Related Experiment Video
Updated: Jan 26, 2026
06:19
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
Published on: August 16, 2024
843
Learning soft tissue behavior of organs for surgical navigation with convolutional neural networks
Micha Pfeiffer1, Carina Riediger2, Jürgen Weitz2
1National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany. micha.pfeiffer@nct-dresden.de.
Summary
This study introduces a novel deep learning method for real-time soft tissue organ deformation modeling in surgical navigation. The system accurately predicts internal organ movement from surface data, enabling enhanced surgical guidance.
Area of Science:
- Medical Imaging
- Computational Biomechanics
- Machine Learning
Background:
- Pre-operative organ models are crucial for surgical navigation.
- Deforming these models with intra-operative data is essential for soft tissue interventions.
- Real-time capable biomechanical models offer a promising solution.
Purpose of the Study:
- To develop a real-time capable, data-driven deformation model for surgical navigation.
- To adapt pre-operative organ models to intra-operative conditions using sensor data.
- To improve the efficiency of target finding during surgical interventions.
Main Methods:
- A fully convolutional neural network was trained to estimate organ displacement fields.
- The network utilizes synthetic data of organ-like meshes for training.
- Input and output data are gridded for parallelized training and inference.
Main Results:
- The system demonstrated good estimation of internal organ displacement on various liver models (in-silico, phantom, in-vivo).
- Performance was evaluated across different material parameters, organ shapes, and visible surface amounts.
- Inference speed exceeded 50 frames per second.
Conclusions:
- A novel method for training real-time deformation models was presented.
- The model's accuracy is comparable to existing registration methods.
- The method is adaptable to new organs without retraining, suitable for surgical navigation and real-time simulation.
Related Concept Videos
01:17Convolution Properties II
583
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
583
02:18Network Covalent Solids
16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K
01:20Convolution Properties I
574
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
574
01:19Cadherins in Tissue Organization
3.9K
The cadherins are a superfamily of cell adhesion molecules comprising over 180 variants, with specific tissues expressing a particular combination of cadherin types. Cadherins generally exhibit homophilic binding; i.e., cadherins on one cell bind to cadherins of the same or closely related type on another cell. Thus, cells of the same type have a specific affinity to bind to each other and sort themselves into clusters to form tissues.
Cell Sorting During Development
Cell sorting plays an...
Cell Sorting During Development
Cell sorting plays an...
3.9K
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
00:54What is Behavior?
10.2K
Behaviors are actions that an organism engages in—they can be related to finding food, reproducing, defending against threats, and many other possible actions. Behaviors include activities related to the environment around the animal—such as migration—as well as social interactions within a species or population. Many behaviors involve motor output—that is, muscle movements—while others involve less visible actions, such as learning.
10.2K