CONVERTING LOW-DOSE TO HIGHER DOSE MAMMOGRAPHIC IMAGES THROUGH MACHINE-LEARNING PROCESSES

A method and system for converting low-dose mammographic images with much noise into higher quality, less noise, higher-dose-like mammographic images, using of a trainable nonlinear regression (TNR) model with a patch-input-pixel-output scheme, which can be called a call pixel-based TNR (PTNR). An image patch is extracted from an input mammogram acquired at a reduced x-ray radiation dose (lower-dose), and pixel values in the patch are entered into the PTNR as input. The output of the PTNR is a single pixel that corresponds to a center pixel of the input image patch. The PTNR is trained with matched pairs of mammograms, inputting low-dose mammograms together with corresponding desired standard x-ray radiation dose mammograms (higher-dose), which are ideal images for the output images. Through the training, the PTNR learns to convert low-dose mammograms to high-dose-like mammograms. Once trained, the trained PTNR does not require the higher-dose mammograms anymore. When a new reduced x-ray radiation dose (low dose) mammogram is entered, the trained PTNR would output a pixel value similar to its desired pixel value, in other words, it would output high-dose-like mammograms or “virtual high-dose” mammograms where noise and artifacts due to low radiation dose are substantially reduced, i.e., a higher image quality. With the “virtual high-dose” mammograms, the detectability of lesions and clinically important findings such as masses and microcalcifications can be improved.