Impact of ultrasound image reconstruction method on breast lesion classification with neural transfer learning
This work addresses the sensitivity of deep learning models in medical imaging to image reconstruction variations, which is crucial for developing reliable computer-aided diagnosis systems, though it is incremental as it builds on known issues in computer vision.
The study investigated how different ultrasound image reconstruction methods affect breast lesion classification using neural transfer learning, finding that varying compression levels decreased classification performance, but data augmentation with differently reconstructed images improved robustness and efficiency.
Deep learning algorithms, especially convolutional neural networks, have become a methodology of choice in medical image analysis. However, recent studies in computer vision show that even a small modification of input image intensities may cause a deep learning model to classify the image differently. In medical imaging, the distribution of image intensities is related to applied image reconstruction algorithm. In this paper we investigate the impact of ultrasound image reconstruction method on breast lesion classification with neural transfer learning. Due to high dynamic range raw ultrasonic signals are commonly compressed in order to reconstruct B-mode images. Based on raw data acquired from breast lesions, we reconstruct B-mode images using different compression levels. Next, transfer learning is applied for classification. Differently reconstructed images are employed for training and evaluation. We show that the modification of the reconstruction algorithm leads to decrease of classification performance. As a remedy, we propose a method of data augmentation. We show that the augmentation of the training set with differently reconstructed B-mode images leads to a more robust and efficient classification. Our study suggests that it is important to take into account image reconstruction algorithms implemented in medical scanners during development of computer aided diagnosis systems.