1 January 2019 in Investigative Radiology
Objectives: The aim of this study was to compare the diagnostic performance of a deep learning algorithm with that of radiologists in diagnosing maxillary sinusitis on Waters’ view radiographs. Materials and Methods: Among 80,475 Waters’ view radiographs, examined between May 2003 and February 2017, 9000 randomly selected cases were classified as normal or maxillary sinusitis based on radiographic findings and divided into training (n = 8000) and validation (n = 1000) sets to develop a deep learning algorithm. Two test sets composed of Waters’ view radiographs with concurrent paranasal sinus computed tomography were labeled based on computed tomography findings: one with temporal separation (n = 140) and the other with geographic separation (n = 200) from the training set. Area under the receiver operating characteristics curve (AUC), sensitivity, and specificity of the algorithm and 5 radiologists were assessed. Interobserver agreement between the algorithm and majority decision of the radiologists was measured. The correlation coefficient between the predicted probability of the algorithm and average confidence level of the radiologists was determined. Results: The AUCs of the deep learning algorithm were 0.93 and 0.88 for the temporal and geographic external test sets, respectively. The AUCs of the radiologists were 0.83 to 0.89 for the temporal and 0.75 to 0.84 for the geographic external test sets. The deep learning algorithm showed statistically significantly higher AUC than radiologist in both test sets. In terms of sensitivity and specificity, the deep learning algorithm was comparable to the radiologists. A strong interobserver agreement was noted between the algorithm and radiologists (Cohen κ coefficient, 0.82). The correlation coefficient between the predicted probability of the algorithm and confidence level of radiologists was 0.89 and 0.84 for the 2 test sets, respectively. Conclusions: The deep learning algorithm could diagnose maxillary sinusitis on Waters’ view radiograph with superior AUC and comparable sensitivity and specificity to those of radiologists.
16 July 2020 in Head & Neck
1 July 2019 in American Journal of Roentgenology
OBJECTIVE. The objective of our study was to compare the sensitivity of a deep learning (DL) algorithm with the assessments by radiologists in diagnosing osteonecrosis of the femoral head (ONFH) using digital radiography. MATERIALS AND METHODS. We performed a two-center, retrospective, noninferiority study of consecutive patients (≥ 16 years old) with a diagnosis of ONFH based on MR images. We investigated the following four datasets of unilaterally cropped hip anteroposterior radiographs: training (n = 1346), internal validation (n = 148), temporal external test (n = 148), and geographic external test (n = 250). Diagnostic performance was measured for a DL algorithm, a less experienced radiologist, and an experienced radiologist. Noninferiority analyses for sensitivity were performed for the DL algorithm and both radiologists. Subgroup analysis for precollapse and postcollapse ONFH was done. RESULTS. Overall, 1892 hips (1037 diseased and 855 normal) were included. Sensitivity and specificity for the temp...
5 February 2020 in European Radiology
1 December 2018 in American Journal of Roentgenology
The objective of our study was to evaluate the association between anterior tibial translation and injuries on the posterior horn medial meniscus (PHMM) and the integrity of the brake stop mechanism of the PHMM in the anterior cruciate ligament (ACL)-deficient knee. This retrospective study included 85 consecutive patients with an arthroscopically confirmed complete ACL tear. Anterior tibial translation was quantitatively measured using sagittal MRI at the midpoint of the lateral femoral condyle. The "uncovered medial meniscus" sign was considered positive if a vertical line tangent to the posteriormost margin of the medial tibial plateau intersected the PHMM at the midpoint of the medial femoral condyle on sagittal MRI. Concomitant injuries on the structures of the posteromedial and posterolateral corners of the knee, including PHMM tear and meniscal ramp lesion, were recorded. Stratified subgroup analysis and multivariable regression analysis were performed to identify factors associated with anterior tibial translation. The uncovered medial meniscus sign was positive in 21.2% (18/85) of patients and was significantly associated with anterior tibial translation. In the stratified subgroup analysis and multivariable regression analysis, positive uncovered medial meniscus sign consistently showed a significant association with anterior tibial translation and generated an additional 2.8 mm of anterior tibial translation. Other injuries, including PHMM tear and meniscal ramp lesion, were not associated with anterior tibial translation. The uncovered medial meniscus sign showed a statistically significant correlation with anterior tibial translation and could be a useful marker for the lost brake stop mechanism of PHMM in the ACL-deficient knee.