Abstract
Accurate image interpretation of Waters’ and Caldwell view radiographs used for sinusitis screening is challenging. Therefore, we developed a deep learning algorithm for diagnosing frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views. The datasets were selected for the training and validation set (n = 1403, sinusitis% = 34.3%) and the test set (n = 132, sinusitis% = 29.5%) by temporal separation. The algorithm can simultaneously detect and classify each paranasal sinus using both Waters’ and Caldwell views without manual cropping. Single- and multi-view models were compared. Our proposed algorithm satisfactorily diagnosed frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views (area under the curve (AUC), 0.71 (95% confidence interval, 0.62–0.80), 0.78 (0.72–0.85), and 0.88 (0.84–0.92), respectively). The one-sided DeLong’s test was used to compare the AUCs, and the Obuchowski–Rockette model was used to pool the AUCs of the radiologists. The algorithm yielded a higher AUC than radiologists for ethmoid and maxillary sinusitis (p = 0.012 and 0.013, respectively). The multi-view model also exhibited a higher AUC than the single Waters’ view model for maxillary sinusitis (p = 0.038). Therefore, our algorithm showed diagnostic performances comparable to radiologists and enhanced the value of radiography as a first-line imaging modality in assessing multiple sinusitis.
Highlights
Sinusitis is an inflammation of the membranes lining the paranasal sinus, which is one of the most frequently diagnosed diseases in the United States, affecting more than 15% of its population annually [1]
While CT is the imaging modality of choice for sinusitis, as it provides the highest overall anatomical detail of the paranasal sinuses, radiography is still widely used as an imaging modality when sinusitis is suspected because of its comparatively low cost, low radiation dose exposure, higher availability, and ease of examination [4,5]
All studies were labeled by consensus of two radiologists (Y.J.B., an attending neuroradiologist with 10 years of experience, and Y.K., a board-certified radiologist with 4 years of experience) based on CT findings according to six types: 0, normal; 1, mucosal thickening (>4 mm for maxillary sinusitis, and >2 mm for frontal and ethmoid sinusitis); 2, air-fluid level; 3, total opacification; 4, interpretable but not belonging to any category; and 5, uninterpretable (Figure 2)
Summary
Sinusitis is an inflammation of the membranes lining the paranasal sinus, which is one of the most frequently diagnosed diseases in the United States, affecting more than 15% of its population annually [1]. Sinusitis is diagnosed by evaluation of the patient’s history and physical examination, because clinical evaluation is usually sufficient to diagnose sinusitis in most cases and empirical treatments are cheap and safe. While CT is the imaging modality of choice for sinusitis, as it provides the highest overall anatomical detail of the paranasal sinuses, radiography is still widely used as an imaging modality when sinusitis is suspected because of its comparatively low cost, low radiation dose exposure, higher availability, and ease of examination [4,5]. The use of radiographic views such as Waters’ and Caldwell views is a conventional method for evaluation of the sinonasal area. Waters’ view, known as the occipitomental view, is considered the best projection for evaluating maxillary sinuses. Because adjacent bony shadows can overlap the sinuses, the interpretation of radiographs for sinusitis is difficult even for experienced radiologists, when judging whether thickened mucous membrane is present [10]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
