Cancer is the second leading cause of death in the United States. While researchers have made great strides leading to declining mortality rates for most cancers, certain types (pancreatic, thyroid) rates continue to stay the same or even increase. Although rates of smoking, a major cause of cancer, have declined, the rates of other risk factors, such as obesity, have increased in the United States. Also, the US population is aging, and cancer rates increase with age. A growing area of attention is also disparities in cancer outcomes. Minority groups and people with low income, education, and access to cancer screening facilities bear a disproportionate burden of the disease and its associated complications. For example, Black/African-American men and Black/African-American women have significantly higher mortality rates from prostate and cervical cancer than non-Hispanic White individuals.
It is well established in the literature that early detection of cancer can lead to significantly improved outcomes. While some cancer types have well-known screening tests, many others do not. The rapid growth of imaging data and the rise of computational tools based on artificial intelligence, machine learning, and data science have opened a new avenue for the early detection of cancers. For example, a recent study showed that AI could help detect lung cancer potentially two years in advance using standard CT scans. Another potential data stream for cancer detection is physiological data from wearable sensors and remote health monitoring devices. These devices have already shown value in managing diabetes and cardiovascular disease by providing timely feedback to individuals with or at risk of these conditions. An additional benefit of remote cancer detection would be reducing disparities for populations whose access to a screening clinic is burdensome.
This Research Topic welcomes scholarly work in the following areas:
1. Use of computational techniques for early cancer detection; while the focus is on artificial intelligence and machine learning, we welcome computing paradigms from data science, signal processing, computer vision, and statistical analysis.
2. Novel computational imaging and sensing paradigms that can enable early detection of cancer.
3. Frameworks based on data from wearable and remote monitoring devices to detect cancers from physiological signals, images, etc.
4. The feasibility of digital health tools and AI to track patients post-treatment: monitor the recovery of patients, predict long-term effects of treatments, predict the likelihood of remission, etc.
Cancer is the second leading cause of death in the United States. While researchers have made great strides leading to declining mortality rates for most cancers, certain types (pancreatic, thyroid) rates continue to stay the same or even increase. Although rates of smoking, a major cause of cancer, have declined, the rates of other risk factors, such as obesity, have increased in the United States. Also, the US population is aging, and cancer rates increase with age. A growing area of attention is also disparities in cancer outcomes. Minority groups and people with low income, education, and access to cancer screening facilities bear a disproportionate burden of the disease and its associated complications. For example, Black/African-American men and Black/African-American women have significantly higher mortality rates from prostate and cervical cancer than non-Hispanic White individuals.
It is well established in the literature that early detection of cancer can lead to significantly improved outcomes. While some cancer types have well-known screening tests, many others do not. The rapid growth of imaging data and the rise of computational tools based on artificial intelligence, machine learning, and data science have opened a new avenue for the early detection of cancers. For example, a recent study showed that AI could help detect lung cancer potentially two years in advance using standard CT scans. Another potential data stream for cancer detection is physiological data from wearable sensors and remote health monitoring devices. These devices have already shown value in managing diabetes and cardiovascular disease by providing timely feedback to individuals with or at risk of these conditions. An additional benefit of remote cancer detection would be reducing disparities for populations whose access to a screening clinic is burdensome.
This Research Topic welcomes scholarly work in the following areas:
1. Use of computational techniques for early cancer detection; while the focus is on artificial intelligence and machine learning, we welcome computing paradigms from data science, signal processing, computer vision, and statistical analysis.
2. Novel computational imaging and sensing paradigms that can enable early detection of cancer.
3. Frameworks based on data from wearable and remote monitoring devices to detect cancers from physiological signals, images, etc.
4. The feasibility of digital health tools and AI to track patients post-treatment: monitor the recovery of patients, predict long-term effects of treatments, predict the likelihood of remission, etc.