A deep-learning model combining radiomics and clinicopathologic data with breast DCE-MRI improves prediction of complete pathological response after chemotherapy.
Key Details
- 1Study led by Chaowei Wu, PhD, at Cedars-Sinai Medical Center.
- 2Model integrates clinicopathologic data, shape radiomics, and retrospective pharmacokinetic quantification radiomics.
- 3Included MRI data from 1,073 breast cancer patients (2002–2016).
- 4Model achieved higher AUCs (up to 0.82 on external datasets) vs. conventional methods.
- 5Reported accuracy 69%, sensitivity 95%, specificity 59%.
- 6Early pCR prediction aids personalized treatment planning.
Why It Matters
Improved prediction of chemotherapy response using AI-driven analysis of DCE-MRI could enable more personalized and effective treatment strategies in breast cancer, potentially improving outcomes. The results show better accuracy and generalizability than existing methods across multiple datasets.
Source
AuntMinnie
Related News
•Health Imaging
AI as Second Reader Surpasses Radiologists in Breast Cancer Screening
AI used as a second reader on mammograms improves cancer detection rates compared to radiologists alone.
•Health Imaging
AI-Powered Ultrasound Tool Predicts Delivery Timing for Pregnant Patients
Researchers have created an AI model using ultrasound to accurately forecast expectant mothers’ delivery timelines.
•AuntMinnie
ChatGPT-4 Turbo Powers Postdeployment Monitoring of ICH Detection AI
Researchers found ChatGPT-4 Turbo could efficiently monitor the performance of Aidoc's ICH detection AI across real-world radiology practices.