Three-Dimensional Anatomical Data Generation Based on Artificial Neural Networks

2025-11-24

AI Summary

High-quality 3D anatomical data for surgical planning and training—particularly for low-contrast soft tissues such as the prostate—remain scarce due to legal, ethical, and technical barriers in acquiring real patient data. Method: We propose a novel paradigm integrating physics-based simulation and deep learning: first, constructing biomimetic hydrogel organ phantoms to acquire multimodal ultrasound imaging data; then, leveraging a 3D generative adversarial network (GAN) jointly optimized with semantic segmentation and mesh reconstruction modules to enable end-to-end generation of 3D anatomical manifold data from ex vivo physical simulations. Contribution/Results: Our approach circumvents reliance on clinical patient data while enabling scalable, reproducible dataset synthesis. Validated on prostate models, it achieves significantly higher segmentation IoU than conventional methods and reconstructs high-fidelity, interactive 3D anatomical meshes—demonstrating strong utility for downstream surgical simulation and machine learning tasks.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Surgical planning and training based on machine learning requires a large amount of 3D anatomical models reconstructed from medical imaging, which is currently one of the major bottlenecks. Obtaining these data from real patients and during surgery is very demanding, if even possible, due to legal, ethical, and technical challenges. It is especially difficult for soft tissue organs with poor imaging contrast, such as the prostate. To overcome these challenges, we present a novel workflow for automated 3D anatomical data generation using data obtained from physical organ models. We additionally use a 3D Generative Adversarial Network (GAN) to obtain a manifold of 3D models useful for other downstream machine learning tasks that rely on 3D data. We demonstrate our workflow using an artificial prostate model made of biomimetic hydrogels with imaging contrast in multiple zones. This is used to physically simulate endoscopic surgery. For evaluation and 3D data generation, we place it into a customized ultrasound scanner that records the prostate before and after the procedure. A neural network is trained to segment the recorded ultrasound images, which outperforms conventional, non-learning-based computer vision techniques in terms of intersection over union (IoU). Based on the segmentations, a 3D mesh model is reconstructed, and performance feedback is provided.

Problem

• Generating 3D anatomical data for surgical planning using artificial neural networks
• Overcoming limited medical imaging contrast for soft tissue organ reconstruction
• Creating synthetic 3D organ models to bypass ethical and technical constraints

Innovation

• Automated 3D data generation from physical organ models
• 3D Generative Adversarial Network creates anatomical model manifold
• Neural network segmentation outperforms conventional computer vision techniques