Deep learning uses CT images to predict cancer treatment response
A deep learning model using time-series CT images of tumors from patients with non–small cell lung cancer was able to predict survival and outcomes better than standard clinical parameters.
That’s the finding of a new study published this week in the journal Clinical Cancer Research.
“We demonstrate that deep learning can integrate imaging scans at multiple time points to improve clinical outcome predictions,” conclude the study’s authors. “AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic, given their low cost and minimal requirements for human input.”
In fact, the deep learning model was more efficient in predicting survival and cancer-specific outcomes—progression, distant metastases and local-regional recurrence—compared with the clinical model.
“Our research demonstrates that deep learning models integrating routine imaging scans obtained at multiple time points can improve predictions of survival and cancer-specific outcomes for lung cancer,” says Hugo Aerts, director of the Computational and Bioinformatics Laboratory at the Dana-Farber Cancer Institute and Brigham and Women’s Hospital. “By comparison, a standard clinical model relying on stage, gender, age, tumor grade, performance, smoking status and tumor size could not reliably predict two-year survival or treatment response.”
The study involved training the deep learning model using serial CT scans of 179 patients with stage 3 non–small cell lung cancer who had been treated with chemoradiation. The training dataset included a total of 581 images and an independent validation dataset of 178 images from 89 patients with non-small cell lung cancer who had been treated with chemoradiation and surgery.
“Radiology scans are captured routinely from lung cancer patients during follow-up examinations and are already digitized data forms, making them ideal for artificial intelligence applications,” Aerts adds. “Deep learning models that quantitatively track changes in lesions over time may help clinicians tailor treatment plans for individual patients and help stratify patients into different risk groups for clinical trials.”