SBIR Phase I Topic 402 - Artificial Intelligence-Aided Imaging for Cancer Prevention, Diagnosis, and Monitoring

点击翻译按钮获取中文摘要

Thermal ablation systems are typically accompanied by ablation treatment planning system to optimize the treatment outcome using pre-operative CT scan. Radiomics is a process of converting medical images into higher-dimensional data and subsequent mining of data to reveal underlying pathophysiology for enhancing clinical decision support making. Radiomics analysis have shown promises in capturing distinct tumor characteristics and predicting prognosis of the tumor. We propose innovative method to calculate microwave ablation zones by supplementing a bioheat transfer model of microwave tissue ablation with microwave sensitive radiomics features, which will generate more accurate and personalized ablation prediction leading to better treatment outcome. Inputs to the bioheat transfer modeling approach include the geometry of the target tumor, physical properties of the tissue, and dimensions of the microwave ablation applicator. The radiomics algorithm extracts properties of the targeted tumor’s size and shape, as well as texture from CT images. Therefore, shape, size, and texture data computed through 3D wavelets are employed as radiomics features for more accurate dose prediction. The proposed radiomics analysis is conducted in three stages: (1)automatic detection of candidate tumors, (2)automatic segmentation of a selected tumor, (3)extraction of features from the segmented tumor, (4)analysis of ablated tumor over period of time.