Rib fracture detection system based on deep learning

Chaohui Jin,Yanbin Tan,Liding Yao,Huogen Wang,Xiaojun Guan,Chun Wang,Xiaowei Song,Ming Chen,Minming Zhang

doi:10.1038/s41598-021-03002-7

Abstract

Rib fracture detection is time-consuming and demanding work for radiologists. This study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately. A total of 1707 patients were included in this study from a single center. We developed a novel rib fracture detection system on chest CT using a three-step algorithm. According to the examination time, 1507, 100 and 100 patients were allocated to the training set, the validation set and the testing set, respectively. Free Response ROC analysis was performed to evaluate the sensitivity and false positivity of the deep learning algorithm. Precision, recall, F1-score, negative predictive value (NPV) and detection and diagnosis were selected as evaluation metrics to compare the diagnostic efficiency of this system with radiologists. The radiologist-only study was used as a benchmark and the radiologist-model collaboration study was evaluated to assess the model’s clinical applicability. A total of 50,170,399 blocks (fracture blocks, 91,574; normal blocks, 50,078,825) were labelled for training. The F1-score of the Rib Fracture Detection System was 0.890 and the precision, recall and NPV values were 0.869, 0.913 and 0.969, respectively. By interacting with this detection system, the F1-score of the junior and the experienced radiologists had improved from 0.796 to 0.925 and 0.889 to 0.970, respectively; the recall scores had increased from 0.693 to 0.920 and 0.853 to 0.972, respectively. On average, the diagnosis time of radiologist assisted with this detection system was reduced by 65.3 s. The constructed Rib Fracture Detection System has a comparable performance with the experienced radiologist and is readily available to automatically detect rib fracture in the clinical setting with high efficacy, which could reduce diagnosis time and radiologists’ workload in the clinical practice.

Highlights

IntroductionThis study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately
Rib fracture detection is time-consuming and demanding work for radiologists
Despite the best human effort, a misdiagnosis rate between 19.2 to 26.8% was reported with chest computer tomography (CT) for rib fractures[7,8], some of which may potentially lead to serious consequences[9]

Summary

Introduction

This study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately. Zhou et al.[15], Weikert et al.[16] and Jin et al.[17] constructed several deep learning models for rib fracture detection with a high diagnostic sensitivity and specificity, in particular, such models have the advantage of dramatically reducing the diagnosis time. Since the performance of a deep learning model is highly dependent on the characteristics of the trained data, such as imaging resolution and fracture extent, the model’s generalizability remains a constant issue. Existing deep learning models often require localized data input and refinement for validation before clinical translation

Objectives

Methods

Results

Conclusion