1
|
Ikushima K, Arimura H, Jin Z, Yabu-Uchi H, Kuwazuru J, Shioyama Y, Sasaki T, Honda H, Sasaki M. Computer-assisted framework for machine-learning-based delineation of GTV regions on datasets of planning CT and PET/CT images. J Radiat Res 2017; 58:123-134. [PMID: 27609193 PMCID: PMC5321188 DOI: 10.1093/jrr/rrw082] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/08/2016] [Revised: 05/14/2016] [Accepted: 07/03/2016] [Indexed: 06/06/2023]
Abstract
We have proposed a computer-assisted framework for machine-learning-based delineation of gross tumor volumes (GTVs) following an optimum contour selection (OCS) method. The key idea of the proposed framework was to feed image features around GTV contours (determined based on the knowledge of radiation oncologists) into a machine-learning classifier during the training step, after which the classifier produces the 'degree of GTV' for each voxel in the testing step. Initial GTV regions were extracted using a support vector machine (SVM) that learned the image features inside and outside each tumor region (determined by radiation oncologists). The leave-one-out-by-patient test was employed for training and testing the steps of the proposed framework. The final GTV regions were determined using the OCS method that can be used to select a global optimum object contour based on multiple active delineations with a LSM around the GTV. The efficacy of the proposed framework was evaluated in 14 lung cancer cases [solid: 6, ground-glass opacity (GGO): 4, mixed GGO: 4] using the 3D Dice similarity coefficient (DSC), which denotes the degree of region similarity between the GTVs contoured by radiation oncologists and those determined using the proposed framework. The proposed framework achieved an average DSC of 0.777 for 14 cases, whereas the OCS-based framework produced an average DSC of 0.507. The average DSCs for GGO and mixed GGO were 0.763 and 0.701, respectively, obtained by the proposed framework. The proposed framework can be employed as a tool to assist radiation oncologists in delineating various GTV regions.
Collapse
Affiliation(s)
- Koujiro Ikushima
- Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
| | - Hidetaka Arimura
- Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
| | - Ze Jin
- Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
- Research Fellow of the Japan Society for the Promotion of Science
| | - Hidetake Yabu-Uchi
- Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
| | - Jumpei Kuwazuru
- Saiseikai Fukuoka General Hospital, 1-3-46, Tenjin, Chuo-ku, Fukuoka 810-0001, Japan
| | - Yoshiyuki Shioyama
- Saga Heavy Ion Medical Accelerator in Tosu, 415, Harakoga-cho, Tosu 841-0071, Japan
| | - Tomonari Sasaki
- Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
| | - Hiroshi Honda
- Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
| | - Masayuki Sasaki
- Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
| |
Collapse
|
2
|
Ikushima K, Arimura H, Jin Z, Yabuuchi H, Kuwazuru J, Shioyama Y, Sasaki T, Honda H, Sasaki M. TU-H-CAMPUS-JeP2-03: Machine-Learning-Based Delineation Framework of GTV Regions of Solid and Ground Glass Opacity Lung Tumors at Datasets of Planning CT and PET/CT Images. Med Phys 2016. [DOI: 10.1118/1.4957686] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
|
3
|
Ikushima K, Sakuma H, Komiyama S, Hirakawa K. Imaging of cyclotron emission from edge channels in quantum Hall conductors. Phys Rev Lett 2004; 93:146804. [PMID: 15524827 DOI: 10.1103/physrevlett.93.146804] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/01/2004] [Indexed: 05/24/2023]
Abstract
A local probing technique of cyclotron emission is applied to image nonequilibrium electrons generated along edge channels in quantum Hall conductors. In a lower-magnetic field region of a quantum Hall state plateau (filling factor 2<nu), cyclotron emission is found to occur along the boundary of a conductor on the side of lower potential (with positive Hall voltage). The emission indicates that electrons are accumulated in the first-excited Landau level, while they are depleted in the lowest Landau level along the boundary as a consequence of adiabatic-transport.
Collapse
Affiliation(s)
- K Ikushima
- Department of Basic Science, University of Tokyo, Komaba, Meguro-ku, Tokyo 153-8902, Japan
| | | | | | | |
Collapse
|
5
|
|
6
|
Abstract
The present report describes a plexiform schwannoma involving the subcutis of the foot in an 8-year-old boy. Gross findings revealed thin fibrous septa in a multilobulated tumor that was partly separated into free body-like nodules in the subcutis. Preoperative CT and MRI failed to delineate this multinodular architecture or free bodies. This is a case presentation including the CT and MR findings associated with plexiform schwannoma.
Collapse
Affiliation(s)
- K Ikushima
- Department of Orthopaedic Surgery, Osaka Medical Center for Cancer and Cardiovascular Diseases, 1-3-3, Nakamichi, Higashinari-ku, Osaka 537-8511, Japan
| | | | | | | | | |
Collapse
|
7
|
Yamashita M, Iwami M, Ikushima K, Komori T, Aoki H, Imanaka H. Studies on a new antibiotic FR-900109. 1. Taxonomy, isolation and characterization. J Antibiot (Tokyo) 1983; 36:1123-8. [PMID: 6630075 DOI: 10.7164/antibiotics.36.1123] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
Abstract
FR-900109 is a new antibiotic obtained from fermentation broth of a streptomyces which was identified as Streptomyces prunicolor. Its elementary analysis and mass spectroscopic measurement suggest that the molecular formula is C27H32O9. It has an ultraviolet absorption maximum at 254 nm. The antibiotic is active against Gram-positive bacteria. Acute toxicity in mice is very low.
Collapse
|