AUTHOR=Li Qingling , Zhu Yanhua , Chen Minglin , Guo Ruomi , Hu Qingyong , Lu Yaxin , Deng Zhenghui , Deng Songqing , Zhang Tiecheng , Wen Huiquan , Gao Rong , Nie Yuanpeng , Li Haicheng , Chen Jianning , Shi Guojun , Shen Jun , Cheung Wai Wilson , Liu Zifeng , Guo Yulan , Chen Yanming 

TITLE=Development and Validation of a Deep Learning Algorithm to Automatic Detection of Pituitary Microadenoma From MRI

JOURNAL=Frontiers in Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2021.758690

DOI=10.3389/fmed.2021.758690

ISSN=2296-858X

ABSTRACT=ABSTRACT
Background: It is often difficult to diagnose pituitary microadenoma (PM) by magnetic resonance imaging (MRI) alone, due to its relatively small in size, variable anatomical structure, complex clinical symptoms and signs among individuals. We develop and validate a deep learning based system to diagnose PM from MRI. 
Methods: A total of 11,935 infertility participants were initially recruited for this project. After applying the exclusion criteria, 1,520 participants (556 PM patients and 964 controls subjects) were included for further stratified into 3 non-overlapping cohorts. The data used for training set were derived from a retrospective study, and in validation dataset, a prospective temporal and geographical validation set were adopted. A total of 780 participants were used for training, 195 participants for testing and 545 participants were used to validate the diagnosis performance. The PM-CAD (define PM-CAD) system consists of two parts: pituitary region detection and PM diagnosis. The diagnosis performance of PM-CAD system was measured using the ROC curve and AUC (area under the ROC curve), calibration curve, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1-score. 
Results PM-CAD system showed 94.36% diagnostic accuracy and 98.13% AUC score in testing dataset. We confirm the robustness and generalization of our PM-CAD system, the diagnostic accuracy in internal dataset was 96.50%, in external dataset was 92.26% and 92.36%, the AUC was 95.5%, 94.7% and 93.7%, respectively. In human-computer competition, the diagnosis performance of our PM-CAD system was comparable to radiologists with > 10 years of professional expertise (diagnosis accuracy of 94.0% versus 95.0%, AUC of 95.6% versus 95.0%). For the misdiagnosis cases from radiologists, our system showed the 100% accuracy diagnosis. A browser-based software was designed to assistant the PM diagnosis.
Conclusions: This is the first report showing that PM-CAD system is a viable tool for detecting PM. Our results suggest that PM-CAD system is applicable to radiology departments, especially in primary health care institutions.