T
Takeshi Hara
Researcher at Gifu University
Publications - 217
Citations - 3843
Takeshi Hara is an academic researcher from Gifu University. The author has contributed to research in topics: Mammography & Fundus (eye). The author has an hindex of 30, co-authored 209 publications receiving 3421 citations.
Papers
More filters
Journal ArticleDOI
Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique
TL;DR: The authors' present results show that their scheme can be regarded as a technique for CAD systems to detect nodules in helical CT pulmonary images.
Journal ArticleDOI
Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 study
Bram van Ginneken,Bram van Ginneken,Samuel G. Armato,Bartjan de Hoop,Saskia van Amelsvoort-van de Vorst,Thomas Duindam,Meindert Niemeijer,Keelin Murphy,Arnold M. R. Schilham,Alessandra Retico,Maria Evelina Fantacci,Maria Evelina Fantacci,Niccolò Camarlinghi,Niccolò Camarlinghi,Francesco Bagagli,Francesco Bagagli,Ilaria Gori,Takeshi Hara,Hiroshi Fujita,G. Gargano,Roberto Bellotti,Sabina Tangaro,Lourdes Bolanos,Francesco De Carlo,Piergiorgio Cerello,S.C. Cheran,Ernesto Lopez Torres,Mathias Prokop,Mathias Prokop +28 more
TL;DR: ANODE09 is introduced, a database of 55 scans from a lung cancer screening program and a web-based framework for objective evaluation of nodule detection algorithms, and it is demonstrated that combining the output of algorithms leads to marked performance improvements.
Journal ArticleDOI
Quantitative Evaluation of Liver Function with Use of Gadoxetate Disodium–enhanced MR Imaging
TL;DR: The liver function correlating with ICG-PDR can be estimated quantitatively from the signal intensities and the volumes of the liver and spleen on gadoxetate disodium-enhanced MR images, which may improve the estimation of segmental liver function.
Journal ArticleDOI
Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method.
TL;DR: A single network trained by pixel‐to‐label deep learning to address the challenging issue of anatomical structure segmentation in 3D CT cases is proposed to achieve availability and reliability with better efficiency, generality, and flexibility than conventional segmentation methods, which must be guided by human expertise.
Proceedings ArticleDOI
Automated microaneurysm detection method based on double ring filter in retinal fundus images
Atsushi Mizutani,Chisako Muramatsu,Yuji Hatanaka,Shinsuke Suemori,Takeshi Hara,Hiroshi Fujita +5 more
TL;DR: A computerized detection scheme for the detection of microaneurysms on retinal fundus images, obtained from the Retinopathy Online Challenge database, with good results for the training cases because the "gold standard" for the test cases is not known.