Machine learning for medical ultrasound: status, methods, and future opportunities
Abstract Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Springer US
2021
|
Online Access: | https://hdl.handle.net/1721.1/131504 |
_version_ | 1811091477819817984 |
---|---|
author | Brattain, Laura J Telfer, Brian A Dhyani, Manish Grajo, Joseph R Samir, Anthony E |
author2 | Lincoln Laboratory |
author_facet | Lincoln Laboratory Brattain, Laura J Telfer, Brian A Dhyani, Manish Grajo, Joseph R Samir, Anthony E |
author_sort | Brattain, Laura J |
collection | MIT |
description | Abstract
Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited image quality control. Tremendous opportunities have arisen in the last decade as a result of exponential growth in available computational power coupled with progressive miniaturization of US devices. As US devices become smaller, enhanced computational capability can contribute significantly to decreasing variability through advanced image processing. In this paper, we review leading machine learning (ML) approaches and research directions in US, with an emphasis on recent ML advances. We also present our outlook on future opportunities for ML techniques to further improve clinical workflow and US-based disease diagnosis and characterization. |
first_indexed | 2024-09-23T15:03:03Z |
format | Article |
id | mit-1721.1/131504 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T15:03:03Z |
publishDate | 2021 |
publisher | Springer US |
record_format | dspace |
spelling | mit-1721.1/1315042023-10-06T20:24:48Z Machine learning for medical ultrasound: status, methods, and future opportunities Brattain, Laura J Telfer, Brian A Dhyani, Manish Grajo, Joseph R Samir, Anthony E Lincoln Laboratory Abstract Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited image quality control. Tremendous opportunities have arisen in the last decade as a result of exponential growth in available computational power coupled with progressive miniaturization of US devices. As US devices become smaller, enhanced computational capability can contribute significantly to decreasing variability through advanced image processing. In this paper, we review leading machine learning (ML) approaches and research directions in US, with an emphasis on recent ML advances. We also present our outlook on future opportunities for ML techniques to further improve clinical workflow and US-based disease diagnosis and characterization. 2021-09-20T17:17:21Z 2021-09-20T17:17:21Z 2018-02-28 2020-09-24T21:22:34Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/131504 en https://doi.org/10.1007/s00261-018-1517-0 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. Springer Science+Business Media, LLC, part of Springer Nature application/pdf Springer US Springer US |
spellingShingle | Brattain, Laura J Telfer, Brian A Dhyani, Manish Grajo, Joseph R Samir, Anthony E Machine learning for medical ultrasound: status, methods, and future opportunities |
title | Machine learning for medical ultrasound: status, methods, and future opportunities |
title_full | Machine learning for medical ultrasound: status, methods, and future opportunities |
title_fullStr | Machine learning for medical ultrasound: status, methods, and future opportunities |
title_full_unstemmed | Machine learning for medical ultrasound: status, methods, and future opportunities |
title_short | Machine learning for medical ultrasound: status, methods, and future opportunities |
title_sort | machine learning for medical ultrasound status methods and future opportunities |
url | https://hdl.handle.net/1721.1/131504 |
work_keys_str_mv | AT brattainlauraj machinelearningformedicalultrasoundstatusmethodsandfutureopportunities AT telferbriana machinelearningformedicalultrasoundstatusmethodsandfutureopportunities AT dhyanimanish machinelearningformedicalultrasoundstatusmethodsandfutureopportunities AT grajojosephr machinelearningformedicalultrasoundstatusmethodsandfutureopportunities AT samiranthonye machinelearningformedicalultrasoundstatusmethodsandfutureopportunities |