The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results
Abstract In recent years, the incidence of nodular thyroid diseases has been increasing annually. Ultrasonography has become a routine diagnostic tool for thyroid nodules due to its high real-time capabilities and low invasiveness. However, thyroid images obtained from current ultrasound tests often...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-11-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-024-01486-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846158118216531968 |
|---|---|
| author | Xu Yang Shuo’ou Qu Zhilin Wang Lingxiao Li Xiaofeng An Zhibin Cong |
| author_facet | Xu Yang Shuo’ou Qu Zhilin Wang Lingxiao Li Xiaofeng An Zhibin Cong |
| author_sort | Xu Yang |
| collection | DOAJ |
| description | Abstract In recent years, the incidence of nodular thyroid diseases has been increasing annually. Ultrasonography has become a routine diagnostic tool for thyroid nodules due to its high real-time capabilities and low invasiveness. However, thyroid images obtained from current ultrasound tests often have low resolution and are plagued by significant noise interference. Regional differences in medical conditions and varying levels of physician experience can impact the accuracy and efficiency of diagnostic results. With the advancement of deep learning technology, deep learning models are used to identify whether a nodule in a thyroid ultrasound image is benign or malignant. This helps to close the gap between doctors’ experience and equipment differences, improving the accuracy of the initial diagnosis of thyroid nodules. To cope with the problem that thyroid ultrasound images contain complex background and noise as well as poorly defined local features. in this paper, we first construct an improved ResNet50 classification model that uses a two-branch input and incorporates a global attention lightening module. This model is used to improve the accuracy of benign and malignant nodule classification in thyroid ultrasound images and to reduce the computational effort due to the two-branch structure.We constructed a U-net segmentation model incorporating our proposed ACR module, which uses hollow convolution with different dilation rates to capture multi-scale contextual information for feature extraction of nodules in thyroid ultrasound images and uses the results of the segmentation task as an auxiliary branch for the classification task to guide the classification model to focus on the lesion region more efficiently in the case of weak local features. The classification model is guided to focus on the lesion region more efficiently, and the classification and segmentation sub-networks are respectively improved specifically for this study, which is used to improve the accuracy of classifying the benign and malignant nature of the nodules in thyroid ultrasound images. The experimental results show that the four evaluation metrics of accuracy, precision, recall, and f1 of the improved model are 96.01%, 93.3%, 98.8%, and 96.0%, respectively. The improvements were 5.7%, 1.6%, 13.1%, and 7.4%, respectively, compared with the baseline classification model. |
| format | Article |
| id | doaj-art-a2b643521d6542be9f5017a2718b980b |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-a2b643521d6542be9f5017a2718b980b2024-11-24T12:47:48ZengBMCBMC Medical Imaging1471-23422024-11-0124111610.1186/s12880-024-01486-zThe study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation resultsXu Yang0Shuo’ou Qu1Zhilin Wang2Lingxiao Li3Xiaofeng An4Zhibin Cong5School of Electronic Information Engineering, Changchun University of Science and TechnologySchool of Electronic Information Engineering, Changchun University of Science and TechnologySchool of Electronic Information Engineering, Changchun University of Science and TechnologyHuman Resources Department, The Third Affiliated Hospital OF C.C.U.C.MEducation Quality Monitoring Center, Jilin Engineering Normal UniversityDepartment of Electrodiagnosis, The Affiliated Hospital to Changchun University of Traditional Chinese MedicineAbstract In recent years, the incidence of nodular thyroid diseases has been increasing annually. Ultrasonography has become a routine diagnostic tool for thyroid nodules due to its high real-time capabilities and low invasiveness. However, thyroid images obtained from current ultrasound tests often have low resolution and are plagued by significant noise interference. Regional differences in medical conditions and varying levels of physician experience can impact the accuracy and efficiency of diagnostic results. With the advancement of deep learning technology, deep learning models are used to identify whether a nodule in a thyroid ultrasound image is benign or malignant. This helps to close the gap between doctors’ experience and equipment differences, improving the accuracy of the initial diagnosis of thyroid nodules. To cope with the problem that thyroid ultrasound images contain complex background and noise as well as poorly defined local features. in this paper, we first construct an improved ResNet50 classification model that uses a two-branch input and incorporates a global attention lightening module. This model is used to improve the accuracy of benign and malignant nodule classification in thyroid ultrasound images and to reduce the computational effort due to the two-branch structure.We constructed a U-net segmentation model incorporating our proposed ACR module, which uses hollow convolution with different dilation rates to capture multi-scale contextual information for feature extraction of nodules in thyroid ultrasound images and uses the results of the segmentation task as an auxiliary branch for the classification task to guide the classification model to focus on the lesion region more efficiently in the case of weak local features. The classification model is guided to focus on the lesion region more efficiently, and the classification and segmentation sub-networks are respectively improved specifically for this study, which is used to improve the accuracy of classifying the benign and malignant nature of the nodules in thyroid ultrasound images. The experimental results show that the four evaluation metrics of accuracy, precision, recall, and f1 of the improved model are 96.01%, 93.3%, 98.8%, and 96.0%, respectively. The improvements were 5.7%, 1.6%, 13.1%, and 7.4%, respectively, compared with the baseline classification model.https://doi.org/10.1186/s12880-024-01486-zDeep learningThyroid ultrasound imagesResnet50U-net: attention mechanism |
| spellingShingle | Xu Yang Shuo’ou Qu Zhilin Wang Lingxiao Li Xiaofeng An Zhibin Cong The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results BMC Medical Imaging Deep learning Thyroid ultrasound images Resnet50 U-net: attention mechanism |
| title | The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results |
| title_full | The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results |
| title_fullStr | The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results |
| title_full_unstemmed | The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results |
| title_short | The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results |
| title_sort | study on ultrasound image classification using a dual branch model based on resnet50 guided by u net segmentation results |
| topic | Deep learning Thyroid ultrasound images Resnet50 U-net: attention mechanism |
| url | https://doi.org/10.1186/s12880-024-01486-z |
| work_keys_str_mv | AT xuyang thestudyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT shuoouqu thestudyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT zhilinwang thestudyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT lingxiaoli thestudyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT xiaofengan thestudyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT zhibincong thestudyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT xuyang studyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT shuoouqu studyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT zhilinwang studyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT lingxiaoli studyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT xiaofengan studyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults AT zhibincong studyonultrasoundimageclassificationusingadualbranchmodelbasedonresnet50guidedbyunetsegmentationresults |