The following is a fascinating and progressive article. It shows the importance of AI, image processing and deep learning. It is clear large quanties of imagery data are needed to advance it.
The longer we stall on fetal cardiac view retention, the more limiting our prospects will be for advancements in this field. Published FASP guidance from 9 years ago is surely obsolete now. We've summarised key observations from this article below.
"There are ways that AI is already making cardiac imaging easier, faster, and more accurate. Some of these examples already validated are automated measurement features, including left ventricular EF, chamber dimensions, wall thickness, Doppler measurements, and so on".
"Automated measurement packages and image optimization can save sonographers time."
"Products have been developed to help guide a novice sonographer toward a technically correct image. These tools could be especially beneficial when a user is a nonexpert. This software uses an algorithm to guide the user to capture a diagnostic image using real-time positional directions. Deep learning software guides the user by recognizing incorrect or off-axis views and providing guidance on how to move the probe in order to obtain diagnostic images. Once the images are deemed diagnostic by the software, they are acquired automatically"
"AI could be extremely advantageous for the benefit of patients, sonographers, and cardiologists."
"Deep learning is a subset of machine learning that is used in circumstances in which a very large amount of data must be processed."
"For echocardiography, such a data set would include studies from both sexes along with a range of body mass index, ages, and image quality. This is imperative for the machine to learn patterns on the basis of the images alone."
Full article;
AI is here already in the UK...
"The NHS AI Lab is supporting the training and testing of AI technologies to ensure that we are making the most of AI's potential in medical imaging".
"However, there are concerns about the effectiveness and reliability of some of these tools. To develop algorithms successfully, you need large volumes of good quality data. Part of this data needs to be kept for training the algorithm and another part needs to be kept separately for testing its performance. This can help innovators to understand the performance of their AI tool"
AI powered handheld ultrasound devices have now been rolled out for trials in Africa with limited functionality.
"the WHO recently released guidance on AI in healthcare, warning that the tech can be prone to biases if trained on overly narrow datasets"
"Only last week, for example, an independent review commissioned by the UK government said immediate action was needed to tackle the impact of ethnic and other biases in the use of medical devices – especially imaging devices"
We just can't see a logical explanation for the current FASP guidance suggesting there's no requirement to save cardiac views.
London Hospitals use this already;
https://guysandstthomasspecialistcare.co.uk/news/healthcare-innovations-fetal-cardiology/