Lee, HyunkwangYune, SehyoMansouri, MohammadKim, MyeongchanTajmir, Shahein H.Guerrier, Claude E.Ebert, Sarah A.Pomerantz, StuartRomero, JavierKamalian, MohammadGonzalez, RamonLev, MichaelDo, Synho2022-03-212018-12-17Lee, Hyunkwang, Sehyo Yune, Mohammad Mansouri, Myeongchan Kim, Shahein H. Tajmir, Claude E. Guerrier, Sarah A. Ebert et al. "An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets." Nature Biomedical Engineering 3, no. 3 (2018): 173-182. DOI: 10.1038/s41551-018-0324-92157-846Xhttps://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37371238Owing to improvements in image recognition via deep learning, machine-learning algorithms could eventually be applied to automated medical diagnoses that can guide clinical decision-making. However, these algorithms remain a 'black box' in terms of how they generate the predictions from the input data. Also, high-performance deep learning requires large, high-quality training datasets. Here, we report the development of an understandable deep-learning system that detects acute intracranial haemorrhage (ICH) and classifies five ICH subtypes from unenhanced head computed-tomography scans. By using a dataset of only 904 cases for algorithm training, the system achieved a performance similar to that of expert radiologists in two independent test datasets containing 200 cases (sensitivity of 98% and specificity of 95%) and 196 cases (sensitivity of 92% and specificity of 95%). The system includes an attention map and a prediction basis retrieved from training data to enhance explainability, and an iterative process that mimics the workflow of radiologists. Our approach to algorithm development can facilitate the development of deep-learning systems for a variety of clinical applications and accelerate their adoption into clinical practice.en-USComputer Science ApplicationsBiomedical EngineeringMedicine (miscellaneous)BioengineeringBiotechnologyJournal Article2022-03-2110.1038/s41551-018-0324-9