LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 2 of total 2

Search options

  1. Article ; Online: Leveraging human expert image annotations to improve pneumonia differentiation through human knowledge distillation

    Daniel Schaudt / Reinhold von Schwerin / Alexander Hafner / Pascal Riedel / Christian Späte / Manfred Reichert / Andreas Hinteregger / Meinrad Beer / Christopher Kloth

    Scientific Reports, Vol 13, Iss 1, Pp 1-

    2023  Volume 13

    Abstract: Abstract In medical imaging, deep learning models can be a critical tool to shorten time-to-diagnosis and support specialized medical staff in clinical decision making. The successful training of deep learning models usually requires large amounts of ... ...

    Abstract Abstract In medical imaging, deep learning models can be a critical tool to shorten time-to-diagnosis and support specialized medical staff in clinical decision making. The successful training of deep learning models usually requires large amounts of quality data, which are often not available in many medical imaging tasks. In this work we train a deep learning model on university hospital chest X-ray data, containing 1082 images. The data was reviewed, differentiated into 4 causes for pneumonia, and annotated by an expert radiologist. To successfully train a model on this small amount of complex image data, we propose a special knowledge distillation process, which we call Human Knowledge Distillation. This process enables deep learning models to utilize annotated regions in the images during the training process. This form of guidance by a human expert improves model convergence and performance. We evaluate the proposed process on our study data for multiple types of models, all of which show improved results. The best model of this study, called PneuKnowNet, shows an improvement of + 2.3% points in overall accuracy compared to a baseline model and also leads to more meaningful decision regions. Utilizing this implicit data quality-quantity trade-off can be a promising approach for many scarce data domains beyond medical imaging.
    Keywords Medicine ; R ; Science ; Q
    Subject code 006
    Language English
    Publishing date 2023-06-01T00:00:00Z
    Publisher Nature Portfolio
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: A Critical Assessment of Generative Models for Synthetic Data Augmentation on Limited Pneumonia X-ray Data

    Daniel Schaudt / Christian Späte / Reinhold von Schwerin / Manfred Reichert / Marianne von Schwerin / Meinrad Beer / Christopher Kloth

    Bioengineering, Vol 10, Iss 12, p

    2023  Volume 1421

    Abstract: In medical imaging, deep learning models serve as invaluable tools for expediting diagnoses and aiding specialized medical professionals in making clinical decisions. However, effectively training deep learning models typically necessitates substantial ... ...

    Abstract In medical imaging, deep learning models serve as invaluable tools for expediting diagnoses and aiding specialized medical professionals in making clinical decisions. However, effectively training deep learning models typically necessitates substantial quantities of high-quality data, a resource often lacking in numerous medical imaging scenarios. One way to overcome this deficiency is to artificially generate such images. Therefore, in this comparative study we train five generative models to artificially increase the amount of available data in such a scenario. This synthetic data approach is evaluated on a a downstream classification task, predicting four causes for pneumonia as well as healthy cases on 1082 chest X-ray images. Quantitative and medical assessments show that a Generative Adversarial Network (GAN)-based approach significantly outperforms more recent diffusion-based approaches on this limited dataset with better image quality and pathological plausibility. We show that better image quality surprisingly does not translate to improved classification performance by evaluating five different classification models and varying the amount of additional training data. Class-specific metrics like precision, recall, and F1-score show a substantial improvement by using synthetic images, emphasizing the data rebalancing effect of less frequent classes. However, overall performance does not improve for most models and configurations, except for a DreamBooth approach which shows a +0.52 improvement in overall accuracy. The large variance of performance impact in this study suggests a careful consideration of utilizing generative models for limited data scenarios, especially with an unexpected negative correlation between image quality and downstream classification improvement.
    Keywords deep learning ; generative models ; medical imaging ; pneumonia ; synthetic data ; Technology ; T ; Biology (General) ; QH301-705.5
    Subject code 006
    Language English
    Publishing date 2023-12-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top