Using Ultrasound and Radiomics to Predict Cancer Treatment Response
Author Information
Author(s): Abuliezi Dilimire, She Yufen, Liao Zhongfan, Luo Yuan, Yang Yin, Huang Qin, Tao Anqi, Zhuang Hua
Primary Institution: West China Hospital of Sichuan University
Hypothesis
This study aimed to explore a combined transrectal ultrasound (TRUS) and radiomics model for predicting tumor regression grade (TRG) after neoadjuvant chemoradiotherapy (NCRT) in patients with locally advanced rectal cancer (LARC).
Conclusion
The combined model based on TRUS and radiomics demonstrated remarkable predictive capability for TRG after NCRT.
Supporting Evidence
- The combined model achieved an accuracy of 0.863 and an AUC of 0.913.
- Eight TRUS parameters were identified as statistically significant for distinguishing between good and poor response groups.
- The study included a total of 190 patients, surpassing the minimum sample size requirement for statistical reliability.
Takeaway
Doctors used special ultrasound pictures and computer analysis to better predict how well cancer treatment will work for patients.
Methodology
The study involved 190 patients with locally advanced rectal cancer, using transrectal ultrasound and radiomics to predict treatment response.
Potential Biases
Potential bias due to the retrospective nature and selection criteria of the study.
Limitations
The study was retrospective and did not consider confounding effects from different NCRT methods.
Participant Demographics
190 patients with locally advanced rectal cancer, including 53 in the good response group and 137 in the poor response group.
Statistical Information
P-Value
p<0.05
Confidence Interval
[0.792–0.909]
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website