# Optimizing the Procedure of CT Segmentation Labeling

arXiv: https://arxiv.org/abs/2303.14089 · HTML: https://mlsanity.com/paper/2303.14089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Dataset Growth in Medical Image Analysis Research](https://mlsanity.com/paper/1908.07765/) (2019)
- [Did You Get What You Paid For? Rethinking Annotation Cost of Deep Learning Based Computer Aided Detection in Chest Radiographs](https://mlsanity.com/paper/2209.15314/) (2022)
- [Radiologist-level stroke classification on non-contrast CT scans with Deep U-Net](https://mlsanity.com/paper/2003.14287/) (2020)

## Abstract (arXiv)

In Computed Tomography, machine learning is often used for automated data processing. However, increasing model complexity is accompanied by increasingly large volume datasets, which in turn increases the cost of model training. Unlike most work that mitigates this by advancing model architectures and training algorithms, we consider the annotation procedure and its effect on the model performance. We assume three main virtues of a good dataset collected for a model training to be label quality, diversity, and completeness. We compare the effects of those virtues on the model performance using open medical CT datasets and conclude, that quality is more important than diversity early during labeling; the diversity, in turn, is more important than completeness. Based on this conclusion and additional experiments, we propose a labeling procedure for the segmentation of tomographic images to minimize efforts spent on labeling while maximizing the model performance.