Blogs
Welcome to our blog section on Artificial Intelligence (AI)! Here, we will explore in-depth one of the fastest and most exciting technological fields of the modern era.
Blogs
01/11/2023
Artificial Intelligence (AI) continues to broaden its influence our lives, notably in the vital domain of cancer detection. Researchers are utilizing machine learning to develop AI tools specifically designed for cancer detection, diagnosis, and even patient treatment.
This technology harnesses machine-learning algorithms to build tools capable of identifying tumors or lesions that might be missed by healthcare professionals. Moreover, AI is being leveraged to communicate and assist patients in understanding the complexities surrounding their cancer treatments. However, AI could cause certain drawbacks, including potential overdiagnosis of cancers and biases in detecting cancers, particularly in individuals of different ethnicities.
Dr. Brittany Fasy, an associate professor of computational topology at Montana State University, highlights the need for critical discussions among clinicians, researchers, and patients to determine when and how to utilize computer-assisted diagnosis effectively. "If you're on the lookout for something, then, if you look in enough places, you'll start to see it," she told the ABC News. "So, I think how and when to use computer-assisted diagnosis is an important conversation that needs to happen between clinicians doing the diagnosis, the researchers developing the methods to assist them, and the patients who it affects the most."
One of the breakthroughs in AI-driven cancer detection emerged from MIT and Mass General Cancer Center, where researchers developed and tested an AI tool called Sybil. Trained on low-dose chest computed tomography scans, Sybil accurately predicts the risk of a patient developing lung cancer within six years. Lung cancer, a leading cause of cancer-related deaths globally, often lacks discussions due to social stigmas. Dr. Lecia Sequist, a program director at the Mass General Cancer Center, says: "The incidence of lung cancer and people who have never smoked is rising and so lung cancer is really a disease that could affect anyone, anyone with lungs, which essentially means anyone is at risk for getting lung cancer."
She also emphasizes the goal of early detection using AI tools like Sybil, aiming to make screenings more accessible for a wider population. "We're not doing a good job of screening for lung cancer and like with other screening tests, the reason it's important to do screening is to find cancers when they're early stage and still curable." "If you find a lung cancer, when it's stage I or II, the patient can have surgery, and then has a high chance of being cancer-free up to that point."
Similarly, researchers at Harvard Medical School, the University of Copenhagen, and the Dana-Farber Cancer Institute developed a tool solely using patients' medical records, predicting high-risk individuals for pancreatic cancer up to three years before an actual diagnosis. Dr. Chris Sander, study co-senior investigator, making a statement: "Most pancreatic cancers just present much too late and therefore, patients have a very, very bad survival, which is why we're working on this." "Less than 20% survival, but if you see it, then the five-year survival goes up to 50%. If you see it, you can cut it out."
Despite its promising potential, AI in cancer detection faces significant challenges. One prominent concern revolves around AI's biases, particularly in diagnosing skin cancers, showing inaccuracy for individuals with darker skin tones. Dr. Adewole Adamson, an assistant professor at the University of Texas, stresses the importance of diversified data sets to improve AI tools' accuracy across all patients.
Additionally, there are concerns about overdiagnosing cancer, a point reinforced by previous research indicating that not every detected tumor leads to fatality. Adamson emphasizes the importance of distinguishing between aggressive and non-aggressive cancers to ensure appropriate and timely intervention.
While AI presents promising advancements in cancer detection, researchers and healthcare professionals underscore the necessity for responsible development and deployment. Adamson urges researchers to prioritize equity in AI algorithms, considering various populations to mitigate biases and ensure accurate diagnosis and treatment.
Adamson's critiques do not diminish the potential of AI as a valuable tool in cancer detection but stress the need for responsible development and ethical deployment in healthcare. The overarching goal is to prevent cancer-related fatalities by distinguishing between aggressive and non-aggressive cancers.
Overall, while AI in cancer detection holds immense promise, addressing biases, minimizing overdiagnosis, and ensuring ethical deployment remain pivotal considerations in its development and widespread use in healthcare.
DrAid™ CT Liver Cancer D&T, an AI-based platform for liver cancer detection purpose, designed to assist radiologists in automatically detecting abnormal lesions in the liver through CT imaging, provide clinical solutions to aid in the early identification of liver cancer, as well as assist oncologists in developing treatment plans. With DrAid™ Liver Cancer CT, doctors can feel confident that they have the most advanced technology at their fingertips, enabling them to provide their patients with the highest quality of care.
---------------------------------
Waste time no more and learn about DrAid™ CT Liver Cancer D&T now to identify how the innovative AI platform helps the diagnosis task!