Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses.
We investigated whether the integration of machine learning (ML) into MRI interpretation can provide accurate decision rules for the management of suspicious breast masses. A total of 173 consecutive patients with suspicious breast masses upon complementary assessment (BI-RADS IV/V: n = 100/76) rece...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2020-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0228446 |
| _version_ | 1818578347137957888 |
|---|---|
| author | Stephan Ellmann Evelyn Wenkel Matthias Dietzel Christian Bielowski Sulaiman Vesal Andreas Maier Matthias Hammon Rolf Janka Peter A Fasching Matthias W Beckmann Rüdiger Schulz Wendtland Michael Uder Tobias Bäuerle |
| author_facet | Stephan Ellmann Evelyn Wenkel Matthias Dietzel Christian Bielowski Sulaiman Vesal Andreas Maier Matthias Hammon Rolf Janka Peter A Fasching Matthias W Beckmann Rüdiger Schulz Wendtland Michael Uder Tobias Bäuerle |
| author_sort | Stephan Ellmann |
| collection | DOAJ |
| description | We investigated whether the integration of machine learning (ML) into MRI interpretation can provide accurate decision rules for the management of suspicious breast masses. A total of 173 consecutive patients with suspicious breast masses upon complementary assessment (BI-RADS IV/V: n = 100/76) received standardized breast MRI prior to histological verification. MRI findings were independently assessed by two observers (R1/R2: 5 years of experience/no experience in breast MRI) using six (semi-)quantitative imaging parameters. Interobserver variability was studied by ICC (intraclass correlation coefficient). A polynomial kernel function support vector machine was trained to differentiate between benign and malignant lesions based on the six imaging parameters and patient age. Ten-fold cross-validation was applied to prevent overfitting. Overall diagnostic accuracy and decision rules (rule-out criteria) to accurately exclude malignancy were evaluated. Results were integrated into a web application and published online. Malignant lesions were present in 107 patients (60.8%). Imaging features showed excellent interobserver variability (ICC: 0.81-0.98) with variable diagnostic accuracy (AUC: 0.65-0.82). Overall performance of the ML algorithm was high (AUC = 90.1%; BI-RADS IV: AUC = 91.6%). The ML algorithm provided decision rules to accurately rule-out malignancy with a false negative rate <1% in 31.3% of the BI-RADS IV cases. Thus, integration of ML into MRI interpretation can provide objective and accurate decision rules for the management of suspicious breast masses, and could help to reduce the number of potentially unnecessary biopsies. |
| first_indexed | 2024-12-16T06:44:22Z |
| format | Article |
| id | doaj.art-548078a13a164546acf2f59931704c01 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-16T06:44:22Z |
| publishDate | 2020-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-548078a13a164546acf2f59931704c012022-12-21T22:40:36ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-01151e022844610.1371/journal.pone.0228446Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses.Stephan EllmannEvelyn WenkelMatthias DietzelChristian BielowskiSulaiman VesalAndreas MaierMatthias HammonRolf JankaPeter A FaschingMatthias W BeckmannRüdiger Schulz WendtlandMichael UderTobias BäuerleWe investigated whether the integration of machine learning (ML) into MRI interpretation can provide accurate decision rules for the management of suspicious breast masses. A total of 173 consecutive patients with suspicious breast masses upon complementary assessment (BI-RADS IV/V: n = 100/76) received standardized breast MRI prior to histological verification. MRI findings were independently assessed by two observers (R1/R2: 5 years of experience/no experience in breast MRI) using six (semi-)quantitative imaging parameters. Interobserver variability was studied by ICC (intraclass correlation coefficient). A polynomial kernel function support vector machine was trained to differentiate between benign and malignant lesions based on the six imaging parameters and patient age. Ten-fold cross-validation was applied to prevent overfitting. Overall diagnostic accuracy and decision rules (rule-out criteria) to accurately exclude malignancy were evaluated. Results were integrated into a web application and published online. Malignant lesions were present in 107 patients (60.8%). Imaging features showed excellent interobserver variability (ICC: 0.81-0.98) with variable diagnostic accuracy (AUC: 0.65-0.82). Overall performance of the ML algorithm was high (AUC = 90.1%; BI-RADS IV: AUC = 91.6%). The ML algorithm provided decision rules to accurately rule-out malignancy with a false negative rate <1% in 31.3% of the BI-RADS IV cases. Thus, integration of ML into MRI interpretation can provide objective and accurate decision rules for the management of suspicious breast masses, and could help to reduce the number of potentially unnecessary biopsies.https://doi.org/10.1371/journal.pone.0228446 |
| spellingShingle | Stephan Ellmann Evelyn Wenkel Matthias Dietzel Christian Bielowski Sulaiman Vesal Andreas Maier Matthias Hammon Rolf Janka Peter A Fasching Matthias W Beckmann Rüdiger Schulz Wendtland Michael Uder Tobias Bäuerle Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses. PLoS ONE |
| title | Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses. |
| title_full | Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses. |
| title_fullStr | Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses. |
| title_full_unstemmed | Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses. |
| title_short | Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses. |
| title_sort | implementation of machine learning into clinical breast mri potential for objective and accurate decision making in suspicious breast masses |
| url | https://doi.org/10.1371/journal.pone.0228446 |
| work_keys_str_mv | AT stephanellmann implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT evelynwenkel implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT matthiasdietzel implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT christianbielowski implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT sulaimanvesal implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT andreasmaier implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT matthiashammon implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT rolfjanka implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT peterafasching implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT matthiaswbeckmann implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT rudigerschulzwendtland implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT michaeluder implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses AT tobiasbauerle implementationofmachinelearningintoclinicalbreastmripotentialforobjectiveandaccuratedecisionmakinginsuspiciousbreastmasses |