Positron emission tomography - computed tomography (PET-CT) has been widely used in modern cancer imaging. Accurate tumor delineation from PET and CT plays an important role in radiation therapy. The PET-CT co-segmentation technique, which makes use of advantages of both modalities, has achieved impressive performance for tumor delineation. In this work, we propose a novel 3D image matting based semi-automated co-segmentation method for tumor delineation on dual PET-CT scans. The "matte" values generated by 3D image matting are employed to compute the region costs for the graph based co-segmentation. Compared to previous PET-CT co-segmentation methods, our method is completely data-driven in the design of cost functions, thus using much less hyper-parameters in our segmentation model. Comparative experiments on 54 PET-CT scans of lung cancer patients demonstrated the effectiveness of our method.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6886662 | PMC |
| http://dx.doi.org/10.1007/978-3-319-67564-0_4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Patient With Post-operative Recurrent Pancreatic Cancer Treated With Cone Beam Computed Tomography-Guided Stereotactic Adaptive Radiotherapy: A Case Report.
Cureus
December 2024
Radiation Oncology, Washington University School of Medicine, Saint Louis, USA.
CT-guided adaptive radiotherapy (ART) for the treatment of pancreatic adenocarcinoma is rapidly increasing and has been shown to provide advanced treatment tools comparable to magnetic resonance imaging (MRI)-guided adaptive therapy. Here, we provide the first case report of a local pancreatic recurrence treatment after definitive resection using cone beam computed tomography (CBCT)-guided ART (CT-guided ART) enabled by HyperSight imaging (Varian Medical Systems, Inc., Palo Alto, CA, USA) for daily delineation of organs-at-risk (OARs) and target to improve the quality of online ART.
View Article and Find Full Text PDFExplainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models.
Sci Rep
January 2025
ADAPT Research Centre, School of Computer Science, University of Galway, Galway, Ireland.
This study utilizes the Breast Ultrasound Image (BUSI) dataset to present a deep learning technique for breast tumor segmentation based on a modified UNet architecture. To improve segmentation accuracy, the model integrates attention mechanisms, such as the Convolutional Block Attention Module (CBAM) and Non-Local Attention, with advanced encoder architectures, including ResNet, DenseNet, and EfficientNet. These attention mechanisms enable the model to focus more effectively on relevant tumor areas, resulting in significant performance improvements.
View Article and Find Full Text PDFGeneralized, sublethal damage-based mathematical approach for improved modeling of clonogenic survival curve flattening upon hyperthermia, radiotherapy, and beyond.
Phys Med Biol
January 2025
OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Sachsen, 01307, GERMANY.
Mathematical modeling can offer valuable insights into the behavior of biological systems upon treatment. Different mathematical models (empirical, semi-empirical, and mechanistic) have been designed to predict the efficacy of either hyperthermia (HT), radiotherapy (RT), or their combination. However, mathematical approaches capable of modeling cell survival from shared general principles for both mono-treatments alone and their co-application are rare.
View Article and Find Full Text PDFPreoperative Computed Tomography Radiomics-Based Models for Predicting Microvascular Invasion of Intrahepatic Mass-Forming Cholangiocarcinoma.
J Comput Assist Tomogr
November 2024
From the Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, Jiangsu Province Hospital of Chinese Medicine, Nanjing, Jiangsu Province, China.
Objectives: The aim of the study is to investigate the ability of preoperative CT (Computed Tomography)-based radiomics signature to predict microvascular invasion (MVI) of intrahepatic mass-forming cholangiocarcinoma (IMCC) and develop radiomics-based prediction models.
Materials And Methods: Preoperative clinical data, basic CT features, and radiomics features of 121 IMCC patients (44 with MVI and 77 without MVI) were retrospectively reviewed. The loading and display of CT images, delineation of the volume of interest, and feature extraction were performed using 3D Slicer.
Modeling the lymph node stromal cells in oral squamous cell carcinoma: insights into the stromal cues in nodal metastasis.
Hum Cell
January 2025
Integrated Head and Neck Oncology Program (DSRG-5), Mazumdar Shaw Medical Foundation, Narayana Health, Bangalore, India.
The study explores the development and characterization of lymph node stromal cell cultures (LNSCs) from patients with oral squamous cell carcinoma (OSCC), highlighting the importance of understanding tumor-node cross-talk for effective prognostic and therapeutic interventions. Herein, we describe the development and characterization of primary lymph node stromal cells (LNSCs, N = 14) from nodes of metastatic and non-metastatic OSCC patients. Primary cultures were established by the explant method from positive (N + ; N = 2), and negative nodes (N0; N = 4) of the metastatic patients (N = 3) as well as negative (N0; N = 8) nodes from non-metastatic (N = 4) patients.
View Article and Find Full Text PDFWant 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!