Can adaptive post-processing of storage phosphor plate panoramic radiographs provide better image quality? A comparison of anatomical image quality of panoramic radiographs before and after adaptive processing

Style harmonization of panoramic radiography using deep learning

OBJECTIVES

This study aimed to harmonize panoramic radiograph images from different equipment in a single institution to display similar styles.

METHODS

A total of 15,624 panoramic images were acquired using two different equipment: 8079 images from Rayscan Alpha Plus (R-unit) and 7545 images from Pax-i plus (P-unit). Among these, 222 image pairs (444 images) from the same patients comprised the test dataset to harmonize the P-unit images with the R-unit image style using CycleGAN. Objective evaluations included Frechet Inception Distance (FID) and Learned Perceptual Image Patch Similarity (LPIPS) assessments. Additionally, expert evaluation was conducted by two oral and maxillofacial radiologists on transformed P-unit and R-unit images. The statistical analysis of LPIPS employed a Student's t-test.

RESULTS

The FID and mean LPIPS values of the transformed P-unit images (7.362, 0.488) were lower than those of the original P-unit images (8.380, 0.519), with a significant difference in LPIPS (p < 0.05). The experts evaluated 43.3-46.7% of the transformed P-unit images as R-unit images, 20.0-28.3% as P-units, and 28.3-33.3% as undetermined images.

CONCLUSIONS

CycleGAN has the potential to harmonize panoramic radiograph image styles. Enhancement of the model is anticipated for the application of images produced by additional units.

A comparison of perceived diagnostic image quality in direct digital panoramic images between standard and advanced external GOP image processing

Objective: The objective of the present study was to study the effect of adaptive image processing (GOP processing) on the visibility of anatomical structures in direct digital panoramic images. Material and methods: The study comprised panoramic images of 50 consecutive adult individuals aged 18-60 years. Nine dentists working with dental radiology compared the structural image quality of all standard-processed and GOP-processed panoramic images for six anatomical structures, using a six-point scale for visual grading characteristics analysis. Results: For all anatomic structures a statistically significant difference in favour of the GOP was found. Conclusions: The present study shows that it is possible to improve perceived diagnostic image quality of direct digital panoramic radiography using GOP technology compared to the manufacturers' standard processing. Manufacturers' image-processing programs can be further developed, as there is a possibility of improving the perceived diagnostic content of an image with external processing.