Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study
Abstract Objectives To develop and validate a magnetic resonance imaging-based (MRI) deep multiple instance learning (D-MIL) model and combine it with clinical parameters for preoperative prediction of lymph node metastasis (LNM) in operable cervical cancer. Methods A total of 392 patients with cerv...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-02-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-024-01618-7 |
| _version_ | 1797274350105133056 |
|---|---|
| author | Fengying Qin Xinyan Sun Mingke Tian Shan Jin Jian Yu Jing Song Feng Wen Hongming Xu Tao Yu Yue Dong |
| author_facet | Fengying Qin Xinyan Sun Mingke Tian Shan Jin Jian Yu Jing Song Feng Wen Hongming Xu Tao Yu Yue Dong |
| author_sort | Fengying Qin |
| collection | DOAJ |
| description | Abstract Objectives To develop and validate a magnetic resonance imaging-based (MRI) deep multiple instance learning (D-MIL) model and combine it with clinical parameters for preoperative prediction of lymph node metastasis (LNM) in operable cervical cancer. Methods A total of 392 patients with cervical cancer were retrospectively enrolled. Clinical parameters were analysed by logistical regression to construct a clinical model (M1). A ResNet50 structure is applied to extract features at the instance level without using manual annotations about the tumour region and then construct a D-MIL model (M2). A hybrid model (M3) was constructed by M1 and M2 scores. The diagnostic performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC) and compared using the Delong method. Disease-free survival (DFS) was evaluated by the Kaplan‒Meier method. Results SCC-Ag, maximum lymph node short diameter (LNmax), and tumour volume were found to be independent predictors of M1 model. For the diagnosis of LNM, the AUC of the training/internal/external cohort of M1 was 0.736/0.690/0.732, the AUC of the training/internal/external cohort of M2 was 0.757/0.714/0.765, and the AUC of the training/internal/external cohort of M3 was 0.838/0.764/0.835. M3 showed better performance than M1 and M2. Through the survival analysis, patients with higher hybrid model scores had a shorter time to reach DFS. Conclusion The proposed hybrid model could be used as a personalised non-invasive tool, which is helpful for predicting LNM in operable cervical cancer. The score of the hybrid model could also reflect the DFS of operable cervical cancer. Critical relevance statement Lymph node metastasis is an important factor affecting the prognosis of cervical cancer. Preoperative prediction of lymph node status is helpful to make treatment decisions, improve prognosis, and prolong survival time. Key points • The MRI-based deep-learning model can predict the LNM in operable cervical cancer. • The hybrid model has the highest diagnostic efficiency for the LNM prediction. • The score of the hybrid model can reflect the DFS of operable cervical cancer. Graphical Abstract |
| first_indexed | 2024-03-07T14:57:11Z |
| format | Article |
| id | doaj.art-18a65401d06b4922a3195da38e5d7882 |
| institution | Directory Open Access Journal |
| issn | 1869-4101 |
| language | English |
| last_indexed | 2024-03-07T14:57:11Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj.art-18a65401d06b4922a3195da38e5d78822024-03-05T19:20:17ZengSpringerOpenInsights into Imaging1869-41012024-02-0115111410.1186/s13244-024-01618-7Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre studyFengying Qin0Xinyan Sun1Mingke Tian2Shan Jin3Jian Yu4Jing Song5Feng Wen6Hongming Xu7Tao Yu8Yue Dong9Department of Radiology, Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)Department of Radiology, Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)Department of Radiology, Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)School of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyDepartment of Radiology, Huludao Center HospitalDepartment of Radiology, Shengjing Hospital of China Medical UniversityDepartment of Radiology, Shengjing Hospital of China Medical UniversitySchool of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyDepartment of Radiology, Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)Department of Radiology, Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)Abstract Objectives To develop and validate a magnetic resonance imaging-based (MRI) deep multiple instance learning (D-MIL) model and combine it with clinical parameters for preoperative prediction of lymph node metastasis (LNM) in operable cervical cancer. Methods A total of 392 patients with cervical cancer were retrospectively enrolled. Clinical parameters were analysed by logistical regression to construct a clinical model (M1). A ResNet50 structure is applied to extract features at the instance level without using manual annotations about the tumour region and then construct a D-MIL model (M2). A hybrid model (M3) was constructed by M1 and M2 scores. The diagnostic performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC) and compared using the Delong method. Disease-free survival (DFS) was evaluated by the Kaplan‒Meier method. Results SCC-Ag, maximum lymph node short diameter (LNmax), and tumour volume were found to be independent predictors of M1 model. For the diagnosis of LNM, the AUC of the training/internal/external cohort of M1 was 0.736/0.690/0.732, the AUC of the training/internal/external cohort of M2 was 0.757/0.714/0.765, and the AUC of the training/internal/external cohort of M3 was 0.838/0.764/0.835. M3 showed better performance than M1 and M2. Through the survival analysis, patients with higher hybrid model scores had a shorter time to reach DFS. Conclusion The proposed hybrid model could be used as a personalised non-invasive tool, which is helpful for predicting LNM in operable cervical cancer. The score of the hybrid model could also reflect the DFS of operable cervical cancer. Critical relevance statement Lymph node metastasis is an important factor affecting the prognosis of cervical cancer. Preoperative prediction of lymph node status is helpful to make treatment decisions, improve prognosis, and prolong survival time. Key points • The MRI-based deep-learning model can predict the LNM in operable cervical cancer. • The hybrid model has the highest diagnostic efficiency for the LNM prediction. • The score of the hybrid model can reflect the DFS of operable cervical cancer. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01618-7Lymph node metastasisCervical cancerDeep learningMagnetic resonance imaging |
| spellingShingle | Fengying Qin Xinyan Sun Mingke Tian Shan Jin Jian Yu Jing Song Feng Wen Hongming Xu Tao Yu Yue Dong Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study Insights into Imaging Lymph node metastasis Cervical cancer Deep learning Magnetic resonance imaging |
| title | Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study |
| title_full | Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study |
| title_fullStr | Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study |
| title_full_unstemmed | Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study |
| title_short | Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study |
| title_sort | prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with mri data a multicentre study |
| topic | Lymph node metastasis Cervical cancer Deep learning Magnetic resonance imaging |
| url | https://doi.org/10.1186/s13244-024-01618-7 |
| work_keys_str_mv | AT fengyingqin predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT xinyansun predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT mingketian predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT shanjin predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT jianyu predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT jingsong predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT fengwen predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT hongmingxu predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT taoyu predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy AT yuedong predictionoflymphnodemetastasisinoperablecervicalcancerusingclinicalparametersanddeeplearningwithmridataamulticentrestudy |