, and aid in disease classification. AI models combined with image quantification and clinical information can be used to predict disease progression and design an optimal treatment strategy for every individual.
However, translation of such models/algorithms into clinical trials or standard of care applications is often nontrivial due to the lack of an appropriate framework for model deployment. The Ascinta platform is designed to simplify the evaluation and clinical translation of AI models. The key features of the platform include:
- With a selection of built-in AI models for different applications, Ascinta is very easy to use, with on-premises and cloud-based versions available.
- Different algorithms and models can be combined to create pipelines with multistep workflows.
- It works with existing workstations available to physicians/researchers using a web interface.
- It allows the deployment of models developed in any programming language without the need for cumbersome and time-consuming configuration.
The Ascinta platform represents a vision of a new radiology environment that uses the latest AI tools and biomarkers to better treat and diagnose disease.
Ascinta is now a start-up company, as spin-off from our laboratory and BC Cancer: www.ascinta.com