Yae Won Park1,2, Jihwan Eom3, Sooyon Kim4, Hwiyoung Kim1, Sung Soo Ahn1,2, Cheol Ryong Ku2,5, Eui Hyun Kim2,5, Eun Jig Lee2,6, Sun Ho Kim7, Seung-Koo Lee1,2. 1. Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea. 2. Pituitary Tumor Center, Severance Hospital, Seoul, Korea. 3. Department of Computer Science, Yonsei University, Seoul, Korea. 4. Department of Statistics and Data Science, Yonsei University, Seoul, Korea. 5. Department of Endocrinology, Yonsei University College of Medicine, Seoul, Korea. 6. Department of Neurosurgery, Yonsei University College of Medicine, Seoul, Korea. 7. Department of Neurosurgery, Ewha Womans University College of Medicine, Seoul, Korea.
Abstract
CONTEXT: Early identification of the response of prolactinoma patients to dopamine agonists (DA) is crucial in treatment planning. OBJECTIVE: To develop a radiomics model using an ensemble machine learning classifier with conventional magnetic resonance images (MRIs) to predict the DA response in prolactinoma patients. DESIGN: Retrospective study. SETTING: Severance Hospital, Seoul, Korea. PATIENTS: A total of 177 prolactinoma patients who underwent baseline MRI (109 DA responders and 68 DA nonresponders) were allocated to the training (n = 141) and test (n = 36) sets. Radiomic features (n = 107) were extracted from coronal T2-weighed MRIs. After feature selection, single models (random forest, light gradient boosting machine, extra-trees, quadratic discrimination analysis, and linear discrimination analysis) with oversampling methods were trained to predict the DA response. A soft voting ensemble classifier was used to achieve the final performance. The performance of the classifier was validated in the test set. RESULTS: The ensemble classifier showed an area under the curve (AUC) of 0.81 [95% confidence interval (CI), 0.74-0.87] in the training set. In the test set, the ensemble classifier showed an AUC, accuracy, sensitivity, and specificity of 0.81 (95% CI, 0.67-0.96), 77.8%, 78.6%, and 77.3%, respectively. The ensemble classifier achieved the highest performance among all the individual models in the test set. CONCLUSIONS: Radiomic features may be useful biomarkers to predict the DA response in prolactinoma patients.
CONTEXT: Early identification of the response of prolactinomapatients to dopamine agonists (DA) is crucial in treatment planning. OBJECTIVE: To develop a radiomics model using an ensemble machine learning classifier with conventional magnetic resonance images (MRIs) to predict the DA response in prolactinomapatients. DESIGN: Retrospective study. SETTING: Severance Hospital, Seoul, Korea. PATIENTS: A total of 177 prolactinomapatients who underwent baseline MRI (109 DA responders and 68 DA nonresponders) were allocated to the training (n = 141) and test (n = 36) sets. Radiomic features (n = 107) were extracted from coronal T2-weighed MRIs. After feature selection, single models (random forest, light gradient boosting machine, extra-trees, quadratic discrimination analysis, and linear discrimination analysis) with oversampling methods were trained to predict the DA response. A soft voting ensemble classifier was used to achieve the final performance. The performance of the classifier was validated in the test set. RESULTS: The ensemble classifier showed an area under the curve (AUC) of 0.81 [95% confidence interval (CI), 0.74-0.87] in the training set. In the test set, the ensemble classifier showed an AUC, accuracy, sensitivity, and specificity of 0.81 (95% CI, 0.67-0.96), 77.8%, 78.6%, and 77.3%, respectively. The ensemble classifier achieved the highest performance among all the individual models in the test set. CONCLUSIONS: Radiomic features may be useful biomarkers to predict the DA response in prolactinomapatients.
Authors: Markus Huber; Markus M Luedi; Gerrit A Schubert; Christian Musahl; Angelo Tortora; Janine Frey; Jürgen Beck; Luigi Mariani; Emanuel Christ; Lukas Andereggen Journal: Front Endocrinol (Lausanne) Date: 2022-02-16 Impact factor: 5.555
Authors: Darius Kalasauskas; Michael Kosterhon; Naureen Keric; Oliver Korczynski; Andrea Kronfeld; Florian Ringel; Ahmed Othman; Marc A Brockmann Journal: Cancers (Basel) Date: 2022-02-07 Impact factor: 6.639