Deep chest X-ray: Detection and classification of lesions based on deep convolutional neural networks

Cho Yongwon; Lee Sang Min; Cho Young-Hoon; Lee June-Goo; Park Beomhee; Lee Gaeun; Kim Namkug; Seo Joon Beom

首页> 外文期刊>International journal of imaging systems and technology >Deep chest X-ray: Detection and classification of lesions based on deep convolutional neural networks

【24h】

Deep chest X-ray: Detection and classification of lesions based on deep convolutional neural networks

机译：深胸X射线：基于深卷积神经网络的病变检测和分类

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

We investigated whether a convolutional neural network (CNN) can enhance the usability of computer-aided detection (CAD) of chest radiographs for various pulmonary abnormal lesions. The numbers of normal and abnormal patients were 6055 and 3463, respectively. Two radiologists delineated regions of interest for lesions and labeled the disease types as ground truths. The datasets were split into training, tuning, and testing as 7:1: 2. Total test sets were randomly selected in 1214 normal and 690 abnormal. A 5-fold, cross-validation was performed on our datasets. For the classification of normal and abnormal, we developed a CNN based on DenseNet169; for abnormal detection, The You Only Look Once (YOLO) v2 with DenseNet was used. Detection and classification of normal and five classes of diseases (nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax) on chest radiographs were analyzed. Our CNN model classified chest radiographs as normal or abnormal with an accuracy of 97.8%. For the results of the abnormal, F1 score, was 75.2 +/- 2.28% for nodules, 55.0 +/- 4.3% for consolidation, 78.2 +/- 7.85% for interstitial opacity, 81.6 +/- 2.07% for pleural effusion, and 70.0 +/- 7.97% for pneumothorax, respectively. In addition, we conducted the experiments between our method and RetinaNet with only nodules. The results of our method and RetinaNet at cutoff-0.5 in the free response operating characteristic curve were 83.45% and 80.55%, respectively. Our algorithm demonstrated viable detection and disease classification capacity and could be used for CAD of lung diseases on chest radiographs.

机译：我们调查了卷积神经网络（CNN）是否可以增强计算机辅助检测（CAD）的胸部射线照片的可用性，用于各种肺异常病变。正常和异常患者的数量分别为6055和3463。两个放射科医生描绘了病变的感兴趣区域，并将疾病类型标记为地面真理。数据集被分成培训，调整和测试为7：1：2.总测试集在1214正常和690异常中随机选择。在我们的数据集上执行5倍的交叉验证。对于正常和异常的分类，我们开发了基于Densenet169的CNN;对于异常检测，使用您只使用DENSENET的一次（YOLO）V2。分析了胸部射线照片的正常和五类疾病的检测和分类（结节[S]，结核，间质不透明度，胸腔积液和气胸）。我们的CNN模型分类为正常或异常的胸部射线照片，精度为97.8％。对于Nodules的异常，F1分数的结果为结核，合并为75.2 +/- 2.28％，间质不透明度为78.2 +/- 7.85％，胸腔积液81.6 +/- 2.07％， 30.0 +/- 7.97％的气胸。此外，我们在我们的方法和视网膜内进行了实验，只有结节。我们在自由反应操作特征曲线中截止-0.5的方法和视网膜的结果分别为83.45％和80.55％。我们的算法表现出可行的检测和疾病分类能力，可用于胸部X型射线照片上的肺病的CAD。

著录项

来源
《International journal of imaging systems and technology》 |2021年第1期|72-81|共10页
作者
Cho Yongwon; Lee Sang Min; Cho Young-Hoon; Lee June-Goo; Park Beomhee; Lee Gaeun; Kim Namkug; Seo Joon Beom;
展开▼
作者单位

Univ Ulsan Coll Med Asan Med Ctr Dept Convergence Med 88 Olymp Ro 43 Gil Seoul 05505 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea|Univ Ulsan Coll Med Asan Med Ctr Res Inst Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea|Univ Ulsan Coll Med Asan Med Ctr Res Inst Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Convergence Med 88 Olymp Ro 43 Gil Seoul 05505 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Convergence Med 88 Olymp Ro 43 Gil Seoul 05505 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Convergence Med 88 Olymp Ro 43 Gil Seoul 05505 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Convergence Med 88 Olymp Ro 43 Gil Seoul 05505 South Korea|Univ Ulsan Coll Med Asan Med Ctr Dept Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea|Univ Ulsan Coll Med Asan Med Ctr Res Inst Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea;

Univ Ulsan Coll Med Asan Med Ctr Dept Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea|Univ Ulsan Coll Med Asan Med Ctr Res Inst Radiol 88 Olymp Ro 43 Gil Seoul 138736 South Korea;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种 eng
中图分类
关键词
chest radiographs; computer-aided detection; deep learning; lung diseases; machine learning; radiography;

机译：胸部射线照片;计算机辅助检测;深入学习;肺病;机器学习;射线照相;

Deep chest X-ray: Detection and classification of lesions based on deep convolutional neural networks

摘要

著录项

相关主题

期刊订阅