Artificial intelligence film reading method based on convolutional neural network algorithm

Abstract

The invention belongs to the technical field of artificial intelligence, and particularly relates to an artificial intelligence film reading method based on a convolutional neural network algorithm, and the method comprises the steps: 1, obtaining a to-be-detected target image; 2, selecting an image area; 3, target feature extraction; 4, performing target classification according to the features; 5, regressing the bounding box of the target; 6, optimizing the structure; and 7, completing target detection. According to the method, the structure is reasonable, the accuracy of thyroid color Doppler ultrasound diagnosis is improved, misdiagnosis of preoperative thyroid color Doppler ultrasound is prevented, input and output are both in program operation, the effect of human factors in image diagnosis is eliminated, and compared with a traditional method, image features can be better recognized. Moreover, the capability of improving the algorithm through step-by-step grading learning is more suitable for program improvement, and the method is the highest in medical image diagnosis accuracy in the current AI.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence film reading method based on a convolutional neural network algorithm. Background technique [0002] The incidence of thyroid cancer (Thyroid Carcinoma, TC) is increasing rapidly around the world. In China, surgery is still the first choice for doctors to treat TC. However, the vast majority of TCs grow slowly and have a good prognosis. The fatality rate has not been reduced by active surgical treatment. On the contrary, surgery has greatly reduced the quality of life of TC patients. Therefore, overdiagnosis and overtreatment of TC have become The focus of clinical attention. The preoperative diagnosis of TC mostly relies on thyroid color Doppler ultrasound. However, the experience and skills of color Doppler ultrasound doctors are uneven, which directly affects the accuracy of thyroid color Doppler ultrasound diagnosis. Studies have s...

AI Technical Summary

Problems solved by technology

However, no AI software for thyroid color Doppler ultrasound has been developed so far

Images