Deep-learning model improves prediction lung cancer survival

Lung cancer is one of the most common cancers and a leading cause of cancer death worldwide. Non Small Cell Lung cancer (NSCLC) accounts for about 85 percent of all lung cancers. The standard assessment for diagnosis and response to therapy for NSCLC patients relies heavily on the measurement of maximum tumor diameter, which is susceptible to variations in interpretation between observers and over time. A multi-national group of researchers  hypothesized that Artificial Intelligence (AI) algorithms could automatically quantify radiographic characteristics that are related to, and may therefore act as, non-invasive radiomic biomarkers for immunotherapy response (Trebeschi S et al Predicting Response to Cancer Immunotherapy using Non-invasive Radiomic Biomarkers. Ann Oncol. 2019 Mar 21. Doi 10.1093/annonc/mdz108).  The group transferred learning from ImageNet, 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, and trained their models using serial CT scans of 179 patients with stage 3 NSCLC who had been treated with chemoradiation. The researchers included up to four images per patient obtained routinely before treatment and at one, three, and six months after treatment for a total of 581 images.

The investigators analyzed the model’s ability to make significant cancer outcome predictions with two datasets: the training dataset of 581 images and an independent validation dataset of 178 images from 89 patients with NSCLC who had been treated with chemoradiation and surgery. The model’s performance improved with the addition of each follow-up scan. The area under the curve for predicting two-year survival based on pretreatment scans alone was 0.58, which improved significantly to 0.74 after adding all available follow-up scans. Patients classed by the model as having low risk for mortality had six-fold improved overall survival compared with those classed as having high risk.

Compared with the current clinical model that utilizes parameters of stage, gender, age, tumor grade, performance, smoking status, and clinical tumor size, the deep-learning model was more efficient in predicting distant metastases, progression, and local regional recurrence.

Radiology scans are captured routinely from lung cancer patients during follow-up examinations and are already in digitized data forms, making them ideal for artificial intelligence applications,” said lead author Dr H Aerts “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.”  He added “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. 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. To the best of our knowledge, this study is the first of its kind to investigate radiomics as a noninvasive biomarker for response to cancer immunotherapy

Doi 10.1093/annonc/mdz108