Fame-a flexible appearance modeling environment

TLDR

Active appearance models combine pixel intensities and shape to robustly interpret images and have been widely applied in medical image analysis. The paper summarizes medical AAM applications, introduces the public‑domain FAME implementation, and provides guidelines showing its optimization enables interactive medical use. FAME employs parallel analysis for automatic model truncation, compares two AAM training methods, and includes a reference case study on cardiac MRI and face images. The platform’s optimization enables interactive medical applications, and its source code and annotated datasets are publicly released for reproducibility.

Abstract

Combined modeling of pixel intensities and shape has proven to be a very robust and widely applicable approach to interpret images. As such the active appearance model (AAM) framework has been applied to a wide variety of problems within medical image analysis. This paper summarizes AAM applications within medicine and describes a public domain implementation, namely the flexible appearance modeling environment (FAME). We give guidelines for the use of this research platform, and show that the optimization techniques used renders it applicable to interactive medical applications. To increase performance and make models generalize better, we apply parallel analysis to obtain automatic and objective model truncation. Further, two different AAM training methods are compared along with a reference case study carried out on cross-sectional short-axis cardiac magnetic resonance images and face images. Source code and annotated data sets needed to reproduce the results are put in the public domain for further investigation.