Association Between Imaging Characteristics and Different Molecular Subtypes of Breast Cancer

doi:10.1016/j.acra.2016.11.012

Academic Radiology

Volume 24, Issue 4, April 2017, Pages 426-434

https://doi.org/10.1016/j.acra.2016.11.012 Get rights and content

Rationale and Objective

Breast cancer can be divided into four major molecular subtypes based on the expression of hormone receptor (estrogen receptor and progesterone receptor), human epidermal growth factor receptor 2, HER2 status, and molecular proliferation rate (Ki67). In this study, we sought to investigate the association between breast cancer subtype and radiological findings in the Chinese population.

Materials and Methods

Medical records of 300 consecutive invasive breast cancer patients were reviewed from the database: the Breast Imaging Reporting and Data System. The imaging characteristics of the lesions were evaluated. The molecular subtypes of breast cancer were classified into four types: luminal A, luminal B, HER2 overexpressed (HER2), and basal-like breast cancer (BLBC). Univariate and multivariate logistic regression analyses were performed to assess the association between the subtype (dependent variable) and mammography or 15 magnetic resonance imaging (MRI) indicators (independent variables).

Results

Luminal A and B subtypes were commonly associated with “clustered calcification distribution,” “nipple invasion,” or “skin invasion” (P < 0.05). The BLBC subtype was more commonly associated with “rim enhancement” and persistent inflow type enhancement in delayed phase (P < 0.05). HER2 overexpressed cancers showed association with persistent enhancement in the delayed phase on MRI and “clustered calcification distribution” on mammography (P < 0.05).

Conclusion

Certain radiological features are strongly associated with the molecular subtype and hormone receptor status of breast tumor, which are potentially useful tools in the diagnosis and subtyping of breast cancer.

Introduction

Breast cancer is one of the most common cancers and one of the leading causes of death among women worldwide (1). It is a heterogeneous disease with several distinct molecular subtypes based on receptor status, including expression of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2–neu (HER2). Immunochemistry staining of the proliferation marker Ki67 and epidermal growth factor receptor (EGFR) also aid in the molecular subtyping of breast cancer. There are four major molecular subtypes: luminal A (ER+ or PR+ and HER2−), luminal B (ER+ or PR+ and HER2+), HER2 (ER− and PR− and HER2+), and basal-like breast cancer (BLBC) (ER−, PR−, and HER2−), which has a significant overlap with triple-negative breast cancer 2, 3, 4. Determination of molecular subtype may aid in treatment planning and monitoring the efficacy of therapy (5).

The different tumor biology of the molecular subtypes of breast cancer exhibits different morphologic patterns and microscopic pathology appearances (6). Different pathologic subtypes may cause different imaging features 7, 8, 9, 10. We sought to investigate the association between imaging characteristics (ultrasound mammography and magnetic resonance imaging [MRI]) and the pathologic subtype of tumors.

A recent pilot study investigated the relationship of MR image phenotypes and the underlying global gene expression patterns (11), and presented a new approach to understand the underlying molecular biology of breast cancer. Additionally, MRI findings such as tumor size, morphology, shape, and enhancement characteristics have been shown to be useful in differentiating breast cancer subtypes 8, 12, 13. However, the diagnoses are usually established with indicators that are dependent on the operators and not comprehensive orquantitative. Very few studies have been carried out in the Chinese population. In this study, we aimed to investigate the association of breast cancer subtypes and radiological findings in Chinese patients.

Section snippets

Patients

A retrospective review of medical records of 300 consecutive patients with invasive breast cancer in Shenzhen People's Hospital, from 2003 to 2013, was performed. All patients had undergone MRI, and histopathological examination of biopsy or surgical specimens was done within a month of MRI examination. The mean age (±standard deviation) of the patients was 46 ± 10 years (age range, 21–77 years). The baseline characteristics, clinical presentation, and mammography and MRI data were compiled.

Baseline Characteristics

The baseline characteristics are summarized in Table 3. The subtype distributions in the study population (N = 300) are as follows: luminal A, N = 144 (48%); luminal B, N = 85 (28.3%); HER2, N = 56 (18.7%); and BLBC, N = 15 (5%).

Association of Subtype with Baseline Characteristics

Patients without skin abnormality were more likely to have BLBC subtype than luminal A or luminal B subtype (P < 0.05); patients without a palpable mass were more likely to have BLBC subtype than Luminal B or HER2 subtype (P < 0.05). Patients without a positive family

Discussion

In this study, we find that radiological features including “rim enhancement,” “delayed phase—describes the enhancement pattern after 2 minutes or after the curve starts to change: persistent,” and “clustered calcification distribution” showed an association with breast cancer subtype (P < 0.05). The BLBC subtype showed a stronger association with “rim enhancement” (14) and “delayed phase —persistent”; luminal A and luminal B subtypes showed a stronger association with “clustered calcification

Acknowledgment

This work was supported by the Project of Science and Technology in Shenzhen, China (JCYJ20150403101146281).

References (22)

K.E. Huber et al.
Breast cancer molecular subtypes in patients with locally advanced disease: impact on prognosis, patterns of recurrence, and response to therapy
Semin Radiat Oncol
(2009)
K. Armstrong et al.
Breast cancer risk prediction and mammography biopsy decisions: a model-based study
Am J Prev Med
(2013)
R.L. Siegel et al.
Cancer statistics
CA Cancer J Clin
(2015)
A. Toss et al.
Molecular characterization and targeted therapeutic approaches in breast cancer
Breast Cancer Res
(2015)
Cancer Genome Atlas Network
Comprehensive molecular portraits of human breast tumours
Nature
(2012)
C.M. Perou et al.
Molecular portraits of human breast tumours
Nature
(2000)
N. Bhooshan et al.
Cancerous breast lesions on dynamic contrast-enhanced MR images: computerized characterization for image-based prognostic markers
Radiology
(2010)
S.C. Agner et al.
Computerized image analysis for identifying triple-negative breast cancers and differentiating them from other molecular subtypes of breast cancer on dynamic contrast-enhanced MR images: a feasibility study
Radiology
(2014)
M.S. Bae et al.
Quantitative MRI morphology of invasive breast cancer: correlation with immunohistochemical biomarkers and subtypes
Acta Radiol
(2015)
A.G. Bitencourt et al.
Role of MRI in the staging of breast cancer patients: does histological type and molecular subtype matter?
Br J Radiol
(2015)

S. Chiacchio et al.

Association between semiquantitative Pet parameters and molecular subtypes of breast invasive ductal carcinoma

Q J Nucl Med Mol Imaging

(2015)

Cited by (37)

Prediction of Receptor Status in Radiomics: Recent Advances in Breast Cancer Research
2024, Academic Radiology
Breast cancer is a multifactorial heterogeneous disease and the leading cause of cancer-related deaths in women; its diagnosis and treatment require clinical sensitivity and a comprehensive disciplinary research approach. The expression of different receptors on tumor cells not only provides the basis for molecular typing of breast cancer but also has a decisive role in the diagnosis, treatment, and prognosis of breast cancer. To date, immunohistochemistry (IHC), which uses invasive histological sampling, has been extensively used in clinical practice to analyze the status of receptors and to make an accurate diagnosis of breast cancer. As an invasive assay, IHC can provide important biological information on tumors at a single point in time, but cannot predict future changes (due to treatment or tumor mutations) without additional invasive procedures. These issues highlight the need to develop a non-invasive method for predicting receptor status. The emerging field of radiomics may offer a non-invasive approach to identification of receptor status without requiring biopsy. In this paper, we present a review of the latest research results in radiomics for predicting the status of breast cancer receptors, with potential important clinical applications.
Correlation between the CEM imaging characteristics and different molecular subtypes of breast cancer
2023, Breast
To investigate the correlation between the contrast-enhanced mammography (CEM) imaging characteristics and different molecular subtypes of breast cancer (BC).
We retrospectively included 313 eligible female patients who underwent CEM examination and surgery in our hospital from July 2017 to July 2021. Their lesions were confirmed on histopathological examination and immunohistochemical analysis. BC was divided into luminal A, luminal B, HER2-enriched, and triple-negative BC (TNBC) subtypes according to immunohistochemical markers. Nine features were extracted from CEM images, including tumor shape, margins, spiculated mass, lobulated mass, malignant calcification, lesion conspicuity, internal enhancement pattern, multifocal mass, and swollen axillary lymph nodes. Statistical analysis was performed using SPSS 25.0. Univariate analysis and binomial regression were used to analyze the correlation between CEM imaging features and BC molecular subtypes.
There were 184 (58.8 %) Luminal A, 44 (14.1 %) Luminal B, 47 (15.0 %) HER-2-enriched and 38 (12.1 %) TNBC, respectively. Molecular subtypes were significantly related to the tumor shape, margins, spiculated mass, internal enhancement pattern, malignant calcification and swollen axillary lymph nodes. Spiculated and calcified tumors were associated with Luminal subtypes, especially Luminal B (P < 0.05). Irregular tumor shape and malignant calcification were associated with HER-2-enriched subtype (P < 0.05). Oval or round tumor shape, rim enhancement, and swollen axillary lymph nodes were associated with TNBC (P < 0.05).
CEM imaging features could distinguish BC molecular subtypes. In particular, TNBC showed oval or round tumor shape, rim enhancement, and swollen axillary lymph nodes, providing insights into the diagnosis and prognosis of TNBC.
Explainable domain transfer of distant supervised cancer subtyping model via imaging-based rules extraction
2023, Artificial Intelligence in Medicine
Image texture analysis has for decades represented a promising opportunity for cancer assessment and disease progression evaluation, evolving in a discipline, i.e., radiomics. However, the road to a complete translation into clinical practice is still hampered by intrinsic limitations. As purely supervised classification models fail in devising robust imaging-based biomarkers for prognosis, cancer subtyping approaches would benefit from the employment of distant supervision, for instance exploiting survival/recurrence information. In this work, we assessed, tested, and validated the domain-generality of our previously proposed Distant Supervised Cancer Subtyping model on Hodgkin Lymphoma. We evaluate the model performance on two independent datasets coming from two hospitals, comparing and analyzing the results. Although successful and consistent, the comparison confirmed the instability of radiomics due to an across-center lack of reproducibility, leading to explainable results in one center and poor interpretability in the other. We thus propose a Random Forest-based Explainable Transfer Model for testing the domain-invariance of imaging biomarkers extracted from retrospective cancer subtyping. In doing so, we tested the predictive ability of cancer subtyping in a validation and perspective setting, which led to successful results and supported the domain-generality of the proposed approach. On the other hand, the extraction of decision rules enables to draw of risk factors and robust biomarkers to inform clinical decisions. This work shows the potentialities of the Distant Supervised Cancer Subtyping model to be further evaluated in larger multi-center datasets, to reliably translate radiomics into medical practice. The code is available at this GitHub repository.
Prediction of molecular subtypes of breast cancer using BI-RADS features based on a “white box” machine learning approach in a multi-modal imaging setting
2019, European Journal of Radiology
Citation Excerpt :
We found that the ages of onset of HER2 and BLBC subtypes were younger than the age of onset for the luminal subtypes (p < 0.001), which was not surprising because HER2 and BLBC were more malignant and progress more quickly [7]. Breastfeeding history differentiated between Luminal A and Luminal B on the decision tree (p < 0.001), a finding that was consistent with our previous study [25]. We found that calcifications were more frequent in the HER-2 subtype, which was concordant with a previous study [26].
To develop and validate an interpretable and repeatable machine learning model approach to predict molecular subtypes of breast cancer from clinical metainformation together with mammography and MRI images.
We retrospectively assessed 363 breast cancer cases (Luminal A 151, Luminal B 96, HER2 76, and BLBC 40). Eighty-two features defined in the BI-RADS lexicon were visually described. A decision tree model with the Chi-squared automatic interaction detector (CHAID) algorithm was applied for feature selection and classification. A 10-fold cross-validation was performed to investigate the performance (i.e., accuracy, positive predictive value, sensitivity, and F1-score) of the decision tree model.
Seven of the 82 variables were derived from the decision tree-based feature selection and used as features for the classification of molecular subtypes including mass margin calcification on mammography, mass margin types of kinetic curves in the delayed phase, mass internal enhancement characteristics, non-mass enhancement distribution on MRI, and breastfeeding history. The decision tree model accuracy was 74.1%. For each molecular subtype group, Luminal A achieved a sensitivity, positive predictive value, and F1-score of 79.47%, 75.47%, and 77.42%, respectively; Luminal B showed a sensitivity, positive predictive value, and F1-score of 64.58%, 55.86%, and 59.90%, respectively; HER2 had a sensitivity, positive predictive value, and F1-scores of 81.58%, 95.38%, and 87.94%, respectively; BLBC showed sensitivity, positive predictive value, and F1-scores of 62.50%, 89.29%, and 73.53%, respectively.
We applied a complete “white box” machine learning method to predict the molecular subtype of breast cancer based on the BI-RADS feature description in a multi-modal setting. By combining BI-RADS features in both mammography and MRI, the prediction accuracy is boosted and robust. The proposed method can be easily applied widely regardless of variability of imaging vendors and settings because of the applicability and acceptance of the BI-RADS.
Breast Cancer Molecular Subtype Prediction by Mammographic Radiomic Features
2019, Academic Radiology
Citation Excerpt :
Recently, breast cancer subtype characterization has made progress on using radiological images. For example, certain qualitative and visual information of the imaging characteristics assessed on breast magnetic resonance imaging (MRI), mammography, or ultrasound has been shown to be related to the molecular subtypes of breast cancer (5–8). Radiomics refers to the extraction and analysis of a large amount of quantitative imaging features from medical images, which has been extensively studied in recent literature, demonstrating predictive or prognostic associations between quantitative imaging features and medical outcome (9,10).
This study aimed to investigate whether quantitative radiomic features extracted from digital mammogram images are associated with molecular subtypes of breast cancer.
In this institutional review board–approved retrospective study, we collected 331 Chinese women who were diagnosed with invasive breast cancer in 2015. This cohort included 29 triple-negative, 45 human epidermal growth factor receptor 2 (HER2)-enriched, 36 luminal A, and 221 luminal B lesions. A set of 39 quantitative radiomic features, including morphologic, grayscale statistic, and texture features, were extracted from the segmented lesion area. Three binary classifications of the subtypes were performed: triple-negative vs non–triple-negative, HER2-enriched vs non–HER2-enriched, and luminal (A + B) vs nonluminal. The Naive Bayes machine learning scheme was employed for the classification, and the least absolute shrink age and selection operator method was used to select the most predictive features for the classifiers. Classification performance was evaluated by the area under receiver operating characteristic curve and accuracy.
The model that used the combination of both the craniocaudal and the mediolateral oblique view images achieved the overall best performance than using either of the two views alone, yielding an area under receiver operating characteristic curve (or accuracy) of 0.865 (0.796) for triple-negative vs non–triple-negative, 0.784 (0.748) for HER2-enriched vs non–HER2-enriched, and 0.752 (0.788) for luminal vs nonluminal subtypes. Twelve most predictive features were selected by the least absolute shrink age and selection operator method and four of them (ie, roundness, concavity, gray mean, and correlation) showed a statistical significance (P < .05) in the subtype classification.
Our study showed that quantitative radiomic imaging features of breast tumor extracted from digital mammograms are associated with breast cancer subtypes. Future larger studies are needed to further evaluate the findings.
Transcripts of cytokeratins as predictors of breast cancer
2018, Gene Reports
Citation Excerpt :
However, several factors are intertwined during malignant transformation and tumor development (DeSantis et al., 2016; Apuri, 2017). For this reason, the search for molecular changes that may affect the biology of cancer development and progression may be important for understanding this disease and improving clinical management of BC patients (Wu and Ma, 2017). Distinct keratins emerge as highly dynamic scaffolds involved in different settings and contribute to cell size determination, translation control, proliferation, cell type-specific organelle transport and malignant transformation (Liu et al., 2018).
Cytokeratins (CK) belong to a large family of intermediate filaments that are primarily expressed in epithelial cells and whose members are expressed in various combinations in normal and malignant entities. In breast cancer (BC), keratin typing is a major tool in tumor histodiagnosis, providing molecular parameters to assess its differentiation status. In our study, we evaluated CK5, CK6, CK8, CK14 and CK18 mRNA levels by qPCR, and CK18, CK5 and CK14 transcripts were effective to differentiate breast tumors from benign diseases. Relative quantification of CK18 mRNA levels was 2.08-fold higher in benign breast disease than in BC. The same expression pattern was observed for CK5 and CK14, which were 2.4 and 4.8-fold higher in nonmalignant tissues, and CK18 correlated with CK5, CK6, CK8 and CK14 mRNA expression. Cytokeratins 8/18 and 5/14 presented the same pattern according to molecular subtypes. However, CK18 itself correlated to clinical outcome in tumor phenotyping. We suggest that the mechanisms underlying the increased expression of cytokeratins in breast tumors may be similar, and CK18, CK5 and CK14 transcripts may be important in the tumorigenic process, distinguishing normal from tumor cells.

View all citing articles on Scopus

View full text

Original InvestigationAssociation Between Imaging Characteristics and Different Molecular Subtypes of Breast Cancer

Rationale and Objective

Materials and Methods

Results

Conclusion

Introduction

Section snippets

Patients

Baseline Characteristics

Association of Subtype with Baseline Characteristics

Discussion

Acknowledgment

Semin Radiat Oncol

Am J Prev Med

Cancer statistics

CA Cancer J Clin

Molecular characterization and targeted therapeutic approaches in breast cancer

Breast Cancer Res

Comprehensive molecular portraits of human breast tumours

Nature

Molecular portraits of human breast tumours

Nature

Cancerous breast lesions on dynamic contrast-enhanced MR images: computerized characterization for image-based prognostic markers

Radiology

Computerized image analysis for identifying triple-negative breast cancers and differentiating them from other molecular subtypes of breast cancer on dynamic contrast-enhanced MR images: a feasibility study

Radiology

Quantitative MRI morphology of invasive breast cancer: correlation with immunohistochemical biomarkers and subtypes

Acta Radiol

Role of MRI in the staging of breast cancer patients: does histological type and molecular subtype matter?

Br J Radiol

Association between semiquantitative Pet parameters and molecular subtypes of breast invasive ductal carcinoma

Q J Nucl Med Mol Imaging

Original Investigation
Association Between Imaging Characteristics and Different Molecular Subtypes of Breast Cancer