Smooth Extrapolation of Unknown Anatomy via Statistical Shape Models

TL;DR

This paper evaluates methods for smooth extrapolation of incomplete anatomical surfaces using statistical shape models, with a focus on improving accuracy and visual quality in surgical planning.

Contribution

It introduces a Thin Plate Spline-based extrapolation technique that outperforms existing methods in producing smooth, accurate surface estimates from partial medical images.

Findings

Thin Plate Spline approach reduces surface estimation error by approximately 1.4 mm.

Feathering produces smooth transitions but can corrupt known surface vertices.

The proposed method improves extrapolation accuracy in leave-one-out tests.

Abstract

Several methods to perform extrapolation of unknown anatomy were evaluated. The primary application is to enhance surgical procedures that may use partial medical images or medical images of incomplete anatomy. Le Fort-based, face-jaw-teeth transplant is one such procedure. From CT data of 36 skulls and 21 mandibles separate Statistical Shape Models of the anatomical surfaces were created. Using the Statistical Shape Models, incomplete surfaces were projected to obtain complete surface estimates. The surface estimates exhibit non-zero error in regions where the true surface is known; it is desirable to keep the true surface and seamlessly merge the estimated unknown surface. Existing extrapolation techniques produce non-smooth transitions from the true surface to the estimated surface, resulting in additional error and a less aesthetically pleasing result. The three extrapolation techniques evaluated were: copying and pasting of the surface estimate (non-smooth baseline), a feathering between the patient surface and surface estimate, and an estimate generated via a Thin Plate Spline trained from displacements between the surface estimate and corresponding vertices of the known patient surface. Feathering and Thin Plate Spline approaches both yielded smooth transitions. However, feathering corrupted known vertex values. Leave-one-out analyses were conducted, with 5% to 50% of known anatomy removed from the left-out patient and estimated via the proposed approaches. The Thin Plate Spline approach yielded smaller errors than the other two approaches, with an average vertex error improvement of 1.46 mm and 1.38 mm for the skull and mandible respectively, over the baseline approach.