A survey on active learning and human-in-the-loop deep learning for medical image analysis

Budd, Samuel; Robinson, Emma C.; Kainz, Bernhard

doi:10.1016/j.media.2021.102062

Cited by 396 publications

(176 citation statements)

References 63 publications

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…Transfer learning is one of the techniques we used to build high accuracy models without having to train the model on a very large ultrasound vessel dataset. As the ultrasound database was collected, we iteratively applied an active learning framework [ 34 , 37 ] to reduce annotation time and cost. This process started by automatically annotating a set of porcine images using the YOLO network trained on a small number of clinician-labeled images.…”

Section: Methodsmentioning

confidence: 99%

AI-Enabled, Ultrasound-Guided Handheld Robotic Device for Femoral Vascular Access

et al. 2021

View full text Add to dashboard Cite

Hemorrhage is a leading cause of trauma death, particularly in prehospital environments when evacuation is delayed. Obtaining central vascular access to a deep artery or vein is important for administration of emergency drugs and analgesics, and rapid replacement of blood volume, as well as invasive sensing and emerging life-saving interventions. However, central access is normally performed by highly experienced critical care physicians in a hospital setting. We developed a handheld AI-enabled interventional device, AI-GUIDE (Artificial Intelligence Guided Ultrasound Interventional Device), capable of directing users with no ultrasound or interventional expertise to catheterize a deep blood vessel, with an initial focus on the femoral vein. AI-GUIDE integrates with widely available commercial portable ultrasound systems and guides a user in ultrasound probe localization, venous puncture-point localization, and needle insertion. The system performs vascular puncture robotically and incorporates a preloaded guidewire to facilitate the Seldinger technique of catheter insertion. Results from tissue-mimicking phantom and porcine studies under normotensive and hypotensive conditions provide evidence of the technique’s robustness, with key performance metrics in a live porcine model including: a mean time to acquire femoral vein insertion point of 53 ± 36 s (5 users with varying experience, in 20 trials), a total time to insert catheter of 80 ± 30 s (1 user, in 6 trials), and a mean number of 1.1 (normotensive, 39 trials) and 1.3 (hypotensive, 55 trials) needle insertion attempts (1 user). These performance metrics in a porcine model are consistent with those for experienced medical providers performing central vascular access on humans in a hospital.

show abstract

Section: Methodsmentioning

confidence: 99%

AI-Enabled, Ultrasound-Guided Handheld Robotic Device for Femoral Vascular Access

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Others have pointed to specific threats in interactive ML related to the information a human provides, including that a user's input reinforces noise in the training data or statistics they see [52]. Recent works have also surveyed research in human-in-the-loop machine learning [53,54]. Some of the papers covered in our survey propose human-in-the-loop systems.…”

Section: Knowledge Elicitation For Expert Decision Makingmentioning

confidence: 99%

A Survey of Domain Knowledge Elicitation in Applied Machine Learning

Kerrigan

Hullman

Bertini

2021

MTI

View full text Add to dashboard Cite

Eliciting knowledge from domain experts can play an important role throughout the machine learning process, from correctly specifying the task to evaluating model results. However, knowledge elicitation is also fraught with challenges. In this work, we consider why and how machine learning researchers elicit knowledge from experts in the model development process. We develop a taxonomy to characterize elicitation approaches according to the elicitation goal, elicitation target, elicitation process, and use of elicited knowledge. We analyze the elicitation trends observed in 28 papers with this taxonomy and identify opportunities for adding rigor to these elicitation approaches. We suggest future directions for research in elicitation for machine learning by highlighting avenues for further exploration and drawing on what we can learn from elicitation research in other fields.

show abstract

“…At present, no application of AL in the digestive system has been found, which may be due to the high inherent coupling between AL selection strategies and the model being trained. These results in later data sets that may not be conducive to model training [ 106 ].…”

Section: Major Techniques and Issuesmentioning

confidence: 99%

A systematic review on application of deep learning in digestive system image processing

2021

View full text Add to dashboard Cite

A survey on active learning and human-in-the-loop deep learning for medical image analysis

Cited by 396 publications

References 63 publications

AI-Enabled, Ultrasound-Guided Handheld Robotic Device for Femoral Vascular Access

AI-Enabled, Ultrasound-Guided Handheld Robotic Device for Femoral Vascular Access

A Survey of Domain Knowledge Elicitation in Applied Machine Learning

A systematic review on application of deep learning in digestive system image processing

Contact Info

Product

Resources

About