Researchers to link images, phenomes to classify prostate cancer cases
Texture analysis, machine learning to be applied to biomarkers in diagnostic images from Memorial Sloan Kettering.
An imaging company has signed a collaboration agreement with Memorial Sloan Kettering Cancer Center to use images from the provider to use them as a basis for a study to improve the diagnosis of prostate cancer.
Median Technologies will use its iBiopsy investigational imaging platform to retrospectively study the MRI images of 200 of the provider’s patients who were diagnosed with prostate cancer and underwent radical prostatectomy, and for whom histological slides and analyses are available.
The Median Technologies platform enables a combination between biomarkers in the images and phenomics, an area of biology concerned with the measurement of phenomes as they change in response to genetic mutation and environmental influences.
Also See: Artificial intelligence helps detect ovarian cancer early and accurately
The Memorial Sloan Kettering-Median study will look at the use of automated texture analysis and machine learning to classify lesions on MRI images to determine whether the lesions are aggressive forms of the disease.
Those conducting the study say the use of noninvasive imaging biomarkers derived from diagnostic MRI images could eventually aid clinical decisions, the selection of treatment options and enable clinicians to better predict patient outcomes.
The collaboration could be useful “in exploring potential applications of machine learning for the detection and classification of disease, with a particular focus on prostate cancer,” said Hedvig Hricak, MD, chair of the Department of Radiology at Memorial Sloan Kettering. “Machine learning and artificial intelligence could ultimately provide precise tools that will augment our ability not only to diagnose prostate cancer but to potentially characterize it biologically and predict its behavior.”
The ability to associate biomarkers in images and phenomics could eventually enable oncologists “to identify associations that may help to predict a patient’s response to treatment, thereby enhancing personalized medicine,” says Fredrik Brag, Median’s CEO.
Prostate cancer is difficult to detect in early stages of the disease; once symptoms become obvious, it typically means that the disease has spread to other parts of the patient’s body.
A worldwide study by the International Agency for Research on Cancer found that prostate cancer is the second most common cause of cancer of men worldwide. In 2012, the IARC study estimated that 1.1 million people were affected by prostate cancer, accounting for 15 percent of all new cancer cases worldwide and an estimated 307,000 deaths, making it the fifth leading cause of death from cancer in men.
Median Technologies will use its iBiopsy investigational imaging platform to retrospectively study the MRI images of 200 of the provider’s patients who were diagnosed with prostate cancer and underwent radical prostatectomy, and for whom histological slides and analyses are available.
The Median Technologies platform enables a combination between biomarkers in the images and phenomics, an area of biology concerned with the measurement of phenomes as they change in response to genetic mutation and environmental influences.Also See: Artificial intelligence helps detect ovarian cancer early and accurately
The Memorial Sloan Kettering-Median study will look at the use of automated texture analysis and machine learning to classify lesions on MRI images to determine whether the lesions are aggressive forms of the disease.
Those conducting the study say the use of noninvasive imaging biomarkers derived from diagnostic MRI images could eventually aid clinical decisions, the selection of treatment options and enable clinicians to better predict patient outcomes.
The collaboration could be useful “in exploring potential applications of machine learning for the detection and classification of disease, with a particular focus on prostate cancer,” said Hedvig Hricak, MD, chair of the Department of Radiology at Memorial Sloan Kettering. “Machine learning and artificial intelligence could ultimately provide precise tools that will augment our ability not only to diagnose prostate cancer but to potentially characterize it biologically and predict its behavior.”
The ability to associate biomarkers in images and phenomics could eventually enable oncologists “to identify associations that may help to predict a patient’s response to treatment, thereby enhancing personalized medicine,” says Fredrik Brag, Median’s CEO.
Prostate cancer is difficult to detect in early stages of the disease; once symptoms become obvious, it typically means that the disease has spread to other parts of the patient’s body.
A worldwide study by the International Agency for Research on Cancer found that prostate cancer is the second most common cause of cancer of men worldwide. In 2012, the IARC study estimated that 1.1 million people were affected by prostate cancer, accounting for 15 percent of all new cancer cases worldwide and an estimated 307,000 deaths, making it the fifth leading cause of death from cancer in men.
More for you
Loading data for hdm_tax_topic #better-outcomes...