Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional networks

Purpose Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phe...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal for computer assisted radiology and surgery Ročník 13; číslo 12; s. 1905 - 1913
Hlavní autori:	Antonio, Victor Andrew A., Ono, Naoaki, Saito, Akira, Sato, Tetsuo, Altaf-Ul-Amin, Md, Kanaya, Shigehiko
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Cham Springer International Publishing 01.12.2018 Springer Nature B.V
Predmet:	Adenocarcinoma of Lung - classification Adenocarcinoma of Lung - diagnosis Adenocarcinoma of Lung - genetics Artificial neural networks Biopsy Classification Computer Imaging Computer Science Entropy (Information theory) Feature extraction Feature recognition Health Informatics Humans Image analysis Image classification Image Processing, Computer-Assisted - methods Imaging Medicine Medicine & Public Health Neural networks Neural Networks (Computer) Object recognition Original Original Article Pattern recognition Pattern Recognition and Graphics Radiology Surgery Transcriptome Tumors Vision Deep learning Autoencoder Independent subspace analysis Lung cancer Computer-aided diagnosis
ISSN:	1861-6410, 1861-6429, 1861-6429
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Purpose Convolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular distributions. Methods In order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size 2048 × 2048 . We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger images. Results We were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with 2048 × 2048 input provides a 98.9% classification accuracy. Conclusion This study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1861-6410 1861-6429 1861-6429
DOI:	10.1007/s11548-018-1835-2