AI Insight
Researchers developed BioDeformUNet, a deep learning model that predicts liver deformation during ablation procedures with accuracy comparable to traditional biomechanical models but 34 times faster. The study analyzed 170 CT image pairs from 157 liver ablation patients, achieving a target registration error of 3.31 mm with inference time of only 0.6 seconds compared to 20.2 seconds for the biomechanical reference method. The model accurately mapped tumor positions in 91.9% of cases, with errors within 3.0 mm voxel resolution.
Why it matters
This advancement enables near real-time assessment of ablation margins during liver cancer procedures, potentially improving treatment precision and patient outcomes. The dramatic speed improvement makes intra-procedural evaluation clinically feasible, allowing surgeons to verify complete tumor coverage before concluding the procedure.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Purpose: To build a 3D U-Net model, BioDeformUNet, to predict the deformation vector field (DVF) of the liver in near real-time, for efficient intra-procedural evaluation of the minimal ablative margin (MAM). Materials and Methods: This retrospective study included 170 contrast-enhanced computed tomography (CECT) image pairs from 157 patients who underwent liver ablation treatment between 2020-2024. Each data instance included one pre-ablation CECT (pre-CECT) and one post-ablation CECT (post-CECT). BioDeformUNet was trained under the guidance of DVFs generated by a biomechanical model-based deformable image registration (DIR) algorithm using a loss function that focused on large liver deformations. Data were split patient-wise into training (92-93 patients), validation (23-24 patients), and testing sets (42 patients). We compared our performance with two deep learning-based DIR methods: VoxelMorph and VFA. Evaluation metrics included: target registration error (TRE), Dice similarity coefficient (DSC), Minimum Ablation Margin (MAM), and inference time. For BioDeformUNet, we additionally evaluated the accuracy of the deformed tumor center-of-mass mapping by comparing the predicted tumor center location with that generated by Morfeus. A mapping error less than 3.0 mm (corresponding to the voxel size) was considered accurate. We used the Wilcoxon signed-rank test to assess the significancy of each test result. Our code is available at https://github.com/XinyueZhang831/BioDeformUNET. Results: The TRE of BioDeformUNet was not significantly different from Morfeus (3.31 BioDeformUNet; 3.23 Morfeus; p-value=0.41). The BioDeformUNet DVF magnitude was within 3.0 mm of Morfeus DVF for an average of 91.9% of the voxels. Tumor mapping errors greater than 3.0 mm occurred in only 8 cases. The inference time of BioDeformUNet was 0.6s per image pair, 0.2s for VoxelMorph, 0.3s for VFA, and 20.2s for Morfeus. Conclusion: BioDeformUNet achieved a similar performance to the biomechanical model-based algorithm but required fewer computational operations, resulting in a 34 times speedup in DVF computation.
Source: BioDeformUNet: A Deep Learning Model for Biomechanically Informed Liver Image Registration