Deep Learning of Tissue Fate Features in Acute Ischemic Stroke.

Proceedings (IEEE Int Conf Bioinformatics Biomed)

Neurovascular Imaging Research Core, Department of Neurology, Univerisity of California, Los Angeles (UCLA).

Published: November 2015

AI Article Synopsis

  • The prediction of tissue survival in acute ischemic stroke treatment is crucial for balancing risks and benefits of interventions like clot retrieval.
  • A new deep learning model analyzes local patches from MRI hypoperfusion features to predict tissue fate right after stroke symptoms begin.
  • Testing on 19 patients demonstrates that this model outperforms traditional single-voxel regression methods, leading to more accurate predictions.

Article Abstract

In acute ischemic stroke treatment, prediction of tissue survival outcome plays a fundamental role in the clinical decision-making process, as it can be used to assess the balance of risk vs. possible benefit when considering endovascular clot-retrieval intervention. For the first time, we construct a deep learning model of tissue fate based on randomly sampled local patches from the hypoperfusion (Tmax) feature observed in MRI immediately after symptom onset. We evaluate the model with respect to the ground truth established by an expert neurologist four days after intervention. Experiments on 19 acute stroke patients evaluated the accuracy of the model in predicting tissue fate. Results show the superiority of the proposed regional learning framework versus a single-voxel-based regression model.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5597003PMC
http://dx.doi.org/10.1109/BIBM.2015.7359869DOI Listing

Publication Analysis

Top Keywords

tissue fate
12
deep learning
8
acute ischemic
8
ischemic stroke
8
tissue
4
learning tissue
4
fate features
4
features acute
4
stroke acute
4
stroke treatment
4

Similar Publications

Conventionally, the size, shape, and biomechanics of cartilages are determined by their voluminous extracellular matrix. By contrast, we found that multiple murine cartilages consist of lipid-filled cells called lipochondrocytes. Despite resembling adipocytes, lipochondrocytes were molecularly distinct and produced lipids exclusively through de novo lipogenesis.

View Article and Find Full Text PDF

Introduction: The venous outflow profile (VOP) is a crucial yet often overlooked aspect affecting stroke outcomes. It plays a major role in the physiopathology of acute cerebral ischemia, as it accounts for both the upstream arterial collaterals and cerebral microperfusion. This enables it to circumvent the limitations of various arterial collateral evaluation systems, which often fail to consider impaired autoregulation and its impact on cerebral blood flow at the microcirculatory levels.

View Article and Find Full Text PDF

Regulation of gene expression in eukaryotic cells is critical for cell survival, proliferation, and cell fate determination. Misregulation of gene expression can have substantial, negative consequences that result in disease or tissue dysfunction that can be targeted for therapeutic intervention. Several strategies to inhibit gene expression at the level of mRNA transcription and translation have been developed, such as anti-sense inhibition and CRISPR-Cas9 gene editing.

View Article and Find Full Text PDF

Skin, as the body's largest organ, acts as the primary defense mechanism against infection and injury. The maintenance of skin health heavily relies on the regulation of epidermal stem cells, crucial for ensuring epidermal homeostasis, hair regeneration, and the repair of epidermal injuries. Recent studies have placed a growing emphasis on G protein-coupled receptor (GPCR) in the context of understanding epidermal stem cells, uncovering its significant role in determining their fate.

View Article and Find Full Text PDF

Modulating tumor-associated macrophages through CSF1R inhibition: a potential therapeutic strategy for HNSCC.

J Transl Med

January 2025

Department of General Surgery of Otorhinolaryngology Head and Neck, The Sixth Affiliated Hospital, Sun Yat-Sen University, No.26, Erheng Road, Yuancun, Tianhe District, Guangzhou, 510655, China.

Purpose: Tumor-associated macrophages (TAMs) are pivotal immune cells within the tumor microenvironment (TME), exhibiting dual roles across various cancer types. Depending on the context, TAMs can either suppress tumor progression and weaken drug sensitivity or facilitate tumor growth and drive therapeutic resistance. This study explores whether targeting TAMs can suppress the progression of head and neck squamous cell carcinoma (HNSCC) and improve the efficacy of chemotherapy.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!