Artificial Swarm Intelligence employed to Amplify Diagnostic Accuracy in Radiology

  title={Artificial Swarm Intelligence employed to Amplify Diagnostic Accuracy in Radiology},
  author={Louis B. Rosenberg and Matthew P. Lungren and Safwan S. Halabi and Gregg Willcox and David Baltaxe and Mimi Lyons},
  journal={2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)},
Swarm Intelligence (SI) is a biological phenomenon in which groups of organisms amplify their combined brainpower by forming real-time systems. It has been studied for decades in fish schools, bird flocks, and bee swarms. Recent advances in networking and AI technologies have enabled distributed human groups to form closed-loop systems modeled after natural swarms. The process is referred to as Artificial Swarm Intelligence (ASI) and has been shown to significantly amplify group performance… 

Figures from this paper

Human–machine partnership with artificial intelligence for chest radiograph diagnosis

The superior diagnostic accuracy of the combined HITL AI solution compared to radiologists and AI alone has broad implications for the surging clinical AI deployment and implementation strategies in future practice.

Artificial Swarm Intelligence

This paper presents the basic concepts of ASI and reviews recently published research that shows its effectiveness in amplifying the collective intelligence of human groups, increasing accuracy when groups make forecasts, generate assessments, reach decisions, and form predictions.

Dense Neural Network used to Amplify the Forecasting Accuracy of real-time Human Swarms

This study explores whether the rich behavioral data collected during "swarming" can be used to further increase the accuracy of swarm-based forecasts and develops a dense neural network to process the data collected and generate a Conviction Index for each forecast that estimates its expected accuracy.

Artificial intelligence in radiology

  • L. Filipović-Grčić
  • Medicine, Computer Science
    Rad Hrvatske akademije znanosti i umjetnosti. Medicinske znanosti
  • 2019
The aim of this article is to explain the most basic principles of artificial intelligence, accentuating the most prominent concepts used in radiology today, such as deep learning and neural networks.

Analysis of Human Behaviors in Real-Time Swarms

It is found that swarm's answer is not simply the arithmetic mean of initial individual “votes” as in a survey, suggesting a more complex mechanism is at play—one that relies on the time-varying behaviors of the participants in swarms.

Architecture for using Machine Learning for Prediction of Pneumonia disease through Clinical Symptoms

Clinical symptoms like compress and vanishing deep twist machine learning, supplementations, and also aggregate learning are used to construct a computational strategy for detecting pneumonia in children, which can decrease the death rate in children.

Artificial Swarming Shown to Amplify Accuracy of Group Decisions in Subjective Judgment Tasks

The results suggest that when small teams make subjective judgements as real-time swarms, they can be significantly more accurate than individual members, and that their accuracy can be further amplified by aggregating the output across small sets of swarms.

Unity Is Intelligence: A Collective Intelligence Experiment on ECG Reading to Improve Diagnostic Performance in Cardiology

A study to investigate the potential of collective intelligence approaches in cardiology and, more precisely, in electrocardiogram reading concludes that CI approaches can support the tasks mentioned above, and possibly other similar ones as well.



Artificial Swarm Intelligence amplifies accuracy when predicting financial markets

It is suggested that enabling groups of traders to form real-time systems online, governed by swarm intelligence algorithms, has the potential to significantly increase the accuracy of financial forecasts.

Artificial Swarm Intelligence vs human experts

  • Louis B. Rosenberg
  • Computer Science
    2016 International Joint Conference on Neural Networks (IJCNN)
  • 2016
By forming a real-time swarm intelligence, the group of random sports fans boosted their collective performance and out-performed experts.

Clinically applicable deep learning for diagnosis and referral in retinal disease

A novel deep learning architecture performs device-independent tissue segmentation of clinical 3D retinal images followed by separate diagnostic classification that meets or exceeds human expert clinical diagnoses of retinal disease.

Artificial Swarms find Social Optima : (Late Breaking Report)

  • Louis B. RosenbergG. Willcox
  • Computer Science
    2018 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)
  • 2018
“swarming” was significantly more effective at enabling groups to converge on the Social Optima than three common voting methods: (i) Plurality voting, (ii) Borda Count and (iii) Condorcet pairwise voting.

Human Swarms, a real-time method for collective intelligence

Modeled after biological swarms, the UNUM platform enables online groups to work in real-time synchrony, collaboratively exploring a decision-space and converging on preferred solutions in a matter of seconds.

Crowds vs swarms, a comparison of intelligence

The results suggest that swarming, with closed-loop feedback, is potentially a more effective method for tapping the insights of groups than traditional polling.

Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists

For the first time, a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts, was compared and most dermatologists were outperformed by the CNN.

CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning

An algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists is developed, and it is found that CheXNet exceeds average radiologist performance on the F1 metric.

Stop Signals Provide Cross Inhibition in Collective Decision-Making by Honeybee Swarms

It is shown that a key feature of a brain—cross inhibition between the evidence-accumulating populations—also exists in a swarm as it chooses its nesting site, and that cross inhibition between populations of scout bees increases the reliability of swarm decision-making by solving the problem of deadlock over equal sites.

On optimal decision-making in brains and social insect colonies

It is shown that social insect colonies may also be able to achieve statistically optimal collective decision-making in a very similar way to primate brains, via direct competition between evidence-accumulating populations.