# pMRF-ADS

**Repository Path**: RobVIP-Lab/p-mrf-ads

## Basic Information

- **Project Name**: pMRF-ADS
- **Description**: The codes for the work "Surface deformation tracking in monocular laparoscopic video
 "(https://www.sciencedirect.com/science/article/pii/S1361841523000361). Published in Medical Image Analysis.
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-09-05
- **Last Updated**: 2025-09-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

#  pMRF-ADS
The codes for the work "Surface deformation tracking in monocular laparoscopic video "(https://www.sciencedirect.com/science/article/pii/S1361841523000361). Published in Medical Image Analysis.

## Environment

- Clone code from https://gitee.com/RobVIP-Lab/p-mrf-ads.

- Please prepare an environment with >=c++17, CUDA, cuBLAS, Eigen3, gflags, boost, OpenCV. (Test with Windows 10, VS2017, x64, CUDA=10.2, boost=1.67, OpenCV=3.4.5 with contrib.)

- To test our method on your own data, prepare a data directory organized in the following structure:

    ```
    + data1        
        |+ json/           # groud-truth landmarks (optional)
        |+ masks/          # binary tool masks (optional)
        |+ tps/            # rgb images
    ```

## Test

Use PowerShell command:

```powershell
PATH --use_local_data --use_wom_data --log_version “mylog” --root "YOUR DATASET PATH"

optional: 
--use_kalman        # Enable kalman filter.
--use_gt_ev         # Use GT label for evaluation (work with 'json' files).
--gt_num            # work with 'json' files.
--rect              # ROI, splited by','.
```

Select ROI with mouse, then ENTER.

## Citation

```bibtex
@article{LIU2023Surface,
title = {Surface deformation tracking in monocular laparoscopic video},
journal = {Medical Image Analysis},
volume = {86},
pages = {102775},
year = {2023},
issn = {1361-8415},
doi = {https://doi.org/10.1016/j.media.2023.102775},
url = {https://www.sciencedirect.com/science/article/pii/S1361841523000361},
author = {Ziteng Liu and Wenpeng Gao and Jiahua Zhu and Zhi Yu and Yili Fu},
keywords = {Monocular laparoscopic video, Surface deformation tracking, Occlusion, Image-guided surgery},
abstract = {Image-guided surgery has been proven to enhance the accuracy and safety of minimally invasive surgery (MIS). Nonrigid deformation tracking of soft tissue is one of the main challenges in image-guided MIS owing to the existence of tissue deformation, homogeneous texture, smoke and instrument occlusion, etc. In this paper, we proposed a piecewise affine deformation model-based nonrigid deformation tracking method. A Markov random field based mask generation method is developed to eliminate tracking anomalies. The deformation information vanishes when the regular constraint is invalid, which further deteriorates the tracking accuracy. Atime-series deformation solidification mechanism is introduced to reduce the degradation of the deformation field of the model. For the quantitative evaluation of the proposed method, we synthesized nine laparoscopic videos mimicking instrument occlusion and tissue deformation. Quantitative tracking robustness was evaluated on the synthetic videos. Three real videos of MIS containing challenges of large-scale deformation, large-range smoke, instrument occlusion, and permanent changes in soft tissue texture were also used to evaluate the performance of the proposed method. Experimental results indicate the proposed method outperforms state-of-the-art methods in terms of accuracy and robustness, which shows good performance in image-guided MIS.}
}

```