Multi-task learning for neural image classification and segmentation using a 3D/2D contextual U-Net model

dc.contributor.advisor Dyer, Eva L.
dc.contributor.author Miano, Joseph D.
dc.contributor.committeeMember Dovrolis, Constantine
dc.contributor.department Computer Science
dc.date.accessioned 2021-06-30T17:37:17Z
dc.date.available 2021-06-30T17:37:17Z
dc.date.created 2020-05
dc.date.issued 2020-05
dc.date.submitted May 2020
dc.date.updated 2021-06-30T17:37:17Z
dc.description.abstract We present a 3D/2D Contextual U-Net model and apply it to segment and classify samples from a heterogeneous mouse brain dataset obtained via X-ray microtomography, which spans 4 distinct brain areas: Striatum, Ventral Posterior Thalamic Nucleus (VP), Cortex, and Zona Incerta (ZI). Our multi-task model takes in a 3D volume and outputs both a 2D segmentation of the central plane and the volume's brain area class, which can then be used to generate 3D reconstructions across samples with heterogeneous microstructure distributions. We investigate various properties of the model, including its quantitative segmentation and classification performance across the 4 brain regions, qualitative performance via the generation of 3D reconstructions, and interpretability via an investigation of the network's latent representations. Because our model performs both classification and segmentation, we also investigate how changing their relative weight during training, via a parameter we call lambda, affects performance and latent representations. Quantitative and qualitative results demonstrate that our model achieves reasonable segmentation and classification performance and can be scaled to large, heterogeneous brain regions. This technique could be used by neuroscientists seeking to automate the creation of multi-scale brain maps that incorporate both microstructure and brain area information.
dc.description.degree Undergraduate
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/64843
dc.language.iso en_US
dc.publisher Georgia Institute of Technology
dc.subject Neural network
dc.subject Deep learning
dc.subject Machine learning
dc.subject X-ray
dc.subject Imaging
dc.subject Segmentation
dc.subject Classification
dc.subject Multi-task
dc.subject Neuroscience
dc.subject Brain
dc.subject MTL
dc.subject U-Net
dc.subject Annotation
dc.subject Reconstruction
dc.subject Heterogeneous data
dc.subject Multi-scale
dc.title Multi-task learning for neural image classification and segmentation using a 3D/2D contextual U-Net model
dc.type Text
dc.type.genre Undergraduate Thesis
dspace.entity.type Publication
local.contributor.corporatename College of Computing
local.contributor.corporatename School of Computer Science
local.contributor.corporatename Undergraduate Research Opportunities Program
local.relation.ispartofseries Undergraduate Research Option Theses
relation.isOrgUnitOfPublication c8892b3c-8db6-4b7b-a33a-1b67f7db2021
relation.isOrgUnitOfPublication 6b42174a-e0e1-40e3-a581-47bed0470a1e
relation.isOrgUnitOfPublication 0db885f5-939b-4de1-807b-f2ec73714200
relation.isSeriesOfPublication e1a827bd-cf25-4b83-ba24-70848b7036ac
thesis.degree.level Undergraduate
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
5.28 MB
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
3.86 KB
Plain Text