Fully Automated Deep Learning System for Bone Age Assessment

By Hyunkwang Lee, Shahein H. Tajmir, Jenny Lee, Maurice Zissen, Bethel Ayele Yeshiwas, Tarik K. Alkasab, Garry Choy, Synho Do. 2017

426 citations recorded by the source corpus.

Skeletal maturity progresses through discrete phases, a fact that is used routinely in pediatrics where bone age assessments (BAAs) are compared to chronological age in the evaluation of endocrine and metabolic disorders. While central to many disease evaluations, little has changed to improve the tedious process since its introduction in 1950. In this study, we propose a fully automated deep learning pipeline to segment a region of interest, standardize and preprocess input radiographs, and perform BAA. Our models use an ImageNet pretrained, fine-tuned convolutional neural network (CNN) to achieve 57.32 and 61.40% accuracies for the female and male cohorts on our held-out test images. Female test radiographs were assigned a BAA within 1 year 90.39% and within 2 years 98.11% of the time. Male test radiographs were assigned 94.18% within 1 year and 99.00% within 2 years. Using the input occlusion method, attention maps were created which reveal what features the trained model uses to perform BAA. These correspond to what human experts look at when manually performing BAA. Finally, the fully automated BAA system was deployed in the clinical environment as a decision supporting system for more accurate and efficient BAAs at much faster interpretation time (<2 s) than the conventional method.

How researchers see this paper

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

Citations in the corpus

Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, background): “They are also being used in real-world applications in e.g. medical imaging (Lee et al., 2017), autonomous driving (Bojarski et al., 2017) and legislation (Lockett et al.).”
MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling (2018, background): “Our results support the findings by others demonstrating the applicability of deep-learning techniques for automation of bone age assessment [6, 8].”
Arti ﬁ cial Intelligence and Machine Learning in Radiology: Opportunities, Challenges, Pitfalls, and Criteria for Success (background): “” [7] A number of encouraging results have been reported in AI-enabled computer-aided diagnosis [8-14] with two achieving human-level performance [12,14].”
Deep learning in medical imaging and radiation therapy. (2018, result): “Similar trends were observed by Lee et al. 309 .”
Pediatric Bone Age Assessment Using Deep Convolutional Neural Networks (2017, background): “Thereafter, we find no sound evidence to support the suggestion that the carpal bones can be considered as the best predictor in the pre-puberty, see [14].”
Current Applications and Future Impact of Machine Learning in Radiology. (2018, unknown): “…learning applications are proposed for patient safety screening (17) or enhancement of safety reports (18), which have the potential for applications in radiology created an algorithm that accurately characterizes bone age based on inputs of hand radiographs of pediatric patients (Fig 7) (42).”
Physician Confidence in Artificial Intelligence: An Online Mobile Survey (2018, background): “…variations in low-grade gliomas [20], identify genetic phenotypes in small cell lung carcinoma [21], decrease false-positive rates in screening mammography computer-aided detection [22], improve pathologic mediastinal lymph node detection [23], and automatically perform bone age assessment [24].”