Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Micro-Net: A unified model for segmentation of various objects in microscopy images

About

Object segmentation and structure localization are important steps in automated image analysis pipelines for microscopy images. We present a convolution neural network (CNN) based deep learning architecture for segmentation of objects in microscopy images. The proposed network can be used to segment cells, nuclei and glands in fluorescence microscopy and histology images after slight tuning of input parameters. The network trains at multiple resolutions of the input image, connects the intermediate layers for better localization and context and generates the output using multi-resolution deconvolution filters. The extra convolutional layers which bypass the max-pooling operation allow the network to train for variable input intensities and object size and make it robust to noisy data. We compare our results on publicly available data sets and show that the proposed network outperforms recent deep learning algorithms.

Shan E Ahmed Raza, Linda Cheung, Muhammad Shaban, Simon Graham, David Epstein, Stella Pelengaris, Michael Khan, Nasir M. Rajpoot• 2018

Related benchmarks

TaskDatasetResultRank
Nuclei Instance SegmentationPanNuke
Neoplastic Score50.4
39
Nuclei DetectionPanNuke averaged across three dataset splits
Precision0.78
31
Nuclei Instance SegmentationCoNSeP (test)
PQ0.449
26
Nuclear Instance SegmentationCoNSeP
DICE79.4
22
Nuclear SegmentationKumar 18 (test)
B-Dice79.7
17
Nuclei ClassificationPanNuke
Neoplastic Precision59
15
Gland SegmentationWarwick-QU GLaS (test A)
F1 Score0.913
14
Gland SegmentationWarwick-QU GLaS (Overall)
Rank Sum21
14
Gland SegmentationWarwick-QU GLaS (test B)
F1 Score0.724
14
Nuclear Instance SegmentationKumar
DICE79.7
14
Showing 10 of 23 rows

Other info

Follow for update