CHSNet: Automatic lesion segmentation network guided by CT image features for acute cerebral hemorrhage

Article Engineering, Biomedical

Region-to-boundary deep learning model with multi-scale feature fusion for medical image segmentation

Xiaowei Liu et al.

Summary: In this study, a novel deep learning model is proposed for boundary segmentation of lesions or organs in medical images. Experimental results demonstrate that the model outperforms other methods, especially in boundary tracking.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2022)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Automated detection and segmentation of intracranial hemorrhage suspect hyperdensities in non-contrast-enhanced CT scans of acute stroke patients

N. Schmitt et al.

Summary: The study demonstrated that an AI-based algorithm showed high sensitivity and specificity in detecting acute intracranial hemorrhages (ICH) and intraparenchymal hemorrhages (IPH) in non-contrast-enhanced head CT scans of suspected acute stroke patients. The algorithm also exhibited strong agreements with neuroradiology residents in detecting ICH and IPH. Additionally, excellent agreement was found between the algorithm and the reference standard in quantifying IPH volumes.

EUROPEAN RADIOLOGY (2022)

Add to Collection

Review Clinical Neurology

World Stroke Organization (WSO): Global Stroke Fact Sheet 2022

Valery L. Feigin et al.

Summary: Stroke is the second-leading cause of death and the third-leading cause of death and disability worldwide. It imposes a significant economic burden, particularly in lower-income and lower-middle-income countries. The provided information serves as an updated resource for communication with stakeholders.

INTERNATIONAL JOURNAL OF STROKE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

ResGANet: Residual group attention network for medical image classification and segmentation

Junlong Cheng et al.

Summary: Deep learning has shown superior performance in medical image analysis, and the proposed ResGANet model outperforms state-of-the-art backbone models in medical image tasks, providing a promising method for enhancing the feature representation of convolutional neural networks (CNNs) in the future.

MEDICAL IMAGE ANALYSIS (2022)

Add to Collection

Article Mathematical & Computational Biology

Deep Transfer Learning for Automatic Prediction of Hemorrhagic Stroke on CT Images

B. Nageswara Rao et al.

Summary: In this study, an automated transfer deep learning method combining ResNet-50 and dense layer is proposed for accurate prediction of intracranial hemorrhage on NCCT brain images. The model achieved high accuracy, specificity, and sensitivity, demonstrating its potential for automatic diagnosis of hemorrhagic stroke.

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Deep Gaussian processes for multiple instance learning: Application to CT intracranial hemorrhage detection *

Miguel Lopez-Perez et al.

Summary: This study presents a novel ICH detection model based on Multiple Instance Learning and Deep Gaussian Processes, which can be trained with scan-level annotations and achieves good results in experiments. The DGPMIL model demonstrates superior performance in multiple experiments and shows great potential for applications in medical image classification.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2022)

Add to Collection

Article Computer Science, Information Systems

MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation

Abhishek Srivastava et al.

Summary: Methods based on convolutional neural networks have improved biomedical image segmentation, but most cannot efficiently handle diverse object sizes or small, biased datasets. This paper introduces the MSRF-Net architecture, specifically designed for medical image segmentation, which uses DSDF blocks to exchange multi-scale features and improve information flow, allowing for accurate segmentation. Extensive experiments show that MSRF-Net outperforms current methods on publicly available datasets, achieving high Dice Coefficients on various biomedical datasets.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2022)

Add to Collection

Article Biology

Automatic hemorrhage segmentation on head CT scan for traumatic brain injury using 3D deep learning model

Papangkorn Inkeaw et al.

Summary: This paper introduces a new method for automatically segmenting hemorrhage subtypes in head CT scans based on a deep learning model. The experimental results show that the proposed method outperforms previous studies in terms of segmentation performance for each hemorrhage subtype.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Biology

DEAU-Net: Attention networks based on dual encoder for Medical Image Segmentation

Zhaojin Fu et al.

Summary: In this paper, we propose a feature attention network based on dual encoder, which achieves excellent performance in learning and extracting detailed features. It has important applications in the field of medical image segmentation.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Review Clinical Neurology

Artificial Intelligence and Acute Stroke Imaging

J. E. Soun et al.

Summary: Artificial intelligence technology has various applications in acute stroke imaging, such as detection, classification, large vessel occlusion detection, prognosis, etc. Emerging techniques like convolutional neural networks show promise in efficiently and accurately performing these tasks.

AMERICAN JOURNAL OF NEURORADIOLOGY (2021)

Add to Collection

Article Biology

Generative adversarial networks in medical image segmentation: A review

Siyi Xun et al.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

A Simplified Framework for the Detection of Intracranial Hemorrhage in CT Brain Images Using Deep Learning

Praveen Kumaravel et al.

Summary: This study investigates the effectiveness of using a deep learning framework with CNN and SVM for detecting ICH in CT brain images, with the modified AlexNet-SVM classifier showing improved performance. This simple and efficient framework can serve as a screening tool to assist in the accurate detection of ICH by medical professionals.

CURRENT MEDICAL IMAGING (2021)

Add to Collection

Article Computer Science, Information Systems

Deep Learning for Hemorrhagic Lesion Detection and Segmentation on Brain CT Images

Lu Li et al.

Summary: This paper proposes a U-net based deep learning framework for automatic detection and segmentation of hemorrhage strokes in CT brain images. By comparing different Deep Learning topologies, adopting adversarial training, and training and evaluating the model on two different datasets, the effectiveness, robustness, and advantages of the proposed deep learning model in hemorrhage lesion diagnosis have been demonstrated, making it possible to be a clinical decision support tool in stroke diagnosis.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Precise segmentation of non-enhanced computed tomography in patients with ischemic stroke based on multi-scale U-Net deep network model

Shaoquan Li et al.

Summary: This study developed a multi-scale U-Net deep network model for automatic image segmentation of acute ischemic stroke lesions on non-enhanced CT images, which showed higher accuracy and shorter processing time compared to the classic U-Net method.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Texture analysis based on U-Net neural network for intracranial hemorrhage identification predicts early enlargement

Yu Liu et al.

Summary: The study demonstrates that intelligent texture analysis of cerebral hemorrhage using U-Net neural network can accurately predict the early expansion of hypertensive cerebral hemorrhage, and parameters of gray level co-occurrence matrix and gray level run length matrix under MI dimensionality reduction have the most excellent predictive value.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications