Classification of Computed Tomography Images in Different Slice Positions Using Deep Learning

Abstract

This study aimed at elucidating the relationship between the number of computed tomography (CT) images, including data concerning the accuracy of models and contrast enhancement for classifying the images. We enrolled 1539 patients who underwent contrast or noncontrast CT imaging, followed by dividing the CT imaging dataset for creating classification models into 10 classes for brain, neck, chest, abdomen, and pelvis with contrast-enhanced and plain imaging. The number of images prepared in each class were 100, 500, 1000, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, and 10,000. Accordingly, the names of datasets were defined as 0.1K, 0.5K, 1K, 2K, 3K, 4K, 5K, 6K, 7K, 8K, 9K, and 10K, respectively. We subsequently created and evaluated the models and compared the convolutional neural network (CNN) architecture between AlexNet and GoogLeNet. The time required for training models of AlexNet was lesser than that for GoogLeNet. The best overall accuracy for the classification of 10 classes was 0.721 with the 10K dataset of GoogLeNet. Furthermore, the best overall accuracy for the classification of the slice position without contrast media was 0.862 with the 2K dataset of AlexNet.

Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning

“…Third, the number of training images in this study was 1200, including the images used for validation of the training. Another study [11] showed that the number of training images affected the accuracy of deep learning. Therefore, a larger number of images would improve the detection rates of the anatomy and the accuracy rates of the standard line.…”

“…These deep learning technologies have also been applied to medical images. Examples include computed tomography image classification [10,11], feature extraction [12,13] and automatic detection of lung tumors [14,15], and automatic detection of breast tumors on X-ray images [16,17]. These machine-aided diagnostic techniques have supported the efforts of radiologists to achieve more accurate diagnoses and tumor detection.…”

Evaluating the Overall Accuracy of Additional Learning and Automatic Classification System for CT Images

“…Deep learning techniques [1][2][3], including deep convolutional neural networks (CNNs), are being employed widely in the field of image processing to conduct image classification [4][5][6], object detection [7,8], and image segmentation [9][10][11][12] tasks. Recently, many studies [4][5][6][7][8][9][10][11][12][13][14][15][16][17] have investigated the applications of deep learning techniques in medical imaging, which now serve as an expansion to this field.…”

“…Although a large number of CT and MRI images are being generated from daily medical examinations, these images are referred to as a follow-up for only a few specific patients. There are many existing models [4][5][6][7]13] for the classification of medical images; however, these models are not usually updated since they are created only when needed. Thus, it is not possible to improve such models because they lack procedures and feasibility to retrain the additional medical images.…”

“…Herein, we focus on additional learning and automatic learning for CT images because a current CT scanner has the ability to generate a large number of images per examination. Although there is an existing report [13] on the classification of CT images including contrast enhancement data, there are no reports on the classification of medical images based on the evaluation of the additional learning and automatic image learning system. This study aims to evaluate the overall accuracy of the additional learning and the automatic classification systems for CT images.…”