Technical Name 多模肺癌臨床智慧決策分享輔助系統
Project Operator Taipei Medical University
Project Host 陳震宇
The proposed technologies apply deep learning methodsbig clinical data for lung cancer decision support. The system consists of: 1) CT radiogenomicspatho-genomics for automatic cancer detectionprediction of EGFR mutation 2) demographics to predict survival 3) genomics to predict cancer recurrencemetastasis,4) drug response inference for the best target therapy option. The modules are constructed on an AI-based Clinical Decision Support System (CDSS-SDM). The system is expected to provide physicianspatients with personalized medication recommendations.
Technical Film
Scientific Breakthrough
This clinical decision support system ensembles advanced AI image algorithms to achieve personalized medicine in lung cancer. The two breakthrough techniques are CT radiogenomicspatho-genomics. The former employs radiomics to construct a model which can detectclassify lung cancer,infer EGFR mutation status. The latter is a world-leading auto segmentation technology in whole-slide image (published in Nature Communications 2021). It can auto-segmentclassify lung cancer cells in H&E stain pathology slide (accuracy rate achieves 95),predict EGFR mutations status.
Industrial Applicability
This multi-module clinical decision support-shared decision-making system (CDSS-SDM) has the potential to integrate industrial value chain from clinical precision management of lung cancer to AI software industries which link to new drug development. The technologies will be sent as SaMD for TFDAFDA certification. The groundbreaking core technologies are extremely applicable for early accurate diagnosis of lung cancer, survival prediction, drug selectionresponse prediction, as well as clinical trial matching if all treatment option fails.
Matching Needs
Keyword Computer tomography Metadata Artificial Intelligence Clinical Decision Support Systems Radiogenomics Whole Slide Auto-segmentation and Classification Genomics Natural Language Processing Real World Evidence Clinical Pathway
  • Contact