Objectives This study aimed to develop a dual-input convolutional neural network (CNN)–based deep-learning algorithm that utilizes both anteroposterior (AP) and lateral elbow radiographs for the automated detection of pediatric supracondylar fracture in conventional radiography, and assess its feasibility and diagnostic performance. Materials and Methods To develop the deep-learning model, 1266 pairs of AP and lateral elbow radiographs examined between January 2013 and December 2017 at a single institution were split into a training set (1012 pairs, 79.9%) and a validation set (254 pairs, 20.1%). We performed external tests using 2 types of distinct datasets: one temporally and the other geographically separated from the model development. We used 258 pairs of radiographs examined in 2018 at the same institution as a temporal test set and 95 examined between January 2016 and December 2018 at another hospital as a geographic test set. Images underwent preprocessing, including cropping and histogram equalization, and were input into a dual-input neural network constructed by merging 2 ResNet models. An observer study was performed by radiologists on the geographic test set. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the model and human readers were calculated and compared. Results Our trained model showed an AUC of 0.976 in the validation set, 0.985 in the temporal test set, and 0.992 in the geographic test set. In AUC comparison, the model showed comparable results to the human readers in the geographic test set; the AUCs of human readers were in the range of 0.977 to 0.997 (P's > 0.05). The model had a sensitivity of 93.9%, a specificity of 92.2%, a PPV of 80.5%, and an NPV of 97.8% in the temporal test set, and a sensitivity of 100%, a specificity of 86.1%, a PPV of 69.7%, and an NPV of 100% in the geographic test set. Compared with the developed deep-learning model, all 3 human readers showed a significant difference (P's < 0.05) using the McNemar test, with lower specificity and PPV in the model. On the other hand, there was no significant difference (P's > 0.05) in sensitivity and NPV between all 3 human readers and the proposed model. Conclusions The proposed dual-input deep-learning model that interprets both AP and lateral elbow radiographs provided an accurate diagnosis of pediatric supracondylar fracture comparable to radiologists.

No abstract

Background Radiologic evaluation of children with Mycoplasma pneumoniae is important for diagnosis and management. Objective To investigate the correlation between chest radiographic findings and the clinical features in children with Mycoplasma pneumoniae pneumonia. Materials and methods This study included 393 hospitalized children diagnosed with M . pneumoniae pneumonia between January 2000 and August 2016. Their clinical features and chest radiographs were reviewed. Radiographic findings were categorized and grouped as consolidation group ( lobar or segmental consolidation ) and non-consolidation group ( patchy infiltration , localized reticulonodular infiltration , or parahilar peribronchial infiltration ). Results Lobar or segmental consolidation (37%) was the most common finding, followed by parahilar or peribronchial infiltration (27%), localized reticulonodular infiltration (21%) and patchy infiltration (15%). The consolidation group was more frequently accompanied by pleural effusions (63%), compared to the non-consolidation group (16%). Compared with patients in the non-consolidation group , those in the consolidation group were associated with a significantly higher rate of hypoxia, tachypnea, tachycardia, extrapulmonary manifestations, prolonged fever, and longer periods of anti-mycoplasma therapy and hospitalization. Lobar or segmental consolidation was significantly more frequent in children ≥5 years old (44%) compared with children 2–5 years old (34%) and <2 years old (13%). Parahilar peribronchial infiltration was significantly more frequent in children <2 years old (56%) compared with children 2–5 years old (32%) and ≥5 years old (18%). Conclusion The chest radiographic findings of children with M . pneumoniae pneumonia correlate well with the clinical features. Consolidative lesions were frequently observed in older children and were associated with more severe clinical features.

No abstract