|
|
|
|
LEADER |
04126nam a2200985Ia 4500 |
001 |
10.1109-JBHI.2020.3039414 |
008 |
220427s2021 CNT 000 0 und d |
020 |
|
|
|a 21682194 (ISSN)
|
245 |
1 |
0 |
|a Generalized Fixation Invariant Nuclei Detection through Domain Adaptation Based Deep Learning
|
260 |
|
0 |
|b Institute of Electrical and Electronics Engineers Inc.
|c 2021
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1109/JBHI.2020.3039414
|
520 |
3 |
|
|a Nucleus detection is a fundamental task in histological image analysis and an important tool for many follow up analyses. It is known that sample preparation and scanning procedure of histological slides introduce a great amount of variability to the histological images and poses challenges for automated nucleus detection. Here, we studied the effect of histopathological sample fixation on the accuracy of a deep learning based nuclei detection model trained with hematoxylin and eosin stained images. We experimented with training data that includes three methods of fixation; PAXgene, formalin and frozen, and studied the detection accuracy results of various convolutional neural networks. Our results indicate that the variability introduced during sample preparation affects the generalization of a model and should be considered when building accurate and robust nuclei detection algorithms. Our dataset includes over 67 000 annotated nuclei locations from 16 patients and three different sample fixation types. The dataset provides excellent basis for building an accurate and robust nuclei detection model, and combined with unsupervised domain adaptation, the workflow allows generalization to images from unseen domains, including different tissues and images from different labs. © 2013 IEEE.
|
650 |
0 |
4 |
|a accuracy
|
650 |
0 |
4 |
|a algorithm
|
650 |
0 |
4 |
|a Article
|
650 |
0 |
4 |
|a artificial neural network
|
650 |
0 |
4 |
|a cancer grading
|
650 |
0 |
4 |
|a cell nucleus
|
650 |
0 |
4 |
|a Cell Nucleus
|
650 |
0 |
4 |
|a colonoscopy
|
650 |
0 |
4 |
|a computer assisted tomography
|
650 |
0 |
4 |
|a computer language
|
650 |
0 |
4 |
|a computer model
|
650 |
0 |
4 |
|a controlled study
|
650 |
0 |
4 |
|a convolutional neural network
|
650 |
0 |
4 |
|a Convolutional neural networks
|
650 |
0 |
4 |
|a decision tree
|
650 |
0 |
4 |
|a deep learning
|
650 |
0 |
4 |
|a Deep learning
|
650 |
0 |
4 |
|a Deep learning
|
650 |
0 |
4 |
|a Deep Learning
|
650 |
0 |
4 |
|a Detection accuracy
|
650 |
0 |
4 |
|a detection algorithm
|
650 |
0 |
4 |
|a digital pathology
|
650 |
0 |
4 |
|a domain adaptation
|
650 |
0 |
4 |
|a Domain adaptation
|
650 |
0 |
4 |
|a electroencephalography
|
650 |
0 |
4 |
|a eosin
|
650 |
0 |
4 |
|a follow up
|
650 |
0 |
4 |
|a Follow up
|
650 |
0 |
4 |
|a formaldehyde
|
650 |
0 |
4 |
|a formalin-fixed
|
650 |
0 |
4 |
|a frozen section
|
650 |
0 |
4 |
|a frozen section
|
650 |
0 |
4 |
|a gray matter
|
650 |
0 |
4 |
|a hematoxylin
|
650 |
0 |
4 |
|a histogram
|
650 |
0 |
4 |
|a Histological images
|
650 |
0 |
4 |
|a Histological Techniques
|
650 |
0 |
4 |
|a histology
|
650 |
0 |
4 |
|a histopathology
|
650 |
0 |
4 |
|a human
|
650 |
0 |
4 |
|a human tissue
|
650 |
0 |
4 |
|a Humans
|
650 |
0 |
4 |
|a image analysis
|
650 |
0 |
4 |
|a image processing
|
650 |
0 |
4 |
|a Image Processing, Computer-Assisted
|
650 |
0 |
4 |
|a image quality
|
650 |
0 |
4 |
|a image reconstruction
|
650 |
0 |
4 |
|a image segmentation
|
650 |
0 |
4 |
|a immunohistochemistry
|
650 |
0 |
4 |
|a knee
|
650 |
0 |
4 |
|a learning
|
650 |
0 |
4 |
|a machine learning
|
650 |
0 |
4 |
|a nerve cell network
|
650 |
0 |
4 |
|a Neural Networks, Computer
|
650 |
0 |
4 |
|a nuclei detection
|
650 |
0 |
4 |
|a Nuclei detections
|
650 |
0 |
4 |
|a PAXgene-fixed
|
650 |
0 |
4 |
|a predictive value
|
650 |
0 |
4 |
|a prostatectomy
|
650 |
0 |
4 |
|a Sample preparation
|
650 |
0 |
4 |
|a support vector machine
|
650 |
0 |
4 |
|a tissue fixation
|
650 |
0 |
4 |
|a tissue fixation
|
650 |
0 |
4 |
|a training
|
650 |
0 |
4 |
|a Training data
|
650 |
0 |
4 |
|a validation process
|
650 |
0 |
4 |
|a white matter
|
650 |
0 |
4 |
|a workflow
|
700 |
1 |
|
|a Bova, G.S.
|e author
|
700 |
1 |
|
|a Hognas, G.
|e author
|
700 |
1 |
|
|a Ruusuvuori, P.
|e author
|
700 |
1 |
|
|a Valkonen, M.
|e author
|
773 |
|
|
|t IEEE Journal of Biomedical and Health Informatics
|