Artificial intelligence-based systems and methods for automatic measurements for pre-procedural planning

A computer implemented method for recommending a heart valve based on automatically measuring structural features of anatomies using an automatic measurement system, the method comprising:

• receiving medical images of the anatomies;
• detecting landmarks of the anatomies based on the medical images using an artificial intelligence (AI)-based model comprising two independently trained neural networks comprising a first AI model configured to detect a center of an anatomical structure of interest and a second AI model that is an anatomical landmark detection model;
• constructing an anatomical structural model of the anatomies comprising an annulus and blood vessel branches in the vicinity of the annulus based on the detected landmarks;
• making quantifying measurements of selected structural features of the anatomical structural model, wherein the selected structural features comprise the annulus and location and orientation information of the blood vessel branches in the vicinity of the annulus;
• and
• generating a report including the quantifying measurements and recommendations of sizing and type of the heart valve.

A system for recommending a heart valve based on automatically measuring structural features of anatomies, comprising:

• a database;
• one or more automatic measurement systems connected to the database, wherein each of the one or more automatic measurement systems comprises:
• a non-transitory computer readable medium having stored thereon, a computer program having at least one code section for automatically measuring structural features of anatomies, the at least one code section being executed by at least a processor, causing an automatic measurement system to perform steps comprising:
• receiving medical images of the anatomies;
• detecting landmarks of the anatomies based on the medical images using an artificial intelligence (AI)-based model comprising two independently trained neural networks comprising a first AI model configured to detect a center of an anatomical structure of interest and a second AI model that is an anatomical landmark detection model;
• constructing an anatomical structural model of the anatomies comprising an annulus and blood vessel branches in the vicinity of the annulus based on the detected landmarks;
• making quantifying measurements of selected structural features of the anatomical structural model, wherein the selected structural features comprise the annulus and location and orientation information of the blood vessel branches in the vicinity;
• and
• generating a report including the quantifying measurements and recommendations of sizing and type of the heart valve.