# AI diagnosis from medical images

Neural networks trained on scans flag disease in images such as retinas and mammograms.

Source page: https://www.materialinsights.org/technologies/ai_medical_imaging/

Health and medicine · Diagnosis · No. 198

- Networked and AI age
- Readiness 8 of 9
- System
 Health and medicine · Technology

Since 2018 a computer has been allowed to screen eyes for diabetic damage with no doctor looking at the picture.

Chart: Illustration: AI diagnosis from medical images

##### Where it comes from

Chart: Map of where it comes from

Computer aids for reading scans existed from the 1990s. Deep learning changed them: in 2012 a deep network won a contest on breast cancer tissue images, and in 2016 one graded retinal photographs.

##### Three things to know

1. A 2016 network for diabetic eye disease learned from 128,000 retinal images graded by ophthalmologists.
2. In an early analysis of a Swedish trial of 80,033 women, AI-supported screening found 6.1 cancers per 1,000 women against 5.1 with two human readers.
3. Most AI devices authorised in the United States read radiology images.

##### The journey

1. 1 **Images**Hospitals collect scans, photographs and slides
2. 2 **Labels**Specialists grade each image, often several per image
3. 3 **Training**A neural network learns the patterns that match each grade
4. 4 **Testing**The software is checked on new images and in trials
5. 5 **Approval**Regulators authorise it as a medical device
6. 6 **Clinic**It flags, ranks or reads images alongside or instead of a doctor

##### Go deeper pick a tab to open it in full

## Other sections

- [Overview](https://www.materialinsights.org/technologies/ai_medical_imaging/tech-overview/index.md)
- [Science](https://www.materialinsights.org/technologies/ai_medical_imaging/tech-science/index.md)
- [Evolution](https://www.materialinsights.org/technologies/ai_medical_imaging/tech-evolution/index.md)
- [Materials](https://www.materialinsights.org/technologies/ai_medical_imaging/tech-materials/index.md)
- [Energy footprint](https://www.materialinsights.org/technologies/ai_medical_imaging/tech-energy-footprint/index.md)
- [Industries](https://www.materialinsights.org/technologies/ai_medical_imaging/tech-industries/index.md)
