Method and system automatically detecting local lesion in radiographic image

Abstract

An automatic detection method and system capable of improving radiographic image abnormal (lung cancer local lesion) detection process in the prior art is provided. The detection method and system employs multi-resolution technology to improve detection efficiency for local lesion with various sizes and further use virtual local lesion to conduct relevance and match, so local lesions of all or most sizes can be detected. The detection method and system employs spherical parameter to represent local lesions, so non-obvious local lesions can be accurately detected. A plurality of classifiers employed by the detection method and system comprise a counter-propagation neural network, data fusion, trimming neural network based on decision-making and convolution neural network structure, so classification grade of lung local lesion classification can be generated; and images with high dubiety can be further detected upon final decision-making.

Description

1. Technical field [0001] The present invention is used for a method and system for digital image processing, more specifically for a method and system for re-screening and abnormal automatic inspection, for example: multi-resolution processing of radioactive chest images with localized lung lesions, digital image processing and deep learning Neural Networks. 2. Background technology [0002] Lung cancer is the leading cancer type in both men and women worldwide, and early detection and treatment of potentially treatable stage localized lung cancer can significantly improve patient survival. Studies have shown that the probability of lung cancer being diagnosed by one radiologist is close to 68%, and the probability increases to 82% when a second reader is added. A long-term lung cancer screening program conducted at the Mayo Clinic found that 90% of small peripheral lung cancers could be detected by tracing chest X-rays of early lung cancers. [0003] Compared with common...

AI Technical Summary

Problems solved by technology

Those experienced lung radiologists can achieve a high degree of accuracy in diagnosis. However, in the training stage of doctors, although they have a high level of clinical skills and experience, there are always some errors that are difficult to correct, so the detection of chest X-rays Imagery of lung focal lesions remains problematic

Images