Automated Training of Deep Convolutional Neural Networks for Cell Segmentation

By Sajith Kecheril Sadanandan, Petter Ranefall, S. Le Guyader, Carolina Wählby. 2017

130 citations recorded by the source corpus.

Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automatically using fluorescently labeled cells, perform similar to manual annotations.

Subfields: Artificial Intelligence, Biophysics, Computer Vision and Pattern Recognition, Media Technology, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. William Graf
2. Erick Moen
3. Markus W. Covert
4. Takamasa Kudo
5. David Van Valen
6. D. Bannon

In Computer Vision and Pattern Recognition

1. William Graf
2. Erick Moen
3. Markus W. Covert
4. Takamasa Kudo
5. David Van Valen
6. D. Bannon

Citations in the corpus

• Deep learning for cellular image analysis (2019, methodology): “In other strategies, the curated outputs of traditional computer-vision pipelines have been used as training data 54 .”
• In silico labeling: Predicting fluorescent labels in unlabeled images (2018, unknown): “(Sadanandan et al., 2017) used deep learning to segment cells from bright field z-stacks, and also showed that cell nuclei can be segmented from non-nuclei fluorescent markers.”