Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features
Purpose: To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. Methods: A tra...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/15/8/2209 |
_version_ | 1811153803143020544 |
---|---|
author | Xingfeng Li Michele Dessi Diana Marcus James Russell Eric O. Aboagye Laura Burney Ellis Alexander Sheeka Won-Ho Edward Park Nishat Bharwani Sadaf Ghaem-Maghami Andrea G. Rockall |
author_facet | Xingfeng Li Michele Dessi Diana Marcus James Russell Eric O. Aboagye Laura Burney Ellis Alexander Sheeka Won-Ho Edward Park Nishat Bharwani Sadaf Ghaem-Maghami Andrea G. Rockall |
author_sort | Xingfeng Li |
collection | DOAJ |
description | Purpose: To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. Methods: A training dataset containing 413 patients and an independent testing dataset consisting of 82 cases were employed in this retrospective study. Manual segmentation of the whole tumor volume on sagittal T2-weighted MRI was performed. Clinical and radiomic features were extracted to predict: (i) DMI of endometrial cancer patients, (ii) endometrial cancer clinical high-risk level, (iii) histological subtype of tumor, and (iv) presence of LVSI. A classification model with different automatically selected hyperparameter values was created. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, F1 score, average recall, and average precision were calculated to evaluate different models. Results: Based on the independent external testing dataset, the AUCs for DMI, high-risk endometrial cancer, endometrial histological type, and LVSI classification were 0.79, 0.82, 0.91, and 0.85, respectively. The corresponding 95% confidence intervals (CI) of the AUCs were [0.69, 0.89], [0.75, 0.91], [0.83, 0.97], and [0.77, 0.93], respectively. Conclusion: It is possible to classify endometrial cancer DMI, risk, histology type, and LVSI using different machine learning methods. |
first_indexed | 2024-03-11T05:10:14Z |
format | Article |
id | doaj.art-92464887d6c34a0291ecfa94100cfead |
institution | Directory Open Access Journal |
issn | 2072-6694 |
language | English |
last_indexed | 2024-03-11T05:10:14Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Cancers |
spelling | doaj.art-92464887d6c34a0291ecfa94100cfead2023-11-17T18:37:48ZengMDPI AGCancers2072-66942023-04-01158220910.3390/cancers15082209Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic FeaturesXingfeng Li0Michele Dessi1Diana Marcus2James Russell3Eric O. Aboagye4Laura Burney Ellis5Alexander Sheeka6Won-Ho Edward Park7Nishat Bharwani8Sadaf Ghaem-Maghami9Andrea G. Rockall10Department of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKThe Imaging Department, Imperial College Healthcare NHS Trust, UK Hammersmith Hospital, Du Cane Road, London W12 0HS, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKThe Imaging Department, Imperial College Healthcare NHS Trust, UK Hammersmith Hospital, Du Cane Road, London W12 0HS, UKThe Imaging Department, Imperial College Healthcare NHS Trust, UK Hammersmith Hospital, Du Cane Road, London W12 0HS, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKDepartment of Surgery and Cancer, Imperial College Hammersmith Campus, Du Cane Road, London W12 0NN, UKPurpose: To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. Methods: A training dataset containing 413 patients and an independent testing dataset consisting of 82 cases were employed in this retrospective study. Manual segmentation of the whole tumor volume on sagittal T2-weighted MRI was performed. Clinical and radiomic features were extracted to predict: (i) DMI of endometrial cancer patients, (ii) endometrial cancer clinical high-risk level, (iii) histological subtype of tumor, and (iv) presence of LVSI. A classification model with different automatically selected hyperparameter values was created. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, F1 score, average recall, and average precision were calculated to evaluate different models. Results: Based on the independent external testing dataset, the AUCs for DMI, high-risk endometrial cancer, endometrial histological type, and LVSI classification were 0.79, 0.82, 0.91, and 0.85, respectively. The corresponding 95% confidence intervals (CI) of the AUCs were [0.69, 0.89], [0.75, 0.91], [0.83, 0.97], and [0.77, 0.93], respectively. Conclusion: It is possible to classify endometrial cancer DMI, risk, histology type, and LVSI using different machine learning methods.https://www.mdpi.com/2072-6694/15/8/2209endometrial cancerT2-weighted MRIradiomicsmachine learning classificationfeature selectiondeep myometrial infiltration |
spellingShingle | Xingfeng Li Michele Dessi Diana Marcus James Russell Eric O. Aboagye Laura Burney Ellis Alexander Sheeka Won-Ho Edward Park Nishat Bharwani Sadaf Ghaem-Maghami Andrea G. Rockall Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features Cancers endometrial cancer T2-weighted MRI radiomics machine learning classification feature selection deep myometrial infiltration |
title | Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features |
title_full | Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features |
title_fullStr | Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features |
title_full_unstemmed | Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features |
title_short | Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features |
title_sort | prediction of deep myometrial infiltration clinical risk category histological type and lymphovascular space invasion in women with endometrial cancer based on clinical and t2 weighted mri radiomic features |
topic | endometrial cancer T2-weighted MRI radiomics machine learning classification feature selection deep myometrial infiltration |
url | https://www.mdpi.com/2072-6694/15/8/2209 |
work_keys_str_mv | AT xingfengli predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT micheledessi predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT dianamarcus predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT jamesrussell predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT ericoaboagye predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT lauraburneyellis predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT alexandersheeka predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT wonhoedwardpark predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT nishatbharwani predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT sadafghaemmaghami predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures AT andreagrockall predictionofdeepmyometrialinfiltrationclinicalriskcategoryhistologicaltypeandlymphovascularspaceinvasioninwomenwithendometrialcancerbasedonclinicalandt2weightedmriradiomicfeatures |