# Probing Perfection: The Relentless Art of Meddling for Pulmonary Airway Segmentation from HRCT via a Human-AI Collaboration Based Active Learning Method

arXiv: https://arxiv.org/abs/2407.03542 · HTML: https://mlsanity.com/paper/2407.03542/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [CE-Net: Context Encoder Network for 2D Medical Image Segmentation](https://mlsanity.com/paper/1903.02740/) (2019)
- [Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels](https://mlsanity.com/paper/2203.03884/) (2022)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Deep Active Learning: Unified and Principled Method for Query and Training](https://mlsanity.com/paper/1911.09162/) (2019)
- [Self-Training: A Survey](https://mlsanity.com/paper/2202.12040/) (2022)
- [Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2207.14191/) (2022)
- [BSDA-Net: A Boundary Shape and Distance Aware Joint Learning Framework for Segmenting and Classifying OCTA Images](https://mlsanity.com/paper/2107.04823/) (2021)
- [Human Treelike Tubular Structure Segmentation: A Comprehensive Review and Future Perspectives](https://mlsanity.com/paper/2207.11203/) (2022)
- [DeepAL: Deep Active Learning in Python](https://mlsanity.com/paper/2111.15258/) (2021)
- [JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection](https://mlsanity.com/paper/2203.00461/) (2022)
- [A Novel Automated Classification and Segmentation for COVID-19 using 3D CT Scans](https://mlsanity.com/paper/2208.02910/) (2022)
- [High Accuracy and Cost-Saving Active Learning 3D WD-UNet for Airway Segmentation](https://mlsanity.com/paper/2310.05638/) (2023)
- [Make it more specific: A novel uncertainty based airway segmentation application on 3D U-Net and its variants](https://mlsanity.com/paper/2402.07403/) (2024)

## Built on by (most cited first, 1 of 1)

- [Progressive Curriculum Learning with Scale-Enhanced U-Net for Continuous Airway Segmentation](https://mlsanity.com/paper/2410.18456/) (2024)

## Abstract (arXiv)

In pulmonary tracheal segmentation, the scarcity of annotated data is a prevalent issue in medical segmentation. Additionally, Deep Learning (DL) methods face challenges: the opacity of 'black box' models and the need for performance enhancement. Our Human-Computer Interaction (HCI) based models (RS_UNet, LC_UNet, UUNet, and WD_UNet) address these challenges by combining diverse query strategies with various DL models. We train four HCI models and repeat these steps: (1) Query Strategy: The HCI models select samples that provide the most additional representative information when labeled in each iteration and identify unlabeled samples with the greatest predictive disparity using Wasserstein Distance, Least Confidence, Entropy Sampling, and Random Sampling. (2) Central line correction: Selected samples are used for expert correction of system-generated tracheal central lines in each training round. (3) Update training dataset: Experts update the training dataset after each DL model's training epoch, enhancing the trustworthiness and performance of the models. (4) Model training: The HCI model is trained using the updated dataset and an enhanced UNet version. Experimental results confirm the effectiveness of these HCI-based approaches, showing that WD-UNet, LC-UNet, UUNet, and RS-UNet achieve comparable or superior performance to state-of-the-art DL models. Notably, WD-UNet achieves this with only 15%-35% of the training data, reducing physician annotation time by 65%-85%.