Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images
Abstract This study aimed to evaluate the performance of traditional-deep learning combination model based on Doppler ultrasound for diagnosing malignant complex cystic and solid breast nodules. A conventional statistical prediction model based on the ultrasound features and basic clinical informati...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-06-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-37319-2 |
_version_ | 1797789815557586944 |
---|---|
author | Han Liu Chun-Jie Hou Jing-Lan Tang Li-Tao Sun Ke-Feng Lu Ying Liu Pei Du |
author_facet | Han Liu Chun-Jie Hou Jing-Lan Tang Li-Tao Sun Ke-Feng Lu Ying Liu Pei Du |
author_sort | Han Liu |
collection | DOAJ |
description | Abstract This study aimed to evaluate the performance of traditional-deep learning combination model based on Doppler ultrasound for diagnosing malignant complex cystic and solid breast nodules. A conventional statistical prediction model based on the ultrasound features and basic clinical information was established. A deep learning prediction model was used to train the training group images and derive the deep learning prediction model. The two models were validated, and their accuracy rates were compared using the data and images of the test group, respectively. A logistic regression method was used to combine the two models to derive a combination diagnostic model and validate it in the test group. The diagnostic performance of each model was represented by the receiver operating characteristic curve and the area under the curve. In the test cohort, the diagnostic efficacy of the deep learning model was better than traditional statistical model, and the combined diagnostic model was better and outperformed the other two models (combination model vs traditional statistical model: AUC: 0.95 > 0.70, P = 0.001; combination model vs deep learning model: AUC: 0.95 > 0.87, P = 0.04). A combination model based on deep learning and ultrasound features has good diagnostic value. |
first_indexed | 2024-03-13T01:56:01Z |
format | Article |
id | doaj.art-ff877b536b85405099b397bef5c4ac96 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-13T01:56:01Z |
publishDate | 2023-06-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-ff877b536b85405099b397bef5c4ac962023-07-02T11:14:08ZengNature PortfolioScientific Reports2045-23222023-06-0113111110.1038/s41598-023-37319-2Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler imagesHan Liu0Chun-Jie Hou1Jing-Lan Tang2Li-Tao Sun3Ke-Feng Lu4Ying Liu5Pei Du6Cancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeCancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeCancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeCancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeCancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeCancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeCancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital), Hangzhou Medical CollegeAbstract This study aimed to evaluate the performance of traditional-deep learning combination model based on Doppler ultrasound for diagnosing malignant complex cystic and solid breast nodules. A conventional statistical prediction model based on the ultrasound features and basic clinical information was established. A deep learning prediction model was used to train the training group images and derive the deep learning prediction model. The two models were validated, and their accuracy rates were compared using the data and images of the test group, respectively. A logistic regression method was used to combine the two models to derive a combination diagnostic model and validate it in the test group. The diagnostic performance of each model was represented by the receiver operating characteristic curve and the area under the curve. In the test cohort, the diagnostic efficacy of the deep learning model was better than traditional statistical model, and the combined diagnostic model was better and outperformed the other two models (combination model vs traditional statistical model: AUC: 0.95 > 0.70, P = 0.001; combination model vs deep learning model: AUC: 0.95 > 0.87, P = 0.04). A combination model based on deep learning and ultrasound features has good diagnostic value.https://doi.org/10.1038/s41598-023-37319-2 |
spellingShingle | Han Liu Chun-Jie Hou Jing-Lan Tang Li-Tao Sun Ke-Feng Lu Ying Liu Pei Du Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images Scientific Reports |
title | Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images |
title_full | Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images |
title_fullStr | Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images |
title_full_unstemmed | Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images |
title_short | Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images |
title_sort | deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color doppler images |
url | https://doi.org/10.1038/s41598-023-37319-2 |
work_keys_str_mv | AT hanliu deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages AT chunjiehou deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages AT jinglantang deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages AT litaosun deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages AT kefenglu deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages AT yingliu deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages AT peidu deeplearningandultrasoundfeaturefusionmodelpredictsthemalignancyofcomplexcysticandsolidbreastnoduleswithcolordopplerimages |