Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 study
| Autor: | Niccolò Camarlinghi, Francesco Bagagli, Arnold M. R. Schilham, Bartjan de Hoop, Lourdes Bolanos, Piergiorgio Cerello, Bram van Ginneken, Mathias Prokop, Keelin Murphy, Thomas Duindam, S.C. Cheran, Maria Evelina Fantacci, G. Gargano, Ernesto Lopez Torres, Hiroshi Fujita, Alessandra Retico, Ilaria Gori, Meindert Niemeijer, Samuel G. Armato, Roberto Bellotti, Francesco De Carlo, Takeshi Hara, Sabina Tangaro, Saskia van Amelsvoort-van de Vorst |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Male
Lung Neoplasms Software Validation Health Informatics Computed tomography Aetiology screening and detection [ONCOL 5] Sensitivity and Specificity Upload Software Medicine Humans Radiology Nuclear Medicine and imaging Aged Radiological and Ultrasound Technology medicine.diagnostic_test business.industry Reproducibility of Results Solitary Pulmonary Nodule Benchmarking Middle Aged Computer Graphics and Computer-Aided Design Computer aided detection Data set Radiographic Image Interpretation Computer-Assisted Female Computer Vision and Pattern Recognition Tomography business Tomography X-Ray Computed Algorithm Lung cancer screening Algorithms |
| Zdroj: | Medical Image Analysis, 14, 6, pp. 707-22 Medical Image Analysis, 14, 707-22 |
| ISSN: | 1361-8415 |
| DOI: | 10.1016/j.media.2010.05.005 |
| Popis: | Contains fulltext : 89675.pdf (Publisher’s version ) (Open Access) Numerous publications and commercial systems are available that deal with automatic detection of pulmonary nodules in thoracic computed tomography scans, but a comparative study where many systems are applied to the same data set has not yet been performed. This paper introduces ANODE09 ( http://anode09.isi.uu.nl), a database of 55 scans from a lung cancer screening program and a web-based framework for objective evaluation of nodule detection algorithms. Any team can upload results to facilitate benchmarking. The performance of six algorithms for which results are available are compared; five from academic groups and one commercially available system. A method to combine the output of multiple systems is proposed. Results show a substantial performance difference between algorithms, and demonstrate that combining the output of algorithms leads to marked performance improvements. 01 december 2010 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect