MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Cone-Beam CT Radiomics for Patients with Liver Tumors Treated by Stereotactic Body Radiation Therapy: A Pilot Study

P Yang1*, J Shan2, Q Zhou2, L Xu1, Z Cao1, T Niu3, M Huang4, X Sun2, (1) Zhejiang University, Hangzhou, ,CN, (2) Department of Radiation Oncology, Sir Run Run Shaw Hospital, Zhejiang Univ., Hangzhou, ,CN,(3) Georgia Institute Of Technology,Woodruff School of Mechanical Engineering,Atlanta,GA(4) Duke University, Department of Radiation Oncology, Durham, NC,

Presentations

(Sunday, 7/12/2020)   [Eastern Time (GMT-4)]

Room: AAPM ePoster Library

Purpose:
To investigate the potential of using cone-beam CT(CBCT) based radiomics approach for assessing treatment response in liver tumors treated with stereotactic body radiation therapy (SBRT).

Methods:
The CBCT and planning CT (pCT) images of 36 liver cancer patients were prospectively included in this study. All the patients received five-fraction SBRT treatment within two weeks at our institution. Radiomics features were extracted from both CBCT and pCT. Pearson correlation test was used to select interchangeable CBCT radiomics features with pCT. All five fractions of CBCT radiomics features were reconstructed into five principle components using principle components analysis (PCA) to characterize therapy-induced tumor change. The Mann-Whitney U-test was used to select distinct features for predicting the treatment response (local efficacy vs local non-efficacy; complete response (CR) vs partial response (PR)) in both the raw and PCA-based CBCT radiomics features. The area under the ROC curve (AUC) was applied to assess feature performance.

Results:
A total of 345 out of 547 CBCT radiomics features were interchangeable with pCT. Six raw and 63 PCA-based CBCT features showed statistical significance in predicting local efficacy. Among these features, the highest AUC was 0.879 (0.744-1.00, 95% CI). For identifying CR from PR, 61 raw and 42 PCA-based CBCT radiomics features showed differential value, with the highest AUC of 0.884 (0.773-1.00, 95% CI).
Conclusion:
Radiomics features extracted from CBCT images showed the potential for assessing the response to the treatment in advance which could serve as an early biomarker for liver tumor SBRT.

Keywords

Radiation Therapy, Image Analysis, Cone-beam CT

Taxonomy

IM- Cone Beam CT: Biomarkers

Contact Email