| Japanese |
|---|
| Title | 音声認識装置を用いた脳血流シンチグラムのレポート作成装置の研究 |
|---|
| Subtitle | 《原著》 |
|---|
| Authors | 本田憲業*, 町田喜久雄*, 間宮敏雄*, 高橋卓*, 瀧島輝雄*, 釜野剛*, 玉城聡*, 村松正行* |
|---|
| Authors(kana) | |
|---|
| Organization | *埼玉医科大学総合医療センター放射線科学教室 |
|---|
| Journal | 核医学 |
|---|
| Volume | 27 |
|---|
| Number | 10 |
|---|
| Page | 1147-1155 |
|---|
| Year/Month | 1990/10 |
|---|
| Article | 原著 |
|---|
| Publisher | 日本核医学会 |
|---|
| Abstract | 「要旨」音声認識装置をもちいた, 脳シンチグラム診断レポート作成システムに必要な語彙の選定, 同システムにおける語彙認識率, レポート作成時間について報告した. レポート作成に必要な語彙は, 患者特定情報, 依頼医特定情報, 臨床情報, 検査法特定情報, 所見存在部位, 大きさ, 形状, 性状, 程度, 確診度, 病名, 方針, 数字, 日付, などに分類し, 登録した. 初回発声での正認識率は平均91.1%(総語数259)で, 語長が短縮すると認識率は低下する傾向(平均語長6.4, 4.1, 3.3に対し, それぞれ, 96.6, 88.9, 88.0%)が認められた. 8例の異常所見レポート作成時間は正味21分26秒, 専門職による口述筆記(日本語ワードプロセッサ使用)で正味15分53秒であった. 非専門職(医師など)によるワードプロセッサ入力にかかる時間, および本装置による所見のデータベース化の利点を考慮すると, 本装置はレポート作成に有用と考えられる. |
|---|
| Practice | 臨床医学：一般 |
|---|
| Keywords | reporting system, speech recognition, brain scintigram, SPECT. |
|---|
| English |
|---|
| Title | Generation of Brain Scintigram Reports with a Speech Recognition Device Controlled by a Personal Computer |
|---|
| Subtitle | - Original Articles - |
|---|
| Authors | Norinari HONDA*, Kikuo MACHIDA*, Toshio MAMIYA*, Taku TAKAHASHI*, Teruo TAKISHIMA*, Tsuyoshi KAMANO*, Satoshi TAMAKI*, Masayuki MURAMATSU* |
|---|
| Authors(kana) | |
|---|
| Organization | *Department of Radiology, Saitama Medical Center, Saitama Medical School |
|---|
| Journal | The Japanese Journal of nuclear medicine |
|---|
| Volume | 27 |
|---|
| Number | 10 |
|---|
| Page | 1147-1155 |
|---|
| Year/Month | 1990/10 |
|---|
| Article | Original article |
|---|
| Publisher | THE JAPANESE SOCIETY OF NUCLEAR MEDICINE |
|---|
| Abstract | Radiology reporting system using a speech recognistion apparatus was applied to generation of reports on brain scintigram and SPECT. The number of words or phrases that were selected for the reporting system by the authors was 259. Rates of correct recognition at the first, second, and third or more utterance of the voices were 91.1, 5.0, and 3.9%, respectively. The recognition rates decreased from 96.6 to 88.0% when the mean lengths of the words or phases varied from 6.4 to 3.3. Net time for the generation of 8 reports by the system was 21 minutes 26 seconds, while that by the traditional dictation-transcription method was 15 minutes and 53 seconds. This system seems to be useful because of much longer input time expected for an average doctor, who usually is not well trained in using a Japanese-word processor, and convinience for database management offered by the system. |
|---|
| Practice | Clinical medicine |
|---|
| Keywords | reporting system, speech recognition, brain scintigram, SPECT. |
|---|