Paul H Yi1,2,3, Jinchi Wei4, Tae Kyung Kim5, Jiwon Shin4, Haris I Sair5,4, Ferdinand K Hui5,4, Gregory D Hager4, Cheng Ting Lin5. 1. University of Maryland Intelligent Imaging Center, Department of Radiology, University of Maryland School of Medicine, Baltimore, MD, USA. paul@intelligentimaging.org. 2. The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA. paul@intelligentimaging.org. 3. Malone Center for Engineering in Healthcare, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA. paul@intelligentimaging.org. 4. Malone Center for Engineering in Healthcare, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA. 5. The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
Abstract
PURPOSE: To develop and test the performance of deep convolutional neural networks (DCNNs) for automated classification of age and sex on chest radiographs (CXR). METHODS: We obtained 112,120 frontal CXRs from the NIH ChestX-ray14 database performed in 48,780 females (44%) and 63,340 males (56%) ranging from 1 to 95 years old. The dataset was split into training (70%), validation (10%), and test (20%) datasets, and used to fine-tune ResNet-18 DCNNs pretrained on ImageNet for (1) determination of sex (using entire dataset and only pediatric CXRs); (2) determination of age < 18 years old or ≥ 18 years old (using entire dataset); and (3) determination of age < 11 years old or 11-18 years old (using only pediatric CXRs). External testing was performed on 662 CXRs from China. Area under the receiver operating characteristic curve (AUC) was used to evaluate DCNN test performance. RESULTS: DCNNs trained to determine sex on the entire dataset and pediatric CXRs only had AUCs of 1.0 and 0.91, respectively (p < 0.0001). DCNNs trained to determine age < or ≥ 18 years old and < 11 vs. 11-18 years old had AUCs of 0.99 and 0.96 (p < 0.0001), respectively. External testing showed AUC of 0.98 for sex (p = 0.01) and 0.91 for determining age < or ≥ 18 years old (p < 0.001). CONCLUSION: DCNNs can accurately predict sex from CXRs and distinguish between adult and pediatric patients in both American and Chinese populations. The ability to glean demographic information from CXRs may aid forensic investigations, as well as help identify novel anatomic landmarks for sex and age.
PURPOSE: To develop and test the performance of deep convolutional neural networks (DCNNs) for automated classification of age and sex on chest radiographs (CXR). METHODS: We obtained 112,120 frontal CXRs from the NIH ChestX-ray14 database performed in 48,780 females (44%) and 63,340 males (56%) ranging from 1 to 95 years old. The dataset was split into training (70%), validation (10%), and test (20%) datasets, and used to fine-tune ResNet-18 DCNNs pretrained on ImageNet for (1) determination of sex (using entire dataset and only pediatric CXRs); (2) determination of age < 18 years old or ≥ 18 years old (using entire dataset); and (3) determination of age < 11 years old or 11-18 years old (using only pediatric CXRs). External testing was performed on 662 CXRs from China. Area under the receiver operating characteristic curve (AUC) was used to evaluate DCNN test performance. RESULTS: DCNNs trained to determine sex on the entire dataset and pediatric CXRs only had AUCs of 1.0 and 0.91, respectively (p < 0.0001). DCNNs trained to determine age < or ≥ 18 years old and < 11 vs. 11-18 years old had AUCs of 0.99 and 0.96 (p < 0.0001), respectively. External testing showed AUC of 0.98 for sex (p = 0.01) and 0.91 for determining age < or ≥ 18 years old (p < 0.001). CONCLUSION: DCNNs can accurately predict sex from CXRs and distinguish between adult and pediatric patients in both American and Chinese populations. The ability to glean demographic information from CXRs may aid forensic investigations, as well as help identify novel anatomic landmarks for sex and age.
Entities:
Keywords:
Age; Chest radiograph; Deep learning; Forensic science; Radiology; Sex
Authors: Soon Ho Yoon; Hye Jin Yoo; Roh Eul Yoo; Hyun Ju Lim; Jeong Hwa Yoon; Chang Min Park; Sang Seob Lee; Seong Ho Yoo Journal: J Korean Med Sci Date: 2016-10 Impact factor: 2.153
Authors: John R Zech; Marcus A Badgeley; Manway Liu; Anthony B Costa; Joseph J Titano; Eric Karl Oermann Journal: PLoS Med Date: 2018-11-06 Impact factor: 11.069