AI medical software: how will the FDA deal with it?
AI medical software: how will the FDA deal with it?

Last week, the FDA announced that they will be investigating a new review framework for artificial intelligence (AI) based medical devices.1 Over the past few years, the FDA actually cleared many AI medical software programs. So what is the difference between these types of AI algorithms and the ones the FDA refers to in their press release of April 2nd? Why can the latter not be handled by current review frameworks?

Artificial intelligence ≠ deep learning ≠ continuous learning

It is commonly thought that software is not really AI-based if it does not use deep learning techniques. Additionally, deep learning is often characterized as ever changing, constantly learning…


How to build a radiology AI algorithm: collecting the right data
How to build a radiology AI algorithm: collecting the right data

As a radiologist, you might come across tasks that you would not mind handing over to artificial intelligence (AI), either because they are of a repetitive nature, prone to false positives/negatives, or because they take up a lot of your valuable time. While there are many companies developing AI-based algorithms for radiology, these vendors do not provide solutions for every existing use case. So what if you come up with your own idea for a killer radiology AI app that is not available and no one is developing it? In that case, you might decide to initiate the development of…


Understanding the role of AI bias in healthcare
Understanding the role of AI bias in healthcare

It is important to understand the role of AI bias in healthcare. As artificial intelligence (AI) applications gain traction in medicine, healthcare leaders have expressed concerns over the unintended effects of AI on social bias and inequity. Artificial intelligence (AI) software can help analyze large amounts of data to improve decision making. More and more, we come to rely on these algorithms for different kinds of purposes. It is, therefore, essential that their results are reliable. Unfortunately, this is not always the case. There are many examples of erroneous results of AI algorithms which are, more often than we would…


How does deep learning in radiology work?
How does deep learning in radiology work?

Deep dive into how deep learning in radiology works

Lately many exciting results with deep learning in radiology have been reported. This is not that much of a surprise, as deep learning is eminently suited for medical image analysis. Deep learning algorithms have been shown to be capable of analyzing many different medical images with high accuracy. Examples are chest X-rays, mammograms, and cardiac MRIs,1–3 but there are many more examples out there.

All these results are very promising, but what is actually inside the black box of deep learning? How do you build a deep neural network?

Deep neural network: the structure

To gain a better understanding of how to build a deep…


8 practical tips to get radiology AI into clinical practice
8 practical tips to get radiology AI into clinical practice

Open a medical journal, a news website, or a radiology blog, and surely artificial intelligence (AI) will be mentioned. AI is making waves in medical imaging. This can be exciting, as AI offers many opportunities to improve the radiology workflow; however, it also poses a challenge. How do you start working with AI in clinical practice without having to deal with a tiring amount of implementation hassle?

Below are our top 8 learnings to help with a smooth implementation of AI solutions at your department.

Tip 1: Include non-imaging clinicians in the radiology AI implementation process


Regulatory approval of medical devices for COVID-19
Regulatory approval of medical devices for COVID-19

For newly developed medical devices to be able to make a difference in the current COVID-19 pandemic, development and regulatory approval needs to be fast. However, regulatory processes are generally not known for their speediness. Developing an efficient and safe product can take years, followed by a regulatory approval process which generally requires up to months, or even years if clinical trials are required. Luckily, the FDA and similar regulatory bodies provide alternative routes-to-market for crisis situations. How do these regulatory pathways work? For which medical devices are they relevant? …


The healthcare system is evolving and personalized healthcare is becoming increasingly important. From this perspective, each patient is unique. Therefore, it is of utmost importance to take into account as much information as possible, including that obtained from the medical images (such as tumor volumes calculated based on MRI images). However, many radiologists are already strained as it is, and adding more details to the radiology report not only takes time, but may also generate extra questions from referring clinicians. During a workday that is already overcrowded, this would lead to a significant increase in workload. …


A 101 guide to the FDA regulatory process for AI radiology software
A 101 guide to the FDA regulatory process for AI radiology software

During 2019, many AI healthcare companies announced FDA clearance for their medical device — this often considers AI radiology software. What does it actually mean when a company claims their artificial intelligence software is approved by the FDA? Why is this important? How does the FDA regulatory pathway for artificial intelligence radiology software currently work? And where do CADe and CADx versus AI fit in this story?

Why is it important that AI radiology software receives a nod by the FDA?

Well, for a start, if you want to use the software in clinical context, it is mandatory. However, as is often the case with rules, they exist for a reason. An FDA stamp…


Deep learning for radiology volume measurements: an introduction to medical image segmentation
Deep learning for radiology volume measurements: an introduction to medical image segmentation

Organ volumes, tumor dimensions, size of lymph nodes — these are some examples of measures that provide valuable information for radiologists to use in diagnostic processes. For example, brain volumetry on MR images to track atrophy development in dementia cases, MRI-based prostate volume measurements to determine PSA density in prostate cancer diagnostics, or tumor volume evaluation in just about any organ that can be imaged. However, obtaining volumes in a precise way is not a quick and easy task if done manually. Structures need to be delineated image by image, slice by slice, making volume measurements a tedious and time-consuming…


How to help radiology AI cope with different scanners and settings?
How to help radiology AI cope with different scanners and settings?

Segmentation of MRI and CT images into the available tissues and structures plays a crucial role in quantification, both in medical research and clinical practice. This segmentation can be done manually, which is very time intensive and subject to intra- and inter-observer variability. Radiology software in the form of segmentation algorithms can be of great help, speeding up the process and creating objective, repeatable measurements.

In prostate cancer, for example, medical image segmentation and quantification of tissue volume is of great importance for both diagnosis and therapy. Here, an accurate segmentation of prostate tissue is required for taking biopsies and…

Quantib

Quantitative Imaging Biomarkers - QuantibBrain (FDA/CE) - innovative SME - image analysis services - machine learning - neuro (dementia, stroke) - onco - cardio

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store