Transfer Learning of the ResNet-18 and DenseNet-121 Model Used to Diagnose
Intracranial Hemorrhage in CT Scanning

Zhou, Qi; Zhu, Wenjie; Li, Fuchen; Yuan, Mingqing; Zheng, Linfeng; Liu, Xu

doi:10.2174/1381612827666211213143357

Cited by 40 publications

(18 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the RSNA and CQ500 datasets, which contain hundreds of 1000s of CT scans, private or internal datasets were used in other studies on brain hematoma classification, [ 10 – 12 , 21 – 23 ] and most of these datasets were relatively small (150–2000 scans). The models used in these studies were trained with sophisticated ML pipelines, but there may have been limitations in the reproducibility and extendibility of the models, considering the wide variety of TBI abnormalities.…”

Section: Resultsmentioning

confidence: 99%

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

et al. 2022

View full text Add to dashboard Cite

Background: The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could automatically identify and quantify computed tomography (CT) findings in traumatic brain injury (TBI). Methods: Systematic review, in accordance with PRISMA 2020 and SPIRIT-AI extension guidelines, with a search of 4 databases (Medline, Embase, IEEE Xplore, and Web of Science) was performed to find AI studies that automated the clinical tasks for identifying and quantifying CT findings of TBI-related abnormalities. Results: A total of 531 unique publications were reviewed, which resulted in 66 articles that met our inclusion criteria. The following components for identification and quantification regarding TBI were covered and automated by existing AI studies: identification of TBI-related abnormalities; classification of intracranial hemorrhage types; slice-, pixel-, and voxel-level localization of hemorrhage; measurement of midline shift; and measurement of hematoma volume. Automated identification of obliterated basal cisterns was not investigated in the existing AI studies. Most of the AI algorithms were based on deep neural networks that were trained on 2- or 3-dimensional CT imaging datasets. Conclusion: We identified several important TBI-related CT findings that can be automatically identified and quantified with AI. A combination of these techniques may provide useful tools to enhance reproducibility of TBI identification and quantification by supporting radiologists and clinicians in their TBI assessments and reducing subjective human factors.

show abstract

Section: Resultsmentioning

confidence: 99%

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

et al. 2022

View full text Add to dashboard Cite

show abstract

“…layer and the PReLU activation function layer are connected to realize the fusion of low-frequency and high-frequency features. The reconstruction part can obtain a feature map containing rich, detailed information ( 26 ).…”

Section: Methodsmentioning

confidence: 99%

High-resolution medical image reconstruction based on residual neural network for diagnosis of cerebral aneurysm

Wang

Liao²,

Ni³

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

ObjectiveCerebral aneurysms are classified as severe cerebrovascular diseases due to hidden and critical onset, which seriously threaten life and health. An effective strategy to control intracranial aneurysms is the regular diagnosis and timely treatment by CT angiography (CTA) imaging technology. However, unpredictable patient movements make it challenging to capture sub-millimeter-level ultra-high resolution images in a CTA scan. In order to improve the doctor's judgment, it is necessary to improve the clarity of the cerebral aneurysm medical image algorithm.MethodsThis paper mainly focuses on researching a three-dimensional medical image super-resolution algorithm applied to cerebral aneurysms. Although some scholars have proposed super-resolution reconstruction methods, there are problems such as poor effect and too much reconstruction time. Therefore, this paper designs a lightweight super-resolution network based on a residual neural network. The residual block structure removes the B.N. layer, which can effectively solve the gradient problem. Considering the high-resolution reconstruction needs to take the complete image as the research object and the fidelity of information, this paper selects the channel domain attention mechanism to improve the performance of the residual neural network.ResultsThe new data set of cerebral aneurysms in this paper was obtained by CTA imaging technology of patients in the Department of neurosurgery, the second affiliated of Guizhou Medical University Hospital. The proposed model was evaluated from objective evaluation, model effect, model performance, and detection comparison. On the brain aneurysm data set, we tested the PSNR and SSIM values of 2 and 4 magnification factors, and the scores of our method were 33.01, 28.39, 33.06, and 28.41, respectively, which were better than those of the traditional SRCNN, ESPCN and FSRCNN. Subsequently, the model is applied to practice in this paper, and the effect, performance index and diagnosis of auxiliary doctors are obtained. The experimental results show that the high-resolution image reconstruction model based on the residual neural network designed in this paper plays a more influential role than other image classification methods. This method has higher robustness, accuracy and intuition.ConclusionWith the wide application of CTA images in the clinical diagnosis of cerebral aneurysms and the increasing number of application samples, this method is expected to become an additional diagnostic tool that can effectively improve the diagnostic accuracy of cerebral aneurysms.

show abstract

“…It is well-known due to its depth and use of residual blocks [ 18 ]. These blocks are essential for solving obstacle issues in training by introducing identity skip connections, which allow layers to copy their inputs to the next layer [ 19 ].…”

Section: Methodsmentioning

confidence: 99%

Automated Detection of Corneal Ulcer Using Combination Image Processing and Deep Learning

et al. 2022

View full text Add to dashboard Cite

A corneal ulcers are one of the most common eye diseases. They come from various infections, such as bacteria, viruses, or parasites. They may lead to ocular morbidity and visual disability. Therefore, early detection can reduce the probability of reaching the visually impaired. One of the most common techniques exploited for corneal ulcer screening is slit-lamp images. This paper proposes two highly accurate automated systems to localize the corneal ulcer region. The designed approaches are image processing techniques with Hough transform and deep learning approaches. The two methods are validated and tested on the publicly available SUSTech-SYSU database. The accuracy is evaluated and compared between both systems. Both systems achieve an accuracy of more than 90%. However, the deep learning approach is more accurate than the traditional image processing techniques. It reaches 98.9% accuracy and Dice similarity 99.3%. However, the first method does not require parameters to optimize an explicit training model. The two approaches can perform well in the medical field. Moreover, the first model has more leverage than the deep learning model because the last one needs a large training dataset to build reliable software in clinics. Both proposed methods help physicians in corneal ulcer level assessment and improve treatment efficiency.

show abstract

Transfer Learning of the ResNet-18 and DenseNet-121 Model Used to Diagnose Intracranial Hemorrhage in CT Scanning

Cited by 40 publications

References 22 publications

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

High-resolution medical image reconstruction based on residual neural network for diagnosis of cerebral aneurysm

Automated Detection of Corneal Ulcer Using Combination Image Processing and Deep Learning

Contact Info

Product

Resources

About