This series shows the four different stages of the same eye scan described in this article. From left to right: the original image; with highlights of anomalies by human experts; with highlights of anomalies by one scan by an AI system; with highlights of anomalies made by an iterative series of scans by an AI system. Note that the iterative process yields a more complete overview of the anomalies present than the single assessment.
How can we make ‘lazy’ artificial intelligence more transparent and relevant to the clinic?
Artificial intelligence (AI) is an important innovation in diagnostics, because it can quickly learn to recognize abnormalities that a doctor would also label as a disease. But the way that these systems work is often opaque, and doctors do have a better “overall picture” when they make the diagnosis. In a new publication, researchers from Radboudumc show how they can make the AI show how it’s working, as well as let it diagnose more like a doctor, thus making AI-systems more relevant to clinical practice.
Doctor vs AI
In recent years, artificial intelligence has been on the rise in the diagnosis of medical imaging. A doctor can look at an X-ray or biopsy to identify abnormalities, but this can increasingly also be done by an AI system by means of “deep learning” (see ’Background: what is deep learning’ below). Such a system learns to arrive at a diagnosis on its own, and in some cases it does this just as well or better than experienced doctors.
The two major differences compared to a human doctor are, first, that AI is often not transparent in how it’s analyzing the images, and, second, that these systems are quite “lazy”. AI looks at what is needed for a particular diagnosis, and then stops. This means that a scan does not always identify all abnormalities, even if the diagnosis is correct. A doctor, especially when considering the treatment plan, looks at the big picture: what do I see? Which anomalies should be removed or treated during surgery?
AI more like the doctor
To make AI systems more attractive for the clinical practice, Cristina González Gonzalo, PhD candidate at the A-eye Research and Diagnostic Image Analysis Group of Radboudumc, developed a two-sided innovation for diagnostic AI. She did this based on eye scans, in which abnormalities of the retina occurred – specifically diabetic retinopathy and age-related macular degeneration. These abnormalities can be easily recognized by both a doctor and AI. But they are also abnormalities that often occur in groups. A classic AI would diagnose one or a few spots and stop the analysis. In the process developed by González Gonzalo however, the AI ??goes through the picture over and over again, learning to ignore the places it has already passed, thus discovering new ones. Moreover, the AI also shows which areas of the eye scan it deemed suspicious, therefore making the diagnostic process transparent.
An iterative process
A basic AI could come up with a diagnosis based on one assessment of the eye scan, and thanks to the first contribution by González Gonzalo, it can show how it arrived at that diagnosis. This visual explanation shows that the system is indeed lazy – stopping the analysis after it as obtained just enough information to make a diagnosis. That’s why she also made the process iterative in an innovative way, forcing the AI to look harder and create more of a ‘complete picture’ that radiologists would have.
How did the system learn to look at the same eye scan with ‘fresh eyes’? The system ignored the familiar parts by digitally filling in the abnormalities already found using healthy tissue from around the abnormality.
The results of all the assessment rounds are then added together and that produces the final diagnosis. In the study, this approach improved the sensitivity of the detection of diabetic retinopathy and age-related macular degeneration by 11.2+/-2.0% per image. What this project proves is that it’s possible to have an AI system assess images more like a doctor, as well as make transparent how it’s doing it. This might help these systems become easier to trust and thus to be adopted by radiologists.
Background: what is ‘deep learning’?
Deep learning is a term used for systems that learn in a way that is similar to how our brain works. It consists of networks of electronic ‘neurons’, each of which learns to recognize one aspect of the desired image. It then follows the principles of ‘learning by doing’, and ‘practice makes perfect’. The system is fed more and more images that include relevant information saying – in this case – whether there is an anomaly in the retina, and if so, which disease it is. The system then learns to recognize which characteristics belong to those diseases, and the more pictures it sees, the better it can recognize those characteristics in undiagnosed images. We do something similar with small children: we repeatedly hold up an object, say an apple, in front of them and say that it is an apple. After some time, you don’t have to say it anymore – even though each apple is slightly different. Another major advantage of these systems is that they complete their training much faster than humans and can work 24 hours a day.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- A breakthrough in AI applications requires well-functioning regulationon June 29, 2020 at 10:20 pm
Is there a need for new regulatory mechanisms to cover damage caused by artificial intelligence, or do the existing liability rules suffice?
- AI’s Big Moment: A Full Battalion in the COVID Infantryon June 29, 2020 at 6:47 pm
In her column on Artificial Intelligence, Katherine Forrest discusses the rise of artificial intelligence's role in the fight against the COVID-19 pandemic and how AI is here to stay even after this ...
- Collaboration Between Clinicians and AI Improves Accuracy of Skin Cancer Diagnosis: Studyon June 29, 2020 at 8:53 am
Artificial intelligence (AI) can improve the diagnostic accuracy of skin cancer when combined with human clinical checks says a new study published in the journal Nature Medicine. The researchers ...
- AI assists in lung cancer diagnosison June 29, 2020 at 8:15 am
AI helps to improve the early diagnosis accuracy rate of lung cancer.Lung cancer is the most common malignant tumor in the world, with morbidity and mortality ranking first in malignant tumors, and ...
- Human-AI collaborations best for skin cancer diagnosis: Studyon June 29, 2020 at 8:12 am
Researchers have found that artificial intelligence (AI) improves skin cancer diagnostic accuracy when used in collaboration with human clinical checks.
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Artificial intelligence diagnostics
- Renalytix AI Looks For U.S. Public Capital In IPO Filingon June 29, 2020 at 2:01 pm
Renalytix AI has filed to raise $86 million in a U.S. IPO. The firm is developing a chronic kidney disease diagnostic system. RNLX is still in development stage ...
- IPO Preview: Renalytix AI Seeks U.S. IPO Investmenton June 29, 2020 at 9:31 am
I’ll provide a final opinion when we learn more IPO details. Cardiff, UK-based Renalytix was founded to create an artificial intelligence-based diagnostics system for kidney and potentially other ...
- Human-Artificial intelligence collaborations best for skin cancer diagnosison June 29, 2020 at 7:12 am
Artificial intelligence (AI) improved skin cancer diagnostic accuracy when used in collaboration with human clinical checks, an international study including University of Queensland researchers has ...
- Artificial Intelligence in Healthcare Market 2020 Global Industry Analysis By Size, Growth Rate and Trends With Forecast To 2026on June 29, 2020 at 6:59 am
Artificial Intelligence in Healthcare Market2020 Global Industry Trends, Size, Share Analysis Report. According to ...
- Global Silicon Photonics Market (2020 to 2026) - Growing Potential of AI-Based Tools for Elderly Care Presents Opportunitieson June 29, 2020 at 6:57 am
Impact Analysis by Offering (Hardware, Software, Services), Technology (Machine Learning, NLP, Context-Aware Computing, Computer Vision), End-Use Application, End User and Region - Global Forecast to ...