Automated Pneumothorax Diagnosis Using Deep Neural Networks
| Autor: | Tony Lindsey, Rebecca L. Lee, Sena Veazey, Ronald D. Grisell, Saul J Vega |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Pipeline (computing) Deep learning Bayesian optimization ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 030208 emergency & critical care medicine Image processing Pattern recognition Regularization (mathematics) 03 medical and health sciences 0302 clinical medicine 030228 respiratory system Binary classification Artificial intelligence Medical diagnosis business Dropout (neural networks) |
| Zdroj: | Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications ISBN: 9783030134686 CIARP |
| DOI: | 10.1007/978-3-030-13469-3_84 |
| Popis: | Thoracic ultrasound can provide information leading to rapid diagnosis of pneumothorax with improved accuracy over the standard physical examination and with higher sensitivity than anteroposterior chest radiography. However, the clinical interpretation of a patient medical image is highly operator dependent. Furthermore, remote environments, such as the battlefield or deep-space exploration, may lack expertise for diagnosing certain pathologies. We have developed an automated image interpretation pipeline for the analysis of thoracic ultrasound data and the classification of pneumothorax events to provide decision support in such situations. Our pipeline consists of image preprocessing, data augmentation, and deep learning architectures for medical diagnosis. In this work, we demonstrate that robust, accurate interpretation of chest images and video can be achieved using deep neural networks. A number of novel image processing techniques were employed to achieve this result. Affine transformations were applied for data augmentation. Hyperparameters were optimized for learning rate, dropout regularization, batch size, and epoch iteration by a sequential model-based Bayesian approach. In addition, we utilized pretrained architectures, applying transfer learning and fine-tuning techniques to fully connected layers. Our pipeline yielded binary classification validation accuracies of \(98.3\%\) for M-mode images and \(99.8\%\) with B-mode video frames. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|