Machine learning methods for 1D ultrasound breast cancer screening

Neil Joshi, Seth Billings, Erika Schwartz, Susan Harvey, Philippe Burlina

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study addresses the development of machine learning methods for reduced space ultrasound to perform automated prescreening of breast cancer. The use of ultrasound in low-resource settings is constrained by lack of trained personnel and equipment costs, and motivates the need for automated, low-cost diagnostic tools. We hypothesize a solution to this problem is the use of 1D ultrasound (single piezoelectric element). We leverage random forest classifiers to classify 1D samples of various types of tissue phantoms simulating cancerous, benign lesions, and non-cancerous tissues. In addition, we investigate the optimal ultrasound power and frequency parameters to maximize performance. We show preliminary results on 2-, 3- A nd 5-class classification problems for the ideal power/frequency combination. These results demonstrate promise towards the use of a single-element ultrasound device to screen for breast cancer.

Original languageEnglish (US)
Title of host publicationProceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages711-715
Number of pages5
Volume2018-January
ISBN (Electronic)9781538614174
DOIs
StatePublished - Jan 16 2018
Event16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 - Cancun, Mexico
Duration: Dec 18 2017Dec 21 2017

Other

Other16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
CountryMexico
CityCancun
Period12/18/1712/21/17

Fingerprint

Learning systems
Screening
Ultrasonics
Tissue
Costs
Classifiers
Personnel

Keywords

  • automated diagnostics
  • breast cancer
  • machine learning
  • ultrasound

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Joshi, N., Billings, S., Schwartz, E., Harvey, S., & Burlina, P. (2018). Machine learning methods for 1D ultrasound breast cancer screening. In Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 (Vol. 2018-January, pp. 711-715). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2017.00-76

Machine learning methods for 1D ultrasound breast cancer screening. / Joshi, Neil; Billings, Seth; Schwartz, Erika; Harvey, Susan; Burlina, Philippe.

Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 711-715.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Joshi, N, Billings, S, Schwartz, E, Harvey, S & Burlina, P 2018, Machine learning methods for 1D ultrasound breast cancer screening. in Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 711-715, 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017, Cancun, Mexico, 12/18/17. https://doi.org/10.1109/ICMLA.2017.00-76
Joshi N, Billings S, Schwartz E, Harvey S, Burlina P. Machine learning methods for 1D ultrasound breast cancer screening. In Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 711-715 https://doi.org/10.1109/ICMLA.2017.00-76
Joshi, Neil ; Billings, Seth ; Schwartz, Erika ; Harvey, Susan ; Burlina, Philippe. / Machine learning methods for 1D ultrasound breast cancer screening. Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 711-715
@inproceedings{a7dcd323cd0a47ab900c20e4e1da88b5,
title = "Machine learning methods for 1D ultrasound breast cancer screening",
abstract = "This study addresses the development of machine learning methods for reduced space ultrasound to perform automated prescreening of breast cancer. The use of ultrasound in low-resource settings is constrained by lack of trained personnel and equipment costs, and motivates the need for automated, low-cost diagnostic tools. We hypothesize a solution to this problem is the use of 1D ultrasound (single piezoelectric element). We leverage random forest classifiers to classify 1D samples of various types of tissue phantoms simulating cancerous, benign lesions, and non-cancerous tissues. In addition, we investigate the optimal ultrasound power and frequency parameters to maximize performance. We show preliminary results on 2-, 3- A nd 5-class classification problems for the ideal power/frequency combination. These results demonstrate promise towards the use of a single-element ultrasound device to screen for breast cancer.",
keywords = "automated diagnostics, breast cancer, machine learning, ultrasound",
author = "Neil Joshi and Seth Billings and Erika Schwartz and Susan Harvey and Philippe Burlina",
year = "2018",
month = "1",
day = "16",
doi = "10.1109/ICMLA.2017.00-76",
language = "English (US)",
volume = "2018-January",
pages = "711--715",
booktitle = "Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Machine learning methods for 1D ultrasound breast cancer screening

AU - Joshi, Neil

AU - Billings, Seth

AU - Schwartz, Erika

AU - Harvey, Susan

AU - Burlina, Philippe

PY - 2018/1/16

Y1 - 2018/1/16

N2 - This study addresses the development of machine learning methods for reduced space ultrasound to perform automated prescreening of breast cancer. The use of ultrasound in low-resource settings is constrained by lack of trained personnel and equipment costs, and motivates the need for automated, low-cost diagnostic tools. We hypothesize a solution to this problem is the use of 1D ultrasound (single piezoelectric element). We leverage random forest classifiers to classify 1D samples of various types of tissue phantoms simulating cancerous, benign lesions, and non-cancerous tissues. In addition, we investigate the optimal ultrasound power and frequency parameters to maximize performance. We show preliminary results on 2-, 3- A nd 5-class classification problems for the ideal power/frequency combination. These results demonstrate promise towards the use of a single-element ultrasound device to screen for breast cancer.

AB - This study addresses the development of machine learning methods for reduced space ultrasound to perform automated prescreening of breast cancer. The use of ultrasound in low-resource settings is constrained by lack of trained personnel and equipment costs, and motivates the need for automated, low-cost diagnostic tools. We hypothesize a solution to this problem is the use of 1D ultrasound (single piezoelectric element). We leverage random forest classifiers to classify 1D samples of various types of tissue phantoms simulating cancerous, benign lesions, and non-cancerous tissues. In addition, we investigate the optimal ultrasound power and frequency parameters to maximize performance. We show preliminary results on 2-, 3- A nd 5-class classification problems for the ideal power/frequency combination. These results demonstrate promise towards the use of a single-element ultrasound device to screen for breast cancer.

KW - automated diagnostics

KW - breast cancer

KW - machine learning

KW - ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85048500753&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048500753&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2017.00-76

DO - 10.1109/ICMLA.2017.00-76

M3 - Conference contribution

AN - SCOPUS:85048500753

VL - 2018-January

SP - 711

EP - 715

BT - Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -