Machine learning algorithm for automatic detection of CT-identifiable hyperdense lesions associated with traumatic brain injury

Murthy, Krishna Nand Keshava; Leary, Owen P.; Merck, Lisa H.; Kimia, Benjamin B.; Collins, Scott; Wright, David W.; Allen, Jason W.; Brock, Jeffrey; Merck, Derek

doi:10.1117/12.2254227

Cited by 13 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Outcomes of TBI were predicted using deep-learning algorithms using DTI [136]. A combination of support vector machines (SVMs) and deep learning algorithms were combined to identify hyperdense lesions associated with TBI using CT [137]. For example, support vector machines identified that cortical thickness was decreased compared to age-matched controls in military personal who had experienced TBIs [138].…”

Section: Future Technologiesmentioning

confidence: 99%

Neuroimaging of Traumatic Brain Injury

Douglas

Toffoli

et al. 2018

Medical Sciences

View full text Add to dashboard Cite

The purpose of this article is to review conventional and advanced neuroimaging techniques performed in the setting of traumatic brain injury (TBI). The primary goal for the treatment of patients with suspected TBI is to prevent secondary injury. In the setting of a moderate to severe TBI, the most appropriate initial neuroimaging examination is a noncontrast head computed tomography (CT), which can reveal life-threatening injuries and direct emergent neurosurgical intervention. We will focus much of the article on advanced neuroimaging techniques including perfusion imaging and diffusion tensor imaging and discuss their potentials and challenges. We believe that advanced neuroimaging techniques may improve the accuracy of diagnosis of TBI and improve management of TBI.

show abstract

Section: Future Technologiesmentioning

confidence: 99%

Neuroimaging of Traumatic Brain Injury

Douglas

Toffoli

et al. 2018

Medical Sciences

View full text Add to dashboard Cite

show abstract

“…By comparing the performances of all these classifiers, ANN trained by using the stochastic gradient descent algorithm exhibits enhanced performance of increasing the accuracy to about 95% and decreasing the standard deviation to value of 14.69. [16] The study implemented ML and computer vision techniques for developing a system that detects CT-identifiable lesions automatically. It employed SIFT and CNN for feature identification that differentiates TBI lesions from the available background.…”

Section: Related Workmentioning

confidence: 99%

Diagnosis of Brain Hemorrhage Using KNN based Radial Basis Classifier

Desan¹

2019

IJATCSE

View full text Add to dashboard Cite

There occurs a peak interest in medical diagnosis with the aid of machine learning. One of the common old age disease is the Alzheimer disease and it is significant for accurate diagnosis of Brain hemorrhage in AD patients on the basis of image processing and machine learning approaches. Brain hemorrhage is the leading death cause between the age group of fifteen and twenty four. Lifesaving of such kind of patients is crucial and totally depends on the identification of the exact location and hemorrhage type in very early stage. The proposed method designed a fully automated machine learning approach for the classification by the novel KNNRBF method of disease with respect to its severity levels (Brain hemorrhage, PICS and Alzheimer disease) even in the absence of an expert. The performance analysis of the proposed system with respect to the performance measures like accuracy, specificity, sensitivity, Jaccard coefficient, kappa and dice coefficient respectively. The future work deals with the implementation of the model in deep learning and in realtime as a radiology optimization tool.

show abstract

“…Machine learning (ML) algorithms have been exploited to detect traumatic brain injury using the support vector machine (SVM) model [9] and to predict cerebral ischemia in subarachnoid hemorrhage using various ML algorithms [10]. However, ML approaches require extensive image preprocessing, manual feature extraction, and selection steps; all of which are complicated and timeconsuming.…”

Section: Introductionmentioning

confidence: 99%

Ensembled Deep Neural Network for Intracranial Hemorrhage Detection and Subtype Classification on Noncontrast CT Images

Wu¹,

Supanich²,

Deng³

2021

JoAIMS

View full text Add to dashboard Cite

Rapid and accurate diagnosis of intracranial hemorrhage is clinically significant to ensure timely treatment. In this study, we developed an ensembled deep neural network for the detection and subtype classification of intracranial hemorrhage. The model consisted of two parallel network pathways, one using three different window level/width settings to enhance the image contrast of brain, blood, and soft tissue. The other extracted spatial information of adjacent image slices to the target slice. Both pathways exploited the EfficientNet-B0 as the basic architecture and were ensembled to generate the final prediction. Class activation mapping was applied in both pathways to highlight the regions of detected hemorrhage and the associated subtypes. The model was trained and tested using Intracranial Hemorrhage Detection Challenge (IHDC) dataset launched by the Radiological Society of North America (RSNA) in 2019, which contained 674,258 head noncontrasts computer tomography images acquired from 19,530 patients. An independent dataset (CQ500) acquired from another institution was used to test the generalizability of the trained model. The overall accuracy, sensitivity, and F1 score for intracranial hemorrhage detection were 95.7%, 85.9%, and 86.7% on IHDC testing dataset and 92.4%, 92.6%, and 93.4% on external CQ500 testing dataset. The heatmaps by class activation mapping successfully demonstrated discriminative feature regions of the predicted hemorrhage locations and subtypes, providing visual guidance for radiologists to assist in rapid diagnosis of intracranial hemorrhage.

show abstract

Machine learning algorithm for automatic detection of CT-identifiable hyperdense lesions associated with traumatic brain injury

Cited by 13 publications

References 33 publications

Neuroimaging of Traumatic Brain Injury

Neuroimaging of Traumatic Brain Injury

Diagnosis of Brain Hemorrhage Using KNN based Radial Basis Classifier

Ensembled Deep Neural Network for Intracranial Hemorrhage Detection and Subtype Classification on Noncontrast CT Images

Contact Info

Product

Resources

About