Self-supervised Mamba-based Mastoidectomy Shape Prediction for Cochlear Implant Surgery

2024-07-22

AI Summary

This study addresses the challenge of accurately predicting the three-dimensional (3D) shape of the mastoidectomy cavity during preoperative planning for cochlear implantation. We propose the first self-supervised 3D shape prediction method based on the Mamba architecture, requiring only preoperative CT scans—no manual annotations. By implicitly modeling the resected region in postoperative CT via joint self-supervised voxel synthesis, CT registration, and surface reconstruction, our method generates a 3D surface model aligned with the intraoperative microscopic view. The framework robustly suppresses metal artifacts and low signal-to-noise ratio interference. Evaluated on mastoidectomy cavity prediction, it achieves a mean Dice score of 0.70—significantly improving both accuracy and efficiency of surgical planning. This work delivers a clinically deployable AI-assisted decision support tool for minimally invasive otologic surgery.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning with Manifolds
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Cochlear Implant (CI) procedures require the insertion of an electrode array into the cochlea within the inner ear. To achieve this, mastoidectomy, a surgical procedure involving the removal of part of the mastoid region of the temporal bone using a high-speed drill provides safe access to the cochlea through the middle and inner ear. In this paper, we propose a novel Mamba-based method to synthesize the mastoidectomy volume using only preoperative Computed Tomography (CT) scans, where the mastoid remains intact. Our approach introduces a self-supervised learning framework designed to predict the mastoidectomy shape and reconstruct a 3D post-mastoidectomy surface directly from preoperative CT scans. This reconstruction aligns with intraoperative microscope views, enabling various downstream surgical applications. For training, we leverage postoperative CT scans to bypass manual data cleaning and labeling, even when the region removed during mastoidectomy is affected by challenges such as metal artifacts, low signal-to-noise ratio, or electrode wiring. Our method achieves a mean Dice score of 0.70 in estimating mastoidectomy regions, demonstrating its effectiveness for accurate and efficient surgical preoperative planning.

Problem

• Predict mastoidectomy shape from preoperative CT scans.
• Reconstruct 3D post-mastoidectomy surface for surgical planning.
• Overcome challenges like metal artifacts in postoperative CT scans.

Innovation

• Self-supervised Mamba-based mastoidectomy shape prediction
• 3D post-mastoidectomy surface reconstruction from CT scans
• Training with postoperative CT scans bypassing manual labeling