Automatic prostate segmentation in MR images is a challenging task due to inter-patient prostate shape and texture variability, and the lack of a clear prostate boundary. We propose a supervised learning framework that combines the atlas based AAM and SVM model to achieve a relatively high segmentation result of the prostate boundary. The performance of the segmentation is evaluated with cross validation on 40 MR image datasets, yielding an average segmentation accuracy near 90%.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6748308PMC
http://dx.doi.org/10.1109/EMBC.2014.6944225DOI Listing

Publication Analysis

Top Keywords

atlas based
8
based aam
8
aam svm
8
svm model
8
prostate segmentation
8
prostate boundary
8
prostate
5
segmentation
5
model fully
4
fully automatic
4

Similar Publications

Aim: To construct a predictive model based on the LODDS stage established for patients with late-onset colon adenocarcinoma to enhance survival stratification.

Methods: Late-onset colon adenocarcinoma data were obtained from the public database. After determining the optimal LODDS truncation value for the training set via X-tile software, we created a new staging system by integrating the T stage and M stage.

View Article and Find Full Text PDF

Telomemore enables single-cell analysis of cell cycle and chromatin condensation.

Nucleic Acids Res

January 2025

Laboratory for Molecular Infection Medicine Sweden (MIMS), Umeå University, Biomedicinbyggnaden 6K och 6L, Umeå universitetssjukhus, 901 87, Umeå, Sweden.

Single-cell RNA-seq methods can be used to delineate cell types and states at unprecedented resolution but do little to explain why certain genes are expressed. Single-cell ATAC-seq and multiome (ATAC + RNA) have emerged to give a complementary view of the cell state. It is however unclear what additional information can be extracted from ATAC-seq data besides transcription factor binding sites.

View Article and Find Full Text PDF

Background: Neoadjuvant, endocrine, and targeted therapies have significantly improved the prognosis of breast cancer (BC). However, due to the high heterogeneity of cancer, some patients cannot benefit from existing treatments. Increasing evidence suggests that amino acids and their metabolites can alter the tumor malignant behavior through reshaping tumor microenvironment and regulation of immune cell function.

View Article and Find Full Text PDF

Human natural killer (NK) cells can be sub-divided into two functional subsets but the clinical significance of these CD56 and CD56 NK cells in anti-tumour immunity remains largely unexplored. We determined the relative abundances of gene signatures for CD56 and CD56 NK cells along with 3 stromal and 18 other immune cell types in the patient tumour transcriptomes from the cancer genome atlas bladder cancer dataset (TCGA-BLCA). Using this computational approach, CD56 NK cells were predicted to be the more abundant tumour-infiltrating NK subset which was also associated with improved patient prognosis.

View Article and Find Full Text PDF

Introduction: Acute myeloid leukemia (AML), a highly heterogeneous hematological malignancy, remains a major challenge in adult oncology. Stem cell research has highlighted the crucial role of long noncoding RNA (lncRNA) in regulating cellular differentiation and self-renewal processes, which are pivotal in AML pathogenesis and therapy resistance.

Methods: This study explores the relationship between cuproptosis-related lncRNAs and AML prognosis, providing novel insights into their impact on hematopoietic stem and progenitor cells.

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!