X-ray chest radiograph rib image suppression method based on joint prediction filtering generation network

• Main Authors: SHI ZHENGHAO, LI WANQIN, YOU ZHENZHEN, FENG YANING, GE FEIHANG
• Format: Patent
• Language: Chinese; English
• Published: 18.08.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an X-ray chest radiograph rib image suppression method of a generative network based on joint predictive filtering. The method specifically comprises the following steps: step 1, preprocessing training set and test set images in a data set; 2, constructing an X-ray chest radiograph rib image suppression network model of a generative network based on joint prediction filtering; step 3, training the model constructed in the step 2 by using the training set data preprocessed in the step 1 to obtain a trained X-ray chest radiograph rib image suppression network model of the generative network based on joint prediction filtering; and step 4, putting the test set image preprocessed in the step 1 into the model trained in the step 3, and finally obtaining a soft tissue image after bone suppression. When the method is adopted to process the X-ray chest radiograph rib image, the negative influence of structural shielding of rib overlapping on reading of the X-ray chest radiograph can be reduced