Thyroid nodule positioning and ultrasonic report error correction method based on target detection network

Abstract

The invention relates to a thyroid nodule positioning and ultrasonic report error correction method based on a target detection network. The method comprises the following steps: establishing a deep convolutional neural network, wherein the deep convolutional neural network comprises a target detection network part and a classifier part, and the target detection network part detects a to-be-classified image to obtain a trachea and carotid artery detection result; the classifier part classifies the images according to the recognized relative positions of the trachea and the carotid artery in the images; and based on an input box event monitoring mechanism, comparing the classification result with keywords in the ultrasonic report, and if the classification result is inconsistent with the keywords in the ultrasonic report, giving a prompt. According to the invention, the phenomenon that left and right focuses are reversed due to manual errors is effectively avoided, so that the consistency and accuracy of text reports and pictures are ensured, and adverse medical accidents are reduced.

Description

technical field [0001] The invention relates to the technical field of image analysis, in particular to a method for thyroid nodule location and ultrasound report error correction based on a target detection network. Background technique [0002] Ultrasound is widely used in the inspection of various tissues and organs of the human body due to its non-invasive, convenient, economical, and radiation-free advantages. At present, domestic clinical work is heavy, and a large number of repetitive inspection tasks make the inspection efficiency low. Ultrasound diagnosticians are prone to fatigue. For symmetrical organs The diagnosis of thyroid nodules is highly dependent on ultrasound, which at least requires the ultrasonic diagnostic documents to be specific about the location of nodules. Only the accuracy of the information can ensure the correct follow-up treatment. Once the information on the left and right sides of the nodule is wrong, it will often cause serious medical acci...

AI Technical Summary

Problems solved by technology

[0002] Ultrasound is widely used in the inspection of various tissues and organs of the human body due to its non-invasive, convenient, economical, and radiation-free advantages. At present, domestic clinical work is heavy, and a large number of repetitive inspection tasks make the inspection efficiency low. Ultrasound diagnosticians are prone to fatigue. For symmetrical organs The diagnosis of thyroid nodules is highly dependent on ultrasound, which at least requires the ultrasonic diagnostic documents to be specific about the location of nodules. The accuracy of the information can ensure the follow-up correct treatment. Once the position information of the left and right sides of the nodule is wrong, it will often cause serious medical accidents caused by the wrong thyroid cutting on the healthy side and the remaining thyroid on the affected side.

Images