# Automated segmentation of intracranial hemorrhages from 3D CT

arXiv: https://arxiv.org/abs/2209.10648 · HTML: https://mlsanity.com/paper/2209.10648/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 21 Sep 2022.

## Builds on (most cited first, 2 of 2)

- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)

## Built on by (most cited first, 2 of 2)

- [The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge](https://mlsanity.com/paper/2301.03281/) (2023)
- [MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output](https://mlsanity.com/paper/2510.10011/) (2025)

## Abstract (arXiv)

Intracranial hemorrhage segmentation challenge (INSTANCE 2022) offers a platform for researchers to compare their solutions to segmentation of hemorrhage stroke regions from 3D CTs. In this work, we describe our solution to INSTANCE 2022. We use a 2D segmentation network, SegResNet from MONAI, operating slice-wise without resampling. The final submission is an ensemble of 18 models. Our solution (team name NVAUTO) achieves the top place in terms of Dice metric (0.721), and overall rank 2. It is implemented with Auto3DSeg.