Stroke Lesion Segmentation with Visual Cortex Anatomy Alike Neural Nets

Li, Chuanlong

doi:10.48550/arxiv.2105.06544

Cited by 2 publications

(3 citation statements)

References 32 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pre-processing is crucial for accurate stroke lesion segmentation, removing noise and bias introduced by multi-centre data collection and preparing data for deep learning models despite the trend towards end-to-end learning. Hence, some studies omit the pre-processing stage and input the data directly to the network, as seen in [6,13] among others.…”

Section: The Role Of Pre-processing In Stroke Lesion Segmentationmentioning

confidence: 99%

“…Unlike the U-Net model, the layers of the decoder work independently of each other, and majority class voting is used to produce the segmentation result. Li [13] presented a CNN-based model inspired by the human visual cortex. The proposed model consisted of three blocks called V1, V2, and V4, respectively, with a bottleneck layer.…”

Section: Evolution Towards Capturing Global Featuresmentioning

confidence: 99%

“…However, some human intervention and verification is still required. It is also time-consuming and laborious to segment the lesions layer by layer [12], and the chances of error and bias are also high as lesions could be of irregular size and shape in each layer [7,13], which necessitates the development of automated techniques.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Malik,

Chong,

Fernandez

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

show abstract

Section: The Role Of Pre-processing In Stroke Lesion Segmentationmentioning

confidence: 99%

Section: Evolution Towards Capturing Global Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Malik,

Chong,

Fernandez

et al. 2024

Bioengineering

View full text Add to dashboard Cite

show abstract

Exploring approaches to tackle cross-domain challenges in brain medical image segmentation: a systematic review

Yanzhen,

Song,

Wanping

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionBrain medical image segmentation is a critical task in medical image processing, playing a significant role in the prediction and diagnosis of diseases such as stroke, Alzheimer's disease, and brain tumors. However, substantial distribution discrepancies among datasets from different sources arise due to the large inter-site discrepancy among different scanners, imaging protocols, and populations. This leads to cross-domain problems in practical applications. In recent years, numerous studies have been conducted to address the cross-domain problem in brain image segmentation.MethodsThis review adheres to the standards of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) for data processing and analysis. We retrieved relevant papers from PubMed, Web of Science, and IEEE databases from January 2018 to December 2023, extracting information about the medical domain, imaging modalities, methods for addressing cross-domain issues, experimental designs, and datasets from the selected papers. Moreover, we compared the performance of methods in stroke lesion segmentation, white matter segmentation and brain tumor segmentation.ResultsA total of 71 studies were included and analyzed in this review. The methods for tackling the cross-domain problem include Transfer Learning, Normalization, Unsupervised Learning, Transformer models, and Convolutional Neural Networks (CNNs). On the ATLAS dataset, domain-adaptive methods showed an overall improvement of ~3 percent in stroke lesion segmentation tasks compared to non-adaptive methods. However, given the diversity of datasets and experimental methodologies in current studies based on the methods for white matter segmentation tasks in MICCAI 2017 and those for brain tumor segmentation tasks in BraTS, it is challenging to intuitively compare the strengths and weaknesses of these methods.ConclusionAlthough various techniques have been applied to address the cross-domain problem in brain image segmentation, there is currently a lack of unified dataset collections and experimental standards. For instance, many studies are still based on n-fold cross-validation, while methods directly based on cross-validation across sites or datasets are relatively scarce. Furthermore, due to the diverse types of medical images in the field of brain segmentation, it is not straightforward to make simple and intuitive comparisons of performance. These challenges need to be addressed in future research.

show abstract

Stroke Lesion Segmentation with Visual Cortex Anatomy Alike Neural Nets

Cited by 2 publications

References 32 publications

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Exploring approaches to tackle cross-domain challenges in brain medical image segmentation: a systematic review

Contact Info

Product

Resources

About