Automated estimation of complete patient bodies from partial scans
MedBOE: Optimization-Based Estimation of Complete Patient Body Models from Whole-Body Medical Imaging
Computer Vision and Pattern Recognition
Summary
Whole-body medical scans sometimes miss parts of a patient's body due to limitations like scanner size or patient positioning. The authors present MedBOE, a new method that can fill in these missing body parts automatically without needing prior training. MedBOE uses a flexible 3D body model to match the visible parts and then estimates the missing regions based on shape and volume constraints. Tests on public datasets show it produces accurate complete body models, helping with measurements important in medical care.
What this means in practice
- •For medical imaging teams: Generate complete patient body models from partial whole-body scans to improve measurement of body metrics for radiotracer dosing and risk assessment.
- •For medical simulation developers: Create accurate full-body anatomical models for imaging simulation and radiation dose calculations when original scans have missing regions.
Authors
Hoijoon Jung, Yuhao Wei, Mingxiao Tu, Younhyun Jung, Michael Fulham, Jinman Kim
Abstract
True whole-body medical imaging captures a patient from head to toe and provides comprehensive anatomical and/or functional information. This coverage enables reconstruction of the external body surface, yielding patient body models. However, scanner geometry (e.g., bore diameter), patient characteristics, and positioning can leave body regions missing (e.g., lateral arms/torso, hands, forearms, elbows), producing incomplete patient body models. Such incompleteness limits downstream medical analyses, including derivation of body-habitus metrics (BHMs), such as body volume and surface area, for injected radiotracer activity regimens, cardiometabolic risk assessment, and computational anatomical modeling for medical imaging simulation and radiation dosimetry. We present the Medical Body model Optimization-based Estimator (MedBOE), an automated, training-free framework for estimating complete patient body models from whole-body images with missing body regions. Our innovation is to leverage the Skinned Multi-Person Linear (SMPL) template, a parametric body mesh representing a broad range of body shapes and poses, in medical imaging. MedBOE aligns the SMPL template to the incomplete patient body models via attribute-guided optimization and estimates missing body regions through geometrically and volumetrically constrained deformation. We evaluated MedBOE using two public datasets: AutoPET (91 whole-body PET-CT images) and Human Implicit Tissues (HIT; 40 whole-body segmentations from MRI images). MedBOE achieved the best overall volumetric and geometric performance among evaluated methods. BHMs derived from MedBOE were within 2% error, suggesting low percentage errors for downstream analyses. MedBOE offers an automated, training-free method for estimating complete patient body models from whole-body images with missing body regions.