Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses
Abstract Objective To develop an automatic segmentation model to delineate the adnexal masses and construct a machine learning model to differentiate between low malignant risk and intermediate-high malignant risk of adnexal masses based on ovarian-adnexal reporting and data system (O-RADS). Methods...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-024-01874-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594686778277888 |
|---|---|
| author | Lu Liu Wenjun Cai Feibo Zheng Hongyan Tian Yanping Li Ting Wang Xiaonan Chen Wenjing Zhu |
| author_facet | Lu Liu Wenjun Cai Feibo Zheng Hongyan Tian Yanping Li Ting Wang Xiaonan Chen Wenjing Zhu |
| author_sort | Lu Liu |
| collection | DOAJ |
| description | Abstract Objective To develop an automatic segmentation model to delineate the adnexal masses and construct a machine learning model to differentiate between low malignant risk and intermediate-high malignant risk of adnexal masses based on ovarian-adnexal reporting and data system (O-RADS). Methods A total of 663 ultrasound images of adnexal mass were collected and divided into two sets according to experienced radiologists: a low malignant risk set (n = 446) and an intermediate-high malignant risk set (n = 217). Deep learning segmentation models were trained and selected to automatically segment adnexal masses. Radiomics features were extracted utilizing a feature analysis system in Pyradiomics. Feature selection was conducted using the Spearman correlation analysis, Mann–Whitney U-test, and least absolute shrinkage and selection operator (LASSO) regression. A nomogram integrating radiomic and clinical features using a machine learning model was established and evaluated. The SHapley Additive exPlanations were used for model interpretability and visualization. Results The FCN ResNet101 demonstrated the highest segmentation performance for adnexal masses (Dice similarity coefficient: 89.1%). Support vector machine achieved the best AUC (0.961, 95% CI: 0.925–0.996). The nomogram using the LightGBM algorithm reached the best AUC (0.966, 95% CI: 0.927–1.000). The diagnostic performance of the nomogram was comparable to that of experienced radiologists (p > 0.05) and outperformed that of less-experienced radiologists (p < 0.05). The model significantly improved the diagnostic accuracy of less-experienced radiologists. Conclusions The segmentation model serves as a valuable tool for the automated delineation of adnexal lesions. The machine learning model exhibited commendable classification capability and outperformed the diagnostic performance of less-experienced radiologists. Critical relevance statement The ultrasound radiomics-based machine learning model holds the potential to elevate the professional ability of less-experienced radiologists and can be used to assist in the clinical screening of ovarian cancer. Key Points We developed an image segmentation model to automatically delineate adnexal masses. We developed a model to classify adnexal masses based on O-RADS. The machine learning model has achieved commendable classification performance. The machine learning model possesses the capability to enhance the proficiency of less-experienced radiologists. We used SHapley Additive exPlanations to interpret and visualize the model. Graphical Abstract |
| format | Article |
| id | doaj-art-47161e3e46a94981b7872c7fe6bdcb18 |
| institution | Kabale University |
| issn | 1869-4101 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj-art-47161e3e46a94981b7872c7fe6bdcb182025-01-19T12:26:16ZengSpringerOpenInsights into Imaging1869-41012025-01-0116111510.1186/s13244-024-01874-7Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal massesLu Liu0Wenjun Cai1Feibo Zheng2Hongyan Tian3Yanping Li4Ting Wang5Xiaonan Chen6Wenjing Zhu7Department of Ultrasound Medicine, South China Hospital, Medical School, Shenzhen UniversityDepartment of Ultrasound, Shenzhen University General Hospital, Medical School, Shenzhen UniversityDepartment of Nuclear Medicine, Qingdao Hospital, University of Health and Rehabilitation Sciences (Qingdao Municipal Hospital)Department of Ultrasound Medicine, South China Hospital, Medical School, Shenzhen UniversityDepartment of Ultrasound Medicine, South China Hospital, Medical School, Shenzhen UniversityDepartment of Ultrasound Medicine, South China Hospital, Medical School, Shenzhen UniversityDepartment of Urology, Shengjing Hospital of China Medical UniversityMedical Research Department, Qingdao Hospital, University of Health and Rehabilitation Sciences (Qingdao Municipal Hospital)Abstract Objective To develop an automatic segmentation model to delineate the adnexal masses and construct a machine learning model to differentiate between low malignant risk and intermediate-high malignant risk of adnexal masses based on ovarian-adnexal reporting and data system (O-RADS). Methods A total of 663 ultrasound images of adnexal mass were collected and divided into two sets according to experienced radiologists: a low malignant risk set (n = 446) and an intermediate-high malignant risk set (n = 217). Deep learning segmentation models were trained and selected to automatically segment adnexal masses. Radiomics features were extracted utilizing a feature analysis system in Pyradiomics. Feature selection was conducted using the Spearman correlation analysis, Mann–Whitney U-test, and least absolute shrinkage and selection operator (LASSO) regression. A nomogram integrating radiomic and clinical features using a machine learning model was established and evaluated. The SHapley Additive exPlanations were used for model interpretability and visualization. Results The FCN ResNet101 demonstrated the highest segmentation performance for adnexal masses (Dice similarity coefficient: 89.1%). Support vector machine achieved the best AUC (0.961, 95% CI: 0.925–0.996). The nomogram using the LightGBM algorithm reached the best AUC (0.966, 95% CI: 0.927–1.000). The diagnostic performance of the nomogram was comparable to that of experienced radiologists (p > 0.05) and outperformed that of less-experienced radiologists (p < 0.05). The model significantly improved the diagnostic accuracy of less-experienced radiologists. Conclusions The segmentation model serves as a valuable tool for the automated delineation of adnexal lesions. The machine learning model exhibited commendable classification capability and outperformed the diagnostic performance of less-experienced radiologists. Critical relevance statement The ultrasound radiomics-based machine learning model holds the potential to elevate the professional ability of less-experienced radiologists and can be used to assist in the clinical screening of ovarian cancer. Key Points We developed an image segmentation model to automatically delineate adnexal masses. We developed a model to classify adnexal masses based on O-RADS. The machine learning model has achieved commendable classification performance. The machine learning model possesses the capability to enhance the proficiency of less-experienced radiologists. We used SHapley Additive exPlanations to interpret and visualize the model. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01874-7UltrasoundSegmentationMachine learningDeep learningAdnexal mass |
| spellingShingle | Lu Liu Wenjun Cai Feibo Zheng Hongyan Tian Yanping Li Ting Wang Xiaonan Chen Wenjing Zhu Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses Insights into Imaging Ultrasound Segmentation Machine learning Deep learning Adnexal mass |
| title | Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses |
| title_full | Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses |
| title_fullStr | Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses |
| title_full_unstemmed | Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses |
| title_short | Automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate-high malignant risk of adnexal masses |
| title_sort | automatic segmentation model and machine learning model grounded in ultrasound radiomics for distinguishing between low malignant risk and intermediate high malignant risk of adnexal masses |
| topic | Ultrasound Segmentation Machine learning Deep learning Adnexal mass |
| url | https://doi.org/10.1186/s13244-024-01874-7 |
| work_keys_str_mv | AT luliu automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT wenjuncai automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT feibozheng automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT hongyantian automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT yanpingli automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT tingwang automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT xiaonanchen automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses AT wenjingzhu automaticsegmentationmodelandmachinelearningmodelgroundedinultrasoundradiomicsfordistinguishingbetweenlowmalignantriskandintermediatehighmalignantriskofadnexalmasses |