COT-16 Development of automatic lesion extraction application using artificial intelligence for the purpose of simplifying tumor volume measurement of meningioma

BACKGROUND: With the widespread use of MRI equipment and brain scans, opportunities to perform follow-up examinations for meningiomas have increased. On the other hand, an objective evaluation index for meningiomas characterized by slow changes on imaging has not been established. To establish a volume-based evaluation index for meningoceles, we are developing an application for automatic lesion extraction using artificial intelligence as a highly reproducible tumor volume measurement technique that enables large volume image data processing. METHODS: In this study, 195 patients with meningioma who underwent contrast-enhanced MRI imaging at Osaka University Hospital were included. The images were manually extracted by three neurosurgeons and used as supervised data. deeplabV3 was used as the learning network. All the supervised data were randomly divided into training (80%) and testing (20%) data, and the application was constructed by deep learning and validation with 5-fold cross-validation. The matching rate of the area of the region automatically extracted by the device against the test data and the mean square error rate of the calculated tumor volume were used as indices of the product measurement performance. RESULTS: The matching rate using the automatic extraction application for the correct data(Dice index) was 91.5% on average. The mean squared error rate of the tumor volume calculated from these extracted regions was 8.84%. CONCLUSION: We consider that this application using artificial intelligence has a certain degree of validity in terms of the accuracy of extracted lesions. In the future, it is necessary not only to improve the performance of the equipment but also to clarify the clinical significance of the new imaging biomarkers based on tumor volume that can be obtained from these lesion extraction techniques.

Semi-Automatic Volumetric and Standard Three-Dimensional Measurements for Primary Tumor Evaluation and Response to Treatment Assessment in Pediatric Rhabdomyosarcoma

Current prognostic classification of rhabdomyosarcoma in children requires precise measurements of the tumor. The purpose of the study was to compare the standard three-dimensional (3D) measurements with semi-automatic tumor volume measurement method concerning assessment of the primary tumor size and the degree of response to treatment for rhabdomyosarcoma in children. Magnetic Resonance Imaging data on 31 children with treated rhabdomyosarcoma based on the Cooperative Weichteilsarkom Studiengruppe (CWS) guidance was evaluated. Tumor sizes were measured by two methods: 3D standard measurements and semi-automatic tumor volume measurement (VOI) at diagnosis, and after 9 and 17/18 weeks of the induction chemotherapy. Response to treatment and prediction values were assessed. The tumor volume medians calculated using VOI were significantly higher in comparison with those calculated using the 3D method both during the diagnosis as well as after 9 weeks of the chemotherapy and during the 17–18th week of the treatment. The volume measurements based on the generalized estimating equations on the VOI method were significantly better than the 3D method (p = 0.037). The volumetric measurements alone can hardly be considered an unequivocal marker used to make decisions on modification of the therapy in patients with rhabdomyosarcoma.