Semantic Segmentation of Neuronal Bodies in Fluorescence Microscopy Using a 2D+3D CNN Training Strategy with Sparsely Annotated Data

  title={Semantic Segmentation of Neuronal Bodies in Fluorescence Microscopy Using a 2D+3D CNN Training Strategy with Sparsely Annotated Data},
  author={Filippo Maria Castelli and Matteo Roffilli and Giacomo Mazzamuto and Irene Costantini and Ludovico Silvestri and Francesco Saverio Pavone},
  booktitle={International Conference on Machine Learning, Optimization, and Data Science},
Semantic segmentation of neuronal structures in 3D high-resolution fluorescence microscopy imaging of the human brain cortex can take advantage of bidimensional CNNs, which yield good results in neuron localization but lead to inaccurate surface reconstruction. 3D CNNs, on the other hand, would require manually annotated volumetric data on a large scale and hence considerable human effort. Semi-supervised alternative strategies which make use only of sparse annotations suffer from longer… 
2 Citations

High-throughput widefield fluorescence imaging of 3D samples using deep learning for 2D projection image restoration

Combining axial z-sweep image acquisition with deep learning-based image restoration enables high-throughput and high-quality fluorescence imaging of complex 3D biological samples using 2D projection images.

Detailed Response to Reviewers-TMI-2021-1480

  • 2022



Automatic Segmentation of Neurons in 3D Samples of Human Brain Cortex

A machine vision approach based on Convolutional Neural Networks for the near real-time segmentation of neurons in three-dimensional images with high specificity and sensitivity is reported.

A combined pipeline for quantitative analysis of human brain cytoarchitecture

A pipeline that solves the problem of performing neuronal mapping in large human brain samples at micrometer resolution and makes it possible to study the structural organization of the brain and expands the histopathological studies to the third dimension is proposed.

Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

This simple and efficient method of semi-supervised learning for deep neural networks is proposed, trained in a supervised fashion with labeled and unlabeled data simultaneously and favors a low-density separation between classes.

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training.