Abstract
Background: Rural clinics still have X-ray facilities that produce physical films, which are sent to the nearest hospital for evaluation. Purchasing digitalization facilities is costly, thus, sending digitized films to the radiologist may be a solution. This can be achieved via digital photo capture. However, there can be different output resolutions that may not be optimized for online diagnosis. This paper investigates if digitized X-ray films can be enhanced using image processing techniques of Contrast-Limited Adaptive Histogram Equalization (CLAHE), Normalized-CLAHE (N-CLAHE) and Min-Max Normalized-CLAHE (MMCLAHE). Methods: We collected and digitized 21 X-ray films with low, medium, and high resolutions and implemented the CLAHE, N-CLAHE and MMCLAHE image enhancement. These methods introduced a limit to clip the histogram of image intensities so as to reduce any noise amplification before file compression with the Fast Fourier Transform (FFT) and Discrete Cosine Transform (DCT). Quantitative metrics of the Peak Signal-to-Noise Ratio (PSNR) and Mean-Squared Error (MSE) were used to compare the accuracies between digitized and processed X-ray films. A qualitative evaluation was performed by a medical practitioner to validate the accuracy of enhanced digitized X-ray. Results: It had been found that both CLAHE and MMCLAHE provided good average PSNR values of 31dB - 32dB and produced low MSE values compared to N-CLAHE. The results of qualitative evaluation attained 89.9% correct diagnosis on nine randomly selected images. Generally, the evaluation indicated that the results fulfill the acceptable criteria for further evaluation and there seemed to be no pathological differences observed. Conclusion: This paper presented a proof of concept on an implementation of the CLAHE technique and its variations on digitized X-ray films. This paper had shown potential improvements with the proposed enhancement methods that may contribute to an increase efficiency in healthcare processes at rural clinics.
Highlights
The pandemic situation has accelerated digitalization to many countries
We investigate the use of Contrast-Limited Adaptive Histogram Equalization (CLAHE) image processing techniques as a proof of concept and we validate the output via quantitative metrics and qualitative evaluation by a medical practitioner
From this table the results show that CLAHE-Discrete Cosine Transform (DCT) gave the lowest average Mean-Squared Error (MSE) of 35.59 and the highest average Peak Signal-to-Noise Ratio (PSNR) values of 32.85dB compared to other methods
Summary
The pandemic situation has accelerated digitalization to many countries. people living in rural areas are having an inconvenience to access medical technologies due to unavailability of specialists and shortage of medical equipments.[1]. We propose a proof of concept work to digitalize physical X-ray films via digital photo capture so that their digital versions can be sent via email or cloud for evaluation by a radiologist elsewhere. This may improve efficiency in remote diagnosis as well as reducing physical storage.[6]. It was reported that a diagnosis was difficult when involving uncommon and difficult pathology cases These studies purely implemented digital photo capture of X-ray films and performed diagnosis without requiring online transmission. These variations open an opportunity to explore image enhancement techniques on images of digitized X-ray films.[9,10,11,12,13,14,15] In this paper, we investigate the use of CLAHE image processing techniques as a proof of concept and we validate the output via quantitative metrics and qualitative evaluation by a medical practitioner
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
