# Adaptive sensitivity-fisher regularization for heterogeneous transfer learning of vascular segmentation in laparoscopic videos

## TL;DR

This paper introduces a new method for accurately identifying blood vessels in laparoscopic surgery videos, improving surgical safety and efficiency.

## Contribution

The novel ASFR method uses adaptive sensitivity-fisher regularization to enhance vascular segmentation in laparoscopic videos through heterogeneous transfer learning.

## Key findings

- The ASFR method achieved an average Dice score of 41.3 for vascular segmentation in laparoscopic videos.
- ASFR outperformed traditional transfer learning approaches and showed adaptability across multiple video segmentation architectures.
- The method effectively mitigates catastrophic forgetting and overfitting in limited data scenarios.

## Abstract

This study aims to enhance surgical safety by developing a method for vascular segmentation in laparoscopic surgery videos with limited visibility. We introduce an adaptive sensitivity-fisher regularization (ASFR) approach to adapt neural networks, initially trained on non-medical datasets, for vascular segmentation in laparoscopic videos.

Our approach utilizes heterogeneous transfer learning by integrating fisher information and sensitivity analysis to mitigate catastrophic forgetting and overfitting caused by limited annotated data in laparoscopic videos. We calculate fisher information to identify and preserve critical model parameters while using sensitivity measures to guide adjustment for new task.

The fine-tuned models demonstrated high accuracy in vascular segmentation across various complex video sequences, including those with obscured vessels. For both invisible and visible vessels, our method achieved an average Dice score of 41.3. In addition to outperforming traditional transfer learning approaches, our method exhibited strong adaptability across multiple advanced video segmentation architectures.

This study introduces a novel heterogeneous transfer learning approach, ASFR, which significantly enhances the precision of vascular segmentation in laparoscopic videos. ASFR effectively addresses critical challenges in surgical image analysis and paves the way for broader applications in laparoscopic surgery, promising improved patient outcomes and increased surgical efficiency.

The online version contains supplementary material available at 10.1007/s11548-025-03404-2.