# Deep learning-based reconstruction and superresolution for MR-guided thermal ablation of malignant liver lesions

**Authors:** Moritz T. Winkelmann, Jens Kübler, Sebastian Gassenmaier, Dominik M. Nickel, Antonia Ashkar, Konstantin Nikolaou, Saif Afat, Rüdiger Hoffmann

PMC · DOI: 10.1186/s40644-025-00869-x · Cancer Imaging · 2025-04-02

## TL;DR

This study shows that deep learning improves image quality and efficiency during MR-guided liver tumor ablation procedures.

## Contribution

DL-VIBE significantly enhances image quality and procedural efficiency in MR-guided thermal ablation of liver malignancies.

## Key findings

- DL-VIBE significantly improved image quality, reduced artifacts, and enhanced sharpness compared to SD-VIBE.
- Procedural metrics like needle tip detectability and ablation zone assessment were better with DL-VIBE.
- DL-VIBE reduced processing and acquisition times, improving procedural efficiency.

## Abstract

This study evaluates the impact of deep learning-enhanced T1-weighted VIBE sequences (DL-VIBE) on image quality and procedural parameters during MR-guided thermoablation of liver malignancies, compared to standard VIBE (SD-VIBE).

Between September 2021 and February 2023, 34 patients (mean age: 65.4 years; 13 women) underwent MR-guided microwave ablation on a 1.5 T scanner. Intraprocedural SD-VIBE sequences were retrospectively processed with a deep learning algorithm (DL-VIBE) to reduce noise and enhance sharpness. Two interventional radiologists independently assessed image quality, noise, artifacts, sharpness, diagnostic confidence, and procedural parameters using a 5-point Likert scale. Interrater agreement was analyzed, and noise maps were created to assess signal-to-noise ratio improvements.

DL-VIBE significantly improved image quality, reduced artifacts and noise, and enhanced sharpness of liver contours and portal vein branches compared to SD-VIBE (p < 0.01). Procedural metrics, including needle tip detectability, confidence in needle positioning, and ablation zone assessment, were significantly better with DL-VIBE (p < 0.01). Interrater agreement was high (Cohen κ = 0.86). Reconstruction times for DL-VIBE were 3 s for k-space reconstruction and 1 s for superresolution processing. Simulated acquisition modifications reduced breath-hold duration by approximately 2 s.

DL-VIBE enhances image quality during MR-guided thermal ablation while improving efficiency through reduced processing and acquisition times.

## Full-text entities

- **Species:** Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC11966842/full.md

## Figures

4 figures with captions in the complete paper: https://tomesphere.com/paper/PMC11966842/full.md

## References

2 references — full list in the complete paper: https://tomesphere.com/paper/PMC11966842/full.md

---
Source: https://tomesphere.com/paper/PMC11966842