Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

[Japanese radiological report creation with continuous speech recognition].

Taro Takahara¹, Mika Nakajima, Toshiaki Nitatori

¹Department of Radiology, Kyorin University.

Nihon Igaku Hoshasen Gakkai Zasshi. Nippon Acta Radiologica

|February 23, 2002

Summary

Continuous speech recognition significantly speeds up radiological report generation compared to typing. This technology offers a practical solution for reducing report turnaround times in radiology departments.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A patient with WHIM syndrome presenting relatively low TREC, KREC, and housekeeping gene levels by newborn screening -a case report and the literature review<sup></sup>.

Immunological medicine·2026

Same author

Outcomes and Safety Profile of Repeated Progressive Site-Directed Therapy for Patients With Oligometastatic Castration-Resistant Prostate Cancer.

International journal of urology : official journal of the Japanese Urological Association·2025

Same author

Synthetic DWI: contrast improvement for diffusion-weighted imaging in prostate using T1 shine-through by synthesizing images with adjusted TR and TE.

Magma (New York, N.Y.)·2025

Same author

Utility of Echo-planar Imaging with Compressed Sensitivity Encoding (EPICS) in the Evaluation of Small Breast Cancers Using Diffusion-weighted Imaging with Background Suppression (DWIBS).

Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine·2024

Same author

A Case of Hemi-ablation with High-intensity Focused Ultrasound for a Localized Reducted Solitary Lesion in the Prostate.

The Tokai journal of experimental and clinical medicine·2024

Same author

Computed diffusion-weighted imaging with a low-apparent diffusion coefficient-pixel cut-off technique for breast cancer detection.

The British journal of radiology·2023

Area of Science:

Radiology
Medical Informatics
Speech Recognition Technology

Context:

Radiological report generation is a critical but time-consuming task for radiologists.
Conventional typing methods can lead to significant delays in report turnaround times.
The adoption of advanced speech-to-text technologies presents a potential solution for improving efficiency.

Purpose:

To evaluate the efficiency and accuracy of a continuous speech-recognition system (AmiVoice) for generating Japanese radiological reports.
To compare the time required for report generation using speech recognition versus conventional typing.
To assess the overall impact of speech recognition on report turnaround time.

Summary:

Two board-certified radiologists utilized the AmiVoice continuous speech-recognition system to create 10 Japanese radiological reports.

Related Experiment Videos

The system achieved a 97.1% accuracy rate with dedicated pronunciations for loan words.

Speech recognition input time (56.2 sec) was substantially faster than conventional typing (142.8 sec), even with correction time included.

Impact:

Continuous speech recognition offers a faster and more efficient method for radiological report generation compared to traditional typing.
The technology has the potential to significantly reduce overall report turnaround times, improving workflow in radiology departments.
The findings suggest that speech recognition is an acceptable and beneficial tool for clinical radiology practice.