Self-supervised Learning for Segmentation and Quantification of Dopamine Neurons in Parkinson's Disease

no code implementations • 11 Jan 2023 • Fatemeh Haghighi, Soumitra Ghosh, Hai Ngu, Sarah Chu, Han Lin, Mohsen Hejrati, Baris Bingol, Somaye Hashemifar

To this end, we propose an end-to-end deep learning framework based on self-supervised learning for the segmentation and quantification of dopaminergic neurons in PD animal models.

Self-Supervised Learning

Multiclass Semantic Segmentation to Identify Anatomical Sub-Regions of Brain and Measure Neuronal Health in Parkinson's Disease

no code implementations • 7 Jan 2023 • Hosein Barzekar, Hai Ngu, Han Hui Lin, Mohsen Hejrati, Steven Ray Valdespino, Sarah Chu, Baris Bingol, Somaye Hashemifar, Soumitra Ghosh

Automated segmentation of anatomical sub-regions with high precision has become a necessity to enable the quantification and characterization of cells/ tissues in histology images.

Data Augmentation Semantic Segmentation

Robust Alzheimer's Progression Modeling using Cross-Domain Self-Supervised Deep Learning

no code implementations • 15 Nov 2022 • Saba Dadsetan, Mohsen Hejrati, Shandong Wu, Somaye Hashemifar

We also show that pretraining on extended (but not labeled) brain MRI data outperforms pretraining on natural images.

regression Self-Supervised Learning

DeepAD: A Robust Deep Learning Model of Alzheimer's Disease Progression for Real-World Clinical Applications

no code implementations • 17 Mar 2022 • Somaye Hashemifar, Claudia Iriondo, Evan Casey, Mohsen Hejrati, for Alzheimer's Disease Neuroimaging Initiative

Our proposed model integrates high dimensional MRI features from a 3D convolutional neural network with other data modalities, including clinical and demographic information, to predict the future trajectory of patients.

Multi-Task Learning