MRI Plane Orientation Detection using a Context-Aware 2.5D Model
This work addresses a domain-specific problem in medical imaging by providing an incremental improvement in automated plane orientation detection to enhance data analysis and diagnostic classifiers.
This study tackled the problem of automatically detecting anatomical plane orientation in MRI slices, which is crucial for handling missing metadata and improving diagnostic accuracy, by developing a context-aware 2.5D model that achieved 99.49% accuracy, reducing errors by 60% compared to a 2D baseline, and boosted brain tumor detection accuracy from 97.0% to 98.0%, cutting misdiagnoses by 33.3%.
Humans can easily identify anatomical planes (axial, coronal, and sagittal) on a 2D MRI slice, but automated systems struggle with this task. Missing plane orientation metadata can complicate analysis, increase domain shift when merging heterogeneous datasets, and reduce accuracy of diagnostic classifiers. This study develops a classifier that accurately generates plane orientation metadata. We adopt a 2.5D context-aware model that leverages multi-slice information to avoid ambiguity from isolated slices and enable robust feature learning. We train the 2.5D model on both 3D slice sequences and static 2D images. While our 2D reference model achieves 98.74% accuracy, our 2.5D method raises this to 99.49%, reducing errors by 60%, highlighting the importance of 2.5D context. We validate the utility of our generated metadata in a brain tumor detection task. A gated strategy selectively uses metadata-enhanced predictions based on uncertainty scores, boosting accuracy from 97.0% with an image-only model to 98.0%, reducing misdiagnoses by 33.3%. We integrate our plane orientation model into an interactive web application and provide it open-source.