Details
| Original language | English |
|---|---|
| Pages (from-to) | 1499-1513 |
| Number of pages | 15 |
| Journal | International journal of computer assisted radiology and surgery |
| Volume | 13 |
| Issue number | 10 |
| Early online date | 29 May 2018 |
| Publication status | Published - Oct 2018 |
Abstract
Purpose: Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. Methods: In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. Results: In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Conclusions: Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.
Keywords
- Convolutional neural networks, Evolutionary algorithm, Image simplification, Understanding deep learning
ASJC Scopus subject areas
- Medicine(all)
- Surgery
- Engineering(all)
- Biomedical Engineering
- Medicine(all)
- Radiology Nuclear Medicine and imaging
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Computer Science Applications
- Medicine(all)
- Health Informatics
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International journal of computer assisted radiology and surgery, Vol. 13, No. 10, 10.2018, p. 1499-1513.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Evolutionary image simplification for lung nodule classification with convolutional neural networks
AU - Lückehe, Daniel
AU - von Voigt, Gabriele
N1 - Publisher Copyright: © 2018, CARS.
PY - 2018/10
Y1 - 2018/10
N2 - Purpose: Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. Methods: In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. Results: In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Conclusions: Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.
AB - Purpose: Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. Methods: In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. Results: In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Conclusions: Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.
KW - Convolutional neural networks
KW - Evolutionary algorithm
KW - Image simplification
KW - Understanding deep learning
UR - http://www.scopus.com/inward/record.url?scp=85047667069&partnerID=8YFLogxK
U2 - 10.1007/s11548-018-1794-7
DO - 10.1007/s11548-018-1794-7
M3 - Article
C2 - 29845453
AN - SCOPUS:85047667069
VL - 13
SP - 1499
EP - 1513
JO - International journal of computer assisted radiology and surgery
JF - International journal of computer assisted radiology and surgery
SN - 1861-6410
IS - 10
ER -