|
Á¢¼ö¹øÈ£ - 270027 6 |
PREDICTION OF TREATMENT OUTCOME USING MRI RADIOMICS AND MACHINE LEARNING
IN OROPHARYNGEAL CANCER PATIENTS AFTER SURGICAL TREATMENT |
DEPARTMENT OF OTORHINOLARYNGOLOGY, YONSEI UNIVERSITY COLLEGE OF MEDICINE, GANGNAM SEVERANCE HOSPITAL, SEOUL, KOREA1, DEPARTMENT OF OTORHINOLARYNGOLOGY, YONSEI UNIVERSITY COLLEGE OF MEDICINE, SEOUL, KOREA2 |
YOUNG MIN PARK1, JAE YOL LIM1, YOON WOO KOH2, MD, SE-HEON KIM2, EUN CHANG CHOI2 |
¸ñÀû: In this study, the authors analyzed preoperative MRI images of
oropharyngeal cancer patients who underwent surgical treatment,
extracted radiomics features, and constructed a disease recurrence and
death prediction model using radiomics features and machine-learning
techniques. ¹æ¹ý:A total of 157 patients participated in this study, and 107 stable
radiomics features were selected and used for constructing a predictive
model. °á°ú:The performance of the combined model (clinical and radiomics) yielded
the following results: AUC = 0.786, accuracy = 0.854, precision =
0.429, recall = 0.500, and f1 score = 0.462. The combined model showed
better performance than either the clinical or radiomics model for
predicting disease recurrence. For predicting death, the combined
model performance was: AUC = 0.841, accuracy = 0.771, precision =
0.308, recall = 0.667, and f1 score = 0.421. The combined model showed
superior performance to the predictive model using only clinical
variables. A Cox proportional hazard model using the combined
variables for predicting patient death yielded a c-index value that
was significantly better than that of the model including only
clinical variables. °á·Ð:A predictive model using clinical variables and MRI radiomics features
showed excellent performance in predicting disease recurrence and
death in oropharyngeal cancer patients. In the future, it is necessary
to verify model performance and confirm its clinical usefulness
through a multicenter study. |
|