Estimation of Pelvic Sagittal Inclination from Anteroposterior Radiograph Using Convolutional Neural Networks: Proof-of-Concept Study

TL;DR

This study presents a CNN-based method to estimate pelvic sagittal inclination from a single AP radiograph, eliminating the need for CT scans and potentially broadening clinical applicability.

Contribution

Developed a novel CNN approach to estimate PSI from plain radiographs without patient-specific CT, reducing radiation and increasing accessibility.

Findings

Accurate PSI estimation from radiographs demonstrated

Method reduces need for CT scans in clinical settings

Potential for wider application in surgical planning

Abstract

Alignment of the bones in standing position provides useful information in surgical planning. In total hip arthroplasty (THA), pelvic sagittal inclination (PSI) angle in the standing position is an important factor in planning of cup alignment and has been estimated mainly from radiographs. Previous methods for PSI estimation used a patient-specific CT to create digitally reconstructed radiographs (DRRs) and compare them with the radiograph to estimate relative position between the pelvis and the x-ray detector. In this study, we developed a method that estimates PSI angle from a single anteroposterior radiograph using two convolutional neural networks (CNNs) without requiring the patient-specific CT, which reduces radiation exposure of the patient and opens up the possibility of application in a larger number of hospitals where CT is not acquired in a routine protocol.