Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects

Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also questions practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers. Despite advancements, challenges such as data biases and the scarcity of "big data" in many biomedical domains persist. We conclude with a discussion on effective innovation and collaborative efforts to further the miss

Multimodal Machine Learning for Clinically-Assistive Imaging-Based Biomedical Applications

Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models and even more recently generative models. Recent years have seen a rise in the discovery of widely-available deep learning architectures that support multimodal data integration, particularly with images. The incorporation of multiple modalities into these models is a thriving research topic, presenting its own unique challenges. In this work, we discuss five challenges to multimodal AI as it pertains to ML (representation, fusion, alignment, translation, and co-learning) and survey recent approaches to addressing these challenges in the context of medical image-based clinical decision support models. We conclude with a discussion of the future of the field, suggesting directions that should be elucidated further for successful clinical models and their translation to the clinical setting.

Self-Supervised Approach to Addressing Zero-Shot Learning Problem

In recent years, self-supervised learning has had significant success in applications involving computer vision and natural language processing. The type of pretext task is important to this boost in performance. One common pretext task is the measure of similarity and dissimilarity between pairs of images. In this scenario, the two images that make up the negative pair are visibly different to humans. However, in entomology, species are nearly indistinguishable and thus hard to differentiate. In this study, we explored the performance of a Siamese neural network using contrastive loss by learning to push apart embeddings of bumblebee species pair that are dissimilar, and pull together similar embeddings. Our experimental results show a 61% F1-score on zero-shot instances, a performance showing 11% improvement on samples of classes that share intersections with the training set.

eGAN: Unsupervised approach to class imbalance using transfer learning

Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to trained models that are unusable for any practical purpose. In this study we explore an unsupervised approach to address these imbalances by leveraging transfer learning from pre-trained image classification models to encoder-based Generative Adversarial Network (eGAN). To the best of our knowledge, this is the first work to tackle this problem using GAN without needing to augment with synthesized fake images. In the proposed approach we use the discriminator network to output a negative or positive score. We classify as minority, test samples with negative scores and as majority those with positive scores. Our approach eliminates epistemic uncertainty in model predictions, as the P(minority) + P(majority) need not sum up to 1. The impact of transfer learning and combinations of different pre-trained image classification models at the generator and discriminator is also explored. Best result of 0.69 F1-score was obtained on CIFAR-10 classification task with imbalance ratio of 1:2500. Our approach also provides a mechanism of thresholding the specificity or sensitivity of our machine learning system. Keywords: Class imbalance, Transfer Learning, GAN, nash equilibrium

AdeNet: Deep learning architecture that identifies damaged electrical insulators in power lines

Ceramic insulators are important to electronic systems, designed and installed to protect humans from the danger of high voltage electric current. However, insulators are not immortal, and natural deterioration can gradually damage them. Therefore, the condition of insulators must be continually monitored, which is normally done using UAVs. UAVs collect many images of insulators, and these images are then analyzed to identify those that are damaged. Here we describe AdeNet as a deep neural network designed to identify damaged insulators, and test multiple approaches to automatic analysis of the condition of insulators. Several deep neural networks were tested, as were shallow learning methods. The best results (88.8\%) were achieved using AdeNet without transfer learning. AdeNet also reduced the false negative rate to $\sim$7\%. While the method cannot fully replace human inspection, its high throughput can reduce the amount of labor required to monitor lines for damaged insulators and provide early warning to replace damaged insulators.

Segmentation of Breast Microcalcifications: A Multi-Scale Approach

Accurate characterization of microcalcifications (MCs) in 2D full-field digital screening mammography is a necessary step towards reducing diagnostic uncertainty associated with the callback of women with suspicious MCs. Quantitative analysis of MCs has the potential to better identify MCs that have a higher likelihood of corresponding to invasive cancer. However, automated identification and segmentation of MCs remains a challenging task with high false positive rates. We present Hessian Difference of Gaussians Regression (HDoGReg), a two stage multi-scale approach to MC segmentation. Candidate high optical density objects are first delineated using blob detection and Hessian analysis. A regression convolutional network, trained to output a function with higher response near MCs, chooses the objects which constitute actual MCs. The method is trained and validated on 435 mammograms from two separate datasets. HDoGReg achieved a mean intersection over the union of 0.670$\pm$0.121 per image, intersection over the union per MC object of 0.607$\pm$0.250 and true positive rate of 0.744 at 0.4 false positive detections per $cm^2$. The results of HDoGReg perform better when compared to state-of-the-art MC segmentation and detection methods.

Feature Selection for Learning to Predict Outcomes of Compute Cluster Jobs with Application to Decision Support

We present a machine learning framework and a new test bed for data mining from the Slurm Workload Manager for high-performance computing (HPC) clusters. The focus was to find a method for selecting features to support decisions: helping users decide whether to resubmit failed jobs with boosted CPU and memory allocations or migrate them to a computing cloud. This task was cast as both supervised classification and regression learning, specifically, sequential problem solving suitable for reinforcement learning. Selecting relevant features can improve training accuracy, reduce training time, and produce a more comprehensible model, with an intelligent system that can explain predictions and inferences. We present a supervised learning model trained on a Simple Linux Utility for Resource Management (Slurm) data set of HPC jobs using three different techniques for selecting features: linear regression, lasso, and ridge regression. Our data set represented both HPC jobs that failed and those that succeeded, so our model was reliable, less likely to overfit, and generalizable. Our model achieved an R^2 of 95\% with 99\% accuracy. We identified five predictors for both CPU and memory properties.

Shape-aware Generative Adversarial Networks for Attribute Transfer

Generative adversarial networks (GANs) have been successfully applied to transfer visual attributes in many domains, including that of human face images. This success is partly attributable to the facts that human faces have similar shapes and the positions of eyes, noses, and mouths are fixed among different people. Attribute transfer is more challenging when the source and target domain share different shapes. In this paper, we introduce a shape-aware GAN model that is able to preserve shape when transferring attributes, and propose its application to some real-world domains. Compared to other state-of-art GANs-based image-to-image translation models, the model we propose is able to generate more visually appealing results while maintaining the quality of results from transfer learning.

Using a Generative Adversarial Network for CT Normalization and its Impact on Radiomic Features

Computer-Aided-Diagnosis (CADx) systems assist radiologists with identifying and classifying potentially malignant pulmonary nodules on chest CT scans using morphology and texture-based (radiomic) features. However, radiomic features are sensitive to differences in acquisitions due to variations in dose levels and slice thickness. This study investigates the feasibility of generating a normalized scan from heterogeneous CT scans as input. We obtained projection data from 40 low-dose chest CT scans, simulating acquisitions at 10%, 25% and 50% dose and reconstructing the scans at 1.0mm and 2.0mm slice thickness. A 3D generative adversarial network (GAN) was used to simultaneously normalize reduced dose, thick slice (2.0mm) images to normal dose (100%), thinner slice (1.0mm) images. We evaluated the normalized image quality using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS). Our GAN improved perceptual similarity by 35%, compared to a baseline CNN method. Our analysis also shows that the GAN-based approach led to a significantly smaller error (p-value < 0.05) in nine studied radiomic features. These results indicated that GANs could be used to normalize heterogeneous CT images and reduce the variability in radiomic feature values.