A novel ultrasound image diagnostic method for thyroid nodules

Abstract

The incidence of thyroid nodules is increasing year by year. Accurate determination of benign and malignant nodules is an important basis for formulating treatment plans. Ultrasonography is the most widely used methodology in the diagnosis of benign and malignant nodules, but diagnosis by doctors is highly subjective, and the rates of missed diagnosis and misdiagnosis are high. To improve the accuracy of clinical diagnosis, this paper proposes a new diagnostic model based on deep learning. The diagnostic model adopts the diagnostic strategy of localization-classification. First, the distribution laws of the nodule size and nodule aspect ratio are obtained through data statistics, a multiscale localization network structure is a priori designed, and the nodule aspect ratio is obtained from the positioning results. Then, uncropped ultrasound images and nodule area image are correspondingly input into a two-way classification network, and an improved attention mechanism is used to enhance the feature extraction performance. Finally, the deep features, the shallow features, and the nodule aspect ratio are fused, and a fully connected layer is used to complete the classification of benign and malignant nodules. The experimental dataset consists of 4021 ultrasound images, where each image has been labeled under the guidance of doctors, and the ratio of the training set, validation set, and test set sizes is close to 3:1:1. The experimental results show that the accuracy of the multiscale localization network reaches 93.74%, and that the accuracy, specificity, and sensitivity of the classification network reach 86.34%, 81.29%, and 90.48%, respectively. Compared with the champion model of the TNSCUI 2020 classification competition, the accuracy rate is 1.52 points higher. Therefore, the network model proposed in this paper can effectively diagnose benign and malignant thyroid nodules.

Exhaustive search for DNA binding sites ofBasillus subtilistranscription factor YsiA by KaScape method

“…Random dsDNA pool was prepared according to the procedures detailed in the research by Hong Chen et al (6).…”

“…The exhaustive search of the binding sequence for YsiA was conducted using KaScape method, following the steps detailed in Hong Chen, et al (6). Briefly, a random dsDNA pool containing 4 bp, 5 bp, 6 bp, or 7 bp was prepared and mixed with purified His-tagged YsiA for 30 minutes.…”

“…The relative binding energy calculation method is a little bit different from the original KaScape paper (6). For each random base length (n) KaScape experiment, the relative binding energy landscape with a series of short sequence length (m) can be calculated.…”

“…Howerver, the sequence amount tested is limited, and the microarray data has the potential to present false positives or results with low accuracy (5). In order to extensively study the relative binding affinity of YsiA, we have used the KaScape method (6) as our main form of analysis to study the dsDNA binding characteristic of YsiA. This approach enables us to inspect all kinds of dsDNA to protein binding, under identical conditions.…”