AI predicts response of lung cancer patients to immunotherapy
Using routine computed tomography scans, researchers are able to determine which lung cancer patients will positively respond to immunotherapy treatment.
Using routine computed tomography scans, researchers are able to determine which lung cancer patients will positively respond to immunotherapy treatment.
Results of a study, published in the journal Cancer Immunology Research, show that the patterns on the CT scans that were most associated with a positive response to treatment—and with overall patient survival—were closely associated with the arrangement of immune cells on the original diagnostic biopsies of those patients.
“In a machine learning setting, we compared changes in the radiomic texture (DelRADx) of computed tomography patterns both within and outside tumor nodules before and after 2-3 cycles of immune checkpoint inhibitor therapy,” state the study’s authors. “We found that DelRADx patterns could predict response to ICI therapy and overall survival for patients.”
While immunotherapy is a rapidly growing and promising field in cancer research, only about 20 percent of all cancer patients benefit from the treatment, which is also very expensive. However, by combining AI and medical imaging, researchers hope to help oncologists identify which patients will actually benefit from the therapy.
“This is important because when a doctor decides based on CT images alone whether a patient has responded to therapy, it is often based on the size of the lesion,” says study co-author Mohammadhadi Khorrami, research assistant at Case Western Reserve University. “We have found that textural change is a better predictor of whether the therapy is working.”
CT scans from 50 patients were used to train the computer and create an algorithm to identify the changes in the lesion. According to Khorrami, one of the more significant advances in the research was the ability of the computer to note the changes in texture, volume and shape of a given lesion— not just its size.
“This is no flash in the pan--this research really seems to be reflecting something about the very biology of the disease, about which is the more aggressive phenotype, and that’s information oncologists do not currently have,” says co-author Anant Madabhushi, director of Case Western Reserve University’s Center for Computational Imaging and Personalized Diagnostics.
Results of a study, published in the journal Cancer Immunology Research, show that the patterns on the CT scans that were most associated with a positive response to treatment—and with overall patient survival—were closely associated with the arrangement of immune cells on the original diagnostic biopsies of those patients.
“In a machine learning setting, we compared changes in the radiomic texture (DelRADx) of computed tomography patterns both within and outside tumor nodules before and after 2-3 cycles of immune checkpoint inhibitor therapy,” state the study’s authors. “We found that DelRADx patterns could predict response to ICI therapy and overall survival for patients.”
While immunotherapy is a rapidly growing and promising field in cancer research, only about 20 percent of all cancer patients benefit from the treatment, which is also very expensive. However, by combining AI and medical imaging, researchers hope to help oncologists identify which patients will actually benefit from the therapy.
“This is important because when a doctor decides based on CT images alone whether a patient has responded to therapy, it is often based on the size of the lesion,” says study co-author Mohammadhadi Khorrami, research assistant at Case Western Reserve University. “We have found that textural change is a better predictor of whether the therapy is working.”
CT scans from 50 patients were used to train the computer and create an algorithm to identify the changes in the lesion. According to Khorrami, one of the more significant advances in the research was the ability of the computer to note the changes in texture, volume and shape of a given lesion— not just its size.
“This is no flash in the pan--this research really seems to be reflecting something about the very biology of the disease, about which is the more aggressive phenotype, and that’s information oncologists do not currently have,” says co-author Anant Madabhushi, director of Case Western Reserve University’s Center for Computational Imaging and Personalized Diagnostics.
More for you
Loading data for hdm_tax_topic #better-outcomes...