A method for the automated classification of benign and malignant masses on digital breast tomosynthesis images using machine learning and radiomic features

Ayaka Sakai, Yuya Onishi, Misaki Matsui, Hidetoshi Adachi, Atsushi Teramoto, Kuniaki Saito, Hiroshi Fujita

Research output: Contribution to journalArticle

Abstract

In digital mammography, which is used for the early detection of breast tumors, oversight may occur due to overlap between normal tissues and lesions. However, since digital breast tomosynthesis can acquire three-dimensional images, tissue overlapping is reduced, and, therefore, the shape and distribution of the lesions can be easily identified. However, it is often difficult to distinguish between benign and malignant breast lesions on images, and the diagnostic accuracy can be reduced due to complications from radiological interpretations, owing to acquisition of a higher number of images. In this study, we developed an automated classification method for diagnosing breast lesions on digital breast tomosynthesis images using radiomics to comprehensively analyze the radiological images. We extracted an analysis area centered on the lesion and calculated 70 radiomic features, including the shape of the lesion, existence of spicula, and texture information. The accuracy was compared by inputting the obtained radiomic features to four classifiers (support vector machine, random forest, naïve Bayes, and multi-layer perceptron), and the final classification result was obtained as an output using a classifier with high accuracy. To confirm the effectiveness of the proposed method, we used 24 cases with confirmed pathological diagnosis on biopsy. We also compared the classification results based on the presence or absence of dimension reduction using least absolute shrinkage and a selection operator (LASSO). As a result, when the support vector machine was used as a classifier, the correct identification rate of the benign tumors was 55% and that of malignant tumors was 84%, with best results. These results indicate that the proposed method may help in more accurately diagnosing cases that are difficult to classify on images.

Original languageEnglish
JournalRadiological Physics and Technology
DOIs
Publication statusAccepted/In press - 01-01-2019

Fingerprint

machine learning
Mammography
breast
lesions
Breast
classifiers
Neural Networks (Computer)
tumors
Three-Dimensional Imaging
Neoplasms
Breast Neoplasms
Biopsy
self organizing systems
shrinkage
Machine Learning
acquisition
textures
operators
Support Vector Machine
output

All Science Journal Classification (ASJC) codes

  • Radiation
  • Physical Therapy, Sports Therapy and Rehabilitation
  • Radiology Nuclear Medicine and imaging

Cite this

@article{69d0b08421514a8fbbed01a3a098fa29,
title = "A method for the automated classification of benign and malignant masses on digital breast tomosynthesis images using machine learning and radiomic features",
abstract = "In digital mammography, which is used for the early detection of breast tumors, oversight may occur due to overlap between normal tissues and lesions. However, since digital breast tomosynthesis can acquire three-dimensional images, tissue overlapping is reduced, and, therefore, the shape and distribution of the lesions can be easily identified. However, it is often difficult to distinguish between benign and malignant breast lesions on images, and the diagnostic accuracy can be reduced due to complications from radiological interpretations, owing to acquisition of a higher number of images. In this study, we developed an automated classification method for diagnosing breast lesions on digital breast tomosynthesis images using radiomics to comprehensively analyze the radiological images. We extracted an analysis area centered on the lesion and calculated 70 radiomic features, including the shape of the lesion, existence of spicula, and texture information. The accuracy was compared by inputting the obtained radiomic features to four classifiers (support vector machine, random forest, na{\"i}ve Bayes, and multi-layer perceptron), and the final classification result was obtained as an output using a classifier with high accuracy. To confirm the effectiveness of the proposed method, we used 24 cases with confirmed pathological diagnosis on biopsy. We also compared the classification results based on the presence or absence of dimension reduction using least absolute shrinkage and a selection operator (LASSO). As a result, when the support vector machine was used as a classifier, the correct identification rate of the benign tumors was 55{\%} and that of malignant tumors was 84{\%}, with best results. These results indicate that the proposed method may help in more accurately diagnosing cases that are difficult to classify on images.",
author = "Ayaka Sakai and Yuya Onishi and Misaki Matsui and Hidetoshi Adachi and Atsushi Teramoto and Kuniaki Saito and Hiroshi Fujita",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s12194-019-00543-5",
language = "English",
journal = "Radiological Physics and Technology",
issn = "1865-0333",
publisher = "Springer Japan",

}

A method for the automated classification of benign and malignant masses on digital breast tomosynthesis images using machine learning and radiomic features. / Sakai, Ayaka; Onishi, Yuya; Matsui, Misaki; Adachi, Hidetoshi; Teramoto, Atsushi; Saito, Kuniaki; Fujita, Hiroshi.

In: Radiological Physics and Technology, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A method for the automated classification of benign and malignant masses on digital breast tomosynthesis images using machine learning and radiomic features

AU - Sakai, Ayaka

AU - Onishi, Yuya

AU - Matsui, Misaki

AU - Adachi, Hidetoshi

AU - Teramoto, Atsushi

AU - Saito, Kuniaki

AU - Fujita, Hiroshi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In digital mammography, which is used for the early detection of breast tumors, oversight may occur due to overlap between normal tissues and lesions. However, since digital breast tomosynthesis can acquire three-dimensional images, tissue overlapping is reduced, and, therefore, the shape and distribution of the lesions can be easily identified. However, it is often difficult to distinguish between benign and malignant breast lesions on images, and the diagnostic accuracy can be reduced due to complications from radiological interpretations, owing to acquisition of a higher number of images. In this study, we developed an automated classification method for diagnosing breast lesions on digital breast tomosynthesis images using radiomics to comprehensively analyze the radiological images. We extracted an analysis area centered on the lesion and calculated 70 radiomic features, including the shape of the lesion, existence of spicula, and texture information. The accuracy was compared by inputting the obtained radiomic features to four classifiers (support vector machine, random forest, naïve Bayes, and multi-layer perceptron), and the final classification result was obtained as an output using a classifier with high accuracy. To confirm the effectiveness of the proposed method, we used 24 cases with confirmed pathological diagnosis on biopsy. We also compared the classification results based on the presence or absence of dimension reduction using least absolute shrinkage and a selection operator (LASSO). As a result, when the support vector machine was used as a classifier, the correct identification rate of the benign tumors was 55% and that of malignant tumors was 84%, with best results. These results indicate that the proposed method may help in more accurately diagnosing cases that are difficult to classify on images.

AB - In digital mammography, which is used for the early detection of breast tumors, oversight may occur due to overlap between normal tissues and lesions. However, since digital breast tomosynthesis can acquire three-dimensional images, tissue overlapping is reduced, and, therefore, the shape and distribution of the lesions can be easily identified. However, it is often difficult to distinguish between benign and malignant breast lesions on images, and the diagnostic accuracy can be reduced due to complications from radiological interpretations, owing to acquisition of a higher number of images. In this study, we developed an automated classification method for diagnosing breast lesions on digital breast tomosynthesis images using radiomics to comprehensively analyze the radiological images. We extracted an analysis area centered on the lesion and calculated 70 radiomic features, including the shape of the lesion, existence of spicula, and texture information. The accuracy was compared by inputting the obtained radiomic features to four classifiers (support vector machine, random forest, naïve Bayes, and multi-layer perceptron), and the final classification result was obtained as an output using a classifier with high accuracy. To confirm the effectiveness of the proposed method, we used 24 cases with confirmed pathological diagnosis on biopsy. We also compared the classification results based on the presence or absence of dimension reduction using least absolute shrinkage and a selection operator (LASSO). As a result, when the support vector machine was used as a classifier, the correct identification rate of the benign tumors was 55% and that of malignant tumors was 84%, with best results. These results indicate that the proposed method may help in more accurately diagnosing cases that are difficult to classify on images.

UR - http://www.scopus.com/inward/record.url?scp=85074820847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074820847&partnerID=8YFLogxK

U2 - 10.1007/s12194-019-00543-5

DO - 10.1007/s12194-019-00543-5

M3 - Article

C2 - 31686300

AN - SCOPUS:85074820847

JO - Radiological Physics and Technology

JF - Radiological Physics and Technology

SN - 1865-0333

ER -