Walmart cuts profit forecasts for second quarter and full year


AI in medical imaging technology

Published: June 21, 2022, 11:15 a.m. Updated: July 7, 2022, 10:34 a.m.Dr. Christian Stoeckigt, Head of Scientific Affairs & Medical Education at Hologic, believes that there are still a number of challenges for AI in medical imaging to reach its full potential. In recent years, we have seen more and more breakthroughs in the application of artificial intelligence, AI, in medical imaging technology. This applies, for example, to AI-supported evaluation of digitized images during mammography and detection of tumor cells in prostate tissue, but also digital cytology during screening for cervical cancer. Microsoft has developed machine learning techniques that help clinicians plan radiotherapy 13 times faster1, while Google Health has made great strides with AI tools both to predict sight-threatening conditions and to improve lung cancer detection2 – examples of how AI can enable transformative diagnostics.1. Create acceptance among patientsIncreased knowledge about AI and its positive effects on care is crucial for patients to be able to accept AI as part of their diagnosis. Christian Stoeckigt believes that those who work in healthcare can play an important role by informing patients about, for example, how AI-supported diagnostics can contribute to faster and safer results.2. Build trust within the clinicCollaboration with radiologists, pathologists and cytodiagnostics will be essential. Clinicians play a central role by identifying unusual cases and exposing these to the algorithm so that it can continuously continue to be refined. In return, clinics will gradually gain more confidence in the results that AI provides them with. One of our customers, a laboratory in Germany, tested the AI-guided diagnostics with a microcarcinoma. In just a few minutes, the algorithm had identified a small number of abnormal cells undetected by conventional techniques – further boosting clinicians’ confidence in the system.3. Clear and unambiguous rulesMost experts in the field agree that we need greater clarity and consensus from governments worldwide to decide on a regulatory strategy for AI. One of the biggest breakthroughs in recent times was the US pharmaceutical agency FDA’s changed regulations and how this addresses AI, something that provides more guidance on how AI systems can be trained. This is a welcome change that many of us working in the AI ​​field would like to see in other regions.Read more about our systems 4. A protective frameworkIt’s a reality that humans make mistakes, but we also need to consider what happens when AI is involved in misdiagnosis and navigate issues of liability. We need a multidisciplinary working group of cytologists, radiologists, oncologists, clinicians and experts in ethics and IT who can develop protocols to protect the AI ​​systems.What happens next?Once these four areas are thoroughly addressed, we will see a wider use of AI-powered diagnostics. AI has the power to deliver more efficient triage of patients so they get the care they need faster, and more individualized treatment for better patient outcomes. Even more exciting is prognostics, where AI will be able to predict which people are more likely to develop certain cancers. It is innovations of this kind that stimulate our research – and which can save even more lives.REFERENCES 1 Oktay O, Schwaighofer A, Carter D, Bristow M, Alvarez-Valle J, Nori A, Microsoft Research blog [Internet]. Cambridge: 2020 Nov 30 [cited 2021 Jun 17]. Available from: en-us/research/ blog/project-inner- reye-evaluation- shows-how-ai-can -augment-and-accelerate-clinicianstability-to-perform-radio – therapy planning- 13-times-faster. Accessed 30 June 2021 2 Google Health. AI-enabled diagnostics previously thought impossible [Internet]. Mountain View: Google [cited 2021 Jun 17] Available from: ing-and-diagnostics/. Accessed 30 June 2021 MISC-07710-NO_SE_001_02 The article is produced by Brand Studio in collaboration with Hologic and not an article by Dagens industri

Click to rate this post!
[Total: 0 Average: 0]
Next Post

Michael Saylor: “I am a Bitcoin maximalist”

Seeming to be a final response to Charles Hoskinson’s statements, Michael Saylor affirmed this Sunday (24) that it is a “bitcoin maximalist”. But after all, what does that mean? Ironically, this term was popularized by Vitalik Buterincreator of Ethereum, after pointing out that investors were tired of witnessing the birth […]

Subscribe US Now