Gastrointestinal tract classification using improved LSTM based CNN
- PDF / 1,612,578 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 13 Downloads / 306 Views
Gastrointestinal tract classification using improved LSTM based CNN Şaban Öztürk 1
& Umut Özkaya
2
Received: 6 August 2019 / Revised: 28 June 2020 / Accepted: 28 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Automated medical image analysis is a challenging field of research that has become quite widespread recently. This process, which is advantageous in terms of both cost and time, is problematic in terms of obtaining annotated data and lack of uniformity. Artificial intelligence is beneficial in the automatic detection of many diseases where early diagnosis is vital for human life. In this study, an effective classification method is presented for a gastrointestinal tract classification task that contains a small number of labeled data and has a sample number of imbalance between classes. According to our approach, using an effective classifier at the end of the convolutional neural network (CNN) structure produces the desired performance even if the CNN structure is not strongly trained. For this purpose, a highly efficient Long Short-Term Memory (LSTM) structure is designed and added to the output of the CNN. Experiments are conducted using AlexNet, GoogLeNet, and ResNet architectures to test the contribution of the proposed approach to the classification performance. Besides, three different experiments are carried out for each architecture where the sample numbers are kept constant as 2500, 5000, and 7500. All experiments are repeated with CNN + ANN and CNN + SVM architectures to compare the performance of our framework. The proposed method has a more successful classification performance than other state-of-the-art methods with 97.90% accuracy. Keywords Colorectal cancer . Endoscopic images . Deep learning . LSTM . Transfer learning
1 Introduction Colorectal cancer (CRC) is caused by the occurrence of malignant polyps in the colon. According to obtained statistical information, colon cancer is one of the most common types
* Şaban Öztürk [email protected]
1
Technology Faculty, Electrical and Electronics Engineering, Amasya University, Amasya, Turkey
2
Engineering and Natural Science Faculty, Electrical and Electronics Engineering, Konya Technical University, Konya, Turkey
Multimedia Tools and Applications
of cancer in the United States [33]. This type of cancer is the third most common type of cancer worldwide and is the second most common cause of mortality [7]. Since early diagnosis is very important for human life, it is highly burdened by expert doctors. Some polyps are likely to be missed if only expert knowledge is used to detect these polyps. Therefore, it is advantageous to use the computer-aided diagnosis (CAD) systems and machine learning algorithms. Machine learning (ML) systems have been used effectively in the analysis of images and videos for many years [23]. When we look at the recent trend of ML, it is generally seen that there is a concentration in the medical field [34]. Firstly, medical imaging systems have become widespread,
Data Loading...
