Prediction Of Molecular Subtypes Research Articles

Breast Cancer Molecular Subtype Prediction: A Mammography-Based AI Approach.

Breast cancer remains a leading cause of mortality among women, with molecular subtypes significantly influencing prognosis and treatment strategies. Currently, identifying the molecular subtype of cancer requires a biopsy-a specialized, expensive, and time-consuming procedure, often yielding to results that must be supported with additional biopsies due to technique errors or tumor heterogeneity. This study introduces a novel approach for predicting breast cancer molecular subtypes using mammography images and advanced artificial intelligence (AI) methodologies. Using the OPTIMAM imaging database, 1397 images from 660 patients were selected. The pretrained deep learning model ResNet-101 was employed to classify tumors into five subtypes: Luminal A, Luminal B1, Luminal B2, HER2, and Triple Negative. Various classification strategies were studied: binary classifications (one vs. all others, specific combinations) and multi-class classification (evaluating all subtypes simultaneously). To address imbalanced data, strategies like oversampling, undersampling, and data augmentation were explored. Performance was evaluated using accuracy and area under the receiver operating characteristic curve (AUC). Binary classification results showed a maximum average accuracy and AUC of 79.02% and 64.69%, respectively, while multi-class classification achieved an average AUC of 60.62% with oversampling and data augmentation. The most notable binary classification was HER2 vs. non-HER2, with an accuracy of 89.79% and an AUC of 73.31%. Binary classification for specific combinations of subtypes revealed an accuracy of 76.42% for HER2 vs. Luminal A and an AUC of 73.04% for HER2 vs. Luminal B1. These findings highlight the potential of mammography-based AI for non-invasive breast cancer subtype prediction, offering a promising alternative to biopsies and paving the way for personalized treatment plans.

MRI Manifestations of Breast Cancer Stroma and their Role in Predicting Molecular Subtype: A Case-control Study.

This study explored whether breast MRI manifestations could be used to predict the stroma distribution of breast cancer (BC) and the role of tumor stroma-based MRI manifestations in molecular subtype prediction. 57 patients with pathologically confirmed invasive BC (non-special type) who had lumpy BC on MRI within one week before surgery were retrospectively collected in the study. Stroma distributions were classified according to their characteristics in the pathological sections. The stromal distribution patterns among molecular subtypes were compared with the MRI manifestations of BC with different stroma distribution types (SDTs). SDTs were significantly different and depended on the BC hormone receptor (HR) (P<0.001). There were also significant differences among five SDTs on T2WI, ADC map, internal delayed enhanced features (IDEF), marginal delayed enhanced features (MDEF), and time signal intensity (TSI) curves. Spiculated margin and the absence of type-I TSI were independent predictors for BC with star grid type stroma. The appearance frequency of hypo-intensity on T2WI in HR- BCs was significantly lower (P=0.043) than in HR+ BCs. Star grid stroma and spiculated margin were key factors in predicting HR+ BCs, and the AUC was 0.927 (95% CI: 0.867-0.987). Breast MRI can be used to predict BC's stromal distribution and molecular subtypes.

Computed tomography radiogenomics: A potential tool for prediction of molecular subtypes in gastric stromal tumor.

Preoperative knowledge of mutational status of gastrointestinal stromal tumors (GISTs) is essential to guide the individualized precision therapy. To develop a combined model that integrates clinical and contrast-enhanced computed tomography (CE-CT) features to predict gastric GISTs with specific genetic mutations, namely KIT exon 11 mutations or KIT exon 11 codons 557-558 deletions. A total of 231 GIST patients with definitive genetic phenotypes were divided into a training dataset and a validation dataset in a 7:3 ratio. The models were constructed using selected clinical features, conventional CT features, and radiomics features extracted from abdominal CE-CT images. Three models were developed: ModelCT sign, modelCT sign + rad, and model CTsign + rad + clinic. The diagnostic performance of these models was evaluated using receiver operating characteristic (ROC) curve analysis and the Delong test. The ROC analyses revealed that in the training cohort, the area under the curve (AUC) values for modelCT sign, modelCT sign + rad, and modelCT sign + rad + clinic for predicting KIT exon 11 mutation were 0.743, 0.818, and 0.915, respectively. In the validation cohort, the AUC values for the same models were 0.670, 0.781, and 0.811, respectively. For predicting KIT exon 11 codons 557-558 deletions, the AUC values in the training cohort were 0.667, 0.842, and 0.720 for modelCT sign, modelCT sign + rad, and modelCT sign + rad + clinic, respectively. In the validation cohort, the AUC values for the same models were 0.610, 0.782, and 0.795, respectively. Based on the decision curve analysis, it was determined that the modelCT sign + rad + clinic had clinical significance and utility. Our findings demonstrate that the combined modelCT sign + rad + clinic effectively distinguishes GISTs with KIT exon 11 mutation and KIT exon 11 codons 557-558 deletions. This combined model has the potential to be valuable in assessing the genotype of GISTs.

EcGBMsub: an integrative stacking ensemble model framework based on eccDNA molecular profiling for improving IDH wild-type glioblastoma molecular subtype classification.

IDH wild-type glioblastoma (GBM) intrinsic subtypes have been linked to different molecular landscapes and outcomes. Accurate prediction of molecular subtypes of GBM is very important to guide clinical diagnosis and treatment. Leveraging machine learning technology to improve the subtype classification was considered a robust strategy. Several single machine learning models have been developed to predict survival or stratify patients. An ensemble learning strategy combines several basic learners to boost model performance. However, it still lacked a robust stacking ensemble learning model with high accuracy in clinical practice. Here, we developed a novel integrative stacking ensemble model framework (ecGBMsub) for improving IDH wild-type GBM molecular subtype classification. In the framework, nine single models with the best hyperparameters were fitted based on extrachromosomal circular DNA (eccDNA) molecular profiling. Then, the top five optimal single models were selected as base models. By randomly combining the five optimal base models, 26 different combinations were finally generated. Nine different meta-models with the best hyperparameters were fitted based on the prediction results of 26 different combinations, resulting in 234 different stacked ensemble models. All models in ecGBMsub were comprehensively evaluated and compared. Finally, the stacking ensemble model named "XGBoost.Enet-stacking-Enet" was chosen as the optimal model in the ecGBMsub framework. A user-friendly web tool was developed to facilitate accessibility to the XGBoost.Enet-stacking-Enet models (https://lizesheng20190820.shinyapps.io/ecGBMsub/).

Combination of DCE-MRI and NME-DWI via Deep Neural Network for Predicting Breast Cancer Molecular Subtypes

BackgroundTo explore whether the combination of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) and nonmono-exponential (NME) model-based diffusion-weighted imaging (DWI) via deep neural network (DNN) can improve the prediction of breast cancer molecular subtypes compared to either imaging technique used alone. Patients and MethodsThis prospective study examined 480 breast cancers in 475 patients undergoing DCE-MRI and NME-DWI at 3.0 T. Breast cancers were classified as follows: human epidermal growth factor receptor 2 enriched (HER2-enriched), luminal A, luminal B (HER2–), luminal B (HER2+), and triple-negative subtypes. A total of 20% cases were withheld as an independent test dataset, and the remaining cases were used to train DNN with an 80% to 20% training-validation split and 5-fold cross-validation. The diagnostic accuracies of DNN in 5-way subtype classification between the DCE-MRI, NME-DWI, and their combined multiparametric-MRI datasets were compared using analysis of variance with least significant difference posthoc test. Areas under the receiver-operating characteristic curves were calculated to assess the performances of DNN in binary subtype classification between the 3 datasets. ResultsThe 5-way classification accuracies of DNN on both DCE-MRI (0.71) and NME-DWI (0.64) were significantly lower (P < .05) than on multiparametric-MRI (0.76), while on DCE-MRI was significantly higher (P < .05) than on NME-DWI. The comparative results of binary classification between the 3 datasets were consistent with the 5-way classification. ConclusionThe combination of DCE-MRI and NME-DWI via DNN achieved a significant improvement in breast cancer molecular subtype prediction compared to either imaging technique used alone. Additionally, DCE-MRI outperformed NME-DWI in differentiating subtypes.

Histomolecular classification of urothelial carcinoma of the urinary bladder : From histological phenotype to genotype and back

Of all urothelial carcinomas (UCs), 25% are muscle invasive and associated with a5-year overall survival rate of 50%. Findings regarding the molecular classification of muscle-invasive urothelial carcinomas (MIUCs) have not yet found their way into clinical practice. Prediction of molecular consensus subtypes in MIUCs with artificial intelligence (AI) based on histologic hematoxylin-eosin (HE) sections. Pathologic review and annotation of The Cancer Genome Atlas (TCGA) Bladder Cancer (BLCA) Cohort (N = 412) and the Dr. Senckenberg Institute of Pathology (SIP) BLCA Cohort (N = 181). An AI model for the prediction of molecular subtypes based on annotated histomorphology was trained. For afive-fold cross-validation with TCGA cases (N = 274), an internal TCGA test set (N = 18) and an external SIP test set (N = 27), we reached mean area under the receiver operating characteristic curve (AUROC) scores of 0.73, 0.8 and 0.75 for the classification of the used molecular subtypes "luminal", "basal/squamous" and "stroma-rich". By training on correlations to individual molecular subtypes, rather than training on one subtype assignment per case, the AI prediction of subtypes could be significantly improved. Follow-up studies with RNA extraction from various areas of AI-predicted molecular heterogeneity may improve molecular classifications and thereby AI algorithms trained on these classifications.

Identification and prediction of molecular subtypes of atherosclerosis based on m6A immune cell infiltration

BackgroundAtherosclerosis is a complex disease with multiple molecular subtypes that are not yet fully understood. Recent studies have suggested that N6-methyladenosine (m6A) alterations may play a role in the pathogenesis of atherosclerosis. However, the relationship between m6A regulators and atherosclerosis remains unclear. MethodsIn this study, we analyzed the expression levels of 25 m6A regulators in a cohort of atherosclerosis (AS) and non-AS patients using the R “limma” package. We also used machine learning models, including random forest (RF), support vector machine (SVM), generalized linear model (GLM), and extreme gradient boosting (XGB), to predict the molecular subtypes of atherosclerosis based on m6A immune cell infiltration. ResultsWe found that METTL3, YTHDF2, IGFBP1, and IGF2BP1 were overexpressed in AS patients compared to non-AS patients, while the other significant m6A regulators showed no significant difference. Our machine learning models achieved high accuracy in predicting the molecular subtypes of atherosclerosis based on m6A immune cell infiltration. ConclusionOur study suggests that m6A alterations may play a role in the pathogenesis of atherosclerosis, and that machine learning models can be used to predict molecular subtypes of atherosclerosis based on m6A immune cell infiltration. These findings may have important implications for the detection and management of atherosclerosis.

A Fully Automated Deep-Learning Model for Predicting the Molecular Subtypes of Posterior Fossa Ependymomas Using T2-Weighted Images.

We aimed to develop and validate a deep learning (DL) model to automatically segment posterior fossa ependymoma (PF-EPN) and predict its molecular subtypes [Group A (PFA) and Group B (PFB)] from preoperative MR images. We retrospectively identified 227 PF-EPNs (development and internal test sets) with available preoperative T2-weighted (T2w) MR images and molecular status to develop and test a 3D nnU-Net (referred to as T2-nnU-Net) for tumor segmentation and molecular subtype prediction. The network was externally tested using an external independent set [n = 40; subset-1 (n = 31) and subset-2 (n =9)] and prospectively enrolled cases [prospective validation set (n = 27)]. The Dice similarity coefficient was used to evaluate the segmentation performance. Receiver operating characteristic analysis for molecular subtype prediction was performed. For tumor segmentation, the T2-nnU-Net achieved a Dice score of 0.94 ± 0.02 in the internal test set. For molecular subtype prediction, the T2-nnU-Net achieved an AUC of 0.93 and accuracy of 0.89 in the internal test set, an AUC of 0.99 and accuracy of 0.93 in the external test set. In the prospective validation set, the model achieved an AUC of 0.93 and an accuracy of 0.89. The predictive performance of T2-nnU-Net was superior or comparable to that of demographic and multiple radiologic features (AUCs ranging from 0.87 to 0.95). A fully automated DL model was developed and validated to accurately segment PF-EPNs and predict molecular subtypes using only T2w MR images, which could help in clinical decision-making.

Artificial intelligence in breast ultrasound: application in clinical practice.

Ultrasound (US) is a widely accessible and extensively used tool for breast imaging. It is commonly used as an additional screening tool, especially for women with dense breast tissue. Advances in artificial intelligence (AI) have led to the development of various AI systems that assist radiologists in identifying and diagnosing breast lesions using US. This article provides an overview of the background and supporting evidence for the use of AI in hand held breast US. It discusses the impact of AI on clinical workflow, covering breast cancer detection, diagnosis, prediction of molecular subtypes, evaluation of axillary lymph node status, and response to neoadjuvant chemotherapy. Additionally, the article highlights the potential significance of AI in breast US for low and middle income countries.

Assessing the Role of Different Heterogeneous Regions in DCE-MRI for Predicting Molecular Subtypes of Breast Cancer based on Network Architecture Search and Vision Transformer.

Breast cancer, the most common female malignancy, is highly heterogeneous, manifesting as different molecular subtypes. It is clinically important to distinguish between these molecular subtypes due to marked differences in prognosis, treatment and survival outcomes. In this study, we first performed convex analysis of mixtures (CAM) analysis on both intratumoral and peritumoral regions in DCE-MRI to generate multiple heterogeneous regions. Then, we developed a vision transformer (ViT)-based DL model and performed network architecture search (NAS) to evaluate all the combination of different heterogeneous regions for predicting molecular subtypes of breast cancer. Experimental results showed that the input plasma from both peritumoral and intratumoral regions, and the fast-flow kinetics from intratumoral regions were critical for predicting different molecular subtypes, achieving an area under receiver operating characteristic curve (AUROC) value of 0.66-0.68.Clinical Relevance- This study reduces the redundancy in multiple heterogeneous subregions and supports the precise prediction of molecular subtypes, which is of potential importance for the medicine care and treatment planning of patients with breast cancer.

P-317 CT radiomics for the preoperative prediction of molecular subtypes in gastric stromal tumor

P-317 CT radiomics for the preoperative prediction of molecular subtypes in gastric stromal tumor

Value of Breast Ultrasound in the Prediction of Molecular Subtypes in Patients with Breast Cancer

Objectives:To correlate between the breast ultrasound imaging features and molecular subtypes of breast cancer and to assess the predictive value of their correlation

Single-nucleus gene and gene set expression-based similarity network fusion identifies autism molecular subtypes

BackgroundAutism spectrum disorder (ASD) is a complex neurodevelopmental disorder that is highly phenotypically and genetically heterogeneous. With the accumulation of biological sequencing data, more and more studies shift to molecular subtype-first approach, from identifying molecular subtypes based on genetic and molecular data to linking molecular subtypes with clinical manifestation, which can reduce heterogeneity before phenotypic profiling.ResultsIn this study, we perform similarity network fusion to integrate gene and gene set expression data of multiple human brain cell types for ASD molecular subtype identification. Then we apply subtype-specific differential gene and gene set expression analyses to study expression patterns specific to molecular subtypes in each cell type. To demonstrate the biological and practical significance, we analyze the molecular subtypes, investigate their correlation with ASD clinical phenotype, and construct ASD molecular subtype prediction models.ConclusionsThe identified molecular subtype-specific gene and gene set expression may be used to differentiate ASD molecular subtypes, facilitating the diagnosis and treatment of ASD. Our method provides an analytical pipeline for the identification of molecular subtypes and even disease subtypes of complex disorders.

Abstract 5404: Predicting protein receptor status from H&amp;E-stained images in breast cancer

Abstract Correct prediction of cancer molecular subtype plays a very important role in determining the treatment of cancer patients. In determining the molecular subtype of breast cancer, protein receptors such as estrogen receptors (ER), progesterone receptors (PR), and human epidermal growth factor receptor type 2 (HER2) are used as key factors. These protein receptors also play an important role in determining the treatment method or predicting the prognosis of breast cancer. To confirm this, a test should be performed by immunohistochemical (IHC) staining. In this study, we investigated the morphological relationship between the molecular subtypes and hematoxylin and eosin (H&amp;E) stained whole slide images (WSIs) without IHC stained images, and performed an experiment to evaluate that the protein receptors can be predicted by these morphological features. The TCGA-BRCA data were utilized in this study. There were 728 cases out of the total 1097 cases where the IHC status for ER, PR, and HER2 was either positive or negative. Each individual case is scanned using different scanners and magnifications. In some cases with multiple slides, we use only the first scanned image. The entire WSI was randomly split into 3:1:1, and used for training, tuning, and test, respectively. Individual WSIs was tiled into 1024 × 1024 patches for this study. The multi-task deep learning model predicts the protein receptor status of individual patches. In this study, a confidence measure was added to remove the uncertainty of the deep learning model. When learning WSIs, patches of less than 70% based on these confidence scores did not affect WSIs. Specifically, when learning morphological features, we used strong augmentation such as grayscale, gaussian blur, color jitter, and posterization to ensure that predictions were not biased by color alone. Based on individual patches, ER accuracy of 76%, PR accuracy of 65%, and HER2 accuracy of 79% are shown. As a result of prediction by majority voting on WSI images through patch predicted results, ER accuracy of 74.6% PR accuracy of 66%, and HER2 accuracy of 76.6% Through this study, it was confirmed that the sufficiently trained deep learning model predicted ER, PR, and HER2, which are important factors of molecular subtype, relatively well. Through this, it was found that there was some correlation between morphological characteristics and molecular subtypes in H&amp;E stained WSIs. If more data are collected through future experiments, a molecular subtype prediction model can be developed. Citation Format: Geongyu Lee, Chungyeul Kim, Tae-Yeong Kwak, Sun Woo Kim, Hyeyoon Chang. Predicting protein receptor status from H&amp;E-stained images in breast cancer. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5404.

Radiomic features from dynamic susceptibility contrast perfusion-weighted imaging improve the three-class prediction of molecular subtypes in patients with adult diffuse gliomas.

To investigate whether radiomic features extracted from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) can improve the prediction of the molecular subtypes of adultdiffuse gliomas, and to further develop and validate a multimodal radiomic model by integrating radiomic features from conventional and perfusion MRI. We extracted 1197 radiomic features from each sequence of conventional MRI and DSC-PWI, respectively. The Boruta algorithm was used for feature selection and combination, and a three-class random forest method was applied to construct the models. We also constructed a combined model by integrating radiomic features and clinical metrics. The models' diagnostic performance for discriminating the molecular subtypes (IDH wild type [IDHwt], IDH mutant and 1p/19q-noncodeleted [IDHmut-noncodel], and IDH mutant and 1p/19q-codeleted [IDHmut-codel]) was compared using AUCs in the validation set. We included 272 patients (training set, n = 166; validation set, n = 106) with grade II-IV gliomas (mean age, 48.7years; range, 19-77years). The proportions of the molecular subtypes were 66.2% IDHwt, 15.1% IDHmut-noncodel, and 18.8% IDHmut-codel. Nineteen radiomic features (13 from conventional MRI and 6 from DSC-PWI) were selected to build the multimodal radiomic model. In the validation set, the multimodal radiomic model showed better performance than the conventional radiomic model did in predicting the IDHwt and IDHmut-codel subtypes, which was comparable to the conventional radiomic model in predicting the IDHmut-noncodel subtype. The multimodal radiomic model yielded similar performance as the combined model in predicting the three molecular subtypes. Adding DSC-PWI to conventional MRI can improve molecular subtype prediction in patients with diffuse gliomas. • The multimodal radiomic model outperformed conventional MRI when predicting both the IDH wild type and IDH mutant and 1p/19q-codeleted subtypes of gliomas. • The multimodal radiomic model showed comparable performance to the combined model in the prediction of the three molecular subtypes. • Radiomic features from T1-weighted gadolinium contrast-enhanced and relative cerebral blood volume images played an important role in the prediction of molecular subtypes.

Value of genomics- and radiomics-based machine learning models in the identification of breast cancer molecular subtypes: a systematic review and meta-analysis.

In the era of precision therapy, early classification of breast cancer (BRCA) molecular subtypes has clinical significance for disease management and prognosis. We explored the accuracy of machine learning (ML) models for early classification of BRCA molecular subtypes through a systematic review of the literature currently available. We retrieved relevant studies published in PubMed, EMBASE, Cochrane, and Web of Science until 15 April 2022. A prediction model risk of bias assessment tool (PROBAST) was applied for the assessment of risk of bias of a genomics-based ML model, and the Radiomics Quality Score (RQS) was simultaneously used to evaluate the quality of this radiomics-based ML model. A random effects model was adopted to analyze the predictive accuracy of genomics-based ML and radiomics-based ML for Luminal A, Luminal B, Basal-like or triple-negative breast cancer (TNBC), and human epidermal growth factor receptor 2 (HER2). The PROSPERO of our study was prospectively registered (CRD42022333611). Of the 38 studies were selected for analysis, 14 ML models were based on gene-transcriptomic, with only 4 external validations; and 43 ML models were based on radiomics, with only 14 external validations. Meta-analysis results showed that c-statistic values of the ML based on radiomics for the identification of BRCA molecular subtypes Luminal A, Luminal B, Basal-like or TNBC, and HER2 were 0.76 [95% confidence interval (CI): 0.60-0.96], 0.78 (95% CI: 0.69-0.87), 0.89 (95% CI: 0.83-0.91), and 0.83 (95% CI: 0.81-0.86), respectively. The c-statistic values of ML based on the gene-transcriptomic analysis cohort for the identification of the previously described BRCA molecular subtypes were 0.96 (95% CI: 0.93-0.99), 0.96 (95% CI: 0.93-0.99), 0.98 (95% CI: 0.95-1.00), and 0.97 (95% CI: 0.96-0.98) respectively. Additionally, the sensitivity of the ML model based on radiomics for each molecular subtype ranged from 0.79 to 0.85, while the sensitivity of the ML model based on gene-transcriptomic was between 0.92 and 0.99. Both radiomics and gene transcriptomics produced ideal effects on BRCA molecular subtype prediction. Compared with radiomics, gene transcriptomics yielded better prediction results, but radiomics was simpler and more convenient from a clinical point of view.

Invasive ductal breast cancer molecular subtype prediction by MRI radiomic and clinical features based on machine learning.

BackgroundMost studies of molecular subtype prediction in breast cancer were mainly based on two-dimensional MRI images, the predictive value of three-dimensional volumetric features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting breast cancer molecular subtypes has not been thoroughly investigated. This study aimed to look into the role of features derived from DCE-MRI and how they could be combined with clinical data to predict invasive ductal breast cancer molecular subtypes.MethodsFrom January 2019 to December 2021, 190 Chinese women with invasive ductal breast cancer were studied (32 triple-negative, 59 HER2-enriched, and 99 luminal lesions) in this institutional review board-approved retrospective cohort study. The image processing software extracted 1130 quantitative radiomic features from the segmented lesion area, including shape-based, first-order statistical, texture, and wavelet features. Three binary classifications of the subtypes were performed: triple-negative vs. non-triple-negative, HER2-overexpressed vs. non-HER2-overexpressed, and luminal (A + B) vs. non-luminal. For the classification, five machine learning methods (random forest, logistic regression, support vector machine, naïve Bayes, and eXtreme Gradient Boosting) were employed. The classifiers were chosen using the least absolute shrinkage and selection operator method. The area evaluated classification performance under the receiver operating characteristic curve, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean.ResultsEXtreme Gradient Boosting model showed the best performance in luminal and non-luminal groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8282, 0.7524, 0.6542, 0.6964, 0.6086, 0.3458, 0.8524 and 0.7016, respectively. Meanwhile, the random forest model showed the best performance in HER2-overexpressed and non-HER2-overexpressed groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8054, 0.2941, 0.9744, 0.7679, 0.4348, 0.0256, 0.8333 and 0.5353, respectively. Furthermore, eXtreme Gradient Boosting model showed the best performance in the triple-negative and non-triple-negative groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.9031, 0.9362, 0.4444, 0.8571, 0.9167, 0.5556, 0.8980 and 0.6450.ConclusionClinical data and three-dimension imaging features from DCE-MRI were identified as potential biomarkers for distinguishing between three molecular subtypes of invasive ductal carcinomas breast cancer. In the future, more extensive studies will be required to evaluate the findings.

Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study.

PurposeThe aim of this study is to investigate radiomics features extracted from the optimal peritumoral region and the intratumoral area on the early phase of dynamic contrast-enhanced MRI (DCE-MRI) for predicting molecular subtypes of invasive ductal breast carcinoma (IDBC).MethodsA total of 422 IDBC patients with immunohistochemical and fluorescence in situ hybridization results from two hospitals (Center 1: 327 cases, Center 2: 95 cases) who underwent preoperative DCE-MRI were retrospectively enrolled. After image preprocessing, radiomic features were extracted from the intratumoral area and four peritumoral regions on DCE-MRI from two centers, and selected the optimal peritumoral region. Based on the intratumoral, peritumoral radiomics features, and clinical–radiological characteristics, five radiomics models were constructed through support vector machine (SVM) in multiple classification tasks related to molecular subtypes and visualized by nomogram. The performance of radiomics models was evaluated by receiver operating characteristic curves, confusion matrix, calibration curves, and decision curve analysis.ResultsA 6-mm peritumoral size was defined the optimal peritumoral region in classification tasks of hormone receptor (HR)-positive vs others, triple-negative breast cancer (TNBC) vs others, and HR-positive vs human epidermal growth factor receptor 2 (HER2)-enriched vs TNBC, and 8 mm was applied in HER2-enriched vs others. The combined clinical–radiological and radiomics models in three binary classification tasks (HR-positive vs others, HER2-enriched vs others, TNBC vs others) obtained optimal performance with AUCs of 0.838, 0.848, and 0.930 in the training cohort, respectively; 0.827, 0.813, and 0.879 in the internal test cohort, respectively; and 0.791, 0.707, and 0.852 in the external test cohort, respectively.ConclusionRadiomics features in the intratumoral and peritumoral regions of IDBC on DCE-MRI had a potential to predict the HR-positive, HER2-enriched, and TNBC molecular subtypes preoperatively.

Prediction of Molecular Subtypes Using Superb Microvascular Imaging and Shear Wave Elastography in Invasive Breast Carcinomas

To investigate the efficacy of the advanced imaging methods, superb microvascular imaging (SMI) and shear wave elastography (SWE) in predicting molecular subtypes in invasive breast carcinomas. A total of 210 biopsy-proven breast carcinomas in 200 patients who underwent ultrasound (US) imaging with SMI and SWE were included in this study. Quantitative analyses were performed using mean elasticity (Emean) score by SWE and vascular index (VI) by SMI. For qualitative assessment of microvascularity, first, lesions were graded according to Adler's classification in four types. Then, a new morphological model was used to classify the microvascular architecture into six patterns: type one, no signal; type two, penetrant; type three, rim-like; type four, dot-like/linear/regional; type five, wheel-like and type six, irregular signals. The correlation between these variables and molecular subtypes, nuclear grade, the Ki-67 levels and axillary status was investigated. The average VI and Emean values were relatively higher in non-luminal subtypes (VI, p=0.002; Emean, p > 0.05). The two microvascularisation models were significantly able to differentiate the molecular subtypes according to the Kruskal Wallis test (p < 0.05). Rim-like, penetrant and regional patterns were primarily observed in luminal subtypes. The dominant pattern in non-luminal subtypes was wheel-like pattern. VI, Emean, Adler's classification and morphological vascularisation model were not significantly correlated with the nuclear grade, Ki-67 index or axillary status. The proposed microvascular categorization model may be more valuable in predicting molecular subtypes of breast carcinomas compared to VI and Emean and may contribute to the management of breast carcinomas as a non-invasive variable.

Breast Cancer Molecular Subtype Prediction on Pathological Images with Discriminative Patch Selection and Multi-Instance Learning.

Molecular subtypes of breast cancer are important references to personalized clinical treatment. For cost and labor savings, only one of the patient’s paraffin blocks is usually selected for subsequent immunohistochemistry (IHC) to obtain molecular subtypes. Inevitable block sampling error is risky due to the tumor heterogeneity and could result in a delay in treatment. Molecular subtype prediction from conventional H&E pathological whole slide images (WSI) using the AI method is useful and critical to assist pathologists to pre-screen proper paraffin block for IHC. It is a challenging task since only WSI-level labels of molecular subtypes from IHC can be obtained without detailed local region information. Gigapixel WSIs are divided into a huge amount of patches to be computationally feasible for deep learning, while with coarse slide-level labels, patch-based methods may suffer from abundant noise patches, such as folds, overstained regions, or non-tumor tissues. A weakly supervised learning framework based on discriminative patch selection and multi-instance learning was proposed for breast cancer molecular subtype prediction from H&E WSIs. Firstly, co-teaching strategy using two networks was adopted to learn molecular subtype representations and filter out some noise patches. Then, a balanced sampling strategy was used to handle the imbalance in subtypes in the dataset. In addition, a noise patch filtering algorithm that used local outlier factor based on cluster centers was proposed to further select discriminative patches. Finally, a loss function integrating local patch with global slide constraint information was used to fine-tune MIL framework on obtained discriminative patches and further improve the prediction performance of molecular subtyping. The experimental results confirmed the effectiveness of the proposed AI method and our models outperformed even senior pathologists, which has the potential to assist pathologists to pre-screen paraffin blocks for IHC in clinic.