Visibility Enhancement of Lesion Regions in Chest X-Ray Images With Image Fidelity Preservation

X-ray image enhancement can aid a physician’s diagnosis by improving lesion visibility. This study proposes a chest X-ray image enhancement framework for enhancing lesion visibility while preserving image features. Our framework assesses the background signals, whereas conventional methods focus on the visibility of the global image. The proposed method predicts the image processing parameters that enhance the lesion signals via the inference neural network. The framework consists of an X-ray image enhancer and an enhanced model predictor for reference. The enhancer regressively estimates the processing parameters for enhancing the lesions using the inference network and processes the input X-ray image. As the inference network requires training, the model predictor computes the reference parameters that maximize the visibility of the lesions within a tolerable loss of fidelity using image pairs—with and without lesions. We created a synthesized dataset, with and without lesions, from healthy chest and phantom lesion X-ray images. The experiments show that after the proposed method was trained on 2000 images, it improved lesion visibility with an acceptable fidelity loss. We also performed pairwise comparisons and confirmed that trade-offs between fidelity loss and visibility gain were attained. A technique for improving lesion visibility while maintaining the fidelity of X-ray images was developed. This method enabled the enhancement of specific signals in the background. Various image processing methods that require parameters could be incorporated into this framework for many different applications.