LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 4 of total 4

Search options

  1. Article ; Online: Augmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset

    Daniel Schaudt / Reinhold von Schwerin / Alexander Hafner / Pascal Riedel / Manfred Reichert / Marianne von Schwerin / Meinrad Beer / Christopher Kloth

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

    2023  Volume 16

    Abstract: Abstract Since the beginning of the COVID-19 pandemic, many different machine learning models have been developed to detect and verify COVID-19 pneumonia based on chest X-ray images. Although promising, binary models have only limited implications for ... ...

    Abstract Abstract Since the beginning of the COVID-19 pandemic, many different machine learning models have been developed to detect and verify COVID-19 pneumonia based on chest X-ray images. Although promising, binary models have only limited implications for medical treatment, whereas the prediction of disease severity suggests more suitable and specific treatment options. In this study, we publish severity scores for the 2358 COVID-19 positive images in the COVIDx8B dataset, creating one of the largest collections of publicly available COVID-19 severity data. Furthermore, we train and evaluate deep learning models on the newly created dataset to provide a first benchmark for the severity classification task. One of the main challenges of this dataset is the skewed class distribution, resulting in undesirable model performance for the most severe cases. We therefore propose and examine different augmentation strategies, specifically targeting majority and minority classes. Our augmentation strategies show significant improvements in precision and recall values for the rare and most severe cases. While the models might not yet fulfill medical requirements, they serve as an appropriate starting point for further research with the proposed dataset to optimize clinical resource allocation and treatment.
    Keywords Medicine ; R ; Science ; Q
    Subject code 006
    Language English
    Publishing date 2023-10-01T00:00:00Z
    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: 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.

  3. 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.

  4. Article ; Online: GANerAid

    Lucas Krenmayr / Roland Frank / Christina Drobig / Michael Braungart / Jan Seidel / Daniel Schaudt / Reinhold von Schwerin / Kathrin Stucke-Straub

    Informatics in Medicine Unlocked, Vol 35, Iss , Pp 101118- (2022)

    Realistic synthetic patient data for clinical trials

    2022  

    Abstract: Human data must be considered one of the most valuable resources of our time, both in research and business contexts. However, particularly in fields that heavily rely on clinical information, such as medicine or pharmacy, not only the collection of ... ...

    Abstract Human data must be considered one of the most valuable resources of our time, both in research and business contexts. However, particularly in fields that heavily rely on clinical information, such as medicine or pharmacy, not only the collection of patient data is expensive and time consuming, but, due to data protection laws and regulations, the ways of how to use them are strictly limited, deeming reuse or sharing very difficult, if not impossible. One promising solution to overcome these problems are artificially created data points with the same statistical properties as the investigated patient population. In this paper, we propose the GANerAid architecture, utilising a Generative Adversarial Network (GAN) approach to create such synthetic patients from random noise. Unlike other methods, GANerAid is based on long short-term memory (LSTM) layers and is thus able to preserve underlying data properties, such as correlations and variable distributions, leading to more satisfying results, even in small-sized samples, with acceptable training speed. GANerAid is published as an open source library and released as a ready-to-use package for Python 3.
    Keywords Synthetic patients ; Machine learning ; Generative Adversarial Network ; Tabular data ; Random noise ; Long short-term memory ; Computer applications to medicine. Medical informatics ; R858-859.7
    Subject code 006
    Language English
    Publishing date 2022-01-01T00:00:00Z
    Publisher Elsevier
    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