Technical Name Artificial intelligence driven automatic tumor detection and follow up, and precision medicine model for acoustic neuroma
Project Operator National Yang-Ming University
Project Host 吳育德
Vestibular schwannoma (VS), also termed acoustic neuroma, is a benign intracranial tumor that grows slowly in the internal auditory canal and extends to the cerebello-pontine angle. Over time, tumor growth is known to cause gradual hearing impairment, tinnitus, dizziness, syncope, trigeminal neuropathy, and facial palsy.
Currently, Gamma Knife radiosurgery (GKRS) is a safe and effective strategy to treat VSs with an over 90% long-term tumor control rate and a lower risk of treatment-related complications. However, a small percentage of patients still have some issues for GKRS treatment. One of the issues is the patients suffer from the treatment failure. Another issue is the presence of transient tumor growth, due to tumor swelling after GKRS, which typically occurs from 6 to 18 months after radiation treatment. Therefore, automatic tumor segment and effective predictors to classify pseudo-progression and efficient shrinkage after GK surgery is a key issue of clinical research in VS.
Scientific Breakthrough
We retrospectively collected the MR images and tumor contours of 516 participants with VS, these had been obtained by the Gamma Knife team at Taipei Veterans General Hospital, Taiwan. The trained dual-pathway U-Net model used multi-parametric MR images (T1-weighted, T1-weighted with contrast, and T2-weighted) as training input, achieving the testing dice score: 0.90.
We calculated the MR radiomics from pre-GKRS images to predict the treatment response and whether the pseudo-progression will occur. After the statistical analysis and the feature selection to retain the most important features, the two-level machine-learning models were built by these features. The two-level classification model respectively achieved the testing AUC: 0.877 and 0.816 for each level.
Industrial Applicability
The assessment system includes the image pre-processing workflow, automatic segmentation and treatment response prediction algorithm. This pipeline is not only useful for clinical physicians to assess the VS treatment response, and also can be adopted to other kinds of benign and malignant brain tumor to build up their own assessment systems. This technique provides another health care solution that can be implemented at the devices of radiotherapy/radiosurgery to assist the treatment planning.
Keyword vestibular schwannoma radiosurgery gamma knife magnetic resonance imaging deep-learning convolutional neural network automatic tumor segmentation radiomics machine learning treatment response prediction
  • Contact
other people also saw