AI | Detecting COVID-19 in Lungs with Deep Learning

Apr, 2024 | Health

“I encourage parents to talk to their doctors about how to protect their little ones against serious RSV illness, using either a vaccine given during pregnancy, or an RSV immunization given to your baby after birth”

Dr Mandy K Cohen

 Director for the Centers for Disease Control and Prevention (CDC) and the Administrator of the Agency for Toxic Substances and Disease Registry

 

Over the past few years, researchers have made great strides in applying machine learning and artificial intelligence to medical imaging. One area that has shown promise is using deep neural networks (DNNs) to analyze lung ultrasound images and detect signs of COVID-19. However, training these complex models requires vast amounts of high-quality medical data with accurate annotations, which can be difficult to obtain.

A team of researchers from Johns Hopkins University led by Dr. Muyinatu Bell investigated different strategies for training DNNs to detect COVID-19 features in lung ultrasounds using both real patient data and simulated ultrasound images generated with modeling software. Their goal was to determine the most effective training approach when real-world data is limited, as was often the case early in the pandemic.

Their findings, published in the journal Communications Medicine, provide valuable insights into how simulated medical data can help address limitations in training deep learning models for healthcare applications. With proper validation using real patient examples, simulated data shows promise as a supplement or alternative to limited annotated real-world examples. The strategies explored can help advance applications of artificial intelligence to interpret medical scans and aid diagnosis.

One barrier to applying deep neural networks to medical image analysis is the vast amount of high-quality annotated data required for training complex models. Manually annotating and labeling thousands of medical images takes experts enormous time and effort. Even when real-world datasets are collected, variables like image quality, patient demographics, and equipment can vary in ways that impact a model’s ability to generalize.

The Johns Hopkins team explored using both real-world lung ultrasound clips from COVID-19 patients and simulated ultrasound images generated with modeling software to train their deep learning models. The simulations allowed for generating unlimited annotated images efficiently, with known ground truths. However, prior studies found simulated data alone did not necessarily transfer well to real patient examples due to domain differences between simulations and reality.

The researchers investigated seven different strategies for training DNNs to segment and detect B-line patterns, a hallmark sign of COVID-19 in lung ultrasounds, either using real data, simulated data, or combinations:

1. Simulated data only
2. Real-world dataset only
3. Combination of 1 and 2
4. Split real-world dataset (training on most, testing on subset)
5. Combination of 1 and 4
6. Combination of 2 and 4
7. Combination of 1, 2, and 4

They tested each strategy’s ability to correctly segment B-lines in real ultrasound clips from COVID-19 patients. Additional experiments explored the impact of image augmentations like rotations and alterations to contrast/blurriness.

The study produced several important findings on effectively training deep learning models when real-world medical data is limited:

– Data augmentation during training significantly improved model performance, especially for segmenting B-lines. This helped address differences between training and test data distributions.

– When real data from the same distribution as test cases wasn’t available, combining simulated and real datasets from other domains (Strategy 3) worked best, outperforming simulated-only or real-only approaches.

– When partially overlapping real test/train data was used (Strategies 4-7), including simulated examples further improved results over real-only, especially in earlier training stages.

– Combining all data sources (Strategy 7) performed most consistently while requiring fewer training iterations than real-only approaches.

– Relying solely on real data from different distributions than test cases (Strategy 2) performed poorly relative to combinations with simulations.

Overall, incorporating carefully constructed simulated data appeared to help address limitations in fully-annotated real-world examples, likely by increasing effective training dataset sizes and diversity. Including simulations also improved training efficiency in some cases.

The results provide valuable guidance on effectively applying both real and simulated medical imaging data to train deep learning models – a crucial area as artificial intelligence expands its role in healthcare. Some key takeaways include:

– Simulated data shows promise as a supplement when real-world examples are limited, improving performance over real-only approaches.

– Combining simulated and real data from various domains works better than simulated alone, likely due to increasing diversity.

– Including data augmentations during training helps reduce differences between available training and intended test cases.

– Larger, more comprehensive simulated datasets may allow training models without needing fully-overlapping real examples.

Going forward, more realistic simulations that capture greater clinical variability could help deep learning models generalize even better. Continued validation using real patient cases will also be important. As better tools emerge to efficiently generate annotated medical examples, simulation-augmented training holds potential to address limitations and accelerate AI-assisted diagnosis. Overall, the study provides a valuable framework for effectively leveraging both real and simulated healthcare data with deep learning.

Reference(s)

  1. https://doi.org/10.1038/s43856-024-00463-5

 

Click TAGS to see related articles :

AI | COVID-19 | DIAGNOSTICS | MACHINE LEARNING | MEDICINE | PUBLIC HEALTH | RESPIRATORY | SARS-COV2

  • Global life expectancy to increase by nearly 5...
    on May, 2024 at 8:41 pm

    The latest findings forecast that global life expectancy will increase by 4.9 years in males and 4.2 years in females between 2022 and 2050. Increases are expected to be largest in countries where life expectancy is lower, contributing to a convergence of increased life expectancy across […]

  • A trial HIV vaccine triggered elusive and...
    on May, 2024 at 3:14 pm

    An HIV vaccine candidate triggered low levels of an elusive type of broadly neutralizing HIV antibodies among a small group of people enrolled in a 2019 clinical trial.

  • A powerful tool speeds success in achieving...
    on May, 2024 at 12:51 am

    Thermoelectric materials could play an important role in the clean energy transition, as they can produce electricity from sources of heat that would otherwise go to waste. Researchers report a new approach to efficiently predict when thermoelectric materials will have improved performance in […]

  • Scientists use generative AI to answer complex...
    on May, 2024 at 8:05 pm

    Researchers used generative AI to develop a physics-informed technique to classify phase transitions in materials or physical systems that is much more efficient than existing machine-learning approaches.

  • Otters, especially females, use tools to survive...
    on May, 2024 at 8:05 pm

    Sea otters are one of the few animals that use tools to access their food, and a new study has found that individual sea otters that use tools -- most of whom are female -- are able to eat larger prey and reduce tooth damage when their preferred prey becomes depleted.

  • New gene delivery vehicle shows promise for human...
    on May, 2024 at 8:05 pm

    In an important step toward more effective gene therapies for brain diseases, researchers have engineered a gene-delivery vehicle that uses a human protein to efficiently cross the blood-brain barrier and deliver a disease-relevant gene to the brain in mice expressing the human protein. Because the […]

About the Author

  • Dilruwan Herath

    Dilruwan Herath is a British infectious disease physician and pharmaceutical medical executive with over 25 years of experience. As a doctor, he specialized in infectious diseases and immunology, developing a resolute focus on public health impact. Throughout his career, Dr. Herath has held several senior medical leadership roles in large global pharmaceutical companies, leading transformative clinical changes and ensuring access to innovative medicines. Currently, he serves as an expert member for the Faculty of Pharmaceutical Medicine on it Infectious Disease Commitee and continues advising life sciences companies. When not practicing medicine, Dr. Herath enjoys painting landscapes, motorsports, computer programming, and spending time with his young family. He maintains an avid interest in science and technology. He is a founder of DarkDrug

Pin It on Pinterest