Lung tumor segmentation is important for therapy in the radiation treatment of patients with thoracic malignancies. In this paper, we describe a 4D image segmentation method based on graph-cuts optimization, shape prior and optical flow. Due to small size, the location, and low contrast between the tumor and the surrounding tissue, tumor segmentation in 3D+t is challenging. We performed 4D lung tumor segmentation in 5 patients, and in each case compared the results with the expert-delineated lung nodules. In each case, 4D image segmentation took approximately ten minutes on a PC with AMD Phenom II and 32GB of memory for segmenting tumor in five phases of lung CT data.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2016.7590941 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Automated Deep Learning-Based Detection and Segmentation of Lung Tumors at CT.
Radiology
January 2025
Stanford University School of Medicine, Department of Radiation Oncology, Stanford, CA, US.
Background Detection and segmentation of lung tumors on CT scans are critical for monitoring cancer progression, evaluating treatment responses, and planning radiation therapy; however, manual delineation is labor-intensive and subject to physician variability. Purpose To develop and evaluate an ensemble deep learning model for automating identification and segmentation of lung tumors on CT scans. Materials and Methods A retrospective study was conducted between July 2019 and November 2024 using a large dataset of CT simulation scans and clinical lung tumor segmentations from radiotherapy plans.
View Article and Find Full Text PDFComparison of postoperative analgesic efficacy between erector spinae plane block and rhomboid intercostal block in breast-conserving surgery and sentinel lymph node biopsy: A randomized non-inferiority clinical trial.
Agri
January 2025
Department of Anesthesiology and Reanimation, İstanbul Medipol University Faculty of Medicine, İstanbul, Türkiye.
Objectives: Breast-conserving surgery is a common breast operation type in the world. Patients may feel severe postoperative pain after the surgery. Several regional anesthesia methods are used for postoperative pain control as a part of multimodal analgesia management after breast surgery.
View Article and Find Full Text PDFMandibular Reconstruction With a Patient-Specific Implant Following Surgical Excision of an Acanthomatous Ameloblastoma in a Dog.
J Vet Dent
January 2025
Department of Dentistry, Oral and Maxillo-facial Surgery, Eastcott Veterinary Referrals, Part of Linnaeus Group, Swindon, UK.
Canine acanthomatous ameloblastoma (CAA) is an invasive benign epithelial odontogenic tumour most commonly affecting the mandible of large breed dogs. To the author's knowledge, this report describes the first computer-aided design patient-specific implant (PSI) that has been placed for a critical sized bone defect in mandibular reconstruction of a dog in the UK. The aim was to restore mandibular stability using a regenerative approach combining a titanium locking plate and compression-resistant matrix infused with recombinant human bone morphogenetic protein-2 (rhBMP-2) to bridge the 85 mm mandibular defect created by a segmental mandibulectomy.
View Article and Find Full Text PDFMicrostructure of the human metastatic vertebral body.
Front Endocrinol (Lausanne)
January 2025
Department of Industrial Engineering, Alma Mater Studiorum - University of Bologna, Bologna, Italy.
Introduction: Bone spinal metastases disrupt the bone homeostasis, inducing a local imbalance in the bone formation and/or resorption, with consequent loss of the structural optimisation of the vertebrae and increase of the risk of fracture. Little is known about the microstructure of the metastatic tissue, the microstructure of the tissue surrounding the lesion, and how it does compare with vertebrae with no lesions observed on the biomedical images. A comprehensive assessment of the microstructural properties of the entire vertebral body can be obtained with micro computed tomography.
View Article and Find Full Text PDFUtilizing machine-learning techniques on MRI radiomics to identify primary tumors in brain metastases.
Front Neurol
January 2025
Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
Objective: To develop a machine learning-based clinical and/or radiomics model for predicting the primary site of brain metastases using multiparametric magnetic resonance imaging (MRI).
Materials And Methods: A total of 202 patients (87 males, 115 females) with 439 brain metastases were retrospectively included, divided into training sets (brain metastases of lung cancer [BMLC] = 194, brain metastases of breast cancer [BMBC] = 108, brain metastases of gastrointestinal tumor [BMGiT] = 48) and test sets (BMLC = 50, BMBC = 27, BMGiT = 12). A total of 3,404 quantitative image features were obtained through semi-automatic segmentation from MRI images (T1WI, T2WI, FLAIR, and T1-CE).
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!