According to the World Health Organization (WHO), cancer accounts for approximately one in every six deaths worldwide, with a predicted 20 million new cancer diagnoses and more than 10 million new cancer deaths in 2020 alone (Expression of Interest: Agreement for Performance of Work (APW) to Support the Development of Metrics Framework for Global Cancer Initiatives, 2021, "Background" section; Huang et al., 2020, p. 61). Fortunately, thanks to advances in artificial intelligence, a field that combines computer science and large datasets to solve problems (Education, 2020), new research techniques can predict the behaviour of tumours through computer-aided detection systems (CADe), increasing the rate of early cancer diagnosis and decreasing the rate of cancer death.
Deng and Wang (2018) describe computer-aided detection (CADe) as the use of a computer-produced output to assist a clinician in making a diagnosis by highlighting specific parts of radiographs that appear abnormal, with the objective of lowering the chance of missing pathologies of interest. To be more specific, this AI-powered tool serves as a consultant in finding and classifying tumours or growths that clinicians may have overlooked, hence enhancing the rate of an accurate cancer diagnosis. The Medtronic endoscopy aid device GI Genius is one such device; it works by integrating a CADe system and an artificial intelligence-based (AI) algorithm known as a convolutional neural network (CNN) into an existing colonoscope so it can recognize common visual qualities, or physical characteristics, of different tumor growth anomalies.
In a 2020 study, Repic et al compared CADe colonoscopy with GI Genius to traditional colonoscopy performed by expert gastroenterologists, claiming that 25% of colorectal neoplasias, which are growths that can eventually become cancerous, are missed during the examination, increasing the risk of colon cancer. During the experiment, the CADe-aided colonoscopies had a much greater tumor detection rate of 54.8% than human-performed colonoscopies (40.4%). Among the 685 individuals, 33.7% had adenomas 5 mm or smaller, found by GI Genius, whereas only 26.5% had similar polyps diagnosed by specialists. Surprisingly, despite the higher detection rate, the time for testing was essentially consistent in both colonoscopies, with a difference of 18 seconds.
This implies that with AI aid in cancer detection, more accurate findings may be obtained while being time-efficient. This decreases diagnosis time and allows for quicker patient intervention.
Through continually increasing technology, the world of medicine has begun to slowly decrease the gap between survivors and the high death rate caused by cancer. With the use of deep learning in artificial intelligence programs and computer-aided detection (CADe), clinicians now have a tool to help detect precancerous polyps in their early stages of growth, particularly those that might have been missed due to a variety of factors such as polyp size, inexperience, or human error. Early intervention can be implemented and many lives can be saved with medical gadgets like GI Genius. The key to cancer diagnosis, like artificial intelligence, is not to reinvent, but rather to strengthen and adapt to meet the world's present demands.
By Shernorise Davidson
References
Catto, J. W., Abbod, M. F., Wild, P. J., Linkens, D. A., Pilarsky, C., Rehman, I., Rosario, D. J., Denzinger, S., Burger, M., Stoehr, R., Knuechel, R., Hartmann, A., & Hamdy, F. C. (2010). The Application of Artificial Intelligence to Microarray Data: Identification of a Novel Gene Signature to Identify Bladder Cancer Progression. European Urology, 57(3), 398–406.
Deng, F., & Wang, D. (2018). Computer aided diagnosis. Radiopaedia.Org. https://doi.org/10.53347/rid-61706
Education, I. C. (2020, June 3). What is Artificial Intelligence (AI)? | IBM. www.ibm.com. https://www.ibm.com/cloud/learn/what-is-artificial-intelligence
Expression of interest: Agreement for Performance of Work (APW) to support the development of metrics framework for global cancer initiatives. (2021, September 2). World Health Organization. https://www.who.int/news-room/articles-detail/expression-of-interest-agreement-for-performance-of-work-(apw)-to-support-the-development-of-metrics-framework-for-global-cancer-initiatives
Han, S. H., Kim, K. W., Kim, S., & Youn, Y. C. (2018). Artificial Neural Network: Understanding the Basic Concepts without Mathematics. Dementia and Neurocognitive Disorders, 17(3), 83. https://doi.org/10.12779/dnd.2018.17.3.83
Hann, A., Troya, J., & Fitting, D. (2021). Current status and limitations of artificial intelligence in colonoscopy. United European Gastroenterology Journal, 9(5), 527–533. https://doi.org/10.1002/ueg2.12108
Huang, S., Yang, J., Fong, S., & Zhao, Q. (2020). Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges. Cancer Letters, 471, 61–71. https://doi.org/10.1016/j.canlet.2019.12.007
Repici, A., Badalamenti, M., Maselli, R., Correale, L., Radaelli, F., Rondonotti, E., Ferrara, E., Spadaccini, M., Alkandari, A., Fugazza, A., Anderloni, A., Galtieri, P. A., Pellegatta, G., Carrara, S., di Leo, M., Craviotto, V., Lamonaca, L., Lorenzetti, R., Andrealli, A., . . . Hassan, C. (2020). Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology, 159(2), 512–520.e7. https://doi.org/10.1053/j.gastro.2020.04.062
Vulpoi, R. A., Luca, M., Ciobanu, A., Olteanu, A., Barboi, O. B., & Drug, V. L. (2022). Artificial Intelligence in Digestive Endoscopy—Where Are We and Where Are We Going? Diagnostics, 12(4), 927. https://doi.org/10.3390/diagnostics12040927
Kommentare