Supervised Learning With Perceptual Similarity for Multimodal Gene Expression Registration of a Mouse Brain Atlas
| Autor: | Henry Markram, Francesco Casalegno, Jan Krepl, Felix Schürmann, Huanxiang Lu, Csaba Erö, Daniel Keller, Emilie Delattre, Dimitri Rodarie |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Individual gene
Computer science gene expression brain atlas Biomedical Engineering Neuroscience (miscellaneous) Image registration Neurosciences. Biological psychiatry. Neuropsychiatry perceptual similarity 03 medical and health sciences 0302 clinical medicine Methods allen mouse brain atlas 030304 developmental biology 0303 health sciences business.industry Deep learning Supervised learning Brain atlas deep learning Pattern recognition Perceptual similarity Expression (mathematics) non-rigid Computer Science Applications image registration machine learning multimodal image registration Artificial intelligence business 030217 neurology & neurosurgery Neuroscience RC321-571 |
| Zdroj: | Frontiers in Neuroinformatics, Vol 15 (2021) Frontiers in Neuroinformatics |
| ISSN: | 1662-5196 |
| DOI: | 10.3389/fninf.2021.691918 |
| Popis: | The acquisition of high quality maps of gene expression in the rodent brain is of fundamental importance to the neuroscience community. The generation of such datasets relies on registering individual gene expression images to a reference volume, a task encumbered by the diversity of staining techniques employed, and by deformations and artifacts in the soft tissue. Recently, deep learning models have garnered particular interest as a viable alternative to traditional intensity-based algorithms for image registration. In this work, we propose a supervised learning model for general multimodal 2D registration tasks, trained with a perceptual similarity loss on a dataset labeled by a human expert and augmented by synthetic local deformations. We demonstrate the results of our approach on the Allen Mouse Brain Atlas (AMBA), comprising whole brain Nissl and gene expression stains. We show that our framework and design of the loss function result in accurate and smooth predictions. Our model is able to generalize to unseen gene expressions and coronal sections, outperforming traditional intensity-based approaches in aligning complex brain structures. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|