User login
Radiomics signatures developed by artificial intelligence can predict sensitivity to treatment in adults with non–small cell lung cancer (NSCLC), according to a study published in Clinical Cancer Research.
“Radiomics features are calculated by algorithmic analysis of tumor images and have been linked to characteristics of NSCLC,” wrote Laurent Dercle, MD, of Columbia University, New York, and colleagues.
With their study, the researchers found that “radiomic signatures, derived from quantitative, artificial intelligence–based analysis of standard-of-care CT images, offer the potential to enhance clinical decision-making as on-treatment markers of efficacy.”
The researchers identified 188 adults with NSCLC: 92 receiving nivolumab, 50 receiving docetaxel, and 46 receiving gefitinib.
The team extracted 1,160 radiomics features from the largest measurable lung lesion in each patient. The researchers used CT images from baseline and the patients’ first treatment assessment (3 weeks for gefitinib and 8 weeks for nivolumab and docetaxel) to develop a model that would predict treatment sensitivity based on changes to the largest lung lesion.
In validation sets following training sets, the prediction models for nivolumab, docetaxel, and gefitinib yielded area under the curve results of 0.77, 0.67, and 0.82, respectively.
“Machine-learning techniques successfully performed a specific complex task: identifying a pattern of baseline and treatment-induced changes on CT images associated with sensitivity to systemic nivolumab, docetaxel, and gefitinib therapy in patients with a diagnosis of NSCLC,” the researchers wrote.
They noted that this study was limited by several factors, including the small sample size and the inability to evaluate the impact of various time intervals on feature selection and classification.
However, the researchers concluded that “this study is a proof of concept that AI [artificial intelligence] support could provide clinicians an early indication of the likelihood of success of treatment with the new generation of systemic anticancer therapies using conventional imaging techniques.”
This study was supported by Bristol-Myers Squibb, the National Institutes of Health, Fondation Philanthropia, and Fondation Nuovo-Soldati. The authors disclosed relationships, including employment, with Bristol-Myers Squibb. They also disclosed relationships with Roche, Novartis, Merck, and Boehringer Ingelheim.
SOURCE: Dercle L et al. Clin Cancer Res. 2020 Mar 20. doi: 10.1158/1078-0432.CCR-19-2942.
Radiomics signatures developed by artificial intelligence can predict sensitivity to treatment in adults with non–small cell lung cancer (NSCLC), according to a study published in Clinical Cancer Research.
“Radiomics features are calculated by algorithmic analysis of tumor images and have been linked to characteristics of NSCLC,” wrote Laurent Dercle, MD, of Columbia University, New York, and colleagues.
With their study, the researchers found that “radiomic signatures, derived from quantitative, artificial intelligence–based analysis of standard-of-care CT images, offer the potential to enhance clinical decision-making as on-treatment markers of efficacy.”
The researchers identified 188 adults with NSCLC: 92 receiving nivolumab, 50 receiving docetaxel, and 46 receiving gefitinib.
The team extracted 1,160 radiomics features from the largest measurable lung lesion in each patient. The researchers used CT images from baseline and the patients’ first treatment assessment (3 weeks for gefitinib and 8 weeks for nivolumab and docetaxel) to develop a model that would predict treatment sensitivity based on changes to the largest lung lesion.
In validation sets following training sets, the prediction models for nivolumab, docetaxel, and gefitinib yielded area under the curve results of 0.77, 0.67, and 0.82, respectively.
“Machine-learning techniques successfully performed a specific complex task: identifying a pattern of baseline and treatment-induced changes on CT images associated with sensitivity to systemic nivolumab, docetaxel, and gefitinib therapy in patients with a diagnosis of NSCLC,” the researchers wrote.
They noted that this study was limited by several factors, including the small sample size and the inability to evaluate the impact of various time intervals on feature selection and classification.
However, the researchers concluded that “this study is a proof of concept that AI [artificial intelligence] support could provide clinicians an early indication of the likelihood of success of treatment with the new generation of systemic anticancer therapies using conventional imaging techniques.”
This study was supported by Bristol-Myers Squibb, the National Institutes of Health, Fondation Philanthropia, and Fondation Nuovo-Soldati. The authors disclosed relationships, including employment, with Bristol-Myers Squibb. They also disclosed relationships with Roche, Novartis, Merck, and Boehringer Ingelheim.
SOURCE: Dercle L et al. Clin Cancer Res. 2020 Mar 20. doi: 10.1158/1078-0432.CCR-19-2942.
Radiomics signatures developed by artificial intelligence can predict sensitivity to treatment in adults with non–small cell lung cancer (NSCLC), according to a study published in Clinical Cancer Research.
“Radiomics features are calculated by algorithmic analysis of tumor images and have been linked to characteristics of NSCLC,” wrote Laurent Dercle, MD, of Columbia University, New York, and colleagues.
With their study, the researchers found that “radiomic signatures, derived from quantitative, artificial intelligence–based analysis of standard-of-care CT images, offer the potential to enhance clinical decision-making as on-treatment markers of efficacy.”
The researchers identified 188 adults with NSCLC: 92 receiving nivolumab, 50 receiving docetaxel, and 46 receiving gefitinib.
The team extracted 1,160 radiomics features from the largest measurable lung lesion in each patient. The researchers used CT images from baseline and the patients’ first treatment assessment (3 weeks for gefitinib and 8 weeks for nivolumab and docetaxel) to develop a model that would predict treatment sensitivity based on changes to the largest lung lesion.
In validation sets following training sets, the prediction models for nivolumab, docetaxel, and gefitinib yielded area under the curve results of 0.77, 0.67, and 0.82, respectively.
“Machine-learning techniques successfully performed a specific complex task: identifying a pattern of baseline and treatment-induced changes on CT images associated with sensitivity to systemic nivolumab, docetaxel, and gefitinib therapy in patients with a diagnosis of NSCLC,” the researchers wrote.
They noted that this study was limited by several factors, including the small sample size and the inability to evaluate the impact of various time intervals on feature selection and classification.
However, the researchers concluded that “this study is a proof of concept that AI [artificial intelligence] support could provide clinicians an early indication of the likelihood of success of treatment with the new generation of systemic anticancer therapies using conventional imaging techniques.”
This study was supported by Bristol-Myers Squibb, the National Institutes of Health, Fondation Philanthropia, and Fondation Nuovo-Soldati. The authors disclosed relationships, including employment, with Bristol-Myers Squibb. They also disclosed relationships with Roche, Novartis, Merck, and Boehringer Ingelheim.
SOURCE: Dercle L et al. Clin Cancer Res. 2020 Mar 20. doi: 10.1158/1078-0432.CCR-19-2942.
FROM CLINICAL CANCER RESEARCH