Search for: All records

The evaluation of machine learning algorithms in biomedical fields for ap-plications involving sequential data lacks both rigor and standardization. Common quantitative scalar evaluation metrics such as sensitivity and specificity can often be misleading and not accurately integrate application requirements. Evaluation metrics must ultimately reflect the needs of users yet be sufficiently sensitive to guide algorithm development. For example, feedback from critical care clinicians who use automated event detection software in clinical applications has been overwhelmingly emphatic that a low false alarm rate, typically measured in units of the number of errors per 24 hours, is the single most important criterion for user acceptance. Though using a single metric is not often as insightful as examining performance over a range of operating conditions, there is, nevertheless, a need for a sin-gle scalar figure of merit. In this chapter, we discuss the deficiencies of existing metrics for a seizure detection task and propose several new metrics that offer a more balanced view of performance. We demonstrate these metrics on a seizure detection task based on the TUH EEG Seizure Corpus. We introduce two promising metrics: (1) a measure based on a concept borrowed from the spoken term detection literature, Actual Term-Weighted Value, and (2) a new metric, Time-Aligned Event Scoring (TAES), that accounts for the temporal align-ment of the hypothesis to the reference annotation. We demonstrate that state of the art technology based on deep learning, though impressive in its performance, still needs significant improvement before it will meet very strict user acceptance guidelines. 

There has been a lack of standardization of the evaluation of sequential decoding systems in the bioengineering community. Assessment of the accuracy of a candidate system’s segmentations and measurement of a false alarm rate are examples of two performance metrics that are very critical to the operational acceptance of a technology. However, measurement of such quantities in a consistent manner require many scoring software implementation details to be resolved. Results can be highly sensitive to these implementation details. In this paper, we revisit and evaluate a set of metrics introduced in our open source scoring software for sequential decoding of multichannel signals. This software was used to rank sixteen automatic seizure detection systems recently developed for the 2020 Neureka® Epilepsy Challenge. The systems produced by the participants provided us with a broad range of design variations that allowed assessment of the consistency of the proposed metrics. We present a comprehensive assessment of four of these new metrics and validate our findings with our previous studies. We also validate a proposed new metric, time-aligned event scoring, that focuses on the segmentation behavior of an algorithm. We demonstrate how we can gain insight into the performance of a system using these metrics. 

The Neural Engineering Data Consortium has recently developed a new subset of its popular open source EEG corpus – TUH EEG (TUEG) [1]. The TUEG Corpus is the world’s largest open source corpus of EEG data and currently has over 3,300 subscribers. There are several valuable subsets of this data, including the TUH Seizure Detection Corpus (TUSZ) [2], which was featured in the Neureka 2020 Epilepsy Challenge [3]. In this poster, we present a new subset of the TUEG Corpus – the TU Artifact Corpus. This corpus contains 310 EEG files in which every artifact has been annotated. This data can be used to evaluate artifact reduction technology. Since TUEG is comprised of actual clinical data, the set of artifacts appearing in the data is rich and challenging. EEG artifacts are defined as waveforms that are not of cerebral origin and may be affected by numerous external and or physiological factors. These extraneous signals are often mistaken for seizures due to their morphological similarity in amplitude and frequency [4]. Artifacts often lead to raised false alarm rates in machine learning systems, which poses a major challenge for machine learning research. Most state-of-the-art systems use some form of artifact reduction technology to suppress these events. The corpus was annotated using a five-way classification that was developed to meet the needs of our constituents. Brief descriptions of each form of the artifact are provided in Ochal et al. [4]. The five basic tags are: • Chewing (CHEW): An artifact resulting from the tensing and relaxing of the jaw muscles. Chewing is a subset of the muscle artifact class. Chewing has the same characteristic high frequency sharp waves with 0.5 sec baseline periods between bursts. This artifact is generally diffuse throughout the different regions of the brain. However, it might have a higher level of activity in one hemisphere. Classification of a muscle artifact as chewing often depends on whether the accompanying patient report mentions any chewing, since other muscle artifacts can appear superficially similar to chewing artifact. • Electrode (ELEC): An electrode artifact encompasses various electrode related artifacts. Electrode pop is an artifact characterized by channels using the same electrode “spiking” with an electrographic phase reversal. Electrostatic is an artifact caused by movement or interference of electrodes and or the presence of dissimilar metals. A lead artifact is caused by the movement of electrodes from the patient’s head and or poor connection of electrodes. This results in disorganized and high amplitude slow waves. • Eye Movement (EYEM): A spike-like waveform created during patient eye movement. This artifact is usually found on all of the frontal polar electrodes with occasional echoing on the frontal electrodes. • Muscle (MUSC): A common artifact with high frequency, sharp waves corresponding to patient movement. These waveforms tend to have a frequency above 30 Hz with no specific pattern, often occurring because of agitation in the patient. • Shiver (SHIV): A specific and sustained sharp wave artifact that occurs when a patient shivers, usually seen on all or most channels. Shivering is a relatively rare subset of the muscle artifact class. Since these artifacts can overlap in time, a concatenated label format was implemented as a compromise between the limitations of our annotation tool and the complexity needed in an annotation data structure used to represent these overlapping events. We distribute an XML format that easily handles overlapping events. Our annotation tool [5], like most annotation tools of this type, is limited to displaying and manipulating a flat or linear annotation. Therefore, we encode overlapping events as a series of concatenated names using symbols such as: • EYEM+CHEW: eye movement and chewing • EYEM+SHIV: eye movement and shivering • CHEW+SHIV: chewing and shivering An example of an overlapping annotation is shown below in Figure 1. This release is an update of TUAR v1.0.0, which was a partially annotated database. In v1.0.0, a similar five way system was used as well as an additional “null” tag. The “null” tag covers anything that was not annotated, including instances of artifact. Only a limited number of artifacts were annotated in v1.0.0. In this updated version, every instance of an artifact is annotated; ultimately, this provides the user with confidence that any part of the record that is not annotated with one of the five classes does not contain an artifact. No new files, patients, or sessions were added in v2.0.0. However, the data was reannotated with these standards. The total number of files remains the same, but the number of artifact events increases significantly. Complete statistics will be provided on the corpus once annotation is complete and the data is released. This is expected to occur in early July – just after the IEEE SPMB submission deadline. The TUAR Corpus is an open-source database that is currently available for use by any registered member of our consortium. To register and receive access, please follow the instructions provided at this web page: https://www.isip.piconepress.com/projects/tuh_eeg/html/downloads.shtml. The data is located here: https://www.isip.piconepress.com/projects/tuh_eeg/downloads/tuh_eeg_artifact/v2.0.0/. 

Scalp electroencephalograms (EEGs) are the primary means by which phy-sicians diagnose brain-related illnesses such as epilepsy and seizures. Au-tomated seizure detection using clinical EEGs is a very difficult machine learning problem due to the low fidelity of a scalp EEG signal. Neverthe-less, despite the poor signal quality, clinicians can reliably diagnose ill-nesses from visual inspection of the signal waveform. Commercially avail-able automated seizure detection systems, however, suffer from unaccepta-bly high false alarm rates. Deep learning algorithms that require large amounts of training data have not previously been effective on this task due to the lack of big data resources necessary for building such models and the complexity of the signals involved. The evolution of big data science, most notably the release of the Temple University EEG (TUEG) Corpus, has mo-tivated renewed interest in this problem. In this chapter, we discuss the application of a variety of deep learning ar-chitectures to automated seizure detection. Architectures explored include multilayer perceptrons, convolutional neural networks (CNNs), long short-term memory networks (LSTMs), gated recurrent units and residual neural networks. We use the TUEG Corpus, supplemented with data from Duke University, to evaluate the performance of these hybrid deep structures. Since TUEG contains a significant amount of unlabeled data, we also dis-cuss unsupervised pre-training methods used prior to training these com-plex recurrent networks. Exploiting spatial and temporal context is critical for accurate disambigua-tion of seizures from artifacts. We explore how effectively several conven-tional architectures are able to model context and introduce a hybrid system that integrates CNNs and LSTMs. The primary error modalities observed by this state-of-the-art system were false alarms generated during brief delta range slowing patterns such as intermittent rhythmic delta activity. A varie-ty of these types of events have been observed during inter-ictal and post-ictal stages. Training models on such events with diverse morphologies has the potential to significantly reduce the remaining false alarms. This is one reason we are continuing our efforts to annotate a larger portion of TUEG. Increasing the data set size significantly allows us to leverage more ad-vanced machine learning methodologies. 

The goal of this document is to describe the file formats used to store annotations for the Temple University Hospital EEG (TUEG) Corpus (Obeid & Picone, 2016). Subsets of the corpus have been manually annotated (Veloso et al., 2017) and are available from our project web site (Choi et al., 2017). These annotations are stored in two formats: a label file (*.lbl*) that represents an annotation as a hierarchical graph, and a time-synchronous event file (*.tse*) that represents an annotation as a flat series of events with start and stop times, type of seizure, and probability. In this document, we describe each of these formats. Tools to read and display this information are also available from our project web site (Capp et al., 2018; McHugh & Picone, 2016). 

Objective: To demonstrate that combining automatic processing of EEG data using high performance machine learning algorithms with manual review by expert annotators can quickly identify subjects with prolonged seizures. Background: Prolonged seizures are markers of seizure severity, risk of transformation into status epilepticus, and medical morbidity. Early recognition of prolonged seizures permits intervention and reduces morbidity. Design/Methods: We triaged the TUH EEG Corpus, an open source database of EEGs, by running a state-of-the-art hybrid LSTM-based deep learning system. Then, we postprocessed the output to identify high confidence hypotheses for seizures that were greater than three minutes in duration. Results: The triaging method selected 25 subjects for further review. 17 subjects had seizures; only 5 met criteria for seizures greater than 3 minutes. 11 subjects did not have a prior diagnosis of epilepsy. Among these, 63% had acute respiratory failure and 36% had cardiac arrest leading to seizures secondary to anoxic brain injury. 18 (72%) EEGs were obtained in long-term monitoring (LTM), 1 (4%) in the epilepsy monitoring unit (EMU), and 6 (24%) as a routine EEG (rEEG). 72.2% of seizures in LTM were identified correctly versus 66.7% in rEEGs. Of the 9 subjects who were deceased, 7 (78%) had been on LTM. The seizure detection algorithm misidentified seizures in 7 subjects (28%). A total of 22 (88%) subjects had some ictal pattern. Patterns mistaken for seizure activity included muscle artifact, generalized periodic discharges, generalized spike-and-wave, triphasic waves, and interestingly, an EEG recording captured during CPR. Conclusions: This hybrid approach, which combines state-of-the-art machine learning seizure detection software with human annotation, successfully identified prolonged seizures in 72% of subjects; 88% had ictal patterns. Prolonged seizures were more common in LTM subjects than the EMU and were associated with acute cardiac or pulmonary insult. 

The goal of this report is to describe to users of the TUH EEG Corpus four important concepts that must be understood to correctly retrieve EEG signals from a data file (e.g., an EDF file). The four key concepts described in this document are: (1) physical placement: the location of the electrodes on the scalp, (2) unipolar montage: the differential recording process used to reduce noise, (3) channel labels: the system used to describe the channels, or digital signals, represented in a computer file and (4) bipolar montages: the differential mapping used to accentuate clinically-relevant events in the signal. This report is not intended to be a primer on the electrophysiology of an EEG, which is a subject unto itself, or a tutorial on how neurologists interpret EEGs. This report simply explains how the signal data in an EEG file must be accessed to accurately support clinical applications (e.g., manual interpretation or annotation of an EEG) and research applications (e.g., automatic interpretation using machine learning). 

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.