WEKO3
アイテム
The project of another low-cost metaphase finder (Third Report)
https://repo.qst.go.jp/records/85201
https://repo.qst.go.jp/records/85201e1692d6e-78a7-4b84-b318-10e2d90273d9
| Item type | 会議発表用資料 / Presentation(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2022-03-11 | |||||
| タイトル | ||||||
| タイトル | The project of another low-cost metaphase finder (Third Report) | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_c94f | |||||
| 資源タイプ | conference object | |||||
| アクセス権 | ||||||
| アクセス権 | metadata only access | |||||
| アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
| 著者 |
Akira, Furukawa
× Akira, Furukawa× Akira, Furukawa |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Biological dosimetry is used to estimate one's dose by biological phenomena. The most popular and “gold standard” phenomenon is the appearance of dicentric chromosomes in metaphases. The metaphase finder is a tool for biological dosimetry that finds metaphase cells on glass slides. It consists of an automated microscope, auto-focus system, X-Y stage, camera, and computer. It does the image analysis of the microscopic images of the glass slides, and displays the positions of metaphase cells. The metaphase finder was used for the personnel who worked at Fukushima nuclear plant to know how much dose they were irradiated. The author has already reported the project of this low-cost metaphase finder system at EPRBiodose 2015, and also the application of artificial intelligence (AI) at EPRBiodose 2018. The author and a software company are now preparing to produce the system commercially. The reported system in 2018 consisted of an automated microscope, an auto-focus system, an X-Y stage, a camera, and a computer. To enhance the accuracy of the system, with the addition of deep learning was tested. The pre-selection of metaphases using mathematical morphology before the AI process enabled the AI classification of true or false metaphases. Then, a total of 1709 images of the metaphase finder detected as 'metaphases' were read into a nine-layer artificial neural network to detect true metaphases. A total of 456 images were used for training, and the rest of the images were used for validation. The false-positive rate of AI was 0.89 and the false-negative rate was 0.90. At this time, the author is reporting that the prototype of AI implemented metaphase finder was combined with the microscope system, and that the metaphase finder system’s accuracy was compared with previous non-AI system, using the same samples. The next goals are to implement a new automated dicentric counter and then obtain a dose-response relationship using the new dicentric counter. |
|||||
| 会議概要（会議名, 開催地, 会期, 主催者等） | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | EPR BioDose 2022 Online | |||||
| 発表年月日 | ||||||
| 日付 | 2022-03-30 | |||||
| 日付タイプ | Issued | |||||
