Thyroid ultrasound image classification and segmentation network, training method, device and medium

Abstract

The invention discloses a thyroid ultrasound image classification and segmentation network, a training method, a device and a medium, and belongs to the technical field of medical information. The network comprises a coding stage, a decoding stage and jump connection between the coding stage and the decoding stage, an attention mechanism module is arranged in the coding stage, so that the network pays more attention to the difference between a thyroid structure and surrounding tissues, and in the coding stage of the network, an output feature map is used as the input of a classification network, so that feature sharing can be carried out on the segmentation and classification tasks, the thyroid ultrasound images are classified and segmented at the same time through the same network, classification and segmentation task training is carried out at the same time in training, and the segmentation and classification accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of medical information, more specifically, to a thyroid ultrasound image classification and segmentation network, a training method, a device and a medium. Background technique [0002] Thyroid cancer is the most common malignancy among endocrine system tumors, and its incidence has been increasing worldwide over the past two decades. Ultrasound is the main method for screening thyroid cancer, and ultrasound imaging technology is currently one of the most commonly used methods for early detection of tumors. Ultrasound is widely used in clinical diagnosis because of its cheapness, no radiation, and low cost. [0003] At present, the examination of the nature of thyroid nodules mainly relies on the analysis of ultrasound images. The radiologist summarizes a series of ultrasound image characteristics of thyroid nodules as signs of cancer, including hypoechoic reflectivity, absence of halos, microcalcif...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the problem that the U Net network in the prior art cannot realize image segmentation and classification at the same time, the present invention provides a thyroid ultrasound image classification and segmentation network, a training method, a device and a medium, which can realize the use of the U Net network to simultaneously analyze thyroid nodules. Sections are classified and segmented, enabling features to be shared in practical applications and saving memory overhead in deployment

Images