A neural network with a human learning paradigm for breast fibroadenoma segmentation in sonography

作者全名："Guo, Yongxin; Chen, Maoshan; Yang, Lei; Yin, Heng; Yang, Hongwei; Zhou, Yufeng"

作者地址："[Guo, Yongxin; Zhou, Yufeng] Chongqing Med Univ, Coll Biomed Engn, State Key Lab Ultrasound Med & Engn, 1 Med Coll Rd, Chongqing 400016, Peoples R China; [Guo, Yongxin; Zhou, Yufeng] Chongqing Med Univ, Chongqing Key Lab Biomed Engn, Chongqing 400016, Peoples R China; [Chen, Maoshan; Yang, Lei; Yin, Heng; Yang, Hongwei] Suining Cent Hosp, Dept Breast & Thyroid Surg, Suining 629000, Peoples R China; [Zhou, Yufeng] Natl Med Prod Adm NMPA Key Lab Qual Evaluat Ultras, 507 Gaoxin Ave, Wuhan 430075, Hubei, Peoples R China"

通信作者："Zhou, YF (通讯作者)，Chongqing Med Univ, Coll Biomed Engn, State Key Lab Ultrasound Med & Engn, 1 Med Coll Rd, Chongqing 400016, Peoples R China.; Zhou, YF (通讯作者)，Chongqing Med Univ, Chongqing Key Lab Biomed Engn, Chongqing 400016, Peoples R China.; Zhou, YF (通讯作者)，Natl Med Prod Adm NMPA Key Lab Qual Evaluat Ultras, 507 Gaoxin Ave, Wuhan 430075, Hubei, Peoples R China."

来源：BIOMEDICAL ENGINEERING ONLINE

ESI学科分类：MOLECULAR BIOLOGY & GENETICS

WOS号：WOS:001142299600001

JCR分区：Q3

影响因子：3.9

年份：2024

卷号：23

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Breast fibroadenomas; Sonography; Segmentation; Human learning paradigm; Deep learning; CNN-transformer hybrid model

摘要："BackgroundBreast fibroadenoma poses a significant health concern, particularly for young women. Computer-aided diagnosis has emerged as an effective and efficient method for the early and accurate detection of various solid tumors. Automatic segmentation of the breast fibroadenoma is important and potentially reduces unnecessary biopsies, but challenging due to the low image quality and presence of various artifacts in sonography.MethodsHuman learning involves modularizing complete information and then integrating it through dense contextual connections in an intuitive and efficient way. Here, a human learning paradigm was introduced to guide the neural network by using two consecutive phases: the feature fragmentation stage and the information aggregation stage. To optimize this paradigm, three fragmentation attention mechanisms and information aggregation mechanisms were adapted according to the characteristics of sonography. The evaluation was conducted using a local dataset comprising 600 breast ultrasound images from 30 patients at Suining Central Hospital in China. Additionally, a public dataset consisting of 246 breast ultrasound images from Dataset_BUSI and DatasetB was used to further validate the robustness of the proposed network. Segmentation performance and inference speed were assessed by Dice similarity coefficient (DSC), Hausdorff distance (HD), and training time and then compared with those of the baseline model (TransUNet) and other state-of-the-art methods.ResultsMost models guided by the human learning paradigm demonstrated improved segmentation on the local dataset with the best one (incorporating C3ECA and LogSparse Attention modules) outperforming the baseline model by 0.76% in DSC and 3.14 mm in HD and reducing the training time by 31.25%. Its robustness and efficiency on the public dataset are also confirmed, surpassing TransUNet by 0.42% in DSC and 5.13 mm in HD.ConclusionsOur proposed human learning paradigm has demonstrated the superiority and efficiency of ultrasound breast fibroadenoma segmentation across both public and local datasets. This intuitive and efficient learning paradigm as the core of neural networks holds immense potential in medical image processing."

基金机构：Future Innovation Program

基金资助正文：The authors would like to express their thanks to Dr. Cai Zhang and Miss Hong Liu for the collection of sonography and valuable discussion.