Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional
Victor Andrew A Antonio1, Naoaki Ono2, Akira Saito3
1Graduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, Japan.
International Journal of Computer Assisted Radiology and Surgery
|August 31, 2018
Summary
This study introduces a novel neural network method for classifying lung adenocarcinoma subtypes from pathological images. The sparse autoencoder achieved 98.9% accuracy, enabling better tumor analysis.
Area of Science:
- Computational pathology
- Artificial intelligence in oncology
- Image analysis and machine learning
Background:
- Convolutional neural networks (CNNs) show promise for image recognition.
- Classifying lung adenocarcinoma subtypes requires evaluating cellular distribution and phenotypic features.
Purpose of the Study:
- To develop a method for classifying lung adenocarcinoma subtypes using neural networks.
- To evaluate phenotypic features from wider areas, considering cellular distributions.
Main Methods:
- Implemented variants of autoencoders as pre-trained convolutional layers.
- Utilized a sparse deep autoencoder to minimize local information entropy.
- Applied the model for feature extraction from pathological images of lung adenocarcinoma (three transcriptome subtypes).
Main Results:
- Demonstrated successful recognition of morphological features of lung adenocarcinoma.
- Showed that larger input images are necessary for recognizing transcriptome subtypes.
- Achieved 98.9% classification accuracy using a sparse autoencoder with a specific input size.
Conclusions:
- Autoencoders show potential as a feature extraction method for pathological images.
- This approach can lead to whole slide image analysis tools for predicting molecular tumor subtypes.
Related Concept Videos
01:17Convolution Properties II
588
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
588
01:20Convolution Properties I
609
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
609
02:26Protein Networks
4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
02:18Network Covalent Solids
16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
01:47Lung Capacity
56.4K
The air in the lungs is measured in volumes and capacities. Lung volume measures reflect the amount of air taken in, released, or left over after a lung function, like a single inhalation. Lung capacity measures are sums of two or more lung volume measures.
56.4K
01:31Adrenergic Receptors: ɑ Subtype
3.0K
Adrenoceptors are classified into α and ꞵ classes based on their potencies to catecholamine agonists. α-adrenoceptors show the following order of catecholamine potency:
Adrenaline ≥ Noradrenaline >> Isoprenaline
α-adrenoceptors are further divided into α1 and α2-adrenoceptors.
α1-Adrenoceptors: These receptors are located postsynaptically on the effector organs and cause constriction of smooth muscle mediated by activation of phospholipase...
Adrenaline ≥ Noradrenaline >> Isoprenaline
α-adrenoceptors are further divided into α1 and α2-adrenoceptors.
α1-Adrenoceptors: These receptors are located postsynaptically on the effector organs and cause constriction of smooth muscle mediated by activation of phospholipase...
3.0K