Evaluation of TP53/PIK3CA mutations using texture and morphology analysis on breast MRI

Woo Kyung Moon, Hong Hao Chen, Sung Ui Shin, Wonshik Han, Ruey Feng Chang

Research output: Contribution to journalArticle

Abstract

Purpose: Somatic mutations in TP53 and PIK3CA genes, the two most frequent genetic alternations in breast cancer, are associated with prognosis and therapeutic response. This study predicted the presence of TP53 and PIK3CA mutations in breast cancer by using texture and morphology analyses on breast MRI. Materials and methods: A total of 107 breast cancers (dataset A) from The Cancer Imaging Archive (TCIA) consisting of 40 TP53 mutation cancer and 67 cancers without TP53 mutation; 35 PIK3CA mutations cancer and 72 without PIK3CA mutation. 122 breast cancer (dataset B) from Seoul National University Hospital containing 54 TP53 mutation cancer and 68 without mutations were used in this study. At first, the tumor area was segmented by a region growing method. Subsequently, gray level co-occurrence matrix (GLCM) texture features were extracted after ranklet transform, and a series of features including compactness, margin, and ellipsoid fitting model were used to describe the morphological characteristics of tumors. Lastly, a logistic regression was used to identify the presence of TP53 and PIK3CA mutations. The classification performances were evaluated by accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Taking into account the trade-offs of sensitivity and specificity, the overall performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The GLCM texture feature based on ranklet transform is more capable of recognizing TP53 and PIK3CA mutations than morphological feature, especially for the TP53 mutation that achieves statistically significant. The area under the ROC curve (AUC) for TP53 mutation dataset A and dataset B achieved 0.78 and 0.81 respectively. For PIK3CA mutation, the AUC of ranklet texture feature was 0.70. Conclusion: Texture analysis of segmented tumor on breast MRI based on ranklet transform is potential in recognizing the presence of TP53 mutation and PIK3CA mutation.

Original languageEnglish
Pages (from-to)60-69
Number of pages10
JournalMagnetic Resonance Imaging
Volume63
DOIs
StatePublished - 1 Nov 2019

Fingerprint

Magnetic resonance imaging
Breast
Textures
Mutation
Tumors
Breast Neoplasms
Neoplasms
ROC Curve
Logistics
Genes
Imaging techniques
Sensitivity and Specificity
p53 Genes
Area Under Curve
Logistic Models

Keywords

  • Breast Cancer
  • Computer-aided diagnosis
  • MRI
  • PIK3CA
  • TP53

Cite this

@article{77d23a7a5d72402490c5a25050b1d3c1,
title = "Evaluation of TP53/PIK3CA mutations using texture and morphology analysis on breast MRI",
abstract = "Purpose: Somatic mutations in TP53 and PIK3CA genes, the two most frequent genetic alternations in breast cancer, are associated with prognosis and therapeutic response. This study predicted the presence of TP53 and PIK3CA mutations in breast cancer by using texture and morphology analyses on breast MRI. Materials and methods: A total of 107 breast cancers (dataset A) from The Cancer Imaging Archive (TCIA) consisting of 40 TP53 mutation cancer and 67 cancers without TP53 mutation; 35 PIK3CA mutations cancer and 72 without PIK3CA mutation. 122 breast cancer (dataset B) from Seoul National University Hospital containing 54 TP53 mutation cancer and 68 without mutations were used in this study. At first, the tumor area was segmented by a region growing method. Subsequently, gray level co-occurrence matrix (GLCM) texture features were extracted after ranklet transform, and a series of features including compactness, margin, and ellipsoid fitting model were used to describe the morphological characteristics of tumors. Lastly, a logistic regression was used to identify the presence of TP53 and PIK3CA mutations. The classification performances were evaluated by accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Taking into account the trade-offs of sensitivity and specificity, the overall performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The GLCM texture feature based on ranklet transform is more capable of recognizing TP53 and PIK3CA mutations than morphological feature, especially for the TP53 mutation that achieves statistically significant. The area under the ROC curve (AUC) for TP53 mutation dataset A and dataset B achieved 0.78 and 0.81 respectively. For PIK3CA mutation, the AUC of ranklet texture feature was 0.70. Conclusion: Texture analysis of segmented tumor on breast MRI based on ranklet transform is potential in recognizing the presence of TP53 mutation and PIK3CA mutation.",
keywords = "Breast Cancer, Computer-aided diagnosis, MRI, PIK3CA, TP53",
author = "Moon, {Woo Kyung} and Chen, {Hong Hao} and Shin, {Sung Ui} and Wonshik Han and Chang, {Ruey Feng}",
year = "2019",
month = "11",
day = "1",
doi = "10.1016/j.mri.2019.08.026",
language = "English",
volume = "63",
pages = "60--69",
journal = "Magnetic Resonance Imaging",
issn = "0730-725X",
publisher = "Elsevier Inc.",

}

Evaluation of TP53/PIK3CA mutations using texture and morphology analysis on breast MRI. / Moon, Woo Kyung; Chen, Hong Hao; Shin, Sung Ui; Han, Wonshik; Chang, Ruey Feng.

In: Magnetic Resonance Imaging, Vol. 63, 01.11.2019, p. 60-69.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluation of TP53/PIK3CA mutations using texture and morphology analysis on breast MRI

AU - Moon, Woo Kyung

AU - Chen, Hong Hao

AU - Shin, Sung Ui

AU - Han, Wonshik

AU - Chang, Ruey Feng

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Purpose: Somatic mutations in TP53 and PIK3CA genes, the two most frequent genetic alternations in breast cancer, are associated with prognosis and therapeutic response. This study predicted the presence of TP53 and PIK3CA mutations in breast cancer by using texture and morphology analyses on breast MRI. Materials and methods: A total of 107 breast cancers (dataset A) from The Cancer Imaging Archive (TCIA) consisting of 40 TP53 mutation cancer and 67 cancers without TP53 mutation; 35 PIK3CA mutations cancer and 72 without PIK3CA mutation. 122 breast cancer (dataset B) from Seoul National University Hospital containing 54 TP53 mutation cancer and 68 without mutations were used in this study. At first, the tumor area was segmented by a region growing method. Subsequently, gray level co-occurrence matrix (GLCM) texture features were extracted after ranklet transform, and a series of features including compactness, margin, and ellipsoid fitting model were used to describe the morphological characteristics of tumors. Lastly, a logistic regression was used to identify the presence of TP53 and PIK3CA mutations. The classification performances were evaluated by accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Taking into account the trade-offs of sensitivity and specificity, the overall performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The GLCM texture feature based on ranklet transform is more capable of recognizing TP53 and PIK3CA mutations than morphological feature, especially for the TP53 mutation that achieves statistically significant. The area under the ROC curve (AUC) for TP53 mutation dataset A and dataset B achieved 0.78 and 0.81 respectively. For PIK3CA mutation, the AUC of ranklet texture feature was 0.70. Conclusion: Texture analysis of segmented tumor on breast MRI based on ranklet transform is potential in recognizing the presence of TP53 mutation and PIK3CA mutation.

AB - Purpose: Somatic mutations in TP53 and PIK3CA genes, the two most frequent genetic alternations in breast cancer, are associated with prognosis and therapeutic response. This study predicted the presence of TP53 and PIK3CA mutations in breast cancer by using texture and morphology analyses on breast MRI. Materials and methods: A total of 107 breast cancers (dataset A) from The Cancer Imaging Archive (TCIA) consisting of 40 TP53 mutation cancer and 67 cancers without TP53 mutation; 35 PIK3CA mutations cancer and 72 without PIK3CA mutation. 122 breast cancer (dataset B) from Seoul National University Hospital containing 54 TP53 mutation cancer and 68 without mutations were used in this study. At first, the tumor area was segmented by a region growing method. Subsequently, gray level co-occurrence matrix (GLCM) texture features were extracted after ranklet transform, and a series of features including compactness, margin, and ellipsoid fitting model were used to describe the morphological characteristics of tumors. Lastly, a logistic regression was used to identify the presence of TP53 and PIK3CA mutations. The classification performances were evaluated by accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Taking into account the trade-offs of sensitivity and specificity, the overall performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The GLCM texture feature based on ranklet transform is more capable of recognizing TP53 and PIK3CA mutations than morphological feature, especially for the TP53 mutation that achieves statistically significant. The area under the ROC curve (AUC) for TP53 mutation dataset A and dataset B achieved 0.78 and 0.81 respectively. For PIK3CA mutation, the AUC of ranklet texture feature was 0.70. Conclusion: Texture analysis of segmented tumor on breast MRI based on ranklet transform is potential in recognizing the presence of TP53 mutation and PIK3CA mutation.

KW - Breast Cancer

KW - Computer-aided diagnosis

KW - MRI

KW - PIK3CA

KW - TP53

UR - http://www.scopus.com/inward/record.url?scp=85070916187&partnerID=8YFLogxK

U2 - 10.1016/j.mri.2019.08.026

DO - 10.1016/j.mri.2019.08.026

M3 - Article

AN - SCOPUS:85070916187

VL - 63

SP - 60

EP - 69

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

SN - 0730-725X

ER -