Researchers are training artificial intelligence models to identify tuberculosis (TB) on chest X-rays, which may help screening and evaluation efforts in TB-prevalent areas with limited access to radiologists, according to a new study appearing online in the journal Radiology.
Paras Lakhani, M.D.
According to the World Health Organization, TB is one of the top 10 causes of death worldwide. In 2016, approximately 10.4 million people fell ill from TB, resulting in 1.8 million deaths. TB can be identified on chest imaging, however TB-prevalent areas typically lack the radiology interpretation expertise needed to screen and diagnose the disease.
“There is a tremendous interest in artificial intelligence, both inside and outside the field of medicine,” said study co-author Paras Lakhani, M.D., from Thomas Jefferson University Hospital (TJUH) in Philadelphia. “An artificial intelligence solution that could interpret radiographs for presence of TB in a cost-effective way could expand the reach of early identification and treatment in developing nations.”
Deep learning is a type of artificial intelligence that allows computers to complete tasks based on existing relationships of data. A deep convolutional neural network (DCNN), modeled after brain structure, employs multiple hidden layers and patterns to classify images.
For the study, Dr. Lakhani and his colleague, Baskaran Sundaram, M.D., obtained 1,007 X-rays of patients with and without active TB. The cases consisted of multiple chest X-ray datasets from the National Institutes of Health, the Belarus Tuberculosis Portal, and TJUH. The datasets were split into training (68.0 percent), validation (17.1 percent), and test (14.9 percent).
The cases were used to train two different DCNN models – AlexNet and GoogLeNet – which learned from TB-positive and TB-negative X-rays. The models’ accuracy was tested on 150 cases that were excluded from the training and validation datasets.
The best performing artificial intelligence model was a combination of the AlexNet and GoogLeNet, with a net accuracy of 96 percent.
“The relatively high accuracy of the deep learning models is exciting,” Dr. Lakhani said. “The applicability for TB is important because it’s a condition for which we have treatment options. It’s a problem that can be solved.”
The two DCNN models had disagreement in 13 of the 150 test cases. For these cases, the researchers evaluated a workflow where an expert radiologist was able to interpret the images, accurately diagnosing 100 percent of the cases. This workflow, which incorporated a human in the loop, had a greater net accuracy of close to 99 percent.
“Application of deep learning to medical imaging is a relatively new field,” Dr. Lakhani said. “In the past, other machine learning approaches could only get to a certain accuracy level of around 80 percent. However, with deep learning, there is potential for more accurate solutions, as this research has shown.”
Dr. Lakhani said that the team plans to further improve the models with mores training cases and other deep learning methods.
“We hope to prospectively apply this in a real world environment,” he said. “An artificial intelligence solution using chest imaging can play a big role in tackling TB.”
The Latest on: Artificial intelligence diagnostics
- Artificial Intelligence vs Human Intelligence: Who Will Win The Ultimate Battle? on September 18, 2018 at 3:14 am
Artificial intelligence vs human intelligence is a ... Watson sifts through the abundance of newly published and existing medical-diagnostic materials to present the doctors with new pieces ... […]
- Arguing the Pros and Cons of Artificial Intelligence in Healthcare on September 17, 2018 at 7:16 am
The idea that artificial intelligence will replace human workers has been around ... Babylon Health announced that an AI algorithm scored higher than humans on the written test on diagnostics used to ... […]
- The promise of artificial intelligence in diagnosing illness on September 17, 2018 at 4:00 am
But advancements in artificial intelligence are about to disrupt disease diagnosis ... The digital images become a historical record of the blood or tissue sample. The entire diagnostic process could ... […]
- Over 40% CAGR Healthcare Artificial Intelligence Market to reach $10 billion by 2024 on September 14, 2018 at 8:34 am
Increasing application of artificial intelligence in diagnostics and imaging industry will further growth. Ask for Sample copy of this report @ https://www.gminsights.com/request-sample/detail/1557 In... […]
- Pentagon maps future plans with Artificial Intelligence on September 14, 2018 at 7:35 am
The Pentagon is making a massive push to accelerate the application of artificial intelligence to ships ... The new carriers use advanced algorithms to perform diagnostics and other on-board maintenan... […]
via Google News and Bing News