Segmentation method of thyroid nodule ultrasonic image based on semantic segmentation network PSPNet

Abstract

The invention discloses a segmentation method for a thyroid nodule ultrasonic image based on a semantic segmentation network PSPNet, and the method comprises the steps: carrying out the collection andpreprocessing of data, carrying out the manual marking of the thyroid nodule ultrasonic image through combining with a pathological diagnosis result, and dividing each pixel value on the image into three types: thyroid nodule, thyroid parenchyma and other contents; wherein the three types of corresponding pixel values are respectively 3, 2 and 1; training a semantic segmentation network PSPNet; testing a result segmented by the semantic segmentation network PSPNet, and calculating segmentation evaluation indexes such as a cross-parallel ratio and pixel precision; if the test result does not reach the expected standard, adjusting parameters such as the sample number, the loss function, the learning rate and the optimizer of single training of the network, and then training and testing thenetwork until the network reaches the expected standard. In the aspect of segmentation result visualization, smooth parenchyma and nodule edges can be rapidly and specifically segmented, and the segmentation result can be used for further diagnosis.

Description

technical field [0001] The invention relates to a segmentation method, in particular to a segmentation method of a thyroid nodule ultrasound image based on a semantic segmentation network PSPNet. Background technique [0002] The thyroid gland, located under the front of the neck, produces thyroid hormones that control the body's metabolism. The thyroid gland not only affects people's heart rate and mental state, but also controls many important body functions, so normal thyroid function is a prerequisite for the normal operation of human organs. Globally, the incidence of thyroid disease in men has increased by 48% in the past 30 years, and that in women has increased by 67%. Thyroid diseases are an increasing threat to human health. Thyroid nodules are a sign of thyroid disease and may result from growths of thyroid cells and / or cysts in the thyroid gland. Thyroid nodules, the thyroid tissue, can be clearly distinguished by imaging. [0003] Ultrasound imaging has becom...

AI Technical Summary

Problems solved by technology

These information are helpful to judge whether the thyroid nodules are getting worse, but the diagnosis process relies on radiologists, and even the attending doctors may have subjective misjudgments. Moreover, the workload of manual marking by doctors is relatively large, so relying on manual work cannot Makes a lot of labeling work

In addition, the ultrasonic images are noisy, and the individual differences of the thyroid gland are obvious. The traditional image segmentation method is not very effective. Accurate segmentation of thyroid nodules is a prerequisite for subsequent quantitative analysis of thyroid abnormalities. Quantitatively judge the thyroid gland from the perspective of thyroid hormones. In addition, the accurate segmentation of nodules also provides objective texture features for the subsequent classification of nodules, assisting doctors in diagnosis and helping doctors improve the accuracy of diagnosis

Images