scholarly journals Active Learning Performance in Labeling Radiology Images Is 90% Effective

2021 ◽  
Vol 1 ◽  
Author(s):  
Patrick Bangert ◽  
Hankyu Moon ◽  
Jae Oh Woo ◽  
Sima Didari ◽  
Heng Hao
Keyword(s):  
Artificial Intelligence ◽  
Active Learning ◽  
Information Content ◽  
Information Gain ◽  
Real Life ◽  
Learning Performance ◽  
Image Labeling ◽  
Human Effort ◽  
Polygonal Shape ◽  
Entire Dataset

To train artificial intelligence (AI) systems on radiology images, an image labeling step is necessary. Labeling for radiology images usually involves a human radiologist manually drawing a (polygonal) shape onto the image and attaching a word to it. As datasets are typically large, this task is repetitive, time-consuming, error-prone, and expensive. The AI methodology of active learning (AL) can assist human labelers by continuously sorting the unlabeled images in order of information gain and thus getting the labeler always to label the most informative image next. We find that after about 10%, depending on the dataset, of the images in a realistic dataset are labeled, virtually all the information content has been learnt and the remaining images can be automatically labeled. These images can then be checked by the radiologist, which is far easier and faster to do. In this way, the entire dataset is labeled with much less human effort. We introduce AL in detail and expose the effectiveness using three real-life datasets. We contribute five distinct elements to the standard AL workflow creating an advanced methodology.

INTELLECTUAL PROPERTY LAW OF COMPUTER-GENERATED WORKS DERIVING FROM ARTIFICIAL INTELLIGENCE

2019 ◽  
Vol 5 (1) ◽  
pp. 339-348
Author(s):  
Akbar Ismanjanov
Keyword(s):  
Artificial Intelligence ◽  
Intellectual Property ◽  
Information Content ◽  
Computer Programs ◽  
Property Law ◽  
Intellectual Property Law ◽  
Human Creativity ◽  
Human Effort

With the proliferation of artificial intelligence, the significant domain forming the copy-rightable works autonomously created by the computer, without significant expenditure of human effort and skill. The reality of today is that information content is predominantly coming from the computer, where the idea-expression dichotomy of originality is rather referring to the computer than a human author. However, the copyright is revolving around the human-centered authorship its showing resistance to non-human creativity. In the context of authorship, the artificial category of a corporation owning property in the interest of their shareholders allowing application concerning the artificial intelligence author. Moreover, computer programs exercising independent choice in the unpredictability of the outcome of the operation can objectively approximate artificial intelligence to the qualification of authorship.

Bayesian Active Learning of Neural Firing Rate Maps with Transformed Gaussian Process Priors

2014 ◽  
Vol 26 (8) ◽  
pp. 1519-1541 ◽  
Author(s):  
Mijung Park ◽  
J. Patrick Weller ◽  
Gregory D. Horwitz ◽  
Jonathan W. Pillow
Keyword(s):  
Active Learning ◽  
Gaussian Process ◽  
Firing Rate ◽  
Utility Function ◽  
Information Gain ◽  
Tuning Curve ◽  
Strong Dependence ◽  
Learning Performance ◽  
Stimulus Selection ◽  
Neural Firing

A firing rate map, also known as a tuning curve, describes the nonlinear relationship between a neuron's spike rate and a low-dimensional stimulus (e.g., orientation, head direction, contrast, color). Here we investigate Bayesian active learning methods for estimating firing rate maps in closed-loop neurophysiology experiments. These methods can accelerate the characterization of such maps through the intelligent, adaptive selection of stimuli. Specifically, we explore the manner in which the prior and utility function used in Bayesian active learning affect stimulus selection and performance. Our approach relies on a flexible model that involves a nonlinearly transformed gaussian process (GP) prior over maps and conditionally Poisson spiking. We show that infomax learning, which selects stimuli to maximize the information gain about the firing rate map, exhibits strong dependence on the seemingly innocuous choice of nonlinear transformation function. We derive an alternate utility function that selects stimuli to minimize the average posterior variance of the firing rate map and analyze the surprising relationship between prior parameterization, stimulus selection, and active learning performance in GP-Poisson models. We apply these methods to color tuning measurements of neurons in macaque primary visual cortex.

Research and Application of Artificial Intelligence Based Integrated Teaching-Learning Modular Approach in Colleges and Universities

2021 ◽  
Author(s):  
Lingchong Jia ◽  
B. Santhosh Kumar ◽  
R. Parthasarathy
Keyword(s):  
Artificial Intelligence ◽  
Student Development ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Learning Performance ◽  
Barriers To Entry ◽  
Final Exam ◽  
Artificial Intelligence Technology ◽  
Bayes Algorithm ◽  
Teaching Learning

Nowadays, in various educational institutions, artificial intelligence technology is applied effectively and successfully. This artificial intelligence improves learning and student development in academic performance. Challenges of the conventional education approach, students’ dependence on teachers in all resources for study, unavailability of professional instructors, and a greater focus on conditioning learning than practical usefulness lead to lower learning performance. In this paper integrated teaching-learning model approach has been proposed using artificial intelligence in student education. It involves speeding up fulfilling education targets by reducing barriers to entry, automating management processes, and maximizing learning performance. The proposed ITLMA method used the naive Bayes algorithm to evaluate the student ranking using a class score, task, project score, and final exam. The result of artificial intelligence-based ITLMA and naive Bayes algorithm hasa high accuracy ratio of 80.1% with less error ratio of 15.7%, high prediction 88.2%, precision 98.2%, and improves student and teacher interaction compared to other existing methods.

scholarly journals Methodology for Interactive Labeling of Patched Asphalt Pavement Images Based on U-Net Convolutional Neural Network

2022 ◽  
Vol 14 (2) ◽  
pp. 861
Author(s):  
Han-Cheng Dan ◽  
Hao-Fan Zeng ◽  
Zhi-Heng Zhu ◽  
Ge-Wen Bai ◽  
Wei Cao
Keyword(s):  
Neural Network ◽  
Active Learning ◽  
Convolutional Neural Network ◽  
Sample Size ◽  
Pavement Distress ◽  
Image Labeling ◽  
Gray Area ◽  
Calculation Results ◽  
Labeling Method ◽  
And Training

Image recognition based on deep learning generally demands a huge sample size for training, for which the image labeling becomes inevitably laborious and time-consuming. In the case of evaluating the pavement quality condition, many pavement distress patching images would need manual screening and labeling, meanwhile the subjectivity of the labeling personnel would greatly affect the accuracy of image labeling. In this study, in order for an accurate and efficient recognition of the pavement patching images, an interactive labeling method is proposed based on the U-Net convolutional neural network, using active learning combined with reverse and correction labeling. According to the calculation results in this paper, the sample size required by the interactive labeling is about half of the traditional labeling method for the same recognition precision. Meanwhile, the accuracy of interactive labeling method based on the mean intersection over union (mean_IOU) index is 6% higher than that of the traditional method using the same sample size and training epochs. In addition, the accuracy analysis of the noise and boundary of the prediction results shows that this method eliminates 92% of the noise in the predictions (the proportion of noise is reduced from 13.85% to 1.06%), and the image definition is improved by 14.1% in terms of the boundary gray area ratio. The interactive labeling is considered as a significantly valuable approach, as it reduces the sample size in each epoch of active learning, greatly alleviates the demand for manpower, and improves learning efficiency and accuracy.

scholarly journals Ethical issues on artificial intelligence in radiology: how is it reported in research articles? The current state and future directions

2021 ◽  
Vol 90 (2) ◽  
pp. e513
Author(s):  
Tomasz Piotrowski ◽  
Joanna Kazmierska ◽  
Mirosława Mocydlarz-Adamcewicz ◽  
Adam Ryczkowski
Keyword(s):  
Artificial Intelligence ◽  
Ethical Issues ◽  
Real Life ◽  
Exclusion Criteria ◽  
Future Directions ◽  
Current State ◽  
Ethical Status ◽  
The Status ◽  
Clinical Questions ◽  
Almost All

Background. This paper evaluates the status of reporting information related to the usage and ethical issues of artificial intelligence (AI) procedures in clinical trial (CT) papers focussed on radiology issues as well as other (non-trial) original radiology articles (OA). Material and Methods. The evaluation was performed by three independent observers who were, respectively physicist, physician and computer scientist. The analysis was performed for two groups of publications, i.e., for CT and OA. Each group included 30 papers published from 2018 to 2020, published before guidelines proposed by Liu et al. (Nat Med. 2020; 26:1364-1374). The set of items used to catalogue and to verify the ethical status of the AI reporting was developed using the above-mentioned guidelines. Results. Most of the reviewed studies, clearly stated their use of AI methods and more importantly, almost all tried to address relevant clinical questions. Although in most of the studies, patient inclusion and exclusion criteria were presented, the widespread lack of rigorous descriptions of the study design apart from a detailed explanation of the AI approach itself is noticeable. Few of the chosen studies provided information about anonymization of data and the process of secure data sharing. Only a few studies explore the patterns of incorrect predictions by the proposed AI tools and their possible reasons. Conclusion. Results of review support idea of implementation of uniform guidelines for designing and reporting studies with use of AI tools. Such guidelines help to design robust, transparent and reproducible tools for use in real life.

scholarly journals AI in oncology: when science fiction meets reality

2018 ◽  
Vol 1 (1) ◽  
pp. 001-002
Author(s):  
Bin Li
Keyword(s):  
Artificial Intelligence ◽  
Science Fiction ◽  
Real Life

Artificial intelligence has long been a hot topic in the science fiction books and movies. But now it seemingly has stepped into our real life in a variety of forms. In this brief editorial, we discuss the various aspects of AI utilizations in our day-to-day life and foresee its applications in oncology.

Sign in / Sign up

Export Citation Format

Share Document