Preoperative prediction of axillary sentinel lymph node burden with multiparametric MRI-based radiomics nomogram in early-stage breast cancer

Assessment of the axilla in women with early-stage breast cancer undergoing primary surgery: a review

Sentinel node biopsy (SNB) is routinely performed in people with node-negative early breast cancer to assess the axilla. SNB has no proven therapeutic benefit. Nodal status information obtained from SNB helps in prognostication and can influence adjuvant systemic and locoregional treatment choices. However, the redundancy of the nodal status information is becoming increasingly apparent. The accuracy of radiological assessment of the axilla, combined with the strong influence of tumour biology on systemic and locoregional therapy requirements, has prompted many to consider alternative options for SNB. SNB contributes significantly to decreased quality of life in early breast cancer patients. Substantial improvements in workflow and cost could accrue by removing SNB from early breast cancer treatment. We review the current viewpoints and ideas for alternative options for assessing and managing a clinically negative axilla in patients with early breast cancer (EBC). Omitting SNB in selected cases or replacing SNB with a non-invasive predictive model appear to be viable options based on current literature.

Application of Texture and Volume Model Analysis to Dedicated Axillary High-resolution 3D T2-weighted MR Imaging: A Novel Method for Diagnosing Lymph Node Metastasis in Patients with Clinically Node-negative Breast Cancer

PURPOSE

To evaluate the effectiveness of the texture analysis of axillary high-resolution 3D T2-weighted imaging (T2WI) in distinguishing positive and negative lymph node (LN) metastasis in patients with clinically node-negative breast cancer.

METHODS

Between December 2017 and May 2021, 242 consecutive patients underwent high-resolution 3D T2WI and were classified into the training (n = 160) and validation cohorts (n = 82). We performed manual 3D segmentation of all visible LNs in axillary level I to extract the texture features. As the additional parameters, the number of the LNs and the total volume of all LNs for each case were calculated. The least absolute shrinkage and selection operator algorithm and Random Forest were used to construct the models. We constructed the texture model using the features from the LN with the largest least axis length in the training cohort. Furthermore, we constructed the 3 models combining the selected texture features of the LN with the largest least axis length, the number of LNs, and the total volume of all LNs: texture-number model, texture-volume model, and texture-number-volume model. As a conventional method, we manually measured the largest cortical diameter. Moreover, we performed the receiver operating curve analysis in the validation cohort and compared area under the curves (AUCs) of the models.

RESULTS

The AUCs of the texture model, texture-number model, texture-volume model, texture-number-volume model, and conventional method in the validation cohort were 0.7677, 0.7403, 0.8129, 0.7448, and 0.6851, respectively. The AUC of the texture-volume model was higher than those of other models and conventional method. The sensitivity, specificity, positive predictive value, and negative predictive value of the texture-volume model were 90%, 69%, 49%, and 96%, respectively.

CONCLUSION

The texture-volume model of high-resolution 3D T2WI effectively distinguished positive and negative LN metastasis for patients with clinically node-negative breast cancer.

A radiogenomic multimodal and whole-transcriptome sequencing for preoperative prediction of axillary lymph node metastasis and drug therapeutic response in breast cancer: a retrospective, machine learning and international multicohort study

BACKGROUND

Axillary lymph nodes (ALN) status serves as a crucial prognostic indicator in breast cancer (BC). The aim of this study was to construct a radiogenomic multimodal model, based on machine learning and whole-transcriptome sequencing (WTS), to accurately evaluate the risk of ALN metastasis (ALNM), drug therapeutic response and avoid unnecessary axillary surgery in BC patients.

METHODS

In this study, conducted a retrospective analysis of 1078 BC patients from The Cancer Genome Atlas (TCGA), The Cancer Imaging Archive (TCIA), and Foshan cohort. These patients were divided into the TCIA cohort ( N =103), TCIA validation cohort ( N =51), Duke cohort ( N =138), Foshan cohort ( N =106), and TCGA cohort ( N =680). Radiological features were extracted from BC radiological images and differentially expressed gene expression was calibrated using technology. A support vector machine model was employed to screen radiological and genetic features, and a multimodal model was established based on radiogenomic and clinical pathological features to predict ALNM. The accuracy of the model predictions was assessed using the area under the curve (AUC) and the clinical benefit was measured using decision curve analysis. Risk stratification analysis of BC patients was performed by gene set enrichment analysis, differential comparison of immune checkpoint gene expression, and drug sensitivity testing.

RESULTS

For the prediction of ALNM, rad-score was able to significantly differentiate between ALN- and ALN+ patients in both the Duke and Foshan cohorts ( P <0.05). Similarly, the gene-score was able to significantly differentiate between ALN- and ALN+ patients in the TCGA cohort ( P <0.05). The radiogenomic multimodal nomogram demonstrated satisfactory performance in the TCIA cohort (AUC 0.82, 95% CI: 0.74-0.91) and the TCIA validation cohort (AUC 0.77, 95% CI: 0.63-0.91). In the risk sub-stratification analysis, there were significant differences in gene pathway enrichment between high and low-risk groups ( P <0.05). Additionally, different risk groups may exhibit varying treatment responses ( P <0.05).

CONCLUSION

Overall, the radiogenomic multimodal model employs multimodal data, including radiological images, genetic, and clinicopathological typing. The radiogenomic multimodal nomogram can precisely predict ALNM and drug therapeutic response in BC patients.

Radiomics in cone-beam breast CT for the prediction of axillary lymph node metastasis in breast cancer: a multi-center multi-device study

OBJECTIVES

To develop a radiomics model in contrast-enhanced cone-beam breast CT (CE-CBBCT) for preoperative prediction of axillary lymph node (ALN) status and metastatic burden of breast cancer.

METHODS

Two hundred and seventy-four patients who underwent CE-CBBCT examination with two scanners between 2012 and 2021 from two institutions were enrolled. The primary tumor was annotated in each patient image, from which 1781 radiomics features were extracted with PyRadiomics. After feature selection, support vector machine models were developed to predict ALN status and metastatic burden. To avoid overfitting on a specific patient subset, 100 randomly stratified splits were made to assign the patients to either training/fine-tuning or test set. Area under the receiver operating characteristic curve (AUC) of these radiomics models was compared to those obtained when training the models only with clinical features and combined clinical-radiomics descriptors. Ground truth was established by histopathology.

RESULTS

One hundred and eighteen patients had ALN metastasis (N + (≥ 1)). Of these, 74 had low burden (N + (1~2)) and 44 high burden (N + (≥ 3)). The remaining 156 patients had none (N0). AUC values across the 100 test repeats in predicting ALN status (N0/N + (≥ 1)) were 0.75 ± 0.05 (0.67~0.93, radiomics model), 0.68 ± 0.07 (0.53~0.85, clinical model), and 0.74 ± 0.05 (0.67~0.88, combined model). For metastatic burden prediction (N + (1~2)/N + (≥ 3)), AUC values were 0.65 ± 0.10 (0.50~0.88, radiomics model), 0.55 ± 0.10 (0.40~0.80, clinical model), and 0.64 ± 0.09 (0.50~0.90, combined model), with all the ranges spanning 0.5. In both cases, the radiomics model was significantly better than the clinical model (both p < 0.01) and comparable with the combined model (p = 0.56 and 0.64).

CONCLUSIONS

Radiomics features of primary tumors could have potential in predicting ALN metastasis in CE-CBBCT imaging.

CLINICAL RELEVANCE STATEMENT

The findings support potential clinical use of radiomics for predicting axillary lymph node metastasis in breast cancer patients and addressing the limited axilla coverage of cone-beam breast CT.

KEY POINTS

• Contrast-enhanced cone-beam breast CT-based radiomics could have potential to predict N0 vs. N + (≥ 1) and, to a limited extent, N + (1~2) vs. N + (≥ 3) from primary tumor, and this could help address the limited axilla coverage, pending future verifications on larger cohorts. • The average AUC of radiomics and combined models was significantly higher than that of clinical models but showed no significant difference between themselves. • Radiomics features descriptive of tumor texture were found informative on axillary lymph node status, highlighting a higher heterogeneity for tumor with positive axillary lymph node.

A Multiparametric MRI-based Radiomics Model for Stratifying Postoperative Recurrence in Luminal B Breast Cancer

This study aims to develop an MRI-based radiomics model to assess the likelihood of recurrence in luminal B breast cancer. The study analyzed medical images and clinical data from 244 patients with luminal B breast cancer. Of 244 patients, 35 had experienced recurrence and 209 had not. The patients were randomly divided into the training set (51.5 ± 12.5 years old; n = 171) and the test set (51.7 ± 11.3 years old; n = 73) in a ratio of 7:3. The study employed univariate and multivariate Cox regression along with the least absolute shrinkage and selection operator (LASSO) regression methods to select radiomics features and calculate a risk score. A combined model was constructed by integrating the risk score with the clinical and pathological characteristics. The study identified two radiomics features (GLSZM and GLRLM) from DCE-MRI that were used to calculate a risk score. The AUCs were 0.860 and 0.868 in the training set and 0.816 and 0.714 in the testing set for 3- and 5-year recurrence risk, respectively. The combined model incorporating the risk score, pN, and endocrine therapy showed improved predictive power, with AUCs of 0.857 and 0.912 in the training set and 0.943 and 0.945 in the testing set for 3- and 5-year recurrence risk, respectively. The calibration curve of the combined model showed good consistency between predicted and measured values. Our study developed an MRI-based radiomics model that integrates clinical and radiomics features to assess the likelihood of recurrence in luminal B breast cancer. The model shows promise for improving clinical risk stratification and treatment decision-making.

Non-invasive prediction model of axillary lymph node status in patients with early-stage breast cancer: a feasibility study based on dynamic contrast-enhanced-MRI radiomics

OBJECTIVES

Accurate axillary evaluation plays an important role in prognosis and treatment planning for breast cancer. This study aimed to develop and validate a dynamic contrast-enhanced (DCE)-MRI-based radiomics model for preoperative evaluation of axillary lymph node (ALN) status in early-stage breast cancer.

METHODS

A total of 410 patients with pathologically confirmed early-stage invasive breast cancer (training cohort, N = 286; validation cohort, N = 124) from June 2018 to August 2022 were retrospectively recruited. Radiomics features were derived from the second phase of DCE-MRI images for each patient. ALN status-related features were obtained, and a radiomics signature was constructed using SelectKBest and least absolute shrinkage and selection operator regression. Logistic regression was applied to build a combined model and corresponding nomogram incorporating the radiomics score (Rad-score) with clinical predictors. The predictive performance of the nomogram was evaluated using receiver operator characteristic (ROC) curve analysis and calibration curves.

RESULTS

Fourteen radiomic features were selected to construct the radiomics signature. The Rad-score, MRI-reported ALN status, BI-RADS category, and tumour size were independent predictors of ALN status and were incorporated into the combined model. The nomogram showed good calibration and favourable performance for discriminating metastatic ALNs (N + (≥1)) from non-metastatic ALNs (N0) and metastatic ALNs with heavy burden (N + (≥3)) from low burden (N + (1-2)), with the area under the ROC curve values of 0.877 and 0.879 in the training cohort and 0.859 and 0.881 in the validation cohort, respectively.

CONCLUSIONS

The DCE-MRI-based radiomics nomogram could serve as a potential non-invasive technique for accurate preoperative evaluation of ALN burden, thereby assisting physicians in the personalized axillary treatment for early-stage breast cancer patients.

ADVANCES IN KNOWLEDGE

This study developed a potential surrogate of preoperative accurate evaluation of ALN status, which is non-invasive and easy-to-use.

Machine Learning-Based Breast Tumor Ultrasound Radiomics for Pre-operative Prediction of Axillary Sentinel Lymph Node Metastasis Burden in Early-Stage Invasive Breast Cancer

OBJECTIVE

The aim of the work described here was to assess the application of ultrasound (US) radiomics with machine learning (ML) classifiers to the prediction of axillary sentinel lymph node metastasis (SLNM) burden in early-stage invasive breast cancer (IBC).

METHODS

In this study, 278 early-stage IBC patients with at least one SLNM (195 in the training set and 83 in the test set) were studied at our institution. Pathologic SLNM burden was used as the reference standard. The US radiomics features of breast tumors were extracted by using 3D-Slicer and PyRadiomics software. Four ML classifiers-linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF) and decision tree (DT)-were used to construct radiomics models for the prediction of SLNM burden. The combined clinicopathologic-radiomics models were also assessed with respect to sensitivity, specificity, accuracy and areas under the curve (AUCs).

RESULTS

Among the US radiomics models, the SVM classifier achieved better predictive performance with an AUC of 0.920 compared with RF (AUC = 0.874), LDA (AUC = 0.835) and DT (AUC = 0.800) in the test set. The clinicopathologic model had low efficacy, with AUCs of 0.678 and 0.710 in the training and test sets, respectively. The combined clinicopathologic (C) factors and SVM classifier (C + SVM) model improved the predictive ability with an AUC of 0.934, sensitivity of 86.7%, specificity of 89.9% and accuracy of 91.0% in the test set.

CONCLUSION

ML-based US radiomics analysis, as a novel and promising predictive tool, is conducive to a precise clinical treatment strategy.

Multi-modal fusion network with intra- and inter-modality attention for prognosis prediction in breast cancer

Accurate breast cancer prognosis prediction can help clinicians to develop appropriate treatment plans and improve life quality for patients. Recent prognostic prediction studies suggest that fusing multi-modal data, e.g., genomic data and pathological images, plays a crucial role in improving predictive performance. Despite promising results of existing approaches, there remain challenges in effective multi-modal fusion. First, albeit a powerful fusion technique, Kronecker product produces high-dimensional quadratic expansion of features that may result in high computational cost and overfitting risk, thereby limiting its performance and applicability in cancer prognosis prediction. Second, most existing methods put more attention on learning cross-modality relations between different modalities, ignoring modality-specific relations that are complementary to cross-modality relations and beneficial for cancer prognosis prediction. To address these challenges, in this study we propose a novel attention-based multi-modal network to accurately predict breast cancer prognosis, which efficiently models both modality-specific and cross-modality relations without bringing in high-dimensional features. Specifically, two intra-modality self-attentional modules and an inter-modality cross-attentional module, accompanied by latent space transformation of channel affinity matrix, are developed to successfully capture modality-specific and cross-modality relations for efficient integration of genomic data and pathological images, respectively. Moreover, we design an adaptive fusion block to take full advantage of both modality-specific and cross-modality relations. Comprehensive experiment demonstrates that our method can effectively boost prognosis prediction performance of breast cancer and compare favorably with the state-of-the-art methods.

Nomogram based on multiparametric analysis of early-stage breast cancer: Prediction of high burden metastatic axillary lymph nodes

BACKGROUND

The Z0011 and AMAROS trials found that axillary lymph node dissection (ALND) was no longer mandatory for early-stage breast cancer patients who had one or two metastatic axillary lymph nodes (mALNs). The aim of our study was to establish a nomogram which could be used to quantitatively predict the individual likelihood of high burden mALN (≥3 mALN).

METHODS

We retrospectively analyzed 564 women with early breast cancer who had all undergone both ultrasound (US) and magnetic resonance imaging (MRI) to examine axillary lymph nodes before radical surgery. All the patients were divided into training (n = 452) and validation (n = 112) cohorts by computer-generated random numbers. Their clinicopathological features and preoperative imaging associated with high burden mALNs were evaluated by logistic regression analysis to develop a nomogram for predicting the probability of high burden mALNs.

RESULTS

Multivariate analysis showed that high burden mALNs were significantly associated with replaced hilum and the shortest diameter >10 mm on MRI, with cortex thickness >3 mm on US (p < 0.05 each). These imaging criteria plus higher grade (grades II and III) and quadrant of breast tumor were used to develop a nomogram calculating the probability of high burden mALNs. The AUC of the nomogram was 0.853 (95% CI: 0.790-0.908) for the training set and 0.783 (95% CI: 0.638-0.929) for the validation set. Both internal and external validation evaluated the accuracy of nomogram to be good.

CONCLUSION

A well-discriminated nomogram was developed to predict the high burden mALN in early-stage breast patients, which may assist the breast surgeon in choosing the appropriate surgical approach.

Radiomics nomogram for predicting axillary lymph node metastasis-a potential method to address the limitation of axilla coverage in cone-beam breast CT: a bi-center retrospective study

PURPOSE

Cone-beam breast CT (CBBCT) has an inherent limitation that the axilla cannot be imaged in its entirety. We aimed to develop and validate a nomogram based on clinical factors and contrast-enhanced (CE) CBBCT radiomics features to predict axillary lymph node (ALN) metastasis and complement limited axilla coverage.

MATERIAL AND METHODS

This retrospective study included 312 patients with breast cancer from two hospitals who underwent CE-CBBCT examination in a clinical trial (NCT01792999) during 2012-2020. Patients from TCIH comprised training set (n = 176) and validation set (n = 43), and patients from SYSUCC comprised external test set (n = 93). 3D ROIs were delineated manually and radiomics features were extracted by 3D Slicer software. RadScore was calculated and radiomics model was constructed after feature selection. Clinical model was built on independent predictors. Nomogram was developed with independent clinical predictors and RadScore. Diagnostic performance was compared among three models by ROC curve, and decision curve analysis (DCA) was used to evaluate the clinical utility of nomogram.

RESULTS

A total of 139 patients were ALN positive and 173 patients were negative. Twelve radiomics features remained after feature selection. Location and focality were selected as independent predictors for ALN status. The AUC of nomogram in external test set was higher than that of clinical model (0.80 vs. 0.66, p = 0.012). DCA demonstrated that the nomogram had higher overall net benefit than that of clinical model.

CONCLUSION

The nomogram combined CE-CBBCT-based radiomics features and clinical factors could have potential in distinguishing ALN positive from negative and addressing the limitation of axilla coverage in CBBCT.

Artificial intelligence in breast imaging: potentials and challenges

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Application of CT and MRI images based on an artificial intelligence algorithm for predicting lymph node metastasis in breast cancer patients: a meta-analysis

BACKGROUND

This study aimed to comprehensively evaluate the accuracy and effect of computed tomography (CT) and magnetic resonance imaging (MRI) based on artificial intelligence (AI) algorithms for predicting lymph node metastasis in breast cancer patients.

METHODS

We systematically searched the PubMed, Embase and Cochrane Library databases for literature from inception to June 2023 using keywords that included 'artificial intelligence', 'CT,' 'MRI', 'breast cancer' and 'lymph nodes'. Studies that met the inclusion criteria were screened and their data were extracted for analysis. The main outcome measures included sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and area under the curve (AUC).

RESULTS

A total of 16 studies were included in the final meta-analysis, covering 4,764 breast cancer patients. Among them, 11 studies used the manual algorithm MRI to calculate breast cancer risk, which had a sensitivity of 0.85 (95% confidence interval [CI] 0.79-0.90; p < 0.001; I2 = 75.3%), specificity of 0.81 (95% CI 0.66-0.83; p < 0.001; I2 = 0%), a positive likelihood ratio of 4.6 (95% CI 4.0-4.8), a negative likelihood ratio of 0.18 (95% CI 0.13-0.26) and a diagnostic odds ratio of 25 (95% CI 17-38). Five studies used manual algorithm CT to calculate breast cancer risk, which had a sensitivity of 0.88 (95% CI 0.79-0.94; p < 0.001; I2 = 87.0%), specificity of 0.80 (95% CI 0.69-0.88; p < 0.001; I2 = 91.8%), a positive likelihood ratio of 4.4 (95% CI 2.7-7.0), a negative likelihood ratio of 0.15 (95% CI 0.08-0.27) and a diagnostic odds ratio of 30 (95% CI 12-72). For MRI and CT, the AUC after study pooling was 0.85 (95% CI 0.82-0.88) and 0.91 (95% CI 0.88-0.93), respectively.

CONCLUSION

Computed tomography and MRI images based on an AI algorithm have good diagnostic accuracy in predicting lymph node metastasis in breast cancer patients and have the potential for clinical application.

MRI radiomics for the preoperative evaluation of lymphovascular invasion in breast cancer: A meta-analysis

PURPOSE

To evaluate the ability of preoperative MRI-based radiomic features in predicting lymphovascular invasion (LVI) in patients with breast cancer.

METHODS

PubMed, Embase, Web of Science, Cochrane Library databases, and four Chinese databases were searched to identify relevant studies published up until June 15, 2023. Two reviewers screened all papers independently for eligibility. We included diagnostic accuracy studies that used radiomics-MRI for LVI in patients with breast cancer, using histopathology as the reference standard. Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Radiomics Quality Score. Overall diagnostic odds ratio (DOR), sensitivity, specificity and area under the curve (AUC) were calculated to assess the prediction efficacy of MRI-based radiomic features in patients with breast cancer. Spearman's correlation coefficient was calculated and subgroup analysis performed to investigate causes of heterogeneity.

RESULTS

Eight studies comprising 1685 female patients were included. The pooled DOR, sensitivity, specificity, and AUC of radiomics in detecting LVI were 23 [confidence interval (CI) 16,32], 0.89(0.86,0.92), 0.82 (0.78,0.86), and 0.83(0.78,0.87), respectively. The meta-analysis showed significant heterogeneity among the included studies. No threshold effect was detected. Subgroup analysis showed that more than 200 participants, radiomics with clinical factors, semiautomatic segmentation method and peritumoral or intra- and peritumoral model [DOR: 28(18,42), 26(19,37), 34(16,70), 40(10,156), respectively] could improve diagnostic performance compared with less than 200 participants, only radiomics, manual segmentation method, and tumor model [DOR: 16(7,37), 21(6,73), 20(12,32), 21(13,32), respectively], but 3.0 T MR and multiple sequences approach [DOR: 27(15,49),17(8,35)] couldn't improve diagnostic performance compared with 1.5 T and DCE radiomic features [DOR:27(7,99),25(17,37)].

CONCLUSION

Our meta-analysis showed that preoperative MRI-based radiomic features performs well in predicting LVI in patients with breast cancer. This noninvasive and convenient tool may be used to facilitate preoperative identification of LVI in breast cancer.

Prediction of axillary lymph node metastasis in early breast cancer patients with ultrasonic videos based deep learning

Objective

To develop a deep learning (DL) model for predicting axillary lymph node (ALN) metastasis using dynamic ultrasound (US) videos in breast cancer patients.

Methods

A total of 271 US videos from 271 early breast cancer patients collected from Xiang'an Hospital of Xiamen University andShantou Central Hospitabetween September 2019 and June 2021 were used as the training, validation, and internal testing set (testing set A). Additionally, an independent dataset of 49 US videos from 49 patients with breast cancer, collected from Shanghai 10th Hospital of Tongji University from July 2021 to May 2022, was used as an external testing set (testing set B). All ALN metastases were confirmed using pathological examination. Three different convolutional neural networks (CNNs) with R2 + 1D, TIN, and ResNet-3D architectures were used to build the models. The performance of the US video DL models was compared with that of US static image DL models and axillary US examination performed by ultra-sonographers. The performances of the DL models and ultra-sonographers were evaluated based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Additionally, gradient class activation mapping (Grad-CAM) technology was also used to enhance the interpretability of the models.

Results

Among the three US video DL models, TIN showed the best performance, achieving an AUC of 0.914 (95% CI: 0.843-0.985) in predicting ALN metastasis in testing set A. The model achieved an accuracy of 85.25% (52/61), with a sensitivity of 76.19% (16/21) and a specificity of 90.00% (36/40). The AUC of the US video DL model was superior to that of the US static image DL model (0.856, 95% CI: 0.753-0.959, P<0.05). The Grad-CAM technology confirmed the heatmap of the model, which highlighted important subregions of the keyframe for ultra-sonographers' review.

Conclusion

A feasible and improved DL model to predict ALN metastasis from breast cancer US video images was developed. The DL model in this study with reliable interpretability would provide an early diagnostic strategy for the appropriate management of axillary in the early breast cancer patients.

Attention-based Deep Learning for the Preoperative Differentiation of Axillary Lymph Node Metastasis in Breast Cancer on DCE-MRI

BACKGROUND

Previous studies have explored the potential on radiomics features of primary breast cancer tumor to identify axillary lymph node (ALN) metastasis. However, the value of deep learning (DL) to identify ALN metastasis remains unclear.

PURPOSE

To investigate the potential of the proposed attention-based DL model for the preoperative differentiation of ALN metastasis in breast cancer on dynamic contrast-enhanced MRI (DCE-MRI).

STUDY TYPE

Retrospective.

POPULATION

A total of 941 breast cancer patients who underwent DCE-MRI before surgery were included in the training (742 patients), internal test (83 patients), and external test (116 patients) cohorts.

FIELD STRENGTH/SEQUENCE

A 3.0 T MR scanner, DCE-MRI sequence.

ASSESSMENT

A DL model containing a 3D deep residual network (ResNet) architecture and a convolutional block attention module, named RCNet, was proposed for ALN metastasis identification. Three RCNet models were established based on the tumor, ALN, and combined tumor-ALN regions on the images. The performance of these models was compared with ResNet models, radiomics models, the Memorial Sloan-Kettering Cancer Center (MSKCC) model, and three radiologists (W.L., H.S., and F. L.).

STATISTICAL TESTS

Dice similarity coefficient for breast tumor and ALN segmentation. Accuracy, sensitivity, specificity, intercorrelation and intracorrelation coefficients, area under the curve (AUC), and Delong test for ALN classification.

RESULTS

The optimal RCNet model, that is, RCNet-tumor+ALN , achieved an AUC of 0.907, an accuracy of 0.831, a sensitivity of 0.824, and a specificity of 0.837 in the internal test cohort, as well as an AUC of 0.852, an accuracy of 0.828, a sensitivity of 0.792, and a specificity of 0.853 in the external test cohort. Additionally, with the assistance of RCNet-tumor+ALN , the radiologists' performance was improved (external test cohort, P < 0.05).

DATA CONCLUSION

DCE-MRI-based RCNet model could provide a noninvasive auxiliary tool to identify ALN metastasis preoperatively in breast cancer, which may assist radiologists in conducting more accurate evaluation of ALN status.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

A novel nomogram model of breast cancer-based imaging for predicting the status of axillary lymph nodes after neoadjuvant therapy

This study is aimed to develop and validate a novel nomogram model that can preoperatively predict axillary lymph node pathological complete response (pCR) after NAT and avoid unnecessary axillary lymph node dissection (ALND) for breast cancer patients. A total of 410 patients who underwent NAT and were pathologically confirmed to be axillary lymph node positive after breast cancer surgery were included. They were divided into two groups: patients with axillary lymph node pCR and patients with residual node lesions after NAT. Then the nomogram prediction model was constructed by univariate and multivariate logistic regression. The result of multivariate logistic regression analysis showed that molecular subtypes, molybdenum target (MG) breast, computerized tomography (CT) breast, ultrasound (US) axilla, magnetic resonance imaging (MRI) axilla, and CT axilla (all p < 0.001) had a significant impact on the evaluation of axillary lymph node status after NAT. The nomogram score appeared that AUC was 0.832 (95% CI 0.786-0.878) in the training cohort and 0.947 (95% CI 0.906-0.988) in the validation cohort, respectively. The decision curve represented that the nomogram has a positive predictive ability, indicating its potential as a practical clinical tool.

Evaluating the Risk of Inguinal Lymph Node Metastases before Surgery Using the Morphonode Predictive Model: A Prospective Diagnostic Study in Vulvar Cancer Patients

Ultrasound examination is an accurate method in the preoperative evaluation of the inguinofemoral lymph nodes when performed by experienced operators. The purpose of the study was to build a robust, multi-modular model based on machine learning to discriminate between metastatic and non-metastatic inguinal lymph nodes in patients with vulvar cancer. One hundred and twenty-seven women were selected at our center from March 2017 to April 2020, and 237 inguinal regions were analyzed (75 were metastatic and 162 were non-metastatic at histology). Ultrasound was performed before surgery by experienced examiners. Ultrasound features were defined according to previous studies and collected prospectively. Fourteen informative features were used to train and test the machine to obtain a diagnostic model (Morphonode Predictive Model). The following data classifiers were integrated: (I) random forest classifiers (RCF), (II) regression binomial model (RBM), (III) decisional tree (DT), and (IV) similarity profiling (SP). RFC predicted metastatic/non-metastatic lymph nodes with an accuracy of 93.3% and a negative predictive value of 97.1%. DT identified four specific signatures correlated with the risk of metastases and the point risk of each signature was 100%, 81%, 16% and 4%, respectively. The Morphonode Predictive Model could be easily integrated into the clinical routine for preoperative stratification of vulvar cancer patients.

Optimized Radiomics Nomogram Based on Automated Breast Ultrasound System: A Potential Tool for Preoperative Prediction of Metastatic Lymph Node Burden in Breast Cancer

Background

Axillary lymph node dissection (ALND) can be safely avoided in women with T1 or T2 primary invasive breast cancer (BC) and one to two metastatic sentinel lymph nodes (SLNs). However, cancellation of ALND based solely on SLN biopsy (SLNB) may lead to adverse outcomes. Therefore, preoperative assessment of LN tumor burden becomes a new focus for ALN status.

Objective

This study aimed to develop and validate a nomogram incorporating the radiomics score (rad-score) based on automated breast ultrasound system (ABUS) and other clinicopathological features for evaluating the ALN status in patients with early-stage BC preoperatively.

Methods

Totally 354 and 163 patients constituted the training and validation cohorts. They were divided into ALN low burden (<3 metastatic LNs) and high burden (≥3 metastatic LNs) based on the histopathological diagnosis. The radiomics features of the segmented breast tumor in ABUS images were extracted and selected to generate the rad-score of each patient. These rad-scores, along with the ALN burden predictors identified from the clinicopathologic characteristics, were included in the multivariate analysis to establish a nomogram. It was further evaluated in the training and validation cohorts.

Results

High ALN burdens accounted for 11.2% and 10.8% in the training and validation cohorts. The rad-score for each patient was developed based on 7 radiomics features extracted from the ABUS images. The radiomics nomogram was built with the rad-score, tumor size, US-reported LN status, and ABUS retraction phenomenon. It achieved better predictive efficacy than the nomogram without the rad-score and exhibited favorable discrimination, calibration and clinical utility in both cohorts.

Conclusion

We developed an ABUS-based radiomics nomogram for the preoperative prediction of ALN burden in BC patients. It would be utilized for the identification of patients with low ALN burden if further validated, which contributed to appropriate axillary treatment and might avoid unnecessary ALND.

Pretreatment Multiparametric MRI-Based Radiomics Analysis for the Diagnosis of Breast Phyllodes Tumors

BACKGROUND

Preoperative pathological grading assessment is important for patients with breast phyllodes tumors (PTs).

PURPOSE

To develop and validate a clinical-radiomics model based on multiparametric MRI and clinical information for the pretreatment differential diagnosis of PTs.

STUDY TYPE

Retrospective.

POPULATION

A total of 216 patients with PTs, 133 in the training cohort (55 benign PTs [BPTs] and 78 borderline/malignant PTs [BMPTs]) and 83 in the validation cohort (28 BPTs and 55 BMPTs).

FIELD STRENGTH/SEQUENCE

1.5 T and 3 T; T2-weighted imaging (T2WI), precontrast T1-weighted imaging (T1WI) and dynamic contrast-enhanced T1-weighted imaging (DCE-T1WI).

ASSESSMENT

A total of 3138 radiomics features were computed to decode the imaging phenotypes of PTs. To build the classification models, the following workflow was followed: minimum-maximum scaling normalization method, recursive feature elimination based on ridge regression (Ridge-RFE), synthetic minority oversampling technique, and support vector machine classifier. We established several models based on the statistically significant features (Ridge-RFE selected) of each sequence to distinguish BPTs from BMPTs, including precontrast T1WI model, DCE-T1WI phase 1 model, T1WI feature fusion model, T2WI model, T1WI + T2WI model, clinical feature model, conventional MRI characteristics model, and combined clinical-radiomics model.

STATISTICAL TESTS

Univariate analysis was utilized to compare variables between the BPT and BMPT groups. The receiver operating characteristic curve (ROC) analysis was used to evaluate the diagnostic performance of these models.

RESULTS

In the training cohort, the clinical-radiomics model had excellent diagnostic efficiency, with an area under ROC (AUC) of 0.91 ± 0.02 (95% CI: 0.87-0.94). In the validation cohort, the AUCs were 0.79 ± 0.05 (95% CI: 0.70-0.87) for the combined model and 0.77 ± 0.05 (95% CI: 0.67-0.85) for the radiomics model.

DATA CONCLUSION

Compared with conventional MRI characteristics, radiomics features extracted from multiparametric MRI are helpful for improving the accuracy of differentiating the pathological grades of PTs preoperatively. The model based on radiomics and clinical information is expected to become a potential noninvasive tool for the assessment of PTs grades.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

A delta-radiomic lymph node model using dynamic contrast enhanced MRI for the early prediction of axillary response after neoadjuvant chemotherapy in breast cancer patients

BACKGROUND

The objective of this paper is to explore the value of a delta-radiomic model of the axillary lymph node (ALN) using dynamic contrast-enhanced (DCE) MRI for early prediction of the axillary pathological complete response (pCR) of breast cancer patients after neoadjuvant chemotherapy (NAC).

METHODS

A total of 120 patients with ALN-positive breast cancer who underwent breast MRI before and after the first cycle of NAC between October 2018 and May 2021 were prospectively included in this study. Patients were divided into a training (n = 84) and validation (n = 36) cohort based on the temporal order of their treatments. Radiomic features were extracted from the largest slice of targeted ALN on DCE-MRI at pretreatment and after one cycle of NAC, and their changes (delta-) were calculated and recorded. Logistic regression was then applied to build radiomic models using the pretreatment (pre-), first-cycle(1st-), and changes (delta-) radiomic features separately. A clinical model was also built and combined with the radiomic models. The models were evaluated by discrimination, calibration, and clinical application and compared using DeLong test.

RESULTS

Among the three radiomic models, the ALN delta-radiomic model performed the best with AUCs of 0.851 (95% CI: 0.770-0.932) and 0.822 (95% CI: 0.685-0.958) in the training and validation cohorts, respectively. The clinical model yielded moderate AUCs of 0.742 (95% CI: 0.637-0.846) and 0.723 (95% CI: 0.550-0.896), respectively. After combining clinical features to the delta-radiomics model, the efficacy of the combined model (AUC = 0.932) in the training cohort was significantly higher than that of both the delta-radiomic model (Delong p = 0.017) and the clinical model (Delong p < 0.001) individually. Additionally, in the validation cohort, the combined model had the highest AUC (0.859) of any of the models we tested although this was not statistically different from any other individual model's validation AUC. Calibration and decision curves showed a good agreement and a high clinical benefit for the combined model.

CONCLUSION

This preliminary study indicates that ALN-based delta-radiomic model combined with clinical features is a promising strategy for the early prediction of downstaging ALN status after NAC. Future axillary MRI applications need to be further explored.

Radiomics model of diffusion-weighted whole-body imaging with background signal suppression (DWIBS) for predicting axillary lymph node status in breast cancer

BACKGROUND

In breast cancer diagnosis and treatment, non-invasive prediction of axillary lymph node (ALN) metastasis can help avoid complications related to sentinel lymph node biopsy.

OBJECTIVE

This study aims to develop and evaluate machine learning models using radiomics features extracted from diffusion-weighted whole-body imaging with background signal suppression (DWIBS) examination for predicting the ALN status.

METHODS

A total of 100 patients with histologically proven, invasive, clinically N0 breast cancer who underwent DWIBS examination consisting of short tau inversion recovery (STIR) and DWIBS sequences before surgery were enrolled. Radiomic features were calculated using segmented primary lesions in DWIBS and STIR sequences and were divided into training (n = 75) and test (n = 25) datasets based on the examination date. Using the training dataset, optimal feature selection was performed using the least absolute shrinkage and selection operator algorithm, and the logistic regression model and support vector machine (SVM) classifier model were constructed with DWIBS, STIR, or a combination of DWIBS and STIR sequences to predict ALN status. Receiver operating characteristic curves were used to assess the prediction performance of radiomics models.

RESULTS

For the test dataset, the logistic regression model using DWIBS, STIR, and a combination of both sequences yielded an area under the curve (AUC) of 0.765 (95% confidence interval: 0.548-0.982), 0.801 (0.597-1.000), and 0.779 (0.567-0.992), respectively, whereas the SVM classifier model using DWIBS, STIR, and a combination of both sequences yielded an AUC of 0.765 (0.548-0.982), 0.757 (0.538-0.977), and 0.779 (0.567-0.992), respectively.

CONCLUSIONS

Use of machine learning models incorporating with the quantitative radiomic features derived from the DWIBS and STIR sequences can potentially predict ALN status.

MRI characteristics of breast edema for assessing axillary lymph node burden in early-stage breast cancer: a retrospective bicentric study

OBJECTIVES

To investigate whether breast edema characteristics at preoperative T2-weighted imaging (T2WI) could help evaluate axillary lymph node (ALN) burden in patients with early-stage breast cancer.

METHODS

This retrospective study included women with clinical T1 and T2 stage breast cancer and preoperative MRI examination in two independent cohorts from May 2014 to December 2020. Low (< 3 LNs+) and high (≥ 3 LNs+) pathological ALN (pALN) burden were recorded as endpoint. Breast edema score (BES) was evaluated at T2WI. Univariable and multivariable analyses were performed by the logistic regression model. The added predictive value of BES was examined utilizing the area under the curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI).

RESULTS

A total of 1092 patients were included in this study. BES was identified as the independent predictor of pALN burden in primary (n = 677) and validation (n = 415) cohorts. The analysis using MRI-ALN status showed that BES significantly improved the predictive performance of pALN burden (AUC: 0.65 vs 0.71, p < 0.001; IDI = 0.045, p < 0.001; continuous NRI = 0.159, p = 0.050). These results were confirmed in the validation cohort (AUC: 0.64 vs 0.69, p = 0.009; IDI = 0.050, p < 0.001; continuous NRI = 0.213, p = 0.047). Furthermore, BES was positively correlated with biologically invasive clinicopathological factors (p < 0.05).

CONCLUSIONS

In individuals with early-stage breast cancer, preoperative MRI characteristics of breast edema could be a promising predictor for pALN burden, which may aid in treatment planning.

KEY POINTS

• In this retrospective study of 1092 patients with early-stage breast cancer from two cohorts, the MRI characteristic of breast edema has independent and additive predictive value for assessing axillary lymph node burden. • Breast edema characteristics at T2WI positively correlated with biologically invasive clinicopathological factors, which may be useful for preoperative diagnosis and treatment planning for individual patients with breast cancer.

A nomogram based on radiomics signature and deep-learning signature for preoperative prediction of axillary lymph node metastasis in breast cancer

PURPOSE

To develop a nomogram based on radiomics signature and deep-learning signature for predicting the axillary lymph node (ALN) metastasis in breast cancer.

METHODS

A total of 151 patients were assigned to a training cohort (n = 106) and a test cohort (n = 45) in this study. Radiomics features were extracted from DCE-MRI images, and deep-learning features were extracted by VGG-16 algorithm. Seven machine learning models were built using the selected features to evaluate the predictive value of radiomics or deep-learning features for the ALN metastasis in breast cancer. A nomogram was then constructed based on the multivariate logistic regression model incorporating radiomics signature, deep-learning signature, and clinical risk factors.

RESULTS

Five radiomics features and two deep-learning features were selected for machine learning model construction. In the test cohort, the AUC was above 0.80 for most of the radiomics models except DecisionTree and ExtraTrees. In addition, the K-nearest neighbor (KNN), XGBoost, and LightGBM models using deep-learning features had AUCs above 0.80 in the test cohort. The nomogram, which incorporated the radiomics signature, deep-learning signature, and MRI-reported LN status, showed good calibration and performance with the AUC of 0.90 (0.85-0.96) in the training cohort and 0.90 (0.80-0.99) in the test cohort. The DCA showed that the nomogram could offer more net benefit than radiomics signature or deep-learning signature.

CONCLUSIONS

Both radiomics and deep-learning features are diagnostic for predicting ALN metastasis in breast cancer. The nomogram incorporating radiomics and deep-learning signatures can achieve better prediction performance than every signature used alone.

Preoperative Prediction of Axillary Lymph Node Metastasis in Breast Cancer Using CNN Based on Multiparametric MRI

BACKGROUND

Multiparametric magnetic resonance imaging (MRI) is widely used in breast cancer screening. Accurate prediction of the axillary lymph nodes metastasis (ALNM) is essential for breast cancer surgery and treatment. However, there is no mature and effective discerning method for ALNM based on multiparametric MRI.

PURPOSE

To evaluate the ALNM using T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) sequences, respectively, and construct a quantitative ALNM discerning model of integrated multiparametric MRI.

STUDY TYPE

Retrospective.

POPULATION

Three-hundred forty-eight breast cancer patients, 163 with ALNM (99.39% females), and 185 without ALNM (100% females). The dataset was randomly divided into the training set (315 cases) and the testing set (33 cases).

FIELD STRENGTH/SEQUENCE

1.5 T; T1WI (VIBRANT), T2WI (FSE), and DWI (echo planar imaging [EPI]).

ASSESSMENT

The lesion region of interest images were cropped and sent to a pretrained ResNet50 network. Then, the results of different sequences were sent to a classifier for ensemble learning to construct the ALNM model of multiparametric MRI.

STATISTICAL TESTS

Performance indicators such as accuracy, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC) were calculated. Student's t-test, chi-square test, Fisher's exact test, and Delong test were performed, and P < 0.05 was considered statistically significant.

RESULTS

T2WI performed the best among the three sequences, and achieved the accuracy and AUC of 0.933/0.989 in the testing set. Compared to T1WI with the accuracy and AUC of 0.691/0.806, the increase is significant. While compared to DWI with the accuracy and AUC of 0.800/0.910, the improvement is not significant (P = 0.126). After integrating three sequences, the accuracy and AUC improved to 0.970 and 0.996.

DATA CONCLUSION

T2WI performed better than DWI and T1WI in discerning ALNM in this breast cancer dataset. The proposed quantitative model of integrated multiparametric MRI could effectively help the ALNM diagnosis.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY STAGE: 2.

Artificial intelligence in multi-parametric magnetic resonance imaging: A review

Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.

Development of an ultrasound-based radiomics nomogram to preoperatively predict Ki-67 expression level in patients with breast cancer

Objective

To develop and validate a radiomics nomogram that could incorporate clinicopathological characteristics and ultrasound (US)-based radiomics signature to non-invasively predict Ki-67 expression level in patients with breast cancer (BC) preoperatively.

Methods

A total of 328 breast lesions from 324 patients with BC who were pathologically confirmed in our hospital from June 2019 to October 2020 were included, and they were divided into high Ki-67 expression level group and low Ki-67 expression level group. Routine US and shear wave elastography (SWE) were performed for each lesion, and the ipsilateral axillary lymph nodes (ALNs) were scanned for abnormal changes. The datasets were randomly divided into training and validation cohorts with a ratio of 7:3. Correlation analysis and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomics features obtained from gray-scale US images of BC patients, and each radiomics score (Rad-score) was calculated. Afterwards, multivariate logistic regression analysis was used to establish a radiomics nomogram based on the radiomics signature and clinicopathological characteristics. The prediction performance of the nomogram was assessed by the area under the receiver operating characteristic curve (AUC), the calibration curve, and decision curve analysis (DCA) using the results of immunohistochemistry as the gold standard.

Results

The radiomics signature, consisted of eight selected radiomics features, achieved a nearly moderate prediction efficacy with AUC of 0.821 (95% CI:0.764-0.880) and 0.713 (95% CI:0.612-0.814) in the training and validation cohorts, respectively. The radiomics nomogram, incorporating maximum diameter of lesions, stiff rim sign, US-reported ALN status, and radiomics signature showed a promising performance for prediction of Ki-67 expression level, with AUC of 0.904 (95% CI:0.860-0.948) and 0.890 (95% CI:0.817-0.964) in the training and validation cohorts, respectively. The calibration curve and DCA indicated promising consistency and clinical applicability.

Conclusion

The proposed US-based radiomics nomogram could be used to non-invasively predict Ki-67 expression level in BC patients preoperatively, and to assist clinicians in making reliable clinical decisions.

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

Purpose

The 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).

Methods

A 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.

Results

A 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.

Conclusion

Radiomics 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.

A Radiomics Model for Preoperative Predicting Sentinel Lymph Node Metastasis in Breast Cancer Based on Dynamic Contrast-Enhanced MRI

Purpose

To develop a radiomics model based on preoperative dynamic contrast-enhanced MRI (DCE-MRI) to identify sentinel lymph node (SLN) metastasis in breast cancer (BC) patients.

Materials and Methods

The MRI images and clinicopathological data of 142 female primary BC patients from January 2017 to December 2018 were included in this study. The patients were randomly divided into the training and testing cohorts at a ratio of 7:3. Four types of radiomics models were built: 1) a radiomics model based on the region of interest (ROI) of breast tumor; 2) a radiomics model based on the ROI of intra- and peri-breast tumor; 3) a radiomics model based on the ROI of axillary lymph node (ALN); 4) a radiomics model based on the ROI of ALN and breast tumor. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were used to assess the performance of the three radiomics models. The technique for order of preference by similarity to ideal solution (TOPSIS) through decision matrix analysis was used to select the best model.

Results

Models 1, 2, 3, and 4 yielded AUCs of 0.977, 0.999, 0.882, and 1.000 in the training set and 0.699, 0.817, 0.906, and 0.696 in the testing set, respectively, in terms of predicting SLN metastasis. Model 3 had the highest AUC in the testing cohort, and only the difference from Model 1 was statistically significant (p = 0.022). DCA showed that Model 3 yielded a greater net benefit to predict SLN metastasis than the other three models in the testing cohort. The best model analyzed by TOPSIS was Model 3, and the method's names for normalization, dimensionality reduction, feature selection, and classification are mean, principal component analysis (PCA), ANOVA, and support vector machine (SVM), respectively.

Conclusion

ALN radiomics feature extraction on DCE-MRI is a potential method to evaluate SLN status in BC patients.

Development and validation of a nomogram based on pretreatment dynamic contrast-enhanced MRI for the prediction of pathologic response after neoadjuvant chemotherapy for triple-negative breast cancer

OBJECTIVES

To develop a nomogram based on pretreatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) in patients with triple-negative breast cancer (TNBC).

METHODS

A total of 108 female patients with TNBC treated with neoadjuvant chemotherapy followed by surgery between January 2017 and October 2020 were enrolled. The patients were randomly divided into the primary cohort (n = 87) and validation cohort (n = 21) at a ratio of 4:1. The pretreatment DCE-MRI and clinicopathological features were reviewed and recorded. Univariate analysis and multivariate logistic regression analyses were used to determine the independent predictors of pCR in the primary cohort. A nomogram was developed based on the predictors, and the predictive performance of the nomogram was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). The validation cohort was used to test the predictive model.

RESULTS

Tumor volume measured on DCE-MRI, time to peak (TTP), and androgen receptor (AR) status were identified as independent predictors of pCR. The AUCs of the nomogram were 0.84 (95% CI: 0.75-0.93) and 0.79 (95% CI: 0.59-0.99) in the primary cohort and validation cohort, respectively.

CONCLUSIONS

Pretreatment DCE-MRI could predict pCR after NAC in patients with TNBC. The nomogram can be used to predict the probability of pCR and may help individualize treatment.

KEY POINTS

• Pretreatment DCE-MRI findings can predict pathologic complete response (pCR) after neoadjuvant chemotherapy in patients with triple-negative breast cancer. • A nomogram based on the independent predictors of tumor volume measured on DCE-MRI, time to peak, and androgen receptor status could help personalized cancer treatment in TNBC patients.

MRI-Based Radiomics Nomogram: Prediction of Axillary Non-Sentinel Lymph Node Metastasis in Patients With Sentinel Lymph Node-Positive Breast Cancer

Background

Overtreatment of axillary lymph node dissection (ALND) may occur in patients with axillary positive sentinel lymph node (SLN) but negative non-SLN (NSLN). Developing a magnetic resonance imaging (MRI)-based radiomics nomogram to predict axillary NSLN metastasis in patients with SLN-positive breast cancer could effectively decrease the probability of overtreatment and optimize a personalized axillary surgical strategy.

Methods

This retrospective study included 285 patients with positive SLN breast cancer. Fifty five of them had metastatic NSLNs and 230 had non-metastatic NSLNs. MRI-based radiomic features of primary tumors were extracted and MRI morphologic findings of the primary tumor and axillary lymph nodes were assessed. Four models, namely, a radiomics signature, an MRI-clinical nomogram, and two MRI-clinical-radiomics nomograms were established based on MRI morphologic findings, clinicopathologic characteristics, and MRI-based radiomic features to predict the NSLN status. The optimal predictors in each model were selected using the 5-fold cross-validation (CV) method. Their predictive performances were determined by the receiver operating characteristic (ROC) curves analysis. The area under the curves (AUCs) of different models was compared by the Delong test. Their discrimination capability, calibration curve, and clinical usefulness were also assessed.

Results

The 5-fold CV analysis showed that the AUCs ranged from 0.770 to 0.847 for the radiomics signature, from 0.720 to 0.824 for the MRI-clinical nomogram, from 0.843 to 0.932 for the MRI-clinical-radiomics nomogram. The optimal predictive factors in the radiomics signature, MRI-clinical nomogram, and MRI-clinical-radiomics nomogram were one texture feature of diffusion-weighted imaging (DWI), two clinicopathologic features together with one MRI morphologic finding, and the DWI-based texture feature together with the two clinicopathologic features plus the one MRI morphologic finding, respectively. The MRI-clinical-radiomics nomogram with CA 15-3 included achieved the highest AUC compared with the radiomics signature (0.868 vs. 0.806, P <0.001) and MRI-clinical nomogram (0.868 vs. 0.761; P <0.001). In addition, the MRI-clinical-radiomics nomogram without CA 15-3 showed a higher performance than that of the radiomics signature (AUC, 0.852 vs. 0.806, P = 0.016) and the MRI-clinical nomogram (AUC, 0.852 vs. 0.761, P = 0.007). The MRI-clinical-radiomics nomograms showed good discrimination and good calibration. Decision curve analysis demonstrated that the MRI-clinical-radiomics nomograms were clinically useful.

Conclusion

The MRI-clinical-radiomics nomograms developed in our study showed high predictive performance, which can be used to predict the axillary NSLN status in SLN-positive breast cancer patients before surgery.

OUP accepted manuscript

The recent, rapid advances in immuno-oncology have revolutionized cancer treatment and spurred further research into tumor biology. Yet, cancer patients respond variably to immunotherapy despite mounting evidence to support its efficacy. Current methods for predicting immunotherapy response are unreliable, as these tests cannot fully account for tumor heterogeneity and microenvironment. An improved method for predicting response to immunotherapy is needed. Recent studies have proposed radiomics—the process of converting medical images into quantitative data (features) that can be processed using machine learning algorithms to identify complex patterns and trends—for predicting response to immunotherapy. Because patients undergo numerous imaging procedures throughout the course of the disease, there exists a wealth of radiological imaging data available for training radiomics models. And because radiomic features reflect cancer biology, such as tumor heterogeneity and microenvironment, these models have enormous potential to predict immunotherapy response more accurately than current methods. Models trained on preexisting biomarkers and/or clinical outcomes have demonstrated potential to improve patient stratification and treatment outcomes. In this review, we discuss current applications of radiomics in oncology, followed by a discussion on recent studies that use radiomics to predict immunotherapy response and toxicity.

Value of the Application of CE-MRI Radiomics and Machine Learning in Preoperative Prediction of Sentinel Lymph Node Metastasis in Breast Cancer

Purpose

To explore the value of machine learning model based on CE-MRI radiomic features in preoperative prediction of sentinel lymph node (SLN) metastasis of breast cancer.

Methods

The clinical, pathological and MRI data of 177 patients with pathologically confirmed breast cancer (81 with SLN positive and 96 with SLN negative) and underwent conventional DCE-MRI before surgery in the First Affiliated Hospital of Soochow University from January 2015 to May 2021 were analyzed retrospectively. The samples were randomly divided into the training set (n=123) and validation set (n= 54) according to the ratio of 7:3. The radiomic features were derived from DCE-MRI phase 2 images, and 1,316 original eigenvectors are normalized by maximum and minimum normalization. The optimal feature filter and selection operator (LASSO) algorithm were used to obtain the optimal features. Five machine learning models of Support Vector Machine, Random Forest, Logistic Regression, Gradient Boosting Decision Tree, and Decision Tree were constructed based on the selected features. Radiomics signature and independent risk factors were incorporated to build a combined model. The receiver operating characteristic curve and area under the curve were used to evaluate the performance of the above models, and the accuracy, sensitivity, and specificity were calculated.

Results

There is no significant difference between all clinical and histopathological variables in breast cancer patients with and without SLN metastasis (P >0.05), except tumor size and BI-RADS classification (P< 0.01). Thirteen features were obtained as optimal features for machine learning model construction. In the validation set, the AUC (0.86) of SVM was the highest among the five machine learning models. Meanwhile, the combined model showed better performance in sentinel lymph node metastasis (SLNM) prediction and achieved a higher AUC (0.88) in the validation set.

Conclusions

We revealed the clinical value of machine learning models established based on CE-MRI radiomic features, providing a highly accurate, non-invasive, and convenient method for preoperative prediction of SLNM in breast cancer patients.

FMRNet: A fused network of multiple tumoral regions for breast tumor classification with ultrasound images

PURPOSE

Recent studies have illustrated that the peritumoral regions of medical images have value for clinical diagnosis. However, the existing approaches using peritumoral regions mainly focus on the diagnostic capability of the single region and ignore the advantages of effectively fusing the intratumoral and peritumoral regions. In addition, these methods need accurate segmentation masks in the testing stage, which are tedious and inconvenient in clinical applications. To address these issues, we construct a deep convolutional neural network that can adaptively fuse the information of multiple tumoral-regions (FMRNet) for breast tumor classification using ultrasound (US) images without segmentation masks in the testing stage.

METHODS

To sufficiently excavate the potential relationship, we design a fused network and two independent modules to extract and fuse features of multiple regions simultaneously. First, we introduce two enhanced combined-tumoral (EC) region modules, aiming to enhance the combined-tumoral features gradually. Then, we further design a three-branch module for extracting and fusing the features of intratumoral, peritumoral, and combined-tumoral regions, denoted as the intratumoral, peritumoral, and combined-tumoral module. Especially, we design a novel fusion module by introducing a channel attention module to adaptively fuse the features of three regions. The model is evaluated on two public datasets including UDIAT and BUSI with breast tumor ultrasound images. Two independent groups of experiments are performed on two respective datasets using the fivefold stratified cross-validation strategy. Finally, we conduct ablation experiments on two datasets, in which BUSI is used as the training set and UDIAT is used as the testing set.

RESULTS

We conduct detailed ablation experiments about the proposed two modules and comparative experiments with other existing representative methods. The experimental results show that the proposed method yields state-of-the-art performance on both two datasets. Especially, in the UDIAT dataset, the proposed FMRNet achieves a high accuracy of 0.945 and a specificity of 0.945, respectively. Moreover, the precision (PRE = 0.909) even dramatically improves by 21.6% on the BUSI dataset compared with the existing method of the best result.

CONCLUSION

The proposed FMRNet shows good performance in breast tumor classification with US images, and proves its capability of exploiting and fusing the information of multiple tumoral-regions. Furthermore, the FMRNet has potential value in classifying other types of cancers using multiple tumoral-regions of other kinds of medical images.

Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence

Breast magnetic resonance imaging (MRI) is the most sensitive imaging modality for breast cancer diagnosis and is widely used clinically. Dynamic contrast-enhanced MRI is the basis for breast MRI, but ultrafast images, T2-weighted images, and diffusion-weighted images are also taken to improve the characteristics of the lesion. Such multiparametric MRI with numerous morphological and functional data poses new challenges to radiologists, and thus, new tools for reliable, reproducible, and high-volume quantitative assessments are warranted. In this context, radiomics, which is an emerging field of research involving the conversion of digital medical images into mineable data for clinical decision-making and outcome prediction, has been gaining ground in oncology. Recent development in artificial intelligence has promoted radiomics studies in various fields including breast cancer treatment and numerous studies have been conducted. However, radiomics has shown a translational gap in clinical practice, and many issues remain to be solved. In this review, we will outline the steps of radiomics workflow and investigate clinical application of radiomics focusing on breast MRI based on published literature, as well as current discussion about limitations and challenges in radiomics.

The Guiding Significance of the Number of Positive Sentinel Lymph Nodes in Frozen Section for Intraoperative Axillary Dissection in Early Breast Cancer

Purpose

The results of large randomised trials have changed the treatment strategy of axillary lymph nodes. Axillary lymph node dissection (ALND) can be avoided in some patients with one to two sentinel lymph nodes (SLNs) metastasis based on final paraffin section (FPS) results which called into question the need for intraoperative frozen section (FS). This study aims to assess the guiding value of the number of positive SLN detected via FS for intraoperative ALND.

Patients and Methods

This study retrospectively analyzed data from 3303 patients with breast cancer who underwent SLN biopsy between 2015 and 2019. Combined with the FPS results, FS sensitivity, specificity, and false negative rate (FNR) were calculated and the difference in the number of positive SLNs between FS and FPS was analyzed.

Results

The overall FNR of FS was 23.21%, which was 76.47% in isolated tumor cells, 62.28% in micrometastasis, and 12.09% in macrometastatic disease. The size of SLN metastasis were significantly associated with a higher FNR (p<0.001). The accuracy rate of the number of positive SLNs detected via FS was 92.62%. Human epidermal growth factor receptor 2 (HER2) (p<0.03) and Ki67 (p<0.02) were significant factors affecting the accuracy rate.

Conclusion

FS is a effective method for SLN biopsy, ALND can be avoided in patients with one or two positive SLNs detected via FS.