Deep Learning for Automatically Visual Evoked Potential Classification During Surgical Decompression of Sellar Region Tumors

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Purpose

Detection of the huge amount of data generated in real-time visual evoked potential (VEP) requires labor-intensive work and experienced electrophysiologists. This study aims to build an automatic VEP classification system by using a deep learning algorithm.

Methods

Patients with sellar region tumor and optic chiasm compression were enrolled. Flash VEP monitoring was applied during surgical decompression. Sequential VEP images were fed into three neural network algorithms to train VEP classification models.

Results

We included 76 patients. During surgical decompression, we observed 68 eyes with increased VEP amplitude, 47 eyes with a transient decrease, and 37 eyes without change. We generated 2,843 sequences (39,802 images) in total (887 sequences with increasing VEP, 276 sequences with decreasing VEP, and 1680 sequences without change). The model combining convolutional and recurrent neural network had the highest accuracy (87.4%; 95% confidence interval, 84.2%–90.1%). The sensitivity of predicting no change VEP, increasing VEP, and decreasing VEP was 92.6%, 78.9%, and 83.7%, respectively. The specificity of predicting no change VEP, increasing VEP, and decreasing VEP was 80.5%, 93.3%, and 100.0%, respectively. The class activation map visualization technique showed that the P2-N3-P3 complex was important in determining the output.

Conclusions

We identified three VEP responses (no change, increase, and decrease) during transsphenoidal surgical decompression of sellar region tumors. We developed a deep learning model to classify the sequential changes of intraoperative VEP.

Translational Relevance

Our model may have the potential to be applied in real-time monitoring during surgical resection of sellar region tumors.

Related collections

Most cited references 23

Record: found
Abstract: found
Article: found

Is Open Access

Recurrent Neural Networks for Multivariate Time Series with Missing Values

Zhengping Che, Sanjay Purushotham, Kyunghyun Cho … (2018)

Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, a.k.a., informative missingness. There is very limited work on exploiting the missing patterns for effective imputation and improving prediction performance. In this paper, we develop novel deep learning models, namely GRU-D, as one of the early attempts. GRU-D is based on Gated Recurrent Unit (GRU), a state-of-the-art recurrent neural network. It takes two representations of missing patterns, i.e., masking and time interval, and effectively incorporates them into a deep model architecture so that it not only captures the long-term temporal dependencies in time series, but also utilizes the missing patterns to achieve better prediction results. Experiments of time series classification tasks on real-world clinical datasets (MIMIC-III, PhysioNet) and synthetic datasets demonstrate that our models achieve state-of-the-art performance and provide useful insights for better understanding and utilization of missing values in time series analysis.

0 comments Cited 257 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: found

Is Open Access

Using recurrent neural network models for early detection of heart failure onset

Edward Choi, Andy Schuetz, Walter Stewart … (2016)

Objective: We explored whether use of deep learning to model temporal relations among events in electronic health records (EHRs) would improve model performance in predicting initial diagnosis of heart failure (HF) compared to conventional methods that ignore temporality. Materials and Methods: Data were from a health system’s EHR on 3884 incident HF cases and 28 903 controls, identified as primary care patients, between May 16, 2000, and May 23, 2013. Recurrent neural network (RNN) models using gated recurrent units (GRUs) were adapted to detect relations among time-stamped events (eg, disease diagnosis, medication orders, procedure orders, etc.) with a 12- to 18-month observation window of cases and controls. Model performance metrics were compared to regularized logistic regression, neural network, support vector machine, and K-nearest neighbor classifier approaches. Results: Using a 12-month observation window, the area under the curve (AUC) for the RNN model was 0.777, compared to AUCs for logistic regression (0.747), multilayer perceptron (MLP) with 1 hidden layer (0.765), support vector machine (SVM) (0.743), and K-nearest neighbor (KNN) (0.730). When using an 18-month observation window, the AUC for the RNN model increased to 0.883 and was significantly higher than the 0.834 AUC for the best of the baseline methods (MLP). Conclusion: Deep learning models adapted to leverage temporal relations appear to improve performance of models for detection of incident heart failure with a short observation window of 12–18 months.

0 comments Cited 191 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Differential diagnosis of sellar masses.

P. Freda, K Post (1999)

The differential diagnosis of nonpituitary sellar masses is broad; differentiating among potential etiologies may not always be straightforward because many of these lesions, tumorous and nontumorous, may mimic the clinical, endocrinologic, and radiologic presentations of pituitary adenomas. This article provides an overview of the clinical and radiographic characteristics of both pituitary tumors and the nonpituitary lesions found in the sellar/parasellar region and discusses, in detail, the specific nonpituitary origins of the sellar masses.

0 comments Cited 63 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Journal

Journal ID (nlm-ta): Transl Vis Sci Technol

Journal ID (iso-abbrev): Transl Vis Sci Technol

Journal ID (hwp): tvst

Journal ID (pmc): Transl Vis Sci Technol

Journal ID (publisher-id): TVST

Title: Translational Vision Science & Technology

Publisher: The Association for Research in Vision and Ophthalmology

ISSN (Electronic): 2164-2591

Publication date Collection: November 2019

Publication date (Electronic): 20 November 2019

Volume: 8

Issue: 6

Electronic Location Identifier: 21

Affiliations

[1 ]Shanghai Pituitary Tumor Center, Shanghai Neurosurgical Research Institute, Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China & Neuroendocrine Unit, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA

[2 ]Department of Ophthalmology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China & Putuo Oculopathy Dental Disease Prevention & Cure Clinic, Shanghai, China

[3 ]Shanghai Pituitary Tumor Center, Shanghai Neurosurgical Research Institute, Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China

[4 ]Department of Ophthalmology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China

Author notes

Correspondence: Yuyan Zhang, 12 Wulumuqi Zhong Road, Department of Ophthalmology, Huashan Hospital, Shanghai, China. e-mail: yuyan8688@ 123456163.com

Xuefei Shou, 12 Wulumuqi Zhong Road, Department of Neurosurgery, Huashan Hospital, Shanghai, China. e-mail: shouxf@ 123456hotmail.com

[*]

Nidan Qiao and Mengju Song contributed equally to the manuscript.

Article

Serial Item and Contribution ID: tvst-08-05-26 Publisher ID: TVST-19-1677

DOI: 10.1167/tvst.8.6.21

PMC ID: 6871542

SO-VID: 480eb81a-6871-41a9-b2bf-a87c737f51b5

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

History

Date received : 10 June 2019

Date accepted : 17 September 2019

Comments

Comment on this article

scite_

Smart Citations

Citing PublicationsSupportingMentioningContrasting

View Citations

See how this article has been cited at scite.ai

scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

Cited by 10

See all cited by

Most referenced authors 301

See all reference authors

Deep Learning for Automatically Visual Evoked Potential Classification During Surgical Decompression of Sellar Region Tumors

Read this article at

Abstract

Purpose

Methods

Results

Conclusions

Translational Relevance

Related collections

Data-Driven Civil Engineering

Most cited references 23

Recurrent Neural Networks for Multivariate Time Series with Missing Values

Using recurrent neural network models for early detection of heart failure onset

Differential diagnosis of sellar masses.

Author and article information

Journal

Affiliations

Author notes

Article

History

Categories

Comments

Comment on this article

Similar content 405

Cited by 10

Most referenced authors 301