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

Editorial for "A Channel-Dimensional Feature-Reconstructed Deep Learning Model for Predicting Breast Cancer Molecular Subtypes on Overall b-Value Diffusion-Weighted MRI"

Level of Evidence

5

Technical Efficacy Stage

2

A Channel-Dimensional Feature-Reconstructed Deep Learning Model for Predicting Breast Cancer Molecular Subtypes on Overall b-Value Diffusion-Weighted MRI

BACKGROUND

Dynamic contrast-enhanced (DCE) MRI commonly outperforms diffusion-weighted (DW) MRI in breast cancer discrimination. However, the side effects of contrast agents limit the use of DCE-MRI, particularly in patients with chronic kidney disease.

PURPOSE

To develop a novel deep learning model to fully exploit the potential of overall b-value DW-MRI without the need for a contrast agent in predicting breast cancer molecular subtypes and to evaluate its performance in comparison with DCE-MRI.

STUDY TYPE

Prospective.

SUBJECTS

486 female breast cancer patients (training/validation/test: 64%/16%/20%).

FIELD STRENGTH/SEQUENCE

3.0 T/DW-MRI (13 b-values) and DCE-MRI (one precontrast and five postcontrast phases).

ASSESSMENT

The breast cancers were divided into four subtypes: luminal A, luminal B, HER2+, and triple negative. A channel-dimensional feature-reconstructed (CDFR) deep neural network (DNN) was proposed to predict these subtypes using pathological diagnosis as the reference standard. Additionally, a non-CDFR DNN (NCDFR-DNN) was built for comparative purposes. A mixture ensemble DNN (ME-DNN) integrating two CDFR-DNNs was constructed to identify subtypes on multiparametric MRI (MP-MRI) combing DW-MRI and DCE-MRI.

STATISTICAL TESTS

Model performance was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Model comparisons were performed using the one-way analysis of variance with least significant difference post hoc test and the DeLong test. P < 0.05 was considered significant.

RESULTS

The CDFR-DNN (accuracies, 0.79 ~ 0.80; AUCs, 0.93 ~ 0.94) demonstrated significantly improved predictive performance than the NCDFR-DNN (accuracies, 0.76 ~ 0.78; AUCs, 0.92 ~ 0.93) on DW-MRI. Utilizing the CDFR-DNN, DW-MRI attained the predictive performance equal (P = 0.065 ~ 1.000) to DCE-MRI (accuracies, 0.79 ~ 0.80; AUCs, 0.93 ~ 0.95). The predictive performance of the ME-DNN on MP-MRI (accuracies, 0.85 ~ 0.87; AUCs, 0.96 ~ 0.97) was superior to those of both the CDFR-DNN and NCDFR-DNN on either DW-MRI or DCE-MRI.

DATA CONCLUSION

The CDFR-DNN enabled overall b-value DW-MRI to achieve the predictive performance comparable to DCE-MRI. MP-MRI outperformed DW-MRI and DCE-MRI in subtype prediction.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY STAGE: 1.

Multiparametric MR-based feature fusion radiomics combined with ADC maps-based tumor proliferative burden in distinguishing TNBC versus non-TNBC

Objective.To investigate the incremental value of quantitative stratified apparent diffusion coefficient (ADC) defined tumor habitats for differentiating triple negative breast cancer (TNBC) from non-TNBC on multiparametric MRI (mpMRI) based feature-fusion radiomics (RFF) model.Approach.466 breast cancer patients (54 TNBC, 412 non-TNBC) who underwent routine breast MRIs in our hospital were retrospectively analyzed. Radiomics features were extracted from whole tumor on T2WI, diffusion-weighted imaging, ADC maps and the 2nd phase of dynamic contrast-enhanced MRI. Four models including the RFFmodel (fused features from all MRI sequences), RADCmodel (ADC radiomics feature), StratifiedADCmodel (tumor habitas defined on stratified ADC parameters) and combinational RFF-StratifiedADCmodel were constructed to distinguish TNBC versus non-TNBC. All cases were randomly divided into a training (n= 337) and test set (n= 129). The four competing models were validated using the area under the curve (AUC), sensitivity, specificity and accuracy.Main results.Both the RFFand StratifiedADCmodels demonstrated good performance in distinguishing TNBC from non-TNBC, with best AUCs of 0.818 and 0.773 in the training and test sets. StratifiedADCmodel revealed significant different tumor habitats (necrosis/cysts habitat, chaotic habitat or proliferative tumor core) between TNBC and non-TNBC with its top three discriminative parameters (p <0.05). The integrated RFF-StratifiedADCmodel demonstrated superior accuracy over the other three models, with higher AUCs of 0.832 and 0.784 in the training and test set, respectively (p <0.05).Significance.The RFF-StratifiedADCmodel through integrating various tumor habitats' information from whole-tumor ADC maps-based StratifiedADCmodel and radiomics information from mpMRI-based RFFmodel, exhibits tremendous promise for identifying TNBC.

Comparison of Dynamic Contrast-Enhanced MRI and Non-Mono-Exponential Model-Based Diffusion-Weighted Imaging for the Prediction of Prognostic Biomarkers and Molecular Subtypes of Breast Cancer Based on Radiomics

BACKGROUND

Dynamic contrast-enhanced (DCE) MRI and non-mono-exponential model-based diffusion-weighted imaging (NME-DWI) that does not require contrast agent can both characterize breast cancer. However, which technique is superior remains unclear.

PURPOSE

To compare the performances of DCE-MRI, NME-DWI and their combination as multiparametric MRI (MP-MRI) in the prediction of breast cancer prognostic biomarkers and molecular subtypes based on radiomics.

STUDY TYPE

Prospective.

POPULATION

A total of 477 female patients with 483 breast cancers (5-fold cross-validation: training/validation, 80%/20%).

FIELD STRENGTH/SEQUENCE

A 3.0 T/DCE-MRI (6 dynamic frames) and NME-DWI (13 b values).

ASSESSMENT

After data preprocessing, high-throughput features were extracted from each tumor volume of interest, and optimal features were selected using recursive feature elimination method. To identify ER+ vs. ER-, PR+ vs. PR-, HER2+ vs. HER2-, Ki-67+ vs. Ki-67-, luminal A/B vs. nonluminal A/B, and triple negative (TN) vs. non-TN, the following models were implemented: random forest, adaptive boosting, support vector machine, linear discriminant analysis, and logistic regression.

STATISTICAL TESTS

Student's t, chi-square, and Fisher's exact tests were applied on clinical characteristics to confirm whether significant differences exist between different statuses (±) of prognostic biomarkers or molecular subtypes. The model performances were compared between the DCE-MRI, NME-DWI, and MP-MRI datasets using the area under the receiver-operating characteristic curve (AUC) and the DeLong test. P < 0.05 was considered significant.

RESULTS

With few exceptions, no significant differences (P = 0.062-0.984) were observed in the AUCs of models for six classification tasks between the DCE-MRI (AUC = 0.62-0.87) and NME-DWI (AUC = 0.62-0.91) datasets, while the model performances on the two imaging datasets were significantly poorer than on the MP-MRI dataset (AUC = 0.68-0.93). Additionally, the random forest and adaptive boosting models (AUC = 0.62-0.93) outperformed other three models (AUC = 0.62-0.90).

DATA CONCLUSION

NME-DWI was comparable with DCE-MRI in predictive performance and could be used as an alternative technique. Besides, MP-MRI demonstrated significantly higher AUCs than either DCE-MRI or NME-DWI.

EVIDENCE LEVEL

2.

TECHNICAL EFFICACY

Stage 2.

Breast Cancer Surrogate Subtype Classification Using Pretreatment Multi-Phase Dynamic Contrast-Enhanced Magnetic Resonance Imaging Radiomics: A Retrospective Single-Center Study

This study aimed to explore the potential of multi-phase dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics for classifying breast cancer surrogate subtypes. This retrospective study analyzed 360 breast cancers from 319 patients who underwent pretreatment DCE-MRI between January 2015 and January 2019. The cohort consisted of 33 triple-negative, 26 human epidermal growth factor receptor 2 (HER2)-positive, 109 luminal A-like, 144 luminal B-like HER2-negative, and 48 luminal B-like HER2-positive lesions. A total of 1781 radiomic features were extracted from manually segmented breast cancers in each DCE-MRI sequence. The model was internally validated and selected using ten times repeated five-fold cross-validation on the primary cohort, with further evaluation using a validation cohort. The most successful models were logistic regression models applied to the third post-contrast subtraction images. These models exhibited the highest area under the curve (AUC) for discriminating between luminal A like vs. others (AUC: 0.78), luminal B-like HER2 negative vs. others (AUC: 0.57), luminal B-like HER2 positive vs. others (AUC: 0.60), HER2 positive vs. others (AUC: 0.81), and triple negative vs. others (AUC: 0.83). In conclusion, the radiomic features extracted from multi-phase DCE-MRI are promising for discriminating between breast cancer subtypes. The best-performing models relied on tissue changes observed during the mid-stage of the imaging process.

Comparison of CT- and MRI-Based Quantification of Tumor Heterogeneity and Vascularity for Correlations with Prognostic Biomarkers and Survival Outcomes: A Single-Center Prospective Cohort Study

BACKGROUND

Tumor heterogeneity and vascularity can be noninvasively quantified using histogram and perfusion analyses on computed tomography (CT) and magnetic resonance imaging (MRI). We compared the association of histogram and perfusion features with histological prognostic factors and progression-free survival (PFS) in breast cancer patients on low-dose CT and MRI.

METHODS

This prospective study enrolled 147 women diagnosed with invasive breast cancer who simultaneously underwent contrast-enhanced MRI and CT before treatment. We extracted histogram and perfusion parameters from each tumor on MRI and CT, assessed associations between imaging features and histological biomarkers, and estimated PFS using the Kaplan-Meier analysis.

RESULTS

Out of 54 histogram and perfusion parameters, entropy on T2- and postcontrast T1-weighted MRI and postcontrast CT, and perfusion (blood flow) on CT were significantly associated with the status of subtypes, hormone receptors, and human epidermal growth factor receptor 2 (p < 0.05). Patients with high entropy on postcontrast CT showed worse PFS than patients with low entropy (p = 0.053) and high entropy on postcontrast CT negatively affected PFS in the Ki67-positive group (p = 0.046).

CONCLUSIONS

Low-dose CT histogram and perfusion analysis were comparable to MRI, and the entropy of postcontrast CT could be a feasible parameter to predict PFS in breast cancer patients.

Cross-attention multi-branch CNN using DCE-MRI to classify breast cancer molecular subtypes

Purpose

The aim of this study is to improve the accuracy of classifying luminal or non-luminal subtypes of breast cancer by using computer algorithms based on DCE-MRI, and to validate the diagnostic efficacy of the model by considering the patient's age of menarche and nodule size.

Methods

DCE-MRI images of patients with non-specific invasive breast cancer admitted to the Second Affiliated Hospital of Dalian Medical University were collected. There were 160 cases in total, with 84 cases of luminal type (luminal A and luminal B and 76 cases of non-luminal type (HER 2 overexpressing and triple negative). Patients were grouped according to thresholds of nodule sizes of 20 mm and age at menarche of 14 years. A cross-attention multi-branch net CAMBNET) was proposed based on the dataset to predict the molecular subtypes of breast cancer. Diagnostic performance was assessed by accuracy, sensitivity, specificity, F1 and area under the ROC curve (AUC). And the model is visualized with Grad-CAM.

Results

Several classical deep learning models were included for diagnostic performance comparison. Using 5-fold cross-validation on the test dataset, all the results of CAMBNET are significantly higher than the compared deep learning models. The average prediction recall, accuracy, precision, and AUC for luminal and non-luminal types of the dataset were 89.11%, 88.44%, 88.52%, and 96.10%, respectively. For patients with tumor size <20 mm, the CAMBNET had AUC of 83.45% and ACC of 90.29% for detecting triple-negative breast cancer. When classifying luminal from non-luminal subtypes for patients with age at menarche years, our CAMBNET model achieved an ACC of 92.37%, precision of 92.42%, recall of 93.33%, F1of 92.33%, and AUC of 99.95%.

Conclusions

The CAMBNET can be applied in molecular subtype classification of breasts. For patients with menarche at 14 years old, our model can yield more accurate results when classifying luminal and non-luminal subtypes. For patients with tumor sizes ≤20 mm, our model can yield more accurate result in detecting triple-negative breast cancer to improve patient prognosis and survival.

Imaging Techniques in Pharmacological Precision Medicine

Biomedical imaging is a powerful tool for medical diagnostics and personalized medicines. Examples of commonly used imaging modalities include Positron Emission Tomography (PET), Ultrasound (US), Single Photon Emission Computed Tomography (SPECT), and hybrid imaging. By combining these modalities, scientists can gain a comprehensive view and better understand physiology and pathology at the preclinical, clinical, and multiscale levels. This can aid in the accuracy of medical diagnoses and treatment decisions. Moreover, biomedical imaging allows for evaluating the metabolic, functional, and structural details of living tissues. This can be particularly useful for the early diagnosis of diseases such as cancer and for the application of personalized medicines. In the case of hybrid imaging, two or more modalities are combined to produce a high-resolution image with enhanced sensitivity and specificity. This can significantly improve the accuracy of diagnosis and offer more detailed treatment plans. In this book chapter, we showcase how continued advancements in biomedical imaging technology can potentially revolutionize medical diagnostics and personalized medicine.

Radiomics nomogram for predicting axillary lymph node metastasis in breast cancer based on DCE-MRI: A multicenter study

OBJECTIVES

This study aims to develop and validate a radiomics nomogram based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to noninvasively predict axillary lymph node (ALN) metastasis in breast cancer.

METHODS

This retrospective study included 263 patients with histologically proven invasive breast cancer and who underwent DCE-MRI examination before surgery in two hospitals. All patients had a defined ALN status based on pathological examination results. Regions of interest (ROIs) of the primary tumor and ipsilateral ALN were manually drawn. A total of 1,409 radiomics features were initially computed from each ROI. Next, the low variance threshold, SelectKBest, and least absolute shrinkage and selection operator (LASSO) algorithms were used to extract the radiomics features. The selected radiomics features were used to establish the radiomics signature of the primary tumor and ALN. A radiomics nomogram model, including the radiomics signature and the independent clinical risk factors, was then constructed. The predictive performance was evaluated by the receiver operating characteristic (ROC) curves, calibration curve, and decision curve analysis (DCA) by using the training and testing sets.

RESULTS

ALNM rates of the training, internal testing, and external testing sets were 43.6%, 44.3% and 32.3%, respectively. The nomogram, including clinical risk factors (tumor diameter) and radiomics signature of the primary tumor and ALN, showed good calibration and discrimination with areas under the ROC curves of 0.884, 0.822, and 0.813 in the training, internal and external testing sets, respectively. DCA also showed that radiomics nomogram displayed better clinical predictive usefulness than the clinical or radiomics signature alone.

CONCLUSIONS

The radiomics nomogram combined with clinical risk factors and DCE-MRI-based radiomics signature may be used to predict ALN metastasis in a noninvasive manner.

Radiomics-based signature of breast cancer on preoperative contrast-enhanced MRI to predict axillary metastasis

Aim: This study aimed to predict axillary metastasis using radiology features in dynamic contrast-enhanced MRI. Methods: This study included 243 breast lesions confirmed as malignant based on axillary status. Most outcome-predictive features were selected using four machine-learning algorithms. Receiver operating characteristic analysis was used to reflect diagnostic performance. Results: Least absolute shrinkage and selection operator was used to dimensionally reduce 1137 radiomics features to three features. Three optimal radiomics features were used to model construction. The logistic regression model achieved an accuracy of 97% and 85% in the training and test groups. Clinical utility was evaluated using decision curve analysis. Conclusion: The novel combination of radiomics analysis and machine-learning algorithm could predict axillary metastasis and prevent invasive manipulation.

Predicting hormone receptors and PAM50 subtypes of breast cancer from multi-scale lesion images of DCE-MRI with transfer learning technique

BACKGROUND

The recent development of artificial intelligence (AI) technologies coupled with medical imaging data has gained considerable attention, and offers a non-invasive approach for cancer diagnosis and prognosis. In this context, improved breast cancer (BC) molecular characteristics assessment models are foreseen to enable personalized strategies with better clinical outcomes compared to existing screening strategies. And it is a promising approach to developing models for hormone receptors (HR) and subtypes of BC patients from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data.

METHODS

In this institutional review board-approved study, 174 BC patients with both DCE-MRI and RNA-seq data in the local database were analyzed. Slice images from tumor lesions and multi-scale peri-tumor regions were used as model inputs, and five representative pre-trained transfer learning (TF) networks, such as Inception-v3 and Xception, were employed to establish prediction models. A comprehensive analysis was performed using five-fold cross-validation to avoid overfitting, and accuracy (ACC) and area under the receiver operating characteristic curve (AUROC) to evaluate model performance.

RESULTS

Xception achieved the superior results when using solely tumor regions, with highest AUROCs of 0.844 (95% CI: [0.841, 0.847]) and 0.784 (95% CI: [0.781, 0.788]) for estrogen receptor (ER) and progesterone receptor (PR), respectively, and best ACC of 0.467 (95% CI: [0.462, 0.470]) for PAM50 subtypes. A significant improvement in the model performance was observed when images of the peri-tumor region were included, with optimal results achieved using images of the tumor and the 10 mm peri-tumor regions. Xception-based TF models performed most effectively in predicting ER and PR statuses, with the AUROCs were 0.942 (95% CI: [0.940, 0.944]) and 0.920 (95% CI: [0.917, 0.922]), respectively, whereas for PAM50 subtypes, the Inception-v3-based network yielded the highest ACC as 0.742 (95% CI: [0.738, 0.746]).

CONCLUSIONS

Transfer learning analysis based on DCE-MRI data of tumor and peri-tumor regions was helpful to the non-invasive assessment of molecular characteristics of BC.

Global Research Trends of Artificial Intelligence on Histopathological Images: A 20-Year Bibliometric Analysis

Cancer has become a major threat to global health care. With the development of computer science, artificial intelligence (AI) has been widely applied in histopathological images (HI) analysis. This study analyzed the publications of AI in HI from 2001 to 2021 by bibliometrics, exploring the research status and the potential popular directions in the future. A total of 2844 publications from the Web of Science Core Collection were included in the bibliometric analysis. The country/region, institution, author, journal, keyword, and references were analyzed by using VOSviewer and CiteSpace. The results showed that the number of publications has grown rapidly in the last five years. The USA is the most productive and influential country with 937 publications and 23,010 citations, and most of the authors and institutions with higher numbers of publications and citations are from the USA. Keyword analysis showed that breast cancer, prostate cancer, colorectal cancer, and lung cancer are the tumor types of greatest concern. Co-citation analysis showed that classification and nucleus segmentation are the main research directions of AI-based HI studies. Transfer learning and self-supervised learning in HI is on the rise. This study performed the first bibliometric analysis of AI in HI from multiple indicators, providing insights for researchers to identify key cancer types and understand the research trends of AI application in HI.

Integrated imaging and molecular analysis to decipher tumor microenvironment in the era of immunotherapy

Radiological imaging is an integral component of cancer care, including diagnosis, staging, and treatment response monitoring. It contains rich information about tumor phenotypes that are governed not only by cancer cellintrinsic biological processes but also by the tumor microenvironment, such as the composition and function of tumor-infiltrating immune cells. By analyzing the radiological scans using a quantitative radiomics approach, robust relations between specific imaging and molecular phenotypes can be established. Indeed, a number of studies have demonstrated the feasibility of radiogenomics for predicting intrinsic molecular subtypes and gene expression signatures in breast cancer based on MRI. In parallel, promising results have been shown for inferring the amount of tumor-infiltrating lymphocytes, a key factor for the efficacy of cancer immunotherapy, from standard-of-care radiological images. Compared with the biopsy-based approach, radiogenomics offers a unique avenue to profile the molecular makeup of the tumor and immune microenvironment as well as its evolution in a noninvasive and holistic manner through longitudinal imaging scans. Here, we provide a systematic review of the state of the art radiogenomics studies in the era of immunotherapy and discuss emerging paradigms and opportunities in AI and deep learning approaches. These technical advances are expected to transform the radiogenomics field, leading to the discovery of reliable imaging biomarkers. This will pave the way for their clinical translation to guide precision cancer therapy.

Radiogenomics analysis reveals the associations of dynamic contrast-enhanced–MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer

Background

To investigate reliable associations between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and gene expression characteristics in breast cancer (BC) and to develop and validate classifiers for predicting PAM50 subtypes and prognosis from DCE-MRI non-invasively.

Methods

Two radiogenomics cohorts with paired DCE-MRI and RNA-sequencing (RNA-seq) data were collected from local and public databases and divided into discovery (n = 174) and validation cohorts (n = 72). Six external datasets (n = 1,443) were used for prognostic validation. Spatial–temporal features of DCE-MRI were extracted, normalized properly, and associated with gene expression to identify the imaging features that can indicate subtypes and prognosis.

Results

Expression of genes including RBP4, MYBL2, and LINC00993 correlated significantly with DCE-MRI features (q-value < 0.05). Importantly, genes in the cell cycle pathway exhibited a significant association with imaging features (p-value < 0.001). With eight imaging-associated genes (CHEK1, TTK, CDC45, BUB1B, PLK1, E2F1, CDC20, and CDC25A), we developed a radiogenomics prognostic signature that can distinguish BC outcomes in multiple datasets well. High expression of the signature indicated a poor prognosis (p-values < 0.01). Based on DCE-MRI features, we established classifiers to predict BC clinical receptors, PAM50 subtypes, and prognostic gene sets. The imaging-based machine learning classifiers performed well in the independent dataset (areas under the receiver operating characteristic curve (AUCs) of 0.8361, 0.809, 0.7742, and 0.7277 for estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2)-enriched, basal-like, and obtained radiogenomics signature). Furthermore, we developed a prognostic model directly using DCE-MRI features (p-value < 0.0001).

Conclusions

Our results identified the DCE-MRI features that are robust and associated with the gene expression in BC and displayed the possibility of using the features to predict clinical receptors and PAM50 subtypes and to indicate BC prognosis.

Preoperative Non-Invasive Prediction of Breast Cancer Molecular Subtypes With a Deep Convolutional Neural Network on Ultrasound Images

Purpose

This study aimed to develop a deep convolutional neural network (DCNN) model to classify molecular subtypes of breast cancer from ultrasound (US) images together with clinical information.

Methods

A total of 1,012 breast cancer patients with 2,284 US images (center 1) were collected as the main cohort for training and internal testing. Another cohort of 117 breast cancer cases with 153 US images (center 2) was used as the external testing cohort. Patients were grouped according to thresholds of nodule sizes of 20 mm and age of 50 years. The DCNN models were constructed based on US images and the clinical information to predict the molecular subtypes of breast cancer. A Breast Imaging-Reporting and Data System (BI-RADS) lexicon model was built on the same data based on morphological and clinical description parameters for diagnostic performance comparison. The diagnostic performance was assessed through the accuracy, sensitivity, specificity, Youden’s index (YI), and area under the receiver operating characteristic curve (AUC).

Results

Our DCNN model achieved better diagnostic performance than the BI-RADS lexicon model in differentiating molecular subtypes of breast cancer in both the main cohort and external testing cohort (all p < 0.001). In the main cohort, when classifying luminal A from non-luminal A subtypes, our model obtained an AUC of 0.776 (95% CI, 0.649–0.885) for patients older than 50 years and 0.818 (95% CI, 0.726–0.902) for those with tumor sizes ≤20 mm. For young patients ≤50 years, the AUC value of our model for detecting triple-negative breast cancer was 0.712 (95% CI, 0.538–0.874). In the external testing cohort, when classifying luminal A from non-luminal A subtypes for patients older than 50 years, our DCNN model achieved an AUC of 0.686 (95% CI, 0.567–0.806).

Conclusions

We employed a DCNN model to predict the molecular subtypes of breast cancer based on US images. Our model can be valuable depending on the patient’s age and nodule sizes.

Primary neuroendocrine carcinomas of the breast and neuroendocrine differentiated breast cancers: Relationship between histopathological and radiological features

PURPOSE

The aim of this study wasto investigate whole-breast imaging findings (mammography, ultrasonography (US), magnetic resonance imaging (MRI),clinical, and histopathological findings of primary neuroendocrine carcinomas of the breast (NEC) and neuroendocrine differentiated breast cancers (NEBC).

METHODS

Patients withadiagnosis of breast cancer with histopathological neuroendocrine features between the years 2010 and 2021 were retrospectively screened.The lesions were divided into two main groups depending on staining with neuroendocrine markers (synaptophysin and chromogranin A). Those showing focal staining were categorized as NEBC while those with diffuse staining as NEC.The mammography, US, and MRI of the lesionswere reviewed in consensus by two breast radiologists in order to assess imaging featuresretrospectively according to the Breast Imaging Reporting and Data System (BI-RADS) 5th lexicon.The findings were compared with breast cancers without neuroendocrine features (BC-WNE) which were randomly selected from the same database.

RESULTS

A total of 105 lesions [NEBC (n = 44), NEC(n = 11), BC-WNE (n = 50)] were evaluated.Patients with neuroendocrine tumors were older (p < 0.001) than those with BC-WNE. Compared with BC-WNE tumors, radiological findings typical of malignancy such as irregular shape [NEBC (7/20); NEC(3/7) vs BC-WNE (35/43); p < 0.001], spiculation [NEBC (2/20); NEC(0/7) vs BC-WNE (21/43); p < 0.001], architectural distortion [(NEBC (3/24); NEC(0/9) vs BC-WNE (31/50); p < 0.001)], calcification [(NEBC (6/24), NEC(0/9) vs BC-WNE (n = 27/50); p = 0.001)] on mamography, non-parallel orientation to skin [(NEBC (n = 17/29), NEC(n = 4/9), BC-WNE (n = 35/42); p = 0.008)], acoustic shadowing [(NEBC (n = 12/29), NEC(1/9), BC-WNE (n = 29/42); p = 0.009)], axillary lymphadenopathy [(NEBC(n = 3/30), NEC(n = 1/9), BC-WNE (21/50); p < 0.001)]on US were less common features of the neuroendocrine carcinomas of breast. Aside from shape features, there was no significant difference in contrast pattern (p = 0.866), kinetic curve (p = 0.454) and diffusion restriction (p = 0.242) on MRI.

CONCLUSION

Characteristic malignant imaging features, including irregular shape, spiculated margins, suspicious calcifications, and posterior acoustic shadowing, are uncommon in neuroendocrine carcinomas of breast. These carcinomas tend to show more benign imaging features when compared with BC-WNE.

Radioproteomics in Breast Cancer: Prediction of Ki-67 Expression With MRI-based Radiomic Models

RATIONALE AND OBJECTIVES

We aimed to investigate the value of magnetic resonance image (MRI)-based radiomics in predicting Ki-67 expression of breast cancer.

METHODS

In this retrospective study, 159 lesions from 154 patients were included. Radiomic features were extracted from contrast-enhanced T1-weighted MRI (C+MRI) and apparent diffusion coefficient (ADC) maps, with open-source software. Dimension reduction was done with reliability analysis, collinearity analysis, and feature selection. Two different Ki-67 expression cut-off values (14% vs 20%) were studied as reference standard for the classifications. Input for the models were radiomic features from individual MRI sequences or their combination. Classifications were performed using a generalized linear model.

RESULTS

Considering Ki-67 cut-off value of 14%, training and testing AUC values were 0.785 (standard deviation [SD], 0.193) and 0.849 for ADC; 0.696 (SD, 0.150) and 0.695 for C+MRI; 0.755 (SD, 0.171) and 0.635 for the combination of both sequences, respectively. Regarding Ki-67 cut-off value of 20%, training and testing AUC values were 0.744 (SD, 0.197) and 0.617 for ADC; 0.629 (SD, 0.251) and 0.741 for C+MRI; 0.761 (SD, 0.207) and 0.618 for the combination of both sequences, respectively.

CONCLUSION

ADC map-based selected radiomic features coupled with generalized linear modeling might be a promising non-invasive method to determine the Ki-67 expression level of breast cancer.

MRI of the Lactating Breast: Computer-Aided Diagnosis False Positive Rates and Background Parenchymal Enhancement Kinetic Features

RATIONALE AND OBJECTIVES

To investigate the application of computer-added diagnosis (CAD) in dynamic contrast-enhanced (DCE) MRI of the healthy lactating breast, focusing on false-positive rates and background parenchymal enhancement (BPE) coloring patterns in comparison with breast cancer features in non-lactating patients.

MATERIALS AND METHODS

The study population was composed of 58 healthy lactating patients and control groups of 113 healthy premenopausal non-lactating patients and 55 premenopausal non-lactating patients with newly-diagnosed breast cancer. Patients were scanned on 1.5-T MRI using conventional DCE protocol. A retrospective analysis of DCE-derived CAD properties was conducted using a commercial software that is regularly utilized in our routine radiological work-up. Qualitative morphological characterization and automatically-obtained quantitative parametric measurements of the BPE-induced CAD coloring were categorized and subgroups' trends and differences between the lactating and cancer cohorts were statistically assessed.

RESULTS

CAD false-positive coloring was found in the majority of lactating cases (87%). Lactation BPE coloring was characteristically non-mass enhancement (NME)-like shaped (87%), bilateral (79%) and symmetric (64%), whereas, unilateral coloring was associated with prior irradiation (p <0.0001). Inter-individual variability in CAD appearance of both scoring-grade and kinetic-curve dominance was found among the lactating cohort. When compared with healthy non-lactating controls, CAD false positive probability was significantly increased [Odds ratio 40.2, p <0001], while in comparison with the breast cancer cohort, CAD features were mostly inconclusive, even though increased size parameters were significantly associated with lactation-BPE (p <0.00001).

CONCLUSION

BPE was identified as a common source for false-positive CAD coloring on breast DCE-MRI among lactating population. Despite several typical characteristics, overlapping features with breast malignancy warrant a careful evaluation and clinical correlation in all cases with suspected lactation induced CAD coloring.

Automatic identification of triple negative breast cancer in ultrasonography using a deep convolutional neural network

Triple negative (TN) breast cancer is a subtype of breast cancer which is difficult for early detection and the prognosis is poor. In this paper, 910 benign and 934 malignant (110 TN and 824 NTN) B-mode breast ultrasound images were collected. A Resnet50 deep convolutional neural network was fine-tuned. The results showed that the averaged area under the receiver operating characteristic curve (AUC) of discriminating malignant from benign ones were 0.9789 (benign vs. TN), 0.9689 (benign vs. NTN). To discriminate TN from NTN breast cancer, the AUC was 0.9000, the accuracy was 88.89%, the sensitivity was 87.5%, and the specificity was 90.00%. It showed that the computer-aided system based on DCNN is expected to be a promising noninvasive clinical tool for ultrasound diagnosis of TN breast cancer.

Evaluation of Background Parenchymal Enhancement and Histogram-Based Diffusion-Weighted Image in Determining the Molecular Subtype of Breast Cancer

RATIONALE AND OBJECTIVES

This study aimed to evaluate the value of background parenchymal enhancement (BPE) and diffusion-weighted image (DWI) histogram features in differentiating among different molecular subtypes of breast cancers and investigate the relationship between BPE and DWI features.

MATERIALS AND METHODS

We prospectively enrolled 142 patients with breast cancer between January and November 2018. All patients underwent breast magnetic resonance imaging before core needle biopsy. The quantitative BPE from dynamic enhanced images and the first-order histogram features extracted from DWI were analyzed. Univariate analysis of variance was used to compare differences in DWI histogram features and BPE characteristics among different molecular subtypes. Spearman test was used to compare the correlation between these imaging indexes.

RESULTS

A total of 142 patients had 142 lesions, including 17 cases of triple-negative breast cancer, 12 cases of luminal A type breast cancer, 39 cases of luminal B type breast cancer, and 74 cases of human epidermal growth factor receptor 2-positive breast cancer. The apparent diffusion coefficient (ADC) 95th percentile, ADC kurtosis, and BPE were significantly different among 4 subtype groups (P < 0.05), especially between the triple-negative subtype and any other subtype (P < 0.05 in pairwise comparisons). There was a weak but significant correlation between BPE and kurtosis of ADC (r = -0.176, P = 0.036).

CONCLUSIONS

Diffusion-weighted image histogram features (95th percentile ADC value and kurtosis value of ADC) and BPE features were different in the 4 molecular subtypes of breast cancer, especially in the triple-negative breast cancer subtype. Background parenchymal enhancement was negatively correlated with the kurtosis value of ADC.

Multicontrast MRI-based radiomics for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with early triple negative breast cancer

INTRODUCTION

To assess pre-therapeutic MRI-based radiomic analysis to predict the pathological complete response to neoadjuvant chemotherapy (NAC) in women with early triple negative breast cancer (TN).

MATERIALS AND METHODS

This monocentric retrospective study included 75 TN female patients with MRI (T1-weighted, T2-weighted, diffusion-weighted and dynamic contrast enhancement images) performed before NAC. For each patient, the tumor(s) and the parenchyma were independently segmented and analyzed with radiomic analysis to extract shape, size, and texture features. Several sets of features were realized based on the 4 different sequence images. Performances of 4 classifiers (random forest, multilayer perceptron, support vector machine (SVM) with linear or quadratic kernel) were compared based on pathological complete response (defined on the excised tissues), on 100 draws with 75% as training set and 25% as test.

RESULTS

The combination of features extracted from different MR images improved the classifier performance (more precisely, the features from T1W, T2W and DWI). The SVM with quadratic kernel showed the best performance with a mean AUC of 0.83, a sensitivity of 0.85 and a specificity of 0.75 in the test set.

CONCLUSION

MRI-based radiomics may be relevant to predict NAC response in TN cancer. Our results promote the use of multi-contrast MRI sources for radiomics, providing enrich source of information to enhance model generalization.

Value of Machine Learning with Multiphases CE-MRI Radiomics for Early Prediction of Pathological Complete Response to Neoadjuvant Therapy in HER2-Positive Invasive Breast Cancer

Background

To assess the value of radiomics based on multiphases contrast-enhanced magnetic resonance imaging (CE-MRI) for early prediction of pathological complete response (pCR) to neoadjuvant therapy (NAT) in patients with human epithelial growth factor receptor 2 (HER2) positive invasive breast cancer.

Methods

A total of 127 patients with newly diagnosed primary HER2 positive invasive breast cancer underwent CE-MRI before NAT and performed surgery after NAT. Radiomic features were extracted from the 1^st postcontrast CE-MRI phase (CE₁) and multi-phases CE-MRI (CE_m),respectively. With selected features using a forward stepwise regression, 23 machine learning classifiers based on CE₁ and CE_m were constructed respectively for differentiating pCR and non-pCR patients. The performances of classifiers were assessed and compared by their accuracy, sensitivity, specificity and AUC (area under curve). The optimal machine learning classification was used to discriminate pCR vs non-pCR in mass and non-mass groups, uni-focal and unilateral multi-focal groups, respectively.

Results

For the task of pCR classification, 6 radiomic features from CE₁ and 6 from CE_m were selected for the construction of machine learning models, respectively. The linear SVM based on CE_m outperformed the logistic regression model using CE₁ with an AUC of 0.84 versus 0.69. In mass and non-mass enhancement groups, the accuracy of linear SVM achieved 84% and 76%. Whereas in unifocal and unilateral multifocal cases, 79% and 75% accuracy were achieved by linear SVM.

Conclusion

Multiphases CE-MRI imaging may offer more heterogeneity information in the tumor and provide a non-invasive approach for early prediction of pCR to NAT in patients with HER2-positive invasive breast cancer.

Identify the triple-negative and non-triple-negative breast cancer by using texture features of medicale ultrasonic image: A STROBE-compliant study

The study aimed to explore the value of ultrasound (US) texture analysis in the differential diagnosis of triple-negative breast cancer (TNBC) and non-TNBC.Retrospective analysis was done on 93 patients with breast cancer (35 patients with TNBC and 38 patients with non-TNBC) who were admitted to Taizhou people's hospital from July 2015 to June 2019. All lesions were pathologically proven at surgery. US images of all patients were collected. Texture analysis of US images was performed using MaZda software package. The differences between textural features in TNBC and non-TNBC were assessed. Receiver operating characteristic curve analysis was used to compare the diagnostic performance of textural parameters showing significant difference.Five optimal texture feature parameters were extracted from gray level run-length matrix, including gray level non-uniformity (GLNU) in horizontal direction, vertical gray level non-uniformity, GLNU in the 45 degree direction, run length non-uniformity in 135 degree direction, GLNU in the 135 degree direction. All these texture parameters were statistically higher in TNBC than in non-TNBC (P <.05). Receiver operating characteristic curve analysis indicated that at a threshold of 268.9068, GLNU in horizontal direction exhibited best diagnostic performance for differentiating TNBC from non-TNBC. Logistic regression model established based on all these parameters showed a sensitivity of 69.3%, specificity of 91.4% and area under the curve of 0.834.US texture features were significantly different between TNBC and non-TNBC, US texture analysis can be used for preliminary differentiation of TNBC from non-TNBC.

Intratumoral Intensity in T2-weighted MRI and the Association With Histological and Molecular Prognostic Factors in Women With Invasive Breast Cancer

OBJECTIVE

To compare the intratumoral T2 signal intensity on MRI and histopathological and molecular expression of biomarkers of aggressiveness (histological grade, hormonal status, HER2, and Ki-67).

METHODS

This retrospective study included all women with invasive breast cancer undergoing MRI from January 2014 to October 2016. The intratumoral T2 signal as interpreted at consensus by two radiologists was compared to histopathological and molecular prognostic factors from the surgical specimen. Statistical analyses used Pearson χ 2 test with a confidence level of 95% (P ≤ 0.05).

RESULTS

Fifty patients with 50 lesions met study criteria (mean age 65.8 ± 13.5 years). Mean lesion size was 28 mm ± 15.7 mm (range, 15 to 76 mm). Cancer types were invasive ductal (35/50, 70%), invasive lobular (10/50, 20%), and mixed (5/50, 10%). Most lesions were histological grade 1 or 2 (41/50, 82%) and luminal type (45/50, 90%). On T2 images, lesions were hypointense in 62% (31/50), isointense in 20% (10/50), and hyperintense in 18% (9/50) of cases. Among hypointense lesions, 94% (29/31) were low or intermediate grade tumors (P = 0.02), low HER2 overexpression (30/31, 97%) (P = 0.005), and high ER status (30/31, 97%) (P = 0.006), high PR (26/31, 84%) (P = 0.02), and low incidence of necrosis (2/31, 6%). The difference in Ki-67 tumoral expression between groups was not significant.

CONCLUSION

Intratumoral T2 hypointensity in invasive breast cancer is associated with better prognostic tumors, such as histological low-grade high hormone receptor status.

Artificial Intelligence in Breast MRI Radiogenomics: Towards Accurate Prediction of Neoadjuvant Chemotherapy Responses

Neoadjuvant Chemotherapy (NAC) in breast cancer patients has considerable prognostic and treatment potential and can be tailored to individual patients as part of precision medicine protocols. This work reviews recent advances in artificial intelligence so as to enable the use of radiogenomics for accurate NAC analysis and prediction. The work addresses a new problem in radiogenomics mining: How to combine structural radiomics information and non-structural genomics information for accurate NAC prediction. This requires the automated extraction of parameters from structural breast radiomics data, and finding non-structural feature vectors with diagnostic value, which then are combined with genomics data acquired from exocrine bodies in blood samples from a cohort of cancer patients to enable accurate NAC prediction. A self-attention-based deep learning approach, along with an effective multi-channel tumour image reconstruction algorithm of high dimensionality, is proposed. The aim was to generate non-structural feature vectors for accurate prediction of the NAC responses by combining imaging datasets with exocrine body related genomics analysis.

Histogram analysis of quantitative parameters from synthetic MRI: Correlations with prognostic factors and molecular subtypes in invasive ductal breast cancer

PURPOSE

To evaluate intra-tumoral heterogeneity through a histogram analysis of quantitative parameters obtained from synthetic MRI (magnetic resonance imaging), and determine correlations of these histogram characteristics with prognostic factors and molecular subtypes of invasive ductal carcinoma (IDC).

METHODS

A total of 122 IDC from 122 women who underwent preoperative synthetic MRI and DCE (dynamic contrast enhancement)-MRI were investigated. The synthetic MRI parameters (T1, T2, and PD (proton density)) were obtained. For each parameter, the minimum, 10th percentile, mean, median, 90th percentile, maximum, skewness, and kurtosis values of tumor were calculated, and correlations with prognostic factors and subtypes were assessed. The Mann-Whitney U test or the Student^'s t test were utilized to analyze the association between the histogram features of synthetic MRI parameters and prognostic factors. The Kruskal-Wallis test followed by the post-hoc test was used to analyze differences of synthetic MRI parameters among molecular subtypes.

RESULTS

IDC with high histopathologic grade showed statistically higher PD_maxium, T1_mean and T1_median values than those with low grade (p = 0.003, p = 0.007, p = 0.003). The T1_10th were significantly higher in cancers with PR (progesterone receptor) negativity than those with PR positivity (p = 0.005). ER-negative cancers had significant higher values of T2_10th, T2_mean, and T2_median than ER-positive cancers (p = 0.006, 0.002, and 0.006, respectively). The values of PD_median were significantly higher in IDC with HER2 (human epidermal growth factor receptor 2) positivity than those with HER2 negativity (p = 0.001). When discriminating molecular subtypes of IDC, the T2_mean achieved the highest performance. The T2_mean values of TN (triple-negative), luminal B and luminal A types are arranged in descending order (p <  0.0001).

CONCLUSIONS

Histogram features derived from synthetic MRI quantifies the distributions of tissue relaxation time and proton density, and may serve as a potential biomarker for discriminating histopathological grade, hormone receptor status, HER2 expression status and breast cancer subtypes.

Nodal-based radiomics analysis for identifying cervical lymph node metastasis at levels I and II in patients with oral squamous cell carcinoma using contrast-enhanced computed tomography

OBJECTIVE

Discriminating metastatic from benign cervical lymph nodes (LNs) in oral squamous cell carcinoma (OSCC) patients using pretreatment computed tomography (CT) has been controversial. This study aimed to investigate whether CT-based texture analysis with machine learning can accurately identify cervical lymph node metastasis in OSCC patients.

METHODS

Twenty-three patients (with 201 cervical LNs [150 benign, 51 metastatic] at levels I-V) who underwent preoperative contrast-enhanced CT and subsequent cervical neck dissection were enrolled. Histopathologically proven LNs were randomly divided into the training cohort (70%; n = 141, at levels I-V) and validation cohort (30%; n = 60, at level I/II). Twenty-five texture features and the nodal size of targeted LNs were analyzed on the CT scans. The nodal-based sensitivities, specificities, diagnostic accuracy rates, and the area under the curves (AUCs) of the receiver operating characteristic curves of combined features using a support vector machine (SVM) at levels I/II, I, and II were evaluated and compared with two radiologists and a dentist (readers).

RESULTS

In the validation cohort, the AUCs (0.820 at level I/II, 0.820 at level I, and 0.930 at level II, respectively) of the radiomics approach were superior to three readers (0.798-0.816, 0.773-0.798, and 0.825-0.865, respectively). The best models were more specific at levels I/II and I and accurate at each level than each of the readers (p < .05).

CONCLUSIONS

Machine learning-based analysis with contrast-enhanced CT can be used to noninvasively differentiate between benign and metastatic cervical LNs in OSCC patients.

KEY POINTS

• The best algorithm in the validation cohort can noninvasively differentiate between benign and metastatic cervical LNs at levels I/II, I, and II. • The AUCs of the model at each level were superior to those of multireaders. • Significant differences in the specificities at level I/II and I and diagnostic accuracy rates at each level between the model and multireaders were found.

Use of radiomics based on 18F-FDG PET/CT and machine learning methods to aid clinical decision-making in the classification of solitary pulmonary lesions: an innovative approach

PURPOSE

This study was designed and performed to assess the ability of ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) radiomics features combined with machine learning methods to differentiate between primary and metastatic lung lesions and to classify histological subtypes. Moreover, we identified the optimal machine learning method.

METHODS

A total of 769 patients pathologically diagnosed with primary or metastatic lung cancers were enrolled. We used the LIFEx package to extract radiological features from semiautomatically segmented PET and CT images within the same volume of interest. Patients were randomly distributed in training and validation sets. Through the evaluation of five feature selection methods and nine classification methods, discriminant models were established. The robustness of the procedure was controlled by tenfold cross-validation. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

Based on the radiomics features extracted from PET and CT images, forty-five discriminative models were established. Combined with appropriate feature selection methods, most classifiers showed excellent discriminative ability with AUCs greater than 0.75. In the differentiation between primary and metastatic lung lesions, the feature selection method gradient boosting decision tree (GBDT) combined with the classifier GBDT achieved the highest classification AUC of 0.983 in the PET dataset. In contrast, the feature selection method eXtreme gradient boosting combined with the classifier random forest (RF) achieved the highest AUC of 0.828 in the CT dataset. In the discrimination between squamous cell carcinoma and adenocarcinoma, the combination of GBDT feature selection method with GBDT classification had the highest AUC of 0.897 in the PET dataset. In contrast, the combination of the GBDT feature selection method with the RF classification had the highest AUC of 0.839 in the CT dataset. Most of the decision tree (DT)-based models were overfitted, suggesting that the classification method was not appropriate for practical application.

CONCLUSION

¹⁸F-FDG PET/CT radiomics features combined with machine learning methods can distinguish between primary and metastatic lung lesions and identify histological subtypes in lung cancer. GBDT and RF were considered optimal classification methods for the PET and CT datasets, respectively, and GBDT was considered the optimal feature selection method in our analysis.

Radiomic analysis on magnetic resonance diffusion weighted image in distinguishing triple-negative breast cancer from other subtypes: a feasibility study

PURPOSE

This work aimed to explore whether radiomic features on magnetic resonance diffusion weighted image (MR DWI) can be used to identify triple-negative breast cancer (TNBC) and other subtypes (non-TNBC).

MATERIALS AND METHODS

This retrospective study included 221 unilateral patients who underwent breast MR imaging prior to neoadjuvant chemotherapy. The subtypes of breast cancer include luminal A (n = 63), luminal B (n = 103), human epidermal growth factor receptor-2 (HER2) overexpressing (n = 30), and triple negative (n = 25). Radiomic features were extracted using Omini-Kinetic software on DWI. Student's t-test and Mann-Whitney U test were used to compare the features between TNBC and non-TNBC patients. Logistic regression analysis and receiver operating characteristic (ROC) curve were used to evaluate the diagnostic efficiency of radiomic features. The Fisher discriminant model was employed to distinguish TNBC and non-TNBC patients automatically. An additional validation dataset with 169 patients was utilized to validate the model.

RESULTS

A total of 76 imaging features were extracted from each lesion on DWI images, and 12 radiomic features were statistically significant between TNBC and non-TNBC patients (P < 0.05). The area of receiver operating characteristic curve (AUC) was 0.817 to apply logistic regression analysis. The accuracy of Fisher discriminant model in distinguishing TNBC and non-TNBC patients was 95.4%, and leave-one-out cross validation was achieved with an accuracy of 83.7%. The same classification analysis of the validation dataset showed an accuracy of 83.4% and an AUC of 0.804.

CONCLUSION

Breast lesions exhibit differences in radiomic features from DWI, enabling good discrimination between TNBC and non-TNBC tumors.

Imaging features of breast cancer molecular subtypes: state of the art

Characterization of breast cancer molecular subtypes has been the standard of care for breast cancer management. We aimed to provide a review of imaging features of breast cancer molecular subtypes for the field of precision medicine. We also provide an update on the recent progress in precision medicine for breast cancer, implications for imaging, and recent observations in longitudinal functional imaging with radiomics.

Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade

Purpose

Hyperprogression is an atypical response pattern to immune checkpoint inhibition that has been described within non-small cell lung cancer (NSCLC). The paradoxical acceleration of tumor growth after immunotherapy has been associated with significantly shortened survival, and currently, there are no clinically validated biomarkers to identify patients at risk of hyperprogression.

Experimental design

A total of 109 patients with advanced NSCLC who underwent monotherapy with Programmed cell death protein-1 (PD1)/Programmed death-ligand-1 (PD-L1) inhibitors were included in the study. Using RECIST measurements, we divided the patients into responders (n=50) (complete/partial response or stable disease) and non-responders (n=59) (progressive disease). Tumor growth kinetics were used to further identify hyperprogressors (HPs, n=19) among non-responders. Patients were randomized into a training set (D₁=30) and a test set (D₂=79) with the essential caveat that HPs were evenly distributed among the two sets. A total of 198 radiomic textural patterns from within and around the target nodules and features relating to tortuosity of the nodule associated vasculature were extracted from the pretreatment CT scans.

Results

The random forest classifier using the top features associated with hyperprogression was able to distinguish between HP and other radiographical response patterns with an area under receiver operating curve of 0.85±0.06 in the training set (D₁=30) and 0.96 in the validation set (D₂=79). These features included one peritumoral texture feature from 5 to 10 mm outside the tumor and two nodule vessel-related tortuosity features. Kaplan-Meier survival curves showed a clear stratification between classifier predicted HPs versus non-HPs for overall survival (D₂: HR=2.66, 95% CI 1.27 to 5.55; p=0.009).

Conclusions

Our study suggests that image-based radiomics markers extracted from baseline CTs of advanced NSCLC treated with PD-1/PD-L1 inhibitors may help identify patients at risk of hyperprogressions.

Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers

OBJECTIVES

To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI.

METHODS

A total of 244 patients were analyzed, 99 in training dataset scanned at 1.5 T and 83 in testing-1 and 62 in testing-2 scanned at 3 T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2-), HER2+, and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the training dataset, by using a conventional CNN and the convolutional long short-term memory (CLSTM). Then, transfer learning was applied to re-tune the model using testing-1(2) and evaluated in testing-2(1).

RESULTS

In the training dataset, the mean accuracy evaluated using tenfold cross-validation was higher by using CLSTM (0.91) than by using CNN (0.79). When the developed model was applied to the independent testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%.

CONCLUSIONS

The recurrent network using CLSTM could track changes in signal intensity during DCE acquisition, and achieved a higher accuracy compared with conventional CNN during training. For datasets acquired using different settings, transfer learning can be applied to re-tune the model and improve accuracy.

KEY POINTS

• Deep learning can be applied to differentiate breast cancer molecular subtypes. • The recurrent neural network using CLSTM could track the change of signal intensity in DCE images, and achieved a higher accuracy compared with conventional CNN during training. • For datasets acquired using different scanners with different imaging protocols, transfer learning provided an efficient method to re-tune the classification model and improve accuracy.

Predicting Breast Cancer Molecular Subtype with MRI Dataset Utilizing Convolutional Neural Network Algorithm

To develop a convolutional neural network (CNN) algorithm that can predict the molecular subtype of a breast cancer based on MRI features. An IRB-approved study was performed in 216 patients with available pre-treatment MRIs and immunohistochemical staining pathology data. First post-contrast MRI images were used for 3D segmentation using 3D slicer. A CNN architecture was designed with 14 layers. Residual connections were used in the earlier layers to allow stabilization of gradients during backpropagation. Inception style layers were utilized deeper in the network to allow learned segregation of more complex feature mappings. Extensive regularization was utilized including dropout, L2, feature map dropout, and transition layers. The class imbalance was addressed by doubling the input of underrepresented classes and utilizing a class sensitive cost function. Parameters were tuned based on a 20% validation group. A class balanced holdout set of 40 patients was utilized as the testing set. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. Seventy-four luminal A, 106 luminal B, 13 HER2+, and 23 basal breast tumors were evaluated. Testing set accuracy was measured at 70%. The class normalized macro area under receiver operating curve (ROC) was measured at 0.853. Non-normalized micro-aggregated AUC was measured at 0.871, representing improved discriminatory power for the highly represented Luminal A and Luminal B subtypes. Aggregate sensitivity and specificity was measured at 0.603 and 0.958. MRI analysis of breast cancers utilizing a novel CNN can predict the molecular subtype of breast cancers. Larger data sets will likely improve our model.

Breast dynamic contrast-enhanced-magnetic resonance imaging and radiomics: State of art

Breast cancer represents the most common malignancy in women, being one of the most frequent cause of cancer-related mortality. Ultrasound, mammography, and magnetic resonance imaging (MRI) play a pivotal role in the diagnosis of breast lesions, with different levels of accuracy. Particularly, dynamic contrast-enhanced MRI has shown high diagnostic value in detecting multifocal, multicentric, or contralateral breast cancers. Radiomics is emerging as a promising tool for quantitative tumor evaluation, allowing the extraction of additional quantitative data from radiological imaging acquired with different modalities. Radiomics analysis may provide novel information through the quantification of lesions heterogeneity, that may be relevant in clinical practice for the characterization of breast lesions, prediction of tumor response to systemic therapies and evaluation of prognosis in patients with breast cancers. Several published studies have explored the value of radiomics with good-to-excellent diagnostic and prognostic performances for the evaluation of breast lesions. Particularly, the integrations of radiomics data with other clinical and histopathological parameters have demonstrated to improve the prediction of tumor aggressiveness with high accuracy and provided precise models that will help to guide clinical decisions and patients management. The purpose of this article in to describe the current application of radiomics in breast dynamic contrast-enhanced MRI.

Multiparametric Analysis of Longitudinal Quantitative MRI data to Identify Distinct Tumor Habitats in Preclinical Models of Breast Cancer

This study identifies physiological tumor habitats from quantitative magnetic resonance imaging (MRI) data and evaluates their alterations in response to therapy. Two models of breast cancer (BT-474 and MDA-MB-231) were imaged longitudinally with diffusion-weighted MRI and dynamic contrast-enhanced MRI to quantify tumor cellularity and vascularity, respectively, during treatment with trastuzumab or albumin-bound paclitaxel. Tumors were stained for anti-CD31, anti-Ki-67, and H&E. Imaging and histology data were clustered to identify tumor habitats and percent tumor volume (MRI) or area (histology) of each habitat was quantified. Histological habitats were correlated with MRI habitats. Clustering of both the MRI and histology data yielded three clusters: high-vascularity high-cellularity (HV-HC), low-vascularity high-cellularity (LV-HC), and low-vascularity low-cellularity (LV-LC). At day 4, BT-474 tumors treated with trastuzumab showed a decrease in LV-HC (p = 0.03) and increase in HV-HC (p = 0.03) percent tumor volume compared to control. MDA-MB-231 tumors treated with low-dose albumin-bound paclitaxel showed a longitudinal decrease in LV-HC percent tumor volume at day 3 (p = 0.01). Positive correlations were found between histological and imaging-derived habitats: HV-HC (BT-474: p = 0.03), LV-HC (MDA-MB-231: p = 0.04), LV-LC (BT-474: p = 0.04; MDA-MB-231: p < 0.01). Physiologically distinct tumor habitats associated with therapeutic response were identified with MRI and histology data in preclinical models of breast cancer.

Diagnosis of triple negative breast cancer based on radiomics signatures extracted from preoperative contrast-enhanced chest computed tomography

Background

To explore the diagnostic value of radiomics features of preoperative computed tomography (CT) for triple negative breast cancer (TNBC) for better treatment of patients with breast cancer.

Methods

A total of 890 patients with breast cancer admitted to our hospital from June 2016 to January 2018 were analyzed. They were diagnosed by surgery and pathology to have mass and invasive breast cancer and had contrast-enhanced chest CT examination before operation. 300 patients were randomly selected for the study, including 100 TNBC and 200 non-TNBC (NTNBC) patients. Among them 180 were used in discovery group and 120 were used in validation group. The molecular subtypes of breast cancer in the patients were determined immunohistochemistrially. Radiomics features were extracted from three dimensional CT-images. The LASSO logistic method was used to select image features and calculate radiomics scores. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic value of radiomics scores for TNBC.

Results

Five image features were found to be related to TNBC subtype (P < 0.001). These image features based-radiomic signatures had good predictive values for TNBC with the areas under ROC curve (AUC) of 0.881 (95% CI: 0.781–0.921) in the discovery group and 0.851 (95% CI: 0.761–0.961) in the validation group, respectively. The sensitivities and specificities were 0.767, and 0.873 in the discovery group and 0.785 and 0.915 in the validation group.

Conclusions

Radiomic signature based on preoperative CT is capable of distinguishing patients with TNBC and NTNBC. It adds additional value for conventional chest contrast-enhanced CT and helps plan the strategy for clinical treatment of the patients.

Analysis of influencing factors of no/low response to preoperative concurrent chemoradiotherapy in locally advanced rectal cancer

The aim of this study is to investigate the influencing factors associated with no/low response to preoperative concurrent chemoradiotherapy (CCRT) for locally advanced rectal cancer (LARC) patients. A total of 79 patients were included in this prospective study. Fifteen factors that might affect the resistance to CCRT were included in this logistic regression analysis, these factors include the general clinical data of patients, the expression status of tumor stem cell marker CD44v6 and the volumetric imaging parameters of primary tumor lesions. We found that the no/low response status to preoperative CCRT was positively correlated with the real tumor volume (RTV), the total surface area of tumor (TSA), and CD44v6 expression, whereas negatively correlated with the tumor compactness (TC). According to the results of logistic regression analysis, two formulas that could predict whether or not no/low response to preoperative CCRT were established. The Area Under Curve (AUC) of the two formulas and those significant measurement data (RTV, TC, TSA) were 0.900, 0.858, 0.771, 0.754, 0.859, the sensitivity were 95.8%, 79.17%, 62.50%, 95.83%, 62.5%, the specificity were 70.9%, 74.55%, 83.64%,47.27%, 96.36%, the positive predictive values were 58.96%, 57.58%, 62.51%,44.23%, 88.23%, the negative predictive values were 97.48%, 89.13%, 83.64%, 96.29%, and 85.48%, respectively.

Radiogenomic Analysis of Breast Cancer by Linking MRI Phenotypes with Tumor Gene Expression

Background Better understanding of the molecular biology associated with MRI phenotypes may aid in the diagnosis and treatment of breast cancer. Purpose To discover the associations between MRI phenotypes of breast cancer and their underlying molecular biology derived from gene expression data. Materials and Methods This is a secondary analysis of the Multimodality Analysis and Radiologic Guidance in Breast-Conserving Therapy, or MARGINS, study. MARGINS included patients eligible for breast-conserving therapy between November 2000 and December 2008 for preoperative breast MRI. Tumor RNA was collected for sequencing from surgical specimen. Twenty-one computer-generated MRI features of tumors were condensed into seven MRI factors related to tumor size, shape, initial enhancement, late enhancement, smoothness of enhancement, sharpness, and sharpness variation. These factors were associated with gene expression levels from RNA sequencing by using gene set enrichment analysis. Statistical significance of these associations was evaluated by using a sample permutation test and the false discovery rate. Results Gene expression and MRI data were obtained for 295 patients (mean age, 56 years ± 10.3 [standard deviation]). Larger and more irregular tumors showed increased expression of cell cycle and DNA damage checkpoint genes (false discovery rate <0.25; normalized enrichment statistic [NES], 2.15). Enhancement and sharpness of the tumor margin were associated with expression of ribosomal proteins (false discovery rate <0.25; NES, 1.95). Smoothness of enhancement, tumor size, and tumor shape were associated with expression of genes involved in the extracellular matrix (false discovery rate <0.25; NES, 2.25). Conclusion Breast cancer MRI phenotypes were related to their underlying molecular biology revealed by using RNA sequencing. The association between enhancements and sharpness of the tumor margin with the ribosome suggests that these MRI features may be imaging biomarkers for drugs targeting the ribosome. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Cho in this issue.

Texture Analysis of Breast DCE-MRI Based on Intratumoral Subregions for Predicting HER2 2+ Status

Background: Breast tumor heterogeneity is related to risk factors that lead to aggressive tumor growth; however, such heterogeneity has not been thoroughly investigated.

Purpose: To evaluate the performance of texture features extracted from heterogeneity subregions on subtraction MRI images for identifying human epidermal growth factor receptor 2 (HER2) 2+ status of breast cancers.

Materials and Methods: Seventy-six patients with HER2 2+ breast cancer who underwent dynamic contrast-enhanced magnetic resonance imaging were enrolled, including 42 HER2 positive and 34 negative cases confirmed by fluorescence in situ hybridization. The lesion area was delineated semi-automatically on the subtraction MRI images at the second, fourth, and sixth phases (P-1, P-2, and P-3). A regionalization method was used to segment the lesion area into three subregions (rapid, medium, and slow) according to peak arrival time of the contrast agent. We extracted 488 texture features from the whole lesion area and three subregions independently. Wrapper, least absolute shrinkage and selection operator (LASSO), and stepwise methods were used to identify the optimal feature subsets. Univariate analysis was performed as well as support vector machine (SVM) with a leave-one-out-based cross-validation method. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the performance of the classifiers.

Results: In univariate analysis, the variance from medium subregion at P-2 was the best-performing feature for distinguishing HER2 2+ status (AUC = 0.836); for the whole lesion region, the variance at P-2 achieved the best performance (AUC = 0.798). There was no significant difference between the two methods (P = 0.271). In the machine learning with SVM, the best performance (AUC = 0.929) was achieved with LASSO from rapid subregion at P-2; for the whole region, the highest AUC value was 0.847 obtained at P-2 with LASSO. The difference was significant between the two methods (P = 0.021).

Conclusion: The texture analysis of heterogeneity subregions based on intratumoral regionalization method showed potential value for recognizing HER2 2+ status in breast cancer.

New Machine Learning Applications to Accelerate Personalized Medicine in Breast Cancer: Rise of the Support Vector Machines

Artificial intelligence, machine learning, health care robots, and algorithms for clinical decision-making are currently being sought after in diverse fields of clinical medicine and bioengineering. The field of personalized medicine stands to benefit from new technologies so as to harness the omics big data, for example, to individualize and accelerate cancer diagnostics and therapeutics in particular. In this overarching context, breast cancer is one of the most common malignancies worldwide with multiple underlying molecular etiologies and each subtype displaying diverse clinical outcomes. Disease stratification for breast cancer is, therefore, vital to its effective and individualized clinical care. The support vector machine (SVM) is a rising machine learning approach that offers robust classification of high-dimensional big data into small numbers of data points (support vectors), achieving differentiation of subgroups in a short amount of time. Considering the rapid timelines required for both diagnosis and treatment of most aggressive cancers, this new machine learning technique has important clinical and public applications and implications for high-throughput data analysis and contextualization. This expert review describes and examines, first, the SVM models employed to forecast breast cancer subtypes using diverse systems science data, including transcriptomics, epigenetics, proteomics, and radiomics, as well as biological pathway, clinical, pathological, and biochemical data. Then, we compare the performance of the present SVM and other diagnostic and therapeutic prediction models across the data types. We conclude by emphasizing that data integration is a critical bottleneck in systems science, cancer research and development, and health care innovation and that SVM and machine learning approaches offer new solutions and ways forward in biomedical, bioengineering, and clinical applications.

Differentiation between Luminal A and B Molecular Subtypes of Breast Cancer Using Pharmacokinetic Quantitative Parameters with Histogram and Texture Features on Preoperative Dynamic Contrast-Enhanced Magnetic Resonance Imaging

OBJECTIVE

The aim of the present study was to use pharmacokinetic quantitative parameters with histogram and texture features on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to differentiate between the luminal A and luminal B molecular subtypes of breast cancer.

METHODS

We retrospectively reviewed the data of 94 patients with histopathologically proven breast cancer. The pharmacokinetic quantitative parameters (K^trans, K_ep, and V_e) with their corresponding histogram and texture features based on preoperative DCE-MRI were obtained. The parameters were compared using the Mann-Whitney U-test between the luminal A and luminal B groups, the human epidermal growth factor receptor-2 (HER2)-positive luminal B and HER2-negative luminal B groups, and the lymph node metastasis (LNM)-positive and LNM-negative groups. Receiver operating characteristic curves were generated for parameters that presented significant between-group differences.

RESULTS

The maximum values of K^trans, K_ep, and V_e, and the mean and 90th percentile values of V_e were significantly higher in the luminal B group than in the luminal A group. Among the texture features, only skewness of K^trans significantly differed between the luminal A and B groups. All histogram features of K^trans were higher in the HER2-positive luminal B group than in the HER2-negative luminal B group. However, no parameter differed between the LNM-positive and LNM-negative groups.

CONCLUSION

Pharmacokinetic quantitative parameters with histogram and texture features obtained from DCE-MRI are associated with the molecular subtypes of breast cancer, and may serve as potential imaging biomarkers to differentiate between the luminal A and luminal B molecular subtypes.

The Impact of Normalization Approaches to Automatically Detect Radiogenomic Phenotypes Characterizing Breast Cancer Receptors Status

In breast cancer studies, combining quantitative radiomic with genomic signatures can help identifying and characterizing radiogenomic phenotypes, in function of molecular receptor status. Biomedical imaging processing lacks standards in radiomic feature normalization methods and neglecting feature normalization can highly bias the overall analysis. This study evaluates the effect of several normalization techniques to predict four clinical phenotypes such as estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and triple negative (TN) status, by quantitative features. The Cancer Imaging Archive (TCIA) radiomic features from 91 T1-weighted Dynamic Contrast Enhancement MRI of invasive breast cancers were investigated in association with breast invasive carcinoma miRNA expression profiling from the Cancer Genome Atlas (TCGA). Three advanced machine learning techniques (Support Vector Machine, Random Forest, and Naïve Bayesian) were investigated to distinguish between molecular prognostic indicators and achieved an area under the ROC curve (AUC) values of 86%, 93%, 91%, and 91% for the prediction of ER+ versus ER-, PR+ versus PR-, HER2+ versus HER2-, and triple-negative, respectively. In conclusion, radiomic features enable to discriminate major breast cancer molecular subtypes and may yield a potential imaging biomarker for advancing precision medicine.

Textural radiomic features and time-intensity curve data analysis by dynamic contrast-enhanced MRI for early prediction of breast cancer therapy response: preliminary data

BACKGROUND

To investigate the potential of semiquantitative time-intensity curve parameters compared to textural radiomic features on arterial phase images by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for early prediction of breast cancer neoadjuvant therapy response.

METHODS

A retrospective study of 45 patients subjected to DCE-MRI by public datasets containing examination performed prior to the start of treatment and after the treatment first cycle ('QIN Breast DCE-MRI' and 'QIN-Breast') was performed. In total, 11 semiquantitative parameters and 50 texture features were extracted. Non-parametric test, receiver operating characteristic analysis with area under the curve (ROC-AUC), Spearman correlation coefficient, and Kruskal-Wallis test with Bonferroni correction were applied.

RESULTS

Fifteen patients with pathological complete response (pCR) and 30 patients with non-pCR were analysed. Significant differences in median values between pCR patients and non-pCR patients were found for entropy, long-run emphasis, and busyness among the textural features, for maximum signal difference, washout slope, washin slope, and standardised index of shape among the dynamic semiquantitative parameters. The standardised index of shape had the best results with a ROC-AUC of 0.93 to differentiate pCR versus non-pCR patients.

CONCLUSIONS

The standardised index of shape could become a clinical tool to differentiate, in the early stages of treatment, responding to non-responding patients.

Benign or Malignant Characterization of Soft-Tissue Tumors by Using Semiquantitative and Quantitative Parameters of Dynamic Contrast-Enhanced Magnetic Resonance Imaging

PURPOSE

To evaluate the efficacy of the semiquantitative and quantitative parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in differentiating between benign and malignant soft-tissue tumors.

METHODS

A total of 45 patients with pathologically confirmed soft-tissue tumors (15 benign and 30 malignant tumors) underwent DCE-MRI. The semiquantitative parameters assessed were as follows: time to peak (TTP), maximum concentration (MAX Conc), area under the curve of time-concentration curve (AUC-TC), and maximum rise slope (MAX Slope). Quantitative DCE-MRI was analyzed with the extended Tofts-Kety model to assess the following quantitative parameters: volume transfer constant (Ktrans), microvascular permeability reflux constant (Kep), and distribute volume per unit tissue volume (Ve). Data were evaluated using the independent t test or Mann-Whitney U test and receiver operating characteristic (ROC) curves.

RESULTS

The TTP (P = .0035), MAX Conc (P = .0018), AUC-TC (P = .0018), MAX Slope (P = .0018), Ktrans (P = .0018), and Kep (P = .0035) were significantly different between the benign and malignant soft-tissue tumors. The AUC of the ROC curve demonstrated the diagnostic potential of TTP (0.778), MAX Conc (0.849), AUC-TC (0.831), MAX Slope (0.847), Ktrans (0.836), Kep (0.778), and Ve (0.638).

CONCLUSIONS

The use of semiquantitative and quantitative parameters of DCE-MRI enabled differentiation between benign and malignant soft-tissue tumors. The values of TTP were lower, while those of MAX Conc, AUC-TC, MAX Slope, Ktrans, and Kep were higher in malignant than in benign tumors.

Correlation between MR Image-Based Radiomics Features and Risk Scores Associated with Gene Expression Profiles in Breast Cancer

Purpose

To investigate the correlation between magnetic resonance (MR) image-based radiomics features and the genomic features of breast cancer by focusing on biomolecular intrinsic subtypes and gene expression profiles based on risk scores.

Materials and Methods

We used the publicly available datasets from the Cancer Genome Atlas and the Cancer Imaging Archive to extract the radiomics features of 122 breast cancers on MR images. Furthermore, PAM50 intrinsic subtypes were classified and their risk scores were determined from gene expression profiles. The relationship between radiomics features and biomolecular characteristics was analyzed. A penalized generalized regression analysis was performed to build prediction models.

Results

The PAM50 subtype demonstrated a statistically significant association with the maximum 2D diameter (p = 0.0189), degree of correlation (p = 0.0386), and inverse difference moment normalized (p = 0.0337). Among risk score systems, GGI and GENE70 shared 8 correlated radiomic features (p = 0.0008–0.0492) that were statistically significant. Although the maximum 2D diameter was most significantly correlated to both score systems (p = 0.0139, and p = 0.0008), the overall degree of correlation of the prediction models was weak with the highest correlation coefficient of GENE70 being 0.2171.

Conclusion

Maximum 2D diameter, degree of correlation, and inverse difference moment normalized demonstrated significant relationships with the PAM50 intrinsic subtypes along with gene expression profile-based risk scores such as GENE70, despite weak correlations.

Volumetric imaging parameters are significant for predicting the pathological complete response of preoperative concurrent chemoradiotherapy in local advanced rectal cancer

Preoperative concurrent chemoradiotherapy (CCRT) as the standard treatment for locally advanced rectal cancer (LARC) has been widely used in clinic. Its efficiency influences the prognosis and the selection of subsequent treatment. The current criteria for evaluating the prognosis of patients with extremely sensitive preoperative CCRT include the clinical complete remission response (cCR) and pathological complete response (pCR), but those with cCR may not necessarily achieve pCR, and the pCR can be confirmed only after surgery. Some scholars believe that patients with pCR after CCRT can be categorized as 'watch and wait'. Therefore, it is extremely important to find a way to predict the pCR status of patients before therapy. In this study, we examined the expression of stem cell markers and obtained direct and derivative volumetric imaging parameters before treatment. Subsequently, these factors and the general clinical data were adopted into a regression model, and the correlation between them and the pCR was analyzed. We found that the pCR of LARC was positively correlated with tumor compactness (TC), whereas it was negatively correlated with approximate tumor volume (ATV), real tumor volume (RTV), total surface area of the tumor (TSA) and tumor maximum longitudinal length (TML). In these meaningful predictors, the positive predictive values and the negative predictive values of TC were 74.73% and 94.61%, respectively. Compared with other possible predictors, TC is the most encouraging predictor of pCR. Our findings provide a way for clinicians to predict the sensitivity of preoperative CCRT and will help to select individualized treatment options for LARC patients.

On the potential use of dynamic contrast-enhanced (DCE) MRI parameters as radiomic features of cervical cancer

PURPOSE

To evaluate whether the analysis of high-temporal resolution DCE-MRI by various tracer kinetic models could yield useful radiomic features in discriminating cervix carcinoma and normal cervix tissue.

METHODS

Forty-three patients (median age 51 yr; range 26-78 yr) diagnosed with cervical cancer based on postoperative pathology were enrolled in this study with informed consent. DCE-MRI data with temporal resolution of 2 s were acquired and analyzed using the Tofts (TOFTS), extended Tofts (EXTOFTS), conventional two-compartment (CC), adiabatic tissue homogeneity (ATH), and distributed parameter (DP) models. Ability of all kinetic parameters in distinguishing tumor from normal tissue was assessed using Mann-Whitney U test and receiver operating characteristic (ROC) curves. Repeatability of parameter estimates due to sampling of arterial input functions (AIFs) was also studied using intraclass correlation (ICC) analysis.

RESULTS

Fractional extravascular, extracellular volume (Ve) of all models were significantly smaller in cervix carcinoma than normal cervix tissue, and were associated with large values of area under ROC curve (AUC 0.884-0.961). Capillary permeability PS derived from the ATH, CC, and DP models also yielded large AUC values (0.730, 0.860, and 0.797). Transfer constant Ktrans derived from TOFTS and EXTOFTS models yielded smaller AUC (0.587 and 0.701). Repeatability of parameters derived from all models was robust to AIF sampling, with ICC coefficients typically larger than 0.80.

CONCLUSIONS

With the use of high-temporal resolution DCE-MRI, all tracer kinetic models could reflect pathophysiological differences between cervix carcinoma and normal tissue (with significant differences in Ve and PS) and potentially yield radiomic features with diagnostic value.

Added value of histogram analysis of apparent diffusion coefficient maps for differentiating triple-negative breast cancer from other subtypes of breast cancer on standard MRI

Background

Triple-negative breast cancers generally occur in young women with remarkable potential to be aggressive. It will be of great help to detect this subtype of tumor early. To retrospectively evaluate the performance of histogram analysis of apparent diffusion coefficient (ADC) maps in distinguishing triple-negative breast cancer (TNBC) from other subtypes of breast cancer (non-TNBC), when combined with magnetic resonance imaging (MRI) features.

Materials and methods

From February 2014 to December 2018, 192 patients were included in this study taking preoperative standard MRI (s-MRI) and DWI. Seventy-six of them were pathologically confirmed with TNBC and rest 116 with other subtypes. First, their clinical-pathological features and morphological characteristics on MRI were assessed, including tumor size, foci quantity, tumor shape, margin, internal enhancement, and time-signal intensity curve types, in addition to the signal intensity on T2-weighted images. Second, whole-lesion apparent diffusion coefficient (ADC) histogram analysis was executed. Finally, both univariate and multivariate regression analyses were applied to identify the most useful variables in separating TNBCs from non-TNBCs, and then their effects were evaluated following receiver operating characteristic curve analysis.

Result

Multivariate regression analysis indicated that circumscribed margin, rim enhancement, and ADC₉₀ were important predictors for TNBC. Increased area under curve (AUC) and improved specificity can be obtained when combined s-MRI and DWI (circumscribed margin+rim enhancement+ADC₉₀>1.47×10⁻³ mm²/s) is taken as the criterion, other than s-MRI (circumscribed margin+rim enhancement) alone (s-MRI+DWI vs s-MRI; AUC, 0.833 vs 0.797; specificity, 98.3% vs 89.7%; sensitivity, 68.4% vs 69.7%).

Conclusion

Circumscribed margin and rim enhancement on s-MRI and ADC₉₀ are three important elements in detecting TNBC, while ADC histogram analysis can provide additional value in this detection.