Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder

Collagen fiber centerline tracking in fibrotic tissue via deep neural networks with variational autoencoder-based synthetic training data generation

The role of fibrillar collagen in the tissue microenvironment is critical in disease contexts ranging from cancers to chronic inflammations, as evidenced by many studies. Quantifying fibrillar collagen organization has become a powerful approach for characterizing the topology of collagen fibers and studying the role of collagen fibers in disease progression. We present a deep learning-based pipeline to quantify collagen fibers' topological properties in microscopy-based collagen images from pathological tissue samples. Our method leverages deep neural networks to extract collagen fiber centerlines and deep generative models to create synthetic training data, addressing the current shortage of large-scale annotations. As a part of this effort, we have created and annotated a collagen fiber centerline dataset, with the hope of facilitating further research in this field. Quantitative measurements such as fiber orientation, alignment, density, and length can be derived based on the centerline extraction results. Our pipeline comprises three stages. Initially, a variational autoencoder is trained to generate synthetic centerlines possessing controllable topological properties. Subsequently, a conditional generative adversarial network synthesizes realistic collagen fiber images from the synthetic centerlines, yielding a synthetic training set of image-centerline pairs. Finally, we train a collagen fiber centerline extraction network using both the original and synthetic data. Evaluation using collagen fiber images from pancreas, liver, and breast cancer samples collected via second-harmonic generation microscopy demonstrates our pipeline's superiority over several popular fiber centerline extraction tools. Incorporating synthetic data into training further enhances the network's generalizability. Our code is available at https://github.com/uw-loci/collagen-fiber-metrics.

Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding

Introduction

The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information.

Methods

In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers.

Results

We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively.

Conclusion

The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.

Estimating explainable Alzheimer's disease likelihood map via clinically-guided prototype learning

Identifying Alzheimer's disease (AD) involves a deliberate diagnostic process owing to its innate traits of irreversibility with subtle and gradual progression. These characteristics make AD biomarker identification from structural brain imaging (e.g., structural MRI) scans quite challenging. Using clinically-guided prototype learning, we propose a novel deep-learning approach through eXplainable AD Likelihood Map Estimation (XADLiME) for AD progression modeling over 3D sMRIs. Specifically, we establish a set of topologically-aware prototypes onto the clusters of latent clinical features, uncovering an AD spectrum manifold. Considering this pseudo map as an enriched reference, we employ an estimating network to approximate the AD likelihood map over a 3D sMRI scan. Additionally, we promote the explainability of such a likelihood map by revealing a comprehensible overview from clinical and morphological perspectives. During the inference, this estimated likelihood map served as a substitute for unseen sMRI scans for effectively conducting the downstream task while providing thorough explainable states.

Data augmentation for medical imaging: A systematic literature review

Recent advances in Deep Learning have largely benefited from larger and more diverse training sets. However, collecting large datasets for medical imaging is still a challenge due to privacy concerns and labeling costs. Data augmentation makes it possible to greatly expand the amount and variety of data available for training without actually collecting new samples. Data augmentation techniques range from simple yet surprisingly effective transformations such as cropping, padding, and flipping, to complex generative models. Depending on the nature of the input and the visual task, different data augmentation strategies are likely to perform differently. For this reason, it is conceivable that medical imaging requires specific augmentation strategies that generate plausible data samples and enable effective regularization of deep neural networks. Data augmentation can also be used to augment specific classes that are underrepresented in the training set, e.g., to generate artificial lesions. The goal of this systematic literature review is to investigate which data augmentation strategies are used in the medical domain and how they affect the performance of clinical tasks such as classification, segmentation, and lesion detection. To this end, a comprehensive analysis of more than 300 articles published in recent years (2018-2022) was conducted. The results highlight the effectiveness of data augmentation across organs, modalities, tasks, and dataset sizes, and suggest potential avenues for future research.