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. 

The Temple University Hospital Seizure Detection Corpus (TUSZ) [1] has been in distribution since April 2017. It is a subset of the TUH EEG Corpus (TUEG) [2] and the most frequently requested corpus from our 3,000+ subscribers. It was recently featured as the challenge task in the Neureka 2020 Epilepsy Challenge [3]. A summary of the development of the corpus is shown below in Table 1. The TUSZ Corpus is a fully annotated corpus, which means every seizure event that occurs within its files has been annotated. The data is selected from TUEG using a screening process that identifies files most likely to contain seizures [1]. Approximately 7% of the TUEG data contains a seizure event, so it is important we triage TUEG for high yield data. One hour of EEG data requires approximately one hour of human labor to complete annotation using the pipeline described below, so it is important from a financial standpoint that we accurately triage data. A summary of the labels being used to annotate the data is shown in Table 2. Certain standards are put into place to optimize the annotation process while not sacrificing consistency. Due to the nature of EEG recordings, some records start off with a segment of calibration. This portion of the EEG is instantly recognizable and transitions from what resembles lead artifact to a flat line on all the channels. For the sake of seizure annotation, the calibration is ignored, and no time is wasted on it. During the identification of seizure events, a hard “3 second rule” is used to determine whether two events should be combined into a single larger event. This greatly reduces the time that it takes to annotate a file with multiple events occurring in succession. In addition to the required minimum 3 second gap between seizures, part of our standard dictates that no seizure less than 3 seconds be annotated. Although there is no universally accepted definition for how long a seizure must be, we find that it is difficult to discern with confidence between burst suppression or other morphologically similar impressions when the event is only a couple seconds long. This is due to several reasons, the most notable being the lack of evolution which is oftentimes crucial for the determination of a seizure. After the EEG files have been triaged, a team of annotators at NEDC is provided with the files to begin data annotation. An example of an annotation is shown in Figure 1. A summary of the workflow for our annotation process is shown in Figure 2. Several passes are performed over the data to ensure the annotations are accurate. Each file undergoes three passes to ensure that no seizures were missed or misidentified. The first pass of TUSZ involves identifying which files contain seizures and annotating them using our annotation tool. The time it takes to fully annotate a file can vary drastically depending on the specific characteristics of each file; however, on average a file containing multiple seizures takes 7 minutes to fully annotate. This includes the time that it takes to read the patient report as well as traverse through the entire file. Once an event has been identified, the start and stop time for the seizure is stored in our annotation tool. This is done on a channel by channel basis resulting in an accurate representation of the seizure spreading across different parts of the brain. Files that do not contain any seizures take approximately 3 minutes to complete. Even though there is no annotation being made, the file is still carefully examined to make sure that nothing was overlooked. In addition to solely scrolling through a file from start to finish, a file is often examined through different lenses. Depending on the situation, low pass filters are used, as well as increasing the amplitude of certain channels. These techniques are never used in isolation and are meant to further increase our confidence that nothing was missed. Once each file in a given set has been looked at once, the annotators start the review process. The reviewer checks a file and comments any changes that they recommend. This takes about 3 minutes per seizure containing file, which is significantly less time than the first pass. After each file has been commented on, the third pass commences. This step takes about 5 minutes per seizure file and requires the reviewer to accept or reject the changes that the second reviewer suggested. Since tangible changes are made to the annotation using the annotation tool, this step takes a bit longer than the previous one. Assuming 18% of the files contain seizures, a set of 1,000 files takes roughly 127 work hours to annotate. Before an annotator contributes to the data interpretation pipeline, they are trained for several weeks on previous datasets. A new annotator is able to be trained using data that resembles what they would see under normal circumstances. An additional benefit of using released data to train is that it serves as a means of constantly checking our work. If a trainee stumbles across an event that was not previously annotated, it is promptly added, and the data release is updated. It takes about three months to train an annotator to a point where their annotations can be trusted. Even though we carefully screen potential annotators during the hiring process, only about 25% of the annotators we hire survive more than one year doing this work. To ensure that the annotators are consistent in their annotations, the team conducts an interrater agreement evaluation periodically to ensure that there is a consensus within the team. The annotation standards are discussed in Ochal et al. [4]. An extended discussion of interrater agreement can be found in Shah et al. [5]. The most recent release of TUSZ, v1.5.2, represents our efforts to review the quality of the annotations for two upcoming challenges we hosted: an internal deep learning challenge at IBM [6] and the Neureka 2020 Epilepsy Challenge [3]. One of the biggest changes that was made to the annotations was the imposition of a stricter standard for determining the start and stop time of a seizure. Although evolution is still included in the annotations, the start times were altered to start when the spike-wave pattern becomes distinct as opposed to merely when the signal starts to shift from background. This cuts down on background that was mislabeled as a seizure. For seizure end times, all post ictal slowing that was included was removed. The recent release of v1.5.2 did not include any additional data files. Two EEG files had been added because, originally, they were corrupted in v1.5.1 but were able to be retrieved and added for the latest release. The progression from v1.5.0 to v1.5.1 and later to v1.5.2, included the re-annotation of all of the EEG files in order to develop a confident dataset regarding seizure identification. Starting with v1.4.0, we have also developed a blind evaluation set that is withheld for use in competitions. The annotation team is currently working on the next release for TUSZ, v1.6.0, which is expected to occur in August 2020. It will include new data from 2016 to mid-2019. This release will contain 2,296 files from 2016 as well as several thousand files representing the remaining data through mid-2019. In addition to files that were obtained with our standard triaging process, a part of this release consists of EEG files that do not have associated patient reports. Since actual seizure events are in short supply, we are mining a large chunk of data for which we have EEG recordings but no reports. Some of this data contains interesting seizure events collected during long-term EEG sessions or data collected from patients with a history of frequent seizures. It is being mined to increase the number of files in the corpus that have at least one seizure event. We expect v1.6.0 to be released before IEEE SPMB 2020. 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/. 

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/. 

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. 

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 Neural Engineering Data Consortium (NEDC) is developing a large open source database of high-resolution digital pathology images known as the Temple University Digital Pathology Corpus (TUDP) [1]. Our long-term goal is to release one million images. We expect to release the first 100,000 image corpus by December 2020. The data is being acquired at the Department of Pathology at Temple University Hospital (TUH) using a Leica Biosystems Aperio AT2 scanner [2] and consists entirely of clinical pathology images. More information about the data and the project can be found in Shawki et al. [3]. We currently have a National Science Foundation (NSF) planning grant [4] to explore how best the community can leverage this resource. One goal of this poster presentation is to stimulate community-wide discussions about this project and determine how this valuable resource can best meet the needs of the public. The computing infrastructure required to support this database is extensive [5] and includes two HIPAA-secure computer networks, dual petabyte file servers, and Aperio’s eSlide Manager (eSM) software [6]. We currently have digitized over 50,000 slides from 2,846 patients and 2,942 clinical cases. There is an average of 12.4 slides per patient and 10.5 slides per case with one report per case. The data is organized by tissue type as shown below: Filenames: tudp/v1.0.0/svs/gastro/000001/00123456/2015_03_05/0s15_12345/0s15_12345_0a001_00123456_lvl0001_s000.svs tudp/v1.0.0/svs/gastro/000001/00123456/2015_03_05/0s15_12345/0s15_12345_00123456.docx Explanation: tudp: root directory of the corpus v1.0.0: version number of the release svs: the image data type gastro: the type of tissue 000001: six-digit sequence number used to control directory complexity 00123456: 8-digit patient MRN 2015_03_05: the date the specimen was captured 0s15_12345: the clinical case name 0s15_12345_0a001_00123456_lvl0001_s000.svs: the actual image filename consisting of a repeat of the case name, a site code (e.g., 0a001), the type and depth of the cut (e.g., lvl0001) and a token number (e.g., s000) 0s15_12345_00123456.docx: the filename for the corresponding case report We currently recognize fifteen tissue types in the first installment of the corpus. The raw image data is stored in Aperio’s “.svs” format, which is a multi-layered compressed JPEG format [3,7]. Pathology reports containing a summary of how a pathologist interpreted the slide are also provided in a flat text file format. A more complete summary of the demographics of this pilot corpus will be presented at the conference. Another goal of this poster presentation is to share our experiences with the larger community since many of these details have not been adequately documented in scientific publications. There are quite a few obstacles in collecting this data that have slowed down the process and need to be discussed publicly. Our backlog of slides dates back to 1997, meaning there are a lot that need to be sifted through and discarded for peeling or cracking. Additionally, during scanning a slide can get stuck, stalling a scan session for hours, resulting in a significant loss of productivity. Over the past two years, we have accumulated significant experience with how to scan a diverse inventory of slides using the Aperio AT2 high-volume scanner. We have been working closely with the vendor to resolve many problems associated with the use of this scanner for research purposes. This scanning project began in January of 2018 when the scanner was first installed. The scanning process was slow at first since there was a learning curve with how the scanner worked and how to obtain samples from the hospital. From its start date until May of 2019 ~20,000 slides we scanned. In the past 6 months from May to November we have tripled that number and how hold ~60,000 slides in our database. This dramatic increase in productivity was due to additional undergraduate staff members and an emphasis on efficient workflow. The Aperio AT2 scans 400 slides a day, requiring at least eight hours of scan time. The efficiency of these scans can vary greatly. When our team first started, approximately 5% of slides failed the scanning process due to focal point errors. We have been able to reduce that to 1% through a variety of means: (1) best practices regarding daily and monthly recalibrations, (2) tweaking the software such as the tissue finder parameter settings, and (3) experience with how to clean and prep slides so they scan properly. Nevertheless, this is not a completely automated process, making it very difficult to reach our production targets. With a staff of three undergraduate workers spending a total of 30 hours per week, we find it difficult to scan more than 2,000 slides per week using a single scanner (400 slides per night x 5 nights per week). The main limitation in achieving this level of production is the lack of a completely automated scanning process, it takes a couple of hours to sort, clean and load slides. We have streamlined all other aspects of the workflow required to database the scanned slides so that there are no additional bottlenecks. To bridge the gap between hospital operations and research, we are using Aperio’s eSM software. Our goal is to provide pathologists access to high quality digital images of their patients’ slides. eSM is a secure website that holds the images with their metadata labels, patient report, and path to where the image is located on our file server. Although eSM includes significant infrastructure to import slides into the database using barcodes, TUH does not currently support barcode use. Therefore, we manage the data using a mixture of Python scripts and manual import functions available in eSM. The database and associated tools are based on proprietary formats developed by Aperio, making this another important point of community-wide discussion on how best to disseminate such information. Our near-term goal for the TUDP Corpus is to release 100,000 slides by December 2020. We hope to continue data collection over the next decade until we reach one million slides. We are creating two pilot corpora using the first 50,000 slides we have collected. The first corpus consists of 500 slides with a marker stain and another 500 without it. This set was designed to let people debug their basic deep learning processing flow on these high-resolution images. We discuss our preliminary experiments on this corpus and the challenges in processing these high-resolution images using deep learning in [3]. We are able to achieve a mean sensitivity of 99.0% for slides with pen marks, and 98.9% for slides without marks, using a multistage deep learning algorithm. While this dataset was very useful in initial debugging, we are in the midst of creating a new, more challenging pilot corpus using actual tissue samples annotated by experts. The task will be to detect ductal carcinoma (DCIS) or invasive breast cancer tissue. There will be approximately 1,000 images per class in this corpus. Based on the number of features annotated, we can train on a two class problem of DCIS or benign, or increase the difficulty by increasing the classes to include DCIS, benign, stroma, pink tissue, non-neoplastic etc. Those interested in the corpus or in participating in community-wide discussions should join our listserv, nedc_tuh_dpath@googlegroups.com, to be kept informed of the latest developments in this project. You can learn more from our project website: https://www.isip.piconepress.com/projects/nsf_dpath. 

The goal of this work was to design a low-cost computing facility that can support the development of an open source digital pathology corpus containing 1M images [1]. A single image from a clinical-grade digital pathology scanner can range in size from hundreds of megabytes to five gigabytes. A 1M image database requires over a petabyte (PB) of disk space. To do meaningful work in this problem space requires a significant allocation of computing resources. The improvements and expansions to our HPC (highperformance computing) cluster, known as Neuronix [2], required to support working with digital pathology fall into two broad categories: computation and storage. To handle the increased computational burden and increase job throughput, we are using Slurm [3] as our scheduler and resource manager. For storage, we have designed and implemented a multi-layer filesystem architecture to distribute a filesystem across multiple machines. These enhancements, which are entirely based on open source software, have extended the capabilities of our cluster and increased its cost-effectiveness. Slurm has numerous features that allow it to generalize to a number of different scenarios. Among the most notable is its support for GPU (graphics processing unit) scheduling. GPUs can offer a tremendous performance increase in machine learning applications [4] and Slurm’s built-in mechanisms for handling them was a key factor in making this choice. Slurm has a general resource (GRES) mechanism that can be used to configure and enable support for resources beyond the ones provided by the traditional HPC scheduler (e.g. memory, wall-clock time), and GPUs are among the GRES types that can be supported by Slurm [5]. In addition to being able to track resources, Slurm does strict enforcement of resource allocation. This becomes very important as the computational demands of the jobs increase, so that they have all the resources they need, and that they don’t take resources from other jobs. It is a common practice among GPU-enabled frameworks to query the CUDA runtime library/drivers and iterate over the list of GPUs, attempting to establish a context on all of them. Slurm is able to affect the hardware discovery process of these jobs, which enables a number of these jobs to run alongside each other, even if the GPUs are in exclusive-process mode. To store large quantities of digital pathology slides, we developed a robust, extensible distributed storage solution. We utilized a number of open source tools to create a single filesystem, which can be mounted by any machine on the network. At the lowest layer of abstraction are the hard drives, which were split into 4 60-disk chassis, using 8TB drives. To support these disks, we have two server units, each equipped with Intel Xeon CPUs and 128GB of RAM. At the filesystem level, we have implemented a multi-layer solution that: (1) connects the disks together into a single filesystem/mountpoint using the ZFS (Zettabyte File System) [6], and (2) connects filesystems on multiple machines together to form a single mountpoint using Gluster [7]. ZFS, initially developed by Sun Microsystems, provides disk-level awareness and a filesystem which takes advantage of that awareness to provide fault tolerance. At the filesystem level, ZFS protects against data corruption and the infamous RAID write-hole bug by implementing a journaling scheme (the ZFS intent log, or ZIL) and copy-on-write functionality. Each machine (1 controller + 2 disk chassis) has its own separate ZFS filesystem. Gluster, essentially a meta-filesystem, takes each of these, and provides the means to connect them together over the network and using distributed (similar to RAID 0 but without striping individual files), and mirrored (similar to RAID 1) configurations [8]. By implementing these improvements, it has been possible to expand the storage and computational power of the Neuronix cluster arbitrarily to support the most computationally-intensive endeavors by scaling horizontally. We have greatly improved the scalability of the cluster while maintaining its excellent price/performance ratio [1].