A deep-learning model developed using serial image scans of tumors from patients with non-small cell lung cancer (NSCLC) predicted treatment response and survival outcomes better than standard clinical parameters. The study is published in Clinical Cancer Research, a journal of the American Association for Cancer Research, by Hugo Aerts, Ph.D.
Research demonstrates that deep-learning models integrating routine; so imaging scans obtaine at multiple time points can improve predictions of survival and cancer-specific outcomes for lung cancer,” said Aerts. “By comparison, a standard clinical model relying on stage, gender, age, tumor grade, performance; so smoking status, and tumor size could not reliably predict two-year survival or treatment response.
Leading cause of cancer death
Lung cancer is the most common cancer and the leading cause of cancer death worldwide. NSCLC accounts for about 85% of all lung cancers. The standard assessment for diagnosis and response to therapy for these patients; hence relies heavily on the measurement of maximum tumor diameter; which is susceptible to variations in interpretation between observers and over time.
How the Study was Conduct: To see if they could extract more predictive insights as cancers evolve; Aerts and colleagues built deep-learning models. They transfer learning from ImageNet; so a neural network created by researchers at Princeton University and Stanford University that identifies a wide range of ordinary objects from the most relevant features; also train their models using serial CT scans of 179 patients with stage 3 NSCLC who had been treat with chemoradiation.
They included up to four images per patient obtain routinely before treatment; also at one, three, and six months after treatment for a total of 581 images. The investigators analyze the model’s ability to make significant cancer outcome predictions with two datasets; so the training dataset of 581 images and an independent validation dataset; so of 178 images from 89 patients with non-small cell lung cancer who has treat with chemoradiation and surgery.
Addition of each follow-up scan
The models’ performance improve with the addition of each follow-up scan. The area under the curve, a meaure of the model’s accuracy, for predicting two-year survival base on pretreatment scans alone was 0.58; which improve significantly to 0.74 after adding all available follow-up scans. Patients class as having low risk for mortality by the model; so six-fold improve overall survival compare with those class as having high risk.
Compare with the clinical model that utilizes parameters of stage, gender, age, tumor grade; so performance, smoking status, and clinical tumor size, the deep-learning model was more efficient in predicting distant metastasis; progression, and local regional recurrence. Radiology scans are capture routinely from lung cancer patients during follow-up examinations and are already digitize data forms, making them ideal for artificial intelligence applications.
Deep-learning models that quantitatively track changes in lesions over time; hence may help clinicians tailor treatment plans for individual patients and help stratify patients into different risk groups for clinical trials. The main limitation of this proof-of-principle research; so is that it needs to be expand with more data and evaluate in prospective clinical trials, said Aerts.