Object-oriented classification approach for bone metastasis mapping from whole-body bone scintigraphy |
| |
| Institution: | 1. National Institute of Research and Development for Optoelectronics - INOE 2000, Magurele, Romania;2. “Saint John” Emergency Clinical Hospital, Bucharest, Romania;3. University of Bucharest, Faculty of Physics, Magurele, Romania;4. Carol Davila” University of Medicine and Pharmacy, Bucharest, Romania;1. LIP-Coimbra, Departamento de Física, Universidade de Coimbra, 3004-516 Coimbra, Portugal;2. Departamento de Física, Universidade de Coimbra, 3004-516 Coimbra, Portugal;1. Graduate School of Health Sciences, Kumamoto University, 4-24-1 Kuhonji, Chuo-ku, Kumamoto 862-0976, Japan;2. Department of Health Sciences, Faculty of Life Sciences, Kumamoto University, 4-24-1 Kuhonji, Chuo-ku, Kumamoto 862-0976, Japan;1. Department of Medical Physics, Hospital Universitario Ramón y Cajal, Madrid, Spain;2. Biomedical Engineering, ETSIT, Universidad Politécnica de Madrid, Madrid, Spain;3. Medical Physics, Department of Radiology, Rehabilitation and Physiotherapy, Universidad Complutense de Madrid, Madrid, Spain;1. Department of Medical Physics – Oncology, Aarhus University Hospital, Aarhus, Denmark;2. Faculty of Informatics & Science, University of Oradea, Oradea, Romania;3. Cancer Research Institute, University of South Australia, Adelaide, Australia;4. Institut Curie, Université PSL, CNRS UMR3347, Inserm U1021, 91400 Orsay, France;5. Department of Medical Physics, Hygeia Hospital, Athens, Greece;6. Health Physics Department, University Hospital, Novara, Italy;1. Medical Physics, San Raffaele Scientific Institute, Milano, Italy;2. Radiology, San Raffaele Scientific Institute, Milano, Italy;3. Internal Medecine, San Raffaele Scientific Institute, Milano, Italy;4. Faculty of Medecine and Surgery, Vita-Salute San Raffaele University, Milano, Italy;1. Unit of Radiation Research, IEO European Institute of Oncology, IRCCS, Milano, Italy;2. Department of Medical Physics and Instrumentation, Institute Verbeeten, Tilburg, The Netherlands;3. Division of Medical Physics, Department of Radiation Oncology, Erasmus MC Cancer Institute Erasmus University, Rotterdam, The Netherlands;4. Division of Medical Radiation Physics, Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, CH 3010 Bern, Switzerland;5. Department of Medical Physics, Hygeia Hospital, Athens, Greece;6. Formerly Department of Medical, Information and Communication Technology, Jeroen Bosch Ziekenhuis, ‘s-Hertogenbosch, The Netherlands;7. Department of Medical Physics & Clinical Engineering, University Hospital Galway, Newcastle Road, Galway H91, YR71, Ireland;8. Department of Physics, Faculty of Sciences, University of Novi Sad, Novi Sad, Serbia;9. Radiotherapy Department, Oncology Institute Vojvodina, Sremska Kamenica, Serbia;10. Section of Medical Exposures, Department of Radiation Protection in Radiotherapy, National Radiation Protection Institute, Prague, Czech Republic;11. SFPM, Department of Medical Physics, Institut de Cancérologie de l’Ouest 44805 Saint-Herblain, France;12. Department of Electroradiology, Poznan University of Medical Sciences and Department of Medical Physics, Greater Poland Cancer Centre, Garbary 15 st, 61-866 Poznan, Poland;13. Institute of Radiation Physics, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland;14. Medical Physics Department, Galaria, Hospital do Meixoeiro, Complexo Hospitalario Universitario de Vigo, Vigo, Spain;15. Medical Physics Department, Bank of Cyprus Oncology Centre Nicosia, Cyprus;p. Department of Radiotherapy Physics, University College London Hospital, London, UK;q. Department of Medical Physics and Bioengineering, University College London, London, UK;r. Medical Physics department, National Physical Laboratory, Teddington, UK;s. Servei de Radiofisica i Radioprotecció, Hospital de la Santa Creu I Sant Pau, Barcelona, Spain |
| |
| Abstract: | PurposeWhole-body bone scintigraphy is the most widely used method for detecting bone metastases in advanced cancer. However, its interpretation depends on the experience of the radiologist. Some automatic interpretation systems have been developed in order to improve diagnostic accuracy. These systems are pixel-based and do not use spatial or textural information of groups of pixels, which could be very important for classifying images with better accuracy. This paper presents a fast method of object-oriented classification that facilitates easier interpretation of bone scintigraphy images.MethodsNine whole-body images from patients suspected with bone metastases were analyzed in this preliminary study. First, an edge-based segmentation algorithm together with the full lambda-schedule algorithm were used to identify the object in the bone scintigraphy and the textural and spatial attributes of these objects were calculated. Then, a set of objects (224 objects, ~ 46% of the total objects) were selected as training data based on visual examination of the image, and were assigned to various levels of radionuclide accumulation before performing the data classification using both k-nearest-neighbor and support vector machine classifiers. The performance of the proposed method was evaluated using as metric the statistical parameters calculated from error matrix.ResultsThe results revealed that the proposed object-oriented classification approach using either k-nearest-neighbor or support vector machine as classification methods performed well in detecting bone metastasis in terms of overall accuracy (86.62 ± 2.163% and 86.81 ± 2.137% respectively) and kappa coefficient (0.6395 ± 0.0143 and 0.6481 ± 0.0218 respectively).ConclusionsIn conclusion, the described method provided encouraging results in mapping bone metastases in whole-body bone scintigraphy. |
| |
| Keywords: | Image analysis K-nearest-neighbor method Support vector machine method Error matrix |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
