The Effect of Image Resolution on Deep Learning in Radiography.

By Carl Sabottke, B. Spieler. Radiology: Artificial Intelligence, 2020

301 citations recorded by the source corpus.

Purpose To examine variations of convolutional neural network (CNN) performance for multiple chest radiograph diagnoses and image resolutions. Materials and Methods This retrospective study examined CNN performance using the publicly available National Institutes of Health chest radiograph dataset comprising 112 120 chest radiographic images from 30 805 patients. The network architectures examined included ResNet34 and DenseNet121. Image resolutions ranging from 32 × 32 to 600 × 600 pixels were investigated. Network training paradigms used 80% of samples for training and 20% for validation. CNN performance was evaluated based on area under the receiver operating characteristic curve (AUC) and label accuracy. Binary output networks were trained separately for each label or diagnosis under consideration. Results Maximum AUCs were achieved at image resolutions between 256 × 256 and 448 × 448 pixels for binary decision networks targeting emphysema, cardiomegaly, hernias, edema, effusions, atelectasis, masses, and nodules. When comparing performance between networks that utilize lower resolution (64 × 64 pixels) versus higher (320 × 320 pixels) resolution inputs, emphysema, cardiomegaly, hernia, and pulmonary nodule detection had the highest fractional improvements in AUC at higher image resolutions. Specifically, pulmonary nodule detection had an AUC performance ratio of 80.7% ± 1.5 (standard deviation) (0.689 of 0.854) whereas thoracic mass detection had an AUC ratio of 86.7% ± 1.2 (0.767 of 0.886) for these image resolutions. Conclusion Increasing image resolution for CNN training often has a trade-off with the maximum possible batch size, yet optimal selection of image resolution has the potential for further increasing neural network performance for various radiology-based machine learning tasks. Furthermore, identifying diagnosis-specific tasks that require relatively higher image resolution can potentially provide insight into the relative difficulty of identifying different radiology findings. Supplemental material is available for this article. © RSNA, 2020See also the commentary by Lakhani in this issue.

Subfields: Artificial Intelligence, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/5ffcddcb9c8a0d916719b9767449fefee7998b48

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yogesh Kumar
  2. Ruchika Singla
  3. Apeksha Koul
  4. Muhammad Fazal Ijaz

In Pulmonary and Respiratory Medicine

  1. Yogesh Kumar
  2. Ruchika Singla
  3. Apeksha Koul
  4. Muhammad Fazal Ijaz

In Radiology, Nuclear Medicine and Imaging

  1. Yogesh Kumar
  2. Ruchika Singla
  3. Apeksha Koul
  4. Muhammad Fazal Ijaz

Citations in the corpus