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. Broadacre Crop Yield Estimation Using Imaging Spectroscopy from Unmanned Aerial Systems (UAS): A Field-Based Case Study with Snap Bean

   https://doi.org/10.3390/rs13163241  

   Hassanzadeh, Amirhossein ; Zhang, Fei ; van Aardt, Jan ; Murphy, Sean P. ; Pethybridge, Sarah J. ( August 2021 , Remote Sensing)

   null (Ed.)

   Accurate, precise, and timely estimation of crop yield is key to a grower’s ability to proactively manage crop growth and predict harvest logistics. Such yield predictions typically are based on multi-parametric models and in-situ sampling. Here we investigate the extension of a greenhouse study, to low-altitude unmanned aerial systems (UAS). Our principal objective was to investigate snap bean crop (Phaseolus vulgaris) yield using imaging spectroscopy (hyperspectral imaging) in the visible to near-infrared (VNIR; 400–1000 nm) region via UAS. We aimed to solve the problem of crop yield modelling by identifying spectral features explaining yield and evaluating the best time period for accurate yield prediction, early in time. We introduced a Python library, named Jostar, for spectral feature selection. Embedded in Jostar, we proposed a new ranking method for selected features that reaches an agreement between multiple optimization models. Moreover, we implemented a well-known denoising algorithm for the spectral data used in this study. This study benefited from two years of remotely sensed data, captured at multiple instances over the summers of 2019 and 2020, with 24 plots and 18 plots, respectively. Two harvest stage models, early and late harvest, were assessed at two different locations in upstate New York, USA. Six varieties of snap bean were quantified using two components of yield, pod weight and seed length. We used two different vegetation detection algorithms. the Red-Edge Normalized Difference Vegetation Index (RENDVI) and Spectral Angle Mapper (SAM), to subset the fields into vegetation vs. non-vegetation pixels. Partial least squares regression (PLSR) was used as the regression model. Among nine different optimization models embedded in Jostar, we selected the Genetic Algorithm (GA), Ant Colony Optimization (ACO), Simulated Annealing (SA), and Particle Swarm Optimization (PSO) and their resulting joint ranking. The findings show that pod weight can be explained with a high coefficient of determination (R2 = 0.78–0.93) and low root-mean-square error (RMSE = 940–1369 kg/ha) for two years of data. Seed length yield assessment resulted in higher accuracies (R2 = 0.83–0.98) and lower errors (RMSE = 4.245–6.018 mm). Among optimization models used, ACO and SA outperformed others and the SAM vegetation detection approach showed improved results when compared to the RENDVI approach when dense canopies were being examined. Wavelengths at 450, 500, 520, 650, 700, and 760 nm, were identified in almost all data sets and harvest stage models used. The period between 44–55 days after planting (DAP) the optimal time period for yield assessment. Future work should involve transferring the learned concepts to a multispectral system, for eventual operational use; further attention should also be paid to seed length as a ground truth data collection technique, since this yield indicator is far more rapid and straightforward. 

   more » « less
3. The Deep Learning Epilepsy Detection Challenge: Design, Implementation, and Test of a New Crowd-Sourced AI Challenge Ecosystem

   Kiral, Isabell ; Roy, Subhrajit ; Mummert, Todd ; Braz, Alan ; Tsay, Jason ; Tang, Jianbin ; Asif, Umar ; Schaffter, Thomas ; Mehmet, Eren ; Picone, Joseph ; et al ( April 2019 , Challenges in Machine Learning Competitions for All (CiML))

   null (Ed.)

   The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 

   more » « less
4. Decreasing False-alarm Rates in CNN-based Solar Flare Prediction Using SDO/HMI Data

   https://doi.org/10.3847/1538-4365/ac5b0c  

   Deshmukh, Varad ; Flyer, Natasha ; van der Sande, Kiera ; Berger, Thomas ( May 2022 , The Astrophysical Journal Supplement Series)

   A hybrid two-stage machine-learning architecture that addresses the problem of excessive false positives (false alarms) in solar flare prediction systems is investigated. The first stage is a convolutional neural network (CNN) model based on the VGG-16 architecture that extracts features from a temporal stack of consecutive Solar Dynamics Observatory Helioseismic and Magnetic Imager magnetogram images to produce a flaring probability. The probability of flaring is added to a feature vector derived from the magnetograms to train an extremely randomized trees (ERT) model in the second stage to produce a binary deterministic prediction (flare/no-flare) in a 12 hr forecast window. To tune the hyperparameters of the architecture, a new evaluation metric is introduced: the “scaled True Skill Statistic.” It specifically addresses the large discrepancy between the true positive rate and the false positive rate in the highly unbalanced solar flare event training data sets. Through hyperparameter tuning to maximize this new metric, our two-stage architecture drastically reduces false positives by ≈48% without significantly affecting the true positives (reduction by ≈12%), when compared with predictions from the first-stage CNN alone. This, in turn, improves various traditional binary classification metrics sensitive to false positives, such as the precision, F1, and the Heidke Skill Score. The end result is a more robust 12 hr flare prediction system that could be combined with current operational flare-forecasting methods. Additionally, using the ERT-based feature-ranking mechanism, we show that the CNN output probability is highly ranked in terms of flare prediction relevance.

    

   more » « less
5. Accounting for Phenology in the Analysis of Animal Movement

   https://doi.org/10.1111/biom.13052  

   Scharf, Henry R. ; Hooten, Mevin B. ; Wilson, Ryan R. ; Durner, George M. ; Atwood, Todd C. ( March 2019 , Biometrics)

   The analysis of animal tracking data provides important scientific understanding and discovery in ecology. Observations of animal trajectories using telemetry devices provide researchers with information about the way animals interact with their environment and each other. For many species, specific geographical features in the landscape can have a strong effect on behavior. Such features may correspond to a single point (eg, dens or kill sites), or to higher dimensional subspaces (eg, rivers or lakes). Features may be relatively static in time (eg, coastlines or home-range centers), or may be dynamic (eg, sea ice extent or areas of high-quality forage for herbivores). We introduce a novel model for animal movement that incorporates active selection for dynamic features in a landscape. Our approach is motivated by the study of polar bear (Ursus maritimus) movement. During the sea ice melt season, polar bears spend much of their time on sea ice above shallow, biologically productive water where they hunt seals. The changing distribution and characteristics of sea ice throughout the year mean that the location of valuable habitat is constantly shifting. We develop a model for the movement of polar bears that accounts for the effect of this important landscape feature. We introduce a two-stage procedure for approximate Bayesian inference that allows us to analyze over 300 000 observed locations of 186 polar bears from 2012 to 2016. We use our model to estimate a spatial boundary of interest to wildlife managers that separates two subpopulations of polar bears from the Beaufort and Chukchi seas.

    

   more » « less