(searched for: doi:10.1038/s41591-021-01342-5)
JACC: Cardiovascular Imaging; doi:10.1016/j.jcmg.2021.06.007
Download : Download high-res image (35KB)Download : Download full-size image
Biomedicines, Volume 9; doi:10.3390/biomedicines9070720
Artificial intelligence (AI) is being increasingly adopted in medical research and applications. Medical AI devices have continuously been approved by the Food and Drug Administration in the United States and the responsible institutions of other countries. Ultrasound (US) imaging is commonly used in an extensive range of medical fields. However, AI-based US imaging analysis and its clinical implementation have not progressed steadily compared to other medical imaging modalities. The characteristic issues of US imaging owing to its manual operation and acoustic shadows cause difficulties in image quality control. In this review, we would like to introduce the global trends of medical AI research in US imaging from both clinical and basic perspectives. We also discuss US image preprocessing, ingenious algorithms that are suitable for US imaging analysis, AI explainability for obtaining informed consent, the approval process of medical AI devices, and future perspectives towards the clinical application of AI-based US diagnostic support technologies.
Published: 25 May 2021
Deep learning (DL) has been applied with success in proofs of concept across biomedical imaging, including across modalities and medical specialties 1–17. Labeled data is critical to training and testing DL models, and such models traditionally require large amounts of training data, straining the limited (human) resources available for expert labeling/annotation. It would be ideal to prioritize labeling those images that are most likely to improve model performance and skip images that are redundant. However, straightforward, robust, and quantitative metrics for measuring and eliminating redundancy in datasets have not yet been described. Here, we introduce a new method, ENRICH (Eliminate Needless Redundancy for Imaging Challenges), for assessing image dataset redundancy and test it on a well-benchmarked medical imaging dataset3. First, we compute pairwise similarity metrics for images in a given dataset, resulting in a matrix of pairwise-similarity values. We then rank images based on this matrix and use these rankings to curate the dataset, to minimize dataset redundancy. Using this method, we achieve similar AUC scores in a binary classification task with just a fraction of our original dataset (AUC of 0.99 ± 1.35e-05 on 44 percent of available images vs. AUC of 0.99 ± 9.32e-06 on all available images, p-value 0.0002) and better scores than same-sized training subsets chosen at random. We also demonstrate similar Jaccard sores in a multi-class segmentation task while eliminating redundant images. (average Jaccard index of 0.58 on 80 percent of available images vs 0.60 on all available images). Thus, algorithms that reduce dataset redundancy based on image similarity can significantly reduce the number of training images required, while preserving performance, in medical imaging datasets.
Nature Medicine, Volume 27, pp 764-765; doi:10.1038/s41591-021-01354-1
New advances in machine learning could facilitate and reduce disparities in the prenatal diagnosis of congenital health disease, the most common and lethal birth defect.