# Differentiable Deconvolution for Improved Stroke Perfusion Analysis

arXiv: https://arxiv.org/abs/2103.17111 · HTML: https://mlsanity.com/paper/2103.17111/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 26 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 3 of 3)

- [Training Deep Networks with Structured Layers by Matrix Backpropagation](https://mlsanity.com/paper/1509.07838/) (2015)
- [Optimization with soft Dice can lead to a volumetric bias](https://mlsanity.com/paper/1911.02278/) (2019)
- [Perfusion parameter estimation using neural networks and data augmentation](https://mlsanity.com/paper/1810.04898/) (2018)

## Built on by (most cited first, 4 of 4)

- [ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset](https://mlsanity.com/paper/2206.06694/) (2022)
- [ISLES'24: Final Infarct Prediction with Multimodal Imaging and Clinical Data. Where Do We Stand?](https://mlsanity.com/paper/2408.10966/) (2024)
- [CT Perfusion is All We Need: 4D CNN Segmentation of Penumbra and Core in Patients With Suspected Ischemic Stroke](https://mlsanity.com/paper/2303.08757/) (2023)
- [Final infarct prediction in acute ischemic stroke](https://mlsanity.com/paper/2211.04850/) (2022)

## Abstract (arXiv)

Perfusion imaging is the current gold standard for acute ischemic stroke analysis. It allows quantification of the salvageable and non-salvageable tissue regions (penumbra and core areas respectively). In clinical settings, the singular value decomposition (SVD) deconvolution is one of the most accepted and used approaches for generating interpretable and physically meaningful maps. Though this method has been widely validated in experimental and clinical settings, it might produce suboptimal results because the chosen inputs to the model cannot guarantee optimal performance. For the most critical input, the arterial input function (AIF), it is still controversial how and where it should be chosen even though the method is very sensitive to this input. In this work we propose an AIF selection approach that is optimized for maximal core lesion segmentation performance. The AIF is regressed by a neural network optimized through a differentiable SVD deconvolution, aiming to maximize core lesion segmentation agreement with ground truth data. To our knowledge, this is the first work exploiting a differentiable deconvolution model with neural networks. We show that our approach is able to generate AIFs without any manual annotation, and hence avoiding manual rater's influences. The method achieves manual expert performance in the ISLES18 dataset. We conclude that the methodology opens new possibilities for improving perfusion imaging quantification with deep neural networks.