An enhanced random walk algorithm for delineation of head and neck cancers in PET studies
| Autor: | Alessandro Stefano 1, 2, Salvatore Vitabile 3, Giorgio Russo 1, 4, Massimo Ippolito 5, Maria Gabriella Sabini 4, Daniele Sardina 4, Orazio Gambino 6, Roberto Pirrone 6, Edoardo Ardizzone 6, Maria Carla Gilardi 1 |
|---|---|
| Přispěvatelé: | Stefano, A., Vitabile, S., Russo, G., Ippolito, M., Sabini, M., Sardina, D., Gambino, O., Pirrone, R., Ardizzone, E., Gilardi, M., Stefano, A, Vitabile, S, Russo, G, Ippolito, M, Sabini, M, Sardina, D, Gambino, O, Pirrone, R, Ardizzone, E, Gilardi, M |
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Similarity (geometry)
Computer science PET imaging Biomedical Engineering Random walk 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine medicine Image Processing Computer-Assisted Humans Segmentation Computer vision Cluster analysis Event (probability theory) Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni medicine.diagnostic_test business.industry Phantoms Imaging Biological target volume Head and neck cancer segmentation Random walks Computer Science Application Pattern recognition Computer Science Applications Hausdorff distance Positron emission tomography Head and Neck Neoplasms 030220 oncology & carcinogenesis Positron-Emission Tomography Artificial intelligence Computer Vision and Pattern Recognition business Algorithms Biological target volume Head and neck cancer segmentation PET imaging Random walks Algorithms Head and Neck Neoplasms Humans Image Processing Computer-Assisted Phantoms Imaging Positron-Emission Tomography Volume (compression) |
| Zdroj: | Medical & biological engineering & computing (Online) 55 (2017): 897–908. doi:10.1007/s11517-016-1571-0 info:cnr-pdr/source/autori:Alessandro Stefano 1,2, Salvatore Vitabile 3, Giorgio Russo 1,4, Massimo Ippolito 5, Maria Gabriella Sabini 4, Daniele Sardina 4, Orazio Gambino 6, Roberto Pirrone 6, Edoardo Ardizzone 6, Maria Carla Gilardi 1/titolo:An enhanced random walk algorithm for delineation of head and neck cancers in PET studies/doi:10.1007%2Fs11517-016-1571-0/rivista:Medical & biological engineering & computing (Online)/anno:2017/pagina_da:897/pagina_a:908/intervallo_pagine:897–908/volume:55 |
| DOI: | 10.1007/s11517-016-1571-0 |
| Popis: | An algorithm for delineating complex head and neck cancers in positron emission tomography (PET) images is presented in this article. An enhanced random walk (RW) algorithm with automatic seed detection is proposed and used to make the segmentation process feasible in the event of inhomogeneous lesions with bifurcations. In addition, an adaptive probability threshold and a k-means based clustering technique have been integrated in the proposed enhanced RW algorithm. The new threshold is capable of following the intensity changes between adjacent slices along the whole cancer volume, leading to an operator-independent algorithm. Validation experiments were first conducted on phantom studies: High Dice similarity coefficients, high true positive volume fractions, and low Hausdorff distance confirm the accuracy of the proposed method. Subsequently, forty head and neck lesions were segmented in order to evaluate the clinical feasibility of the proposed approach against the most common segmentation algorithms. Experimental results show that the proposed algorithm is more accurate and robust than the most common algorithms in the literature. Finally, the proposed method also shows real-time performance, addressing the physician’s requirements in a radiotherapy environment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|