Teaching AI the Anatomy Behind the Scan: Addressing Anatomical Flaws in Medical Image Segmentation with Learnable Prior
This work addresses anatomical accuracy in medical image segmentation for healthcare applications, representing an incremental improvement over existing methods.
The paper tackled the problem of anatomical flaws in medical image segmentation by introducing AIC-Net, a method that incorporates a learnable anatomical prior to guide predictions, resulting in improved dice scores and Hausdorff distances on multi-organ segmentation tasks.
Imposing key anatomical features, such as the number of organs, their shapes and relative positions, is crucial for building a robust multi-organ segmentation model. Current attempts to incorporate anatomical features include broadening the effective receptive field (ERF) size with data-intensive modules, or introducing anatomical constraints that scales poorly to multi-organ segmentation. We introduce a novel architecture called the Anatomy-Informed Cascaded Segmentation Network (AIC-Net). AIC-Net incorporates a learnable input termed "Anatomical Prior", which can be adapted to patient-specific anatomy using a differentiable spatial deformation. The deformed prior later guides decoder layers towards more anatomy-informed predictions. We repeat this process at a local patch level to enhance the representation of intricate objects, resulting in a cascaded network structure. AIC-Net is a general method that enhances any existing segmentation models to be more anatomy-aware. We have validated the performance of AIC-Net, with various backbones, on two multi-organ segmentation tasks: abdominal organs and vertebrae. For each respective task, our benchmarks demonstrate improved dice score and Hausdorff distance.