More Like this

1. Ensemble Machine Learning for Alzheimer’s disease Classification from Retinal Vasculature

   Lin, Hely ; Fang, Ruogu ( October 2021 , Biomedical Engineering Society Annual Meeting)

   null (Ed.)

   Introduction: Alzheimer’s disease (AD) causes progressive irreversible cognitive decline and is the leading cause of dementia. Therefore, a timely diagnosis is imperative to maximize neurological preservation. However, current treatments are either too costly or limited in availability. In this project, we explored using retinal vasculature as a potential biomarker for early AD diagnosis. This project focuses on stage 3 of a three-stage modular machine learning pipeline which consisted of image quality selection, vessel map generation, and classification [1]. The previous model only used support vector machine (SVM) to classify AD labels which limited its accuracy to 82%. In this project, random forest and gradient boosting were added and, along with SVM, combined into an ensemble classifier, raising the classification accuracy to 89%. Materials and Methods: Subjects classified as AD were those who were diagnosed with dementia in “Dementia Outcome: Alzheimer’s disease” from the UK Biobank Electronic Health Records. Five control groups were chosen with a 5:1 ratio of control to AD patients where the control patients had the same age, gender, and eye side image as the AD patient. In total, 122 vessel images from each group (AD and control) were used. The vessel maps were then segmented from fundus images through U-net. A t-test feature selection was first done on the training folds and the selected features was fed into the classifiers with a p-value threshold of 0.01. Next, 20 repetitions of 5-fold cross validation were performed where the hyperparameters were solely tuned on the training data. An ensemble classifier consisting of SVM, gradient boosting tree, and random forests was built and the final prediction was made through majority voting and evaluated on the test set. Results and Discussion: Through ensemble classification, accuracy increased by 4-12% relative to the individual classifiers, precision by 9-15%, sensitivity by 2-9%, specificity by at least 9-16%, and F1 score by 712%. Conclusions: Overall, a relatively high classification accuracy was achieved using machine learning ensemble classification with SVM, random forest, and gradient boosting. Although the results are very promising, a limitation of this study is that the requirement of needing images of sufficient quality decreased the amount of control parameters that can be implemented. However, through retinal vasculature analysis, this project shows machine learning’s high potential to be an efficient, more cost-effective alternative to diagnosing Alzheimer’s disease. Clinical Application: Using machine learning for AD diagnosis through retinal images will make screening available for a broader population by being more accessible and cost-efficient. Mobile device based screening can also be enabled at primary screening in resource-deprived regions. It can provide a pathway for future understanding of the association between biomarkers in the eye and brain. 

   more » « less
2. Optimizing 3D U-Net-based Brain Tumor Segmentation with Integer-arithmetic Deep Learning Accelerators

   https://doi.org/10.1145/3495210  

   Wang, Weijia ; Lin, Bill ( April 2022 , ACM Journal on Emerging Technologies in Computing Systems)

   While gliomas have become the most common cancerous brain tumors, manual diagnoses from 3D MRIs are time-consuming and possibly inconsistent when conducted by different radiotherapists, which leads to the pressing demand for automatic segmentation of brain tumors. State-of-the-art approaches employ FCNs to automatically segment the MRI scans. In particular, 3D U-Net has achieved notable performance and motivated a series of subsequent works. However, their significant size and heavy computation have impeded their actual deployment. Although there exists a body of literature on the compression of CNNs using low-precision representations, they either focus on storage reduction without computational improvement or cause severe performance degradation. In this article, we propose a CNN training algorithm that approximates weights and activations using non-negative integers along with trained affine mapping functions. Moreover, our approach allows the dot-product operations to be performed in an integer-arithmetic manner and defers the floating-point decoding and encoding phases until the end of layers. Experimental results on BraTS 2018 show that our trained affine mapping approach achieves near full-precision dice accuracy with 8-bit weights and activations. In addition, we achieve a dice accuracy within 0.005 and 0.01 of the full-precision counterparts when using 4-bit and 2-bit precisions, respectively. 

   more » « less
3. GSMA: an approach to identify robust global and test Gene Signatures using Meta-Analysis

   https://doi.org/10.1093/bioinformatics/btz561  

   Shafi, Adib ; Nguyen, Tin ; Peyvandipour, Azam ; Draghici, Sorin ; Kelso, ed., Janet ( July 2019 , Bioinformatics)

   Recent advances in biomedical research have made massive amount of transcriptomic data available in public repositories from different sources. Due to the heterogeneity present in the individual experiments, identifying reproducible biomarkers for a given disease from multiple independent studies has become a major challenge. The widely used meta-analysis approaches, such as Fisher’s method, Stouffer’s method, minP and maxP, have at least two major limitations: (i) they are sensitive to outliers, and (ii) they perform only one statistical test for each individual study, and hence do not fully utilize the potential sample size to gain statistical power.

   Here, we propose a gene-level meta-analysis framework that overcomes these limitations and identifies a gene signature that is reliable and reproducible across multiple independent studies of a given disease. The approach provides a comprehensive global signature that can be used to understand the underlying biological phenomena, and a smaller test signature that can be used to classify future samples of a given disease. We demonstrate the utility of the framework by constructing disease signatures for influenza and Alzheimer’s disease using nine datasets including 1108 individuals. These signatures are then validated on 12 independent datasets including 912 individuals. The results indicate that the proposed approach performs better than the majority of the existing meta-analysis approaches in terms of both sensitivity as well as specificity. The proposed signatures could be further used in diagnosis, prognosis and identification of therapeutic targets.

   Supplementary data are available at Bioinformatics online.

    

   more » « less
4. Adaptive Deep Learning for Soft Real-Time Image Classification

   https://doi.org/https://doi.org/10.3390/technologies9010020  

   Chai, F ; Kang, K. D. ( March 2021 , Technologies)

   null (Ed.)

   CNNs (Convolutional Neural Networks) are becoming increasingly important for real-time applications, such as image classification in traffic control, visual surveillance, and smart manufacturing. It is challenging, however, to meet timing constraints of image processing tasks using CNNs due to their complexity. Performing dynamic trade-offs between the inference accuracy and time for image data analysis in CNNs is challenging too, since we observe that more complex CNNs that take longer to run even lead to lower accuracy in many cases by evaluating hundreds of CNN models in terms of time and accuracy using two popular data sets, MNIST and CIFAR-10. To address these challenges, we propose a new approach that (1) generates CNN models and analyzes their average inference time and accuracy for image classification, (2) stores a small subset of the CNNs with monotonic time and accuracy relationships offline, and (3) efficiently selects an effective CNN expected to support the highest possible accuracy among the stored CNNs subject to the remaining time to the deadline at run time. In our extensive evaluation, we verify that the CNNs derived by our approach are more flexible and cost-efficient than two baseline approaches. We verify that our approach can effectively build a compact set of CNNs and efficiently support systematic time vs. accuracy trade-offs, if necessary, to meet the user-specified timing and accuracy requirements. Moreover, the overhead of our approach is little/acceptable in terms of latency and memory consumption. 

   more » « less
5. Automated identification of diverse Neotropical pollen samples using convolutional neural networks

   https://doi.org/10.1111/2041-210X.13917  

   Punyasena, Surangi W. ; Haselhorst, Derek S. ; Kong, Shu ; Fowlkes, Charless C. ; Moreno, J. Enrique ( June 2022 , Methods in Ecology and Evolution)

   Pollen is used to investigate a diverse range of ecological problems, from identifying plant–pollinator relationships to tracking flowering phenology. Pollen types are identified according to a set of distinctive morphological characters which are understood to capture taxonomic differences and phylogenetic relationships among taxa. However, categorizing morphological variation among hyperdiverse pollen samples represents a challenge even for an expert analyst.

   We present an automated workflow for pollen analysis, from the automated scanning of pollen sample slides to the automated detection and identification of pollen taxa using convolutional neural networks (CNNs). We analysed aerial pollen samples from lowland Panama and used a microscope slide scanner to capture three‐dimensional representations of 150 sample slides. These pollen sample images were annotated by an expert using a virtual microscope. Metadata were digitally recorded for ~100 pollen grains per slide, including location, identification and the analyst's confidence of the given identification. We used these annotated images to train and test our detection and classification CNN models. Our approach is two‐part. We first compared three methods for training CNN models to detect pollen grains on a palynological slide. We next investigated approaches to training CNN models for pollen identification.

   Because the diversity of pollen taxa in environmental and palaeontological samples follows a long‐tailed distribution, we experimented with methods for addressing imbalanced representation using our most abundant 46 taxa. We found that properly weighting pollen taxa in our training objective functions yielded improved accuracy for individual taxa. Our average accuracy for the 46‐way classification problem was 82.3%. We achieved 89.5% accuracy for our 25 most abundant taxa.

   Pollen represents a challenging visual classification problem that can serve as a model for other areas of biology that rely on visual identification. Our results add to the body of research demonstrating the potential for a fully automated pollen classification system for environmental and palaeontological samples. Slide imaging, pollen detection and specimen identification can be automated to produce a streamlined workflow.

    

   more » « less