Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks

Abstract

Cytoarchitectonic parcellations of the human brain serve as anatomical references in multimodal atlas frameworks. They are based on analysis of cell-body stained histological sections and the identification of borders between brain areas. The de-facto standard involves a semi-automatic, reproducible border detection, but does not scale with high-throughput imaging in large series of sections at microscopical resolution. Automatic parcellation, however, is extremely challenging due to high variation in the data, and the need for a large field of view at microscopic resolution. The performance of a recently proposed Convolutional Neural Network model that addresses this problem especially suffers from the naturally limited amount of expert annotations for training. To circumvent this limitation, we propose to pre-train neural networks on a self-supervised auxiliary task, predicting the 3D distance between two patches sampled from the same brain. Compared to a random initialization, fine-tuning from these networks results in significantly better segmentations. We show that the self-supervised model has implicitly learned to distinguish several cortical brain areas -- a strong indicator that the proposed auxiliary task is appropriate for cytoarchitectonic mapping.

Accepted at MICCAI 2018

References in corpus (2)

• Siamese Regression Networks with Efficient mid-level Feature Extraction for 3D Object Pose Estimation
• Parcellation of Visual Cortex on high-resolution histological Brain Sections using Convolutional Neural Networks

Cited by in corpus (17)

• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• 3D Self-Supervised Methods for Medical Imaging
• Convolutional Neural Networks for cytoarchitectonic brain mapping at large scale
• A Self Supervised StyleGAN for Image Annotation and Classification with Extremely Limited Labels
• Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube
• Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections
• Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation
• Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images
• Instance-aware Self-supervised Learning for Nuclei Segmentation
• Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound
• Self-supervised Feature Learning via Exploiting Multi-modal Data for Retinal Disease Diagnosis
• 2D histology meets 3D topology: Cytoarchitectonic brain mapping with Graph Neural Networks
• Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays
• Region-of-interest guided Supervoxel Inpainting for Self-supervision
• An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation
• CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training