# 2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy

arXiv: https://arxiv.org/abs/1907.12868 · HTML: https://mlsanity.com/paper/1907.12868/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation](https://mlsanity.com/paper/2207.06214/) (2022)
- [A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering](https://mlsanity.com/paper/2106.16209/) (2021)
- [Annotating Ambiguous Images: General Annotation Strategy for High-Quality Data with Real-World Biomedical Validation](https://mlsanity.com/paper/2306.12189/) (2023)
- [Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels](https://mlsanity.com/paper/2110.06592/) (2021)
- [Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy](https://mlsanity.com/paper/2110.06630/) (2021)
- [Towards deep learning-powered IVF: A large public benchmark for morphokinetic parameter prediction](https://mlsanity.com/paper/2203.00531/) (2022)

## Abstract (arXiv)

Collagen fiber orientations in bones, visible with Second Harmonic Generation (SHG) microscopy, represent the inner structure and its alteration due to influences like cancer. While analyses of these orientations are valuable for medical research, it is not feasible to analyze the needed large amounts of local orientations manually. Since we have uncertain borders for these local orientations only rough regions can be segmented instead of a pixel-wise segmentation. We analyze the effect of these uncertain borders on human performance by a user study. Furthermore, we compare a variety of 2D and 3D methods such as classical approaches like Fourier analysis with state-of-the-art deep neural networks for the classification of local fiber orientations. We present a general way to use pretrained 2D weights in 3D neural networks, such as Inception-ResNet-3D a 3D extension of Inception-ResNet-v2. In a 10 fold cross-validation our two stage segmentation based on Inception-ResNet-3D and transferred 2D ImageNet weights achieves a human comparable accuracy.