Radiomic machine learning for predicting prognostic biomarkers and molecular subtypes of breast cancer using tumor heterogeneity and angiogenesis properties on MRI

Lee, Ji Young; Lee, Kwang-Sig; Seo, Bo Kyoung; Cho, Kyu Ran; Woo, Ok Hee; Song, Sung Eun; Kim, Min Jung; Lee, Hye Yoon; Kim, Jung Sun; Cha, Jaehyung

doi:10.1007/s00330-021-08146-8

Cited by 73 publications

(77 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the five machine learning models tested, the integrated random forest model was the best for the overall prediction of histological factors (median AUC = 0.76), and the random forest model was best for the prediction of HER2 expression (AUC = 0.86). These results are similar to those reported for an integrated model using texture and perfusion features of breast cancer on MRI (AUC = 0.80) in a recent study by Lee et al [6]. In our study, the most important top five CT parameters for prediction were entropy on contrast-enhanced images, entropy on precontrast images, perfusion of hot spots, TTP of hot spots, and PEI of hot spots.…”

Section: Discussionsupporting

confidence: 92%

“…Recent studies have shown that applying machine learning algorithms to radiolog data is useful for predicting histological factors or treatment response in breast can patients [6,7,[20][21][22]. We evaluated CT-based predictions of histological factors treatment failure using five supervised machine learning algorithms: logistic regress naïve Bayes, decision tree, random forest, and artificial neural network (ANN).…”

Section: Patientsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

Park

Lee

Seo

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01–1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Patientsmentioning

confidence: 99%

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

Park

Lee

Seo

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several studies applied radiomics based on breast MRI for the evaluation of malignancy, differentiation of molecular subtype, prediction of receptor expression, and evaluation of response to neoadjuvant therapy in breast cancer (27,(32)(33)(34)(35). Some studies have reported that quantitative parameters of functional MRI, deep learning analysis, and MRI-based radiomics analysis had the potential in predicting molecular subtype and Ki-67 expression in breast cancer (36)(37)(38)(39)(40)(41)(42)(43)(44)(45). However, no published study reported the accuracy of MRI combining with radiomics in predicting AR expression and explored the importance of different MRI sequences in predicting molecular subtype of breast cancer.…”

Section: Introductionmentioning

confidence: 99%

Multi-Parametric MRI-Based Radiomics Models for Predicting Molecular Subtype and Androgen Receptor Expression in Breast Cancer

Huang

Wei

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

ObjectiveTo investigate whether radiomics features extracted from multi-parametric MRI combining machine learning approach can predict molecular subtype and androgen receptor (AR) expression of breast cancer in a non-invasive way.Materials and MethodsPatients diagnosed with clinical T2–4 stage breast cancer from March 2016 to July 2020 were retrospectively enrolled. The molecular subtypes and AR expression in pre-treatment biopsy specimens were assessed. A total of 4,198 radiomics features were extracted from the pre-biopsy multi-parametric MRI (including dynamic contrast-enhancement T1-weighted images, fat-suppressed T2-weighted images, and apparent diffusion coefficient map) of each patient. We applied several feature selection strategies including the least absolute shrinkage and selection operator (LASSO), and recursive feature elimination (RFE), the maximum relevance minimum redundancy (mRMR), Boruta and Pearson correlation analysis, to select the most optimal features. We then built 120 diagnostic models using distinct classification algorithms and feature sets divided by MRI sequences and selection strategies to predict molecular subtype and AR expression of breast cancer in the testing dataset of leave-one-out cross-validation (LOOCV). The performances of binary classification models were assessed via the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). And the performances of multiclass classification models were assessed via AUC, overall accuracy, precision, recall rate, and F1-score.ResultsA total of 162 patients (mean age, 46.91 ± 10.08 years) were enrolled in this study; 30 were low-AR expression and 132 were high-AR expression. HR+/HER2− cancers were diagnosed in 56 cases (34.6%), HER2+ cancers in 81 cases (50.0%), and TNBC in 25 patients (15.4%). There was no significant difference in clinicopathologic characteristics between low-AR and high-AR groups (P > 0.05), except the menopausal status, ER, PR, HER2, and Ki-67 index (P = 0.043, <0.001, <0.001, 0.015, and 0.006, respectively). No significant difference in clinicopathologic characteristics was observed among three molecular subtypes except the AR status and Ki-67 (P = <0.001 and 0.012, respectively). The Multilayer Perceptron (MLP) showed the best performance in discriminating AR expression, with an AUC of 0.907 and an accuracy of 85.8% in the testing dataset. The highest performances were obtained for discriminating TNBC vs. non-TNBC (AUC: 0.965, accuracy: 92.6%), HER2+ vs. HER2− (AUC: 0.840, accuracy: 79.0%), and HR+/HER2− vs. others (AUC: 0.860, accuracy: 82.1%) using MLP as well. The micro-AUC of MLP multiclass classification model was 0.896, and the overall accuracy was 0.735.ConclusionsMulti-parametric MRI-based radiomics combining with machine learning approaches provide a promising method to predict the molecular subtype and AR expression of breast cancer non-invasively.

show abstract

“…Radiomic features could also reflect the angiogenesis status and microvascular density in bladder urothelial carcinoma and in clear-cell renal-cell carcinoma [ 42 , 43 ]. Radiomic parameters also predict microvascular density and angiogenesis in breast cancer [ 44 , 45 , 46 ]. In the study by Dooman Arefan and collaborators, a set of radiomic features identified the heterogeneity of tumor microenvironment cells, with an abundance of fibroblasts and the presence of endothelial and immune cells [ 44 ].…”

Section: Liver Premetastatic Niche Formation In Crc Patientsmentioning

confidence: 99%

“…Reasonably, the different phases of metastatic niche formation (each one represented by a puzzle piece in the figure) could be detected by radiogenomics approaches in the near future. The references included in the figure show related manuscript with information about tumor cell extravasation [ 34 , 35 ], neoangiogenesis [ 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 ], immunosurveillance evasion [ 44 , 47 , 48 , 49 , 50 , 51 , 52 , 53 ] and tumor growth [ 41 ] that could be theoretically translated to metastatic niche detection. Created with BioRender.com.…”

Section: Figurementioning

confidence: 99%

Radiogenomics: Hunting Down Liver Metastasis in Colorectal Cancer Patients

Pinta

Castillo

Collado

et al. 2021

Cancers

View full text Add to dashboard Cite

Radiomics is a developing new discipline that analyzes conventional medical images to extract quantifiable data that can be mined for new biomarkers that show the biology of pathological processes at microscopic levels. These data can be converted into image-based signatures to improve diagnostic, prognostic and predictive accuracy in cancer patients. The combination of radiomics and molecular data, called radiogenomics, has clear implications for cancer patients’ management. Though some studies have focused on radiogenomics signatures in hepatocellular carcinoma patients, only a few have examined colorectal cancer metastatic lesions in the liver. Moreover, the need to differentiate between liver lesions is fundamental for accurate diagnosis and treatment. In this review, we summarize the knowledge gained from radiomics and radiogenomics studies in hepatic metastatic colorectal cancer patients and their use in early diagnosis, response assessment and treatment decisions. We also investigate their value as possible prognostic biomarkers. In addition, the great potential of image mining to provide a comprehensive view of liver niche formation is examined thoroughly. Finally, new challenges and current limitations for the early detection of the liver premetastatic niche, based on radiomics and radiogenomics, are also discussed.

show abstract

Radiomic machine learning for predicting prognostic biomarkers and molecular subtypes of breast cancer using tumor heterogeneity and angiogenesis properties on MRI

Cited by 73 publications

References 40 publications

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

Multi-Parametric MRI-Based Radiomics Models for Predicting Molecular Subtype and Androgen Receptor Expression in Breast Cancer

Radiogenomics: Hunting Down Liver Metastasis in Colorectal Cancer Patients

Contact Info

Product

Resources

About