| Presentation | 2020-01-29 Automated dection for neck and thoracic lesions on FDG-PET/CT by lesion enhancement using one-class SVM Atsuko Tanaka, Mitsutaka Memoto, Hayato Kaida, Yuichi Kimura, Takashi Nagaoka, Takahiro Yamada, Kazuyuki Ushifusa, Kohei Hanaoka, Kazuhiro Kitajima, Tatsuya Tsuchitani, Kazunari Ishii, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose an anomaly detection based method to detect primary and metastatic lesions in the cervical and thoracic region on FDG-PET/CT by lesion enhancement using one-class SVM (OCSVM). The first step of the proposed method is the automatic extraction of bilateral lungs, cervical region, and the mediastinal region. Secondary, voxel abnormality is measured at each voxel in the extracted regions by organ-specific OCSVMs, that have been trained by normal voxel data previously. Next, lesion candidates are detected by the thresholding process for the voxel abnormalities. In the evaluation using clinical FDG-PET/CT, we confirmed the effectiveness of the proposed method by comparison of the lesion detection performances between the proposed method and our previous method using the Mahalanobis distance. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | one-class SVM / anomaly detection / FDG-PET/CT / computer aided diagnosis |
| Paper # | MI2019-67 |
| Date of Issue | 2020-01-22 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2020/1/29(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | OKINAWAKEN SEINENKAIKAN |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Image Engineering, Analysis, Recognition, etc. |
| Chair | Yoshiki Kawata(Tokushima Univ.) |
| Vice Chair | Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
| Secretary | Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
| Assistant | Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automated dection for neck and thoracic lesions on FDG-PET/CT by lesion enhancement using one-class SVM |
| Sub Title (in English) | |
| Keyword(1) | one-class SVM |
| Keyword(2) | anomaly detection |
| Keyword(3) | FDG-PET/CT |
| Keyword(4) | computer aided diagnosis |
| 1st Author's Name | Atsuko Tanaka |
| 1st Author's Affiliation | Kindai University(Kindai Uni) |
| 2nd Author's Name | Mitsutaka Memoto |
| 2nd Author's Affiliation | Kindai University(Kindai Uni) |
| 3rd Author's Name | Hayato Kaida |
| 3rd Author's Affiliation | Kindai University(Kindai Uni) |
| 4th Author's Name | Yuichi Kimura |
| 4th Author's Affiliation | Kindai University(Kindai Uni) |
| 5th Author's Name | Takashi Nagaoka |
| 5th Author's Affiliation | Kindai University(Kindai Uni) |
| 6th Author's Name | Takahiro Yamada |
| 6th Author's Affiliation | Kindai University(Kindai Uni) |
| 7th Author's Name | Kazuyuki Ushifusa |
| 7th Author's Affiliation | Kindai University(Kindai Uni) |
| 8th Author's Name | Kohei Hanaoka |
| 8th Author's Affiliation | Kindai University Hospital(Kindai Uni Hosp) |
| 9th Author's Name | Kazuhiro Kitajima |
| 9th Author's Affiliation | Hyogo College of Medicine(Hyogo Col of Med) |
| 10th Author's Name | Tatsuya Tsuchitani |
| 10th Author's Affiliation | Hospital of Hyogo College of Medicine(Hosp of Hyogo Col of Med) |
| 11th Author's Name | Kazunari Ishii |
| 11th Author's Affiliation | Kindai University(Kindai Uni) |
| Date | 2020-01-29 |
| Paper # | MI2019-67 |
| Volume (vol) | vol.119 |
| Number (no) | MI-399 |
| Page | pp.pp.11-14(MI), |
| #Pages | 4 |
| Date of Issue | 2020-01-22 (MI) |