Cerebral microbleed detection in traumatic brain injury patients using 3D convolutional neural networks

Standvoss, Kai; Crijns, T.; Goerke, L.; Janssen, Dirk-Jan; Kern, Simon; Niedek, Timo van; Vugt, Joke J.F.A. van; Burgos, Ninon; Gerritse, Emma J.; Mol, Jan-Quinten; Vooren, D. van de; Ghafoorian, Mohsen; Heuvel, Thomas L. A. van den; Manniesing, Rashindra

doi:10.1117/12.2294016

Cited by 8 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In classification tasks, cross-entropy loss is usually employed. This was also used in previous works on CMB detection ( Dou et al, 2016 , Standvoss et al, 2018 , Liu et al, 2019 ). Both cross-entropy (CE) and Dice loss are commonly used for training segmentation networks.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Automated detection of cerebral microbleeds via segmentation in susceptibility-weighted images of patients with traumatic brain injury

Koschmieder

Paul

Heuvel

et al. 2022

NeuroImage: Clinical

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

“… Liu et al (2019) trained and evaluated a system for a variety of CMB populations, including a cohort of mild TBI patients. Standvoss et al (2018) investigated the use of CNNs in moderate to severe TBI cases in a smaller cohort.…”

Section: Introductionmentioning

confidence: 99%

Automated detection of cerebral microbleeds via segmentation in susceptibility-weighted images of patients with traumatic brain injury

Koschmieder

Paul

Heuvel

et al. 2022

NeuroImage: Clinical

View full text Add to dashboard Cite

“…This method had a sensitivity of 93% and outperformed prior methods of detection. Standvoss et al [ 87 ] detected CMBs in traumatic brain injury. In their study, the authors prepared three types of 3D architectures with varying depths, i.e., three, five and eight layers.…”

Section: Applications In 3d Medical Imagingmentioning

confidence: 99%

3D Deep Learning on Medical Images: A Review

Singh

Wang

Gupta

et al. 2020

Sensors

314

150

View full text Add to dashboard Cite

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field.

show abstract

“…and attained 93.05% performance accuracy for their findings. Standvoss et al [23] utilized the RF model for the detection of CMBs from MRI and achieved a sensitivity of 92.0%. Another group of researchers [24] also utilized the random forest model for traumatic brain injury diagnosis and achieved 89.1% performance accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

A Transfer Learning-Based Approach to Detect Cerebral Microbleeds

Alrumiah¹,

Al-Shargabi²

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Cerebral microbleeds are small chronic vascular diseases that occur because of irregularities in the cerebrum vessels. Individuals and elderly people with brain injury and dementia can have small microbleeds in their brains. A recent study has shown that cerebral microbleeds could be remarkably risky in terms of life and can be riskier for patients with dementia. In this study, we proposed an efficient approach to automatically identify microbleeds by reducing the false positives in openly available susceptibility-weighted imaging (SWI) data samples. The proposed structure comprises two different pretrained convolutional models with four stages. These stages include (i) skull removal and augmentation, (ii) making clusters of data samples using the k-mean classifier, (iii) reduction of false positives for efficient performance, and (iv) transfer-learning classification. The proposed technique was assessed using the SWI dataset available for 20 subjects. For our findings, we attained an accuracy of 97.26% with a 1.8% false-positive rate using data augmentation on the AlexNet transfer learning model and a 1.1% false-positive rate with 97.89% accuracy for the ResNet 50 model with data augmentation approaches. The results show that our models outperformed the existing approach for the detection of microbleeds.

show abstract

Cerebral microbleed detection in traumatic brain injury patients using 3D convolutional neural networks

Cited by 8 publications

References 14 publications

Automated detection of cerebral microbleeds via segmentation in susceptibility-weighted images of patients with traumatic brain injury

Automated detection of cerebral microbleeds via segmentation in susceptibility-weighted images of patients with traumatic brain injury

3D Deep Learning on Medical Images: A Review

A Transfer Learning-Based Approach to Detect Cerebral Microbleeds

Contact Info

Product

Resources

About