Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI

Machine learning in breast MRI

Machine-learning techniques have led to remarkable advances in data extraction and analysis of medical imaging. Applications of machine learning to breast MRI continue to expand rapidly as increasingly accurate 3D breast and lesion segmentation allows the combination of radiologist-level interpretation (eg, BI-RADS lexicon), data from advanced multiparametric imaging techniques, and patient-level data such as genetic risk markers. Advances in breast MRI feature extraction have led to rapid dataset analysis, which offers promise in large pooled multiinstitutional data analysis. The object of this review is to provide an overview of machine-learning and deep-learning techniques for breast MRI, including supervised and unsupervised methods, anatomic breast segmentation, and lesion segmentation. Finally, it explores the role of machine learning, current limitations, and future applications to texture analysis, radiomics, and radiogenomics. Level of Evidence: 3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019. J. Magn. Reson. Imaging 2020;52:998-1018.

Radiomic nomogram for prediction of axillary lymph node metastasis in breast cancer

OBJECTIVE

To develop a radiomic nomogram for preoperative prediction of axillary lymph node (LN) metastasis in breast cancer patients.

METHODS

Preoperative magnetic resonance imaging data from 411 breast cancer patients was studied. Patients were assigned to either a training cohort (n = 279) or a validation cohort (n = 132). Eight hundred eight radiomic features were extracted from the first phase of T1-DCE images. A support vector machine was used to develop a radiomic signature, and logistic regression was used to develop a nomogram.

RESULTS

The radiomic signature based on 12 LN status-related features was constructed to predict LN metastasis, its prediction ability was moderate, with an area under the curve (AUC) of 0.76 and 0.78 in training and validation cohorts, respectively. Based on a radiomic signature and clinical features, a nomogram was developed and showed excellent predictive ability for LN metastasis (AUC 0.84 and 0.87 in training and validation sets, respectively). Another radiomic signature was constructed to distinguish the number of metastatic LNs (less than 2 positive nodes/more than 2 positive nodes), which also showed moderate performance (AUC 0.79).

CONCLUSIONS

We developed a nomogram and a radiomic signature that can be used to identify LN metastasis and distinguish the number of metastatic LNs (less than 2 positive nodes/more than 2 positive nodes). Both nomogram and radiomic signature can be used as tools to assist clinicians in assessing LN metastasis in breast cancer patients.

KEY POINTS

• ALNM is an important factor affecting breast cancer patients' treatment and prognosis. • Traditional imaging examinations have limited value for evaluating axillary LNs status. • We developed a radiomic nomogram based on MR imagings to predict LN metastasis.

MRI Volume Changes of Axillary Lymph Nodes as Predictor of Pathologic Complete Responses to Neoadjuvant Chemotherapy in Breast Cancer

INTRODUCTION

Longitudinal monitoring of breast tumor volume over the course of chemotherapy is informative of pathologic response. This study aims to determine whether axillary lymph node (aLN) volume by magnetic resonance imaging (MRI) could augment the prediction accuracy of treatment response to neoadjuvant chemotherapy (NAC).

MATERIALS AND METHODS

Level-2a curated data from the I-SPY-1 TRIAL (2002-2006) were used. Patients had stage 2 or 3 breast cancer. MRI was acquired pre-, during, and post-NAC. A subset with visible aLNs on MRI was identified (N = 132). Prediction of pathologic complete response (PCR) was made using breast tumor volume changes, nodal volume changes, and combined breast tumor and nodal volume changes with sub-stratification with and without large lymph nodes (3 mL or ∼1.79 cm diameter cutoff). Receiver operating characteristic curve analysis was used to quantify prediction performance.

RESULTS

The rate of change of aLN and breast tumor volume were informative of pathologic response, with prediction being most informative early in treatment (area under the curve (AUC), 0.57-0.87) compared with later in treatment (AUC, 0.50-0.75). Larger aLN volume was associated with hormone receptor negativity, with the largest nodal volume for triple negative subtypes. Sub-stratification by node size improved predictive performance, with the best predictive model for large nodes having AUC of 0.87.

CONCLUSION

aLN MRI offers clinically relevant information and has the potential to predict treatment response to NAC in patients with breast cancer.

Radiomics analysis of magnetic resonance imaging improves diagnostic performance of lymph node metastasis in patients with cervical cancer

BACKGROUND AND PURPOSE

Robust parameters are needed to predict lymph node metastasis (LNM) in locally advanced cervical cancer patients in order to select optimal treatment regimen. The aim of this study is to utilize radiomics analysis of magnetic resonance imaging (MRI) to improve diagnostic performance of LNM in cervical cancer patients.

MATERIALS AND METHODS

A total of 189 cervical cancer patients were divided into a training cohort (n = 126) and a validation cohort (n = 63). For each patient, we extracted radiomic features from intratumoral and peritumoral tissues on sagittal T2WI and axial apparent diffusion coefficient (ADC) maps. Afterward, the radiomic features associated with LNM status were selected by univariate ROC testing and logistic regression with the least absolute shrinkage and selection operator (LASSO) penalty in the training cohort. Based on the selected features, a support vector machine (SVM) model was established to predict LNM status. To further improve the diagnostic performance, a decision tree which combines the radiomics model with clinical factors was built.

RESULTS

Radiomics model of the intratumoral and peritumoral tissues on T2WI (T2_tumor+peri) showed best sensitivity and clinical LN (c-LN) status showed best specificity to predict LNM. The decision tree that combines radiomics model of T2_tumor+peri and c-LN status achieved best diagnostic performance, with AUC and sensitivity of 0.895 and 94.3%, 0.847 and 100% in the training and validation cohort respectively.

CONCLUSIONS

The decision tree, which incorporates radiomics model of T2_tumor+peri and c-LN status can be potentially applied in the preoperative prediction of LNM in locally advanced cervical cancer patients.

MRI-Based Radiomics Signature for the Preoperative Prediction of Extracapsular Extension of Prostate Cancer

BACKGROUND

Radiomics approaches based on multiparametric MRI (mp-MRI) have shown high accuracy in prostate cancer (PCa) management. However, there is a need to apply radiomics to the preoperative prediction of extracapsular extension (ECE).

PURPOSE

To develop and validate a radiomics signature to preoperatively predict the probability of ECE for patients with PCa, compared with the radiologists' interpretations.

STUDY TYPE

Retrospective.

POPULATION

In total, 210 patients with pathology-confirmed ECE status (101 positive, 109 negative) were enrolled.

FIELD STRENGTH/SEQUENCE

T₂ -weighted imaging (T₂ WI), diffusion-weighted imaging, and dynamic contrast-enhanced imaging were performed on two 3.0T MR scanners.

ASSESSMENT

A radiomics signature was constructed to predict the probability of ECE prior to radical prostatectomy (RP). In all, 17 stable radiomics features of 1619 extracted features based on T₂ WI were selected. The same images were also evaluated by three radiologists. The predictive performance of the radiomics signature was validated and compared with radiologists' interpretations.

STATISTICAL TESTS

A radiomics signature was developed by a least absolute shrinkage and selection operator (LASSO) regression algorithm. Samples enrolled were randomly divided into two groups (143 for training and 67 for validation). Discrimination, calibration, and clinical usefulness were validated by analysis of the receiver operating characteristic (ROC) curve, calibration curve, and the decision curve, respectively. The predictive performance was then compared with visual assessments of three radiologists.

RESULTS

The radiomics signature yielded an AUC of 0.902 and 0.883 in the training and validation cohort, respectively, and outperformed the visual assessment (AUC: 0.600-0.697) in the validation cohort. Pairwise comparisons demonstrated that the radiomics signature was more sensitive than the radiologists (75.00% vs. 46.88%-50.00%, all P < 0.05), but obtained comparable specificities (91.43% vs. (88.57%-94.29%); P ranged from 0.64-1.00).

DATA CONCLUSION

A radiomics signature was developed and validated that outperformed the radiologists' visual assessments in predicting ECE status.

LEVEL OF EVIDENCE

4 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:1914-1925.

Preliminary utilization of radiomics in differentiating uterine sarcoma from atypical leiomyoma: Comparison on diagnostic efficacy of MRI features and radiomic features

OBJECTIVES

To explore whether MRI and radiomic features can differentiate uterine sarcoma from atypical leiomyoma. And to compare diagnostic performance of radiomic model with radiologists.

METHODS

78 patients (29 sarcomas, 49 leiomyomas) imaged with pelvic MRI prior to surgery were included in this retrospective study. Certain clinical and MRI features were evaluated for one lesion per patient. Radiological diagnosis was made based on MRI features. A radiomic model using automated texture analysis based on ADC maps was built to predict pathological results. The association between MRI features and pathological results was determined by multivariable logistic regression after controlling for other variables in univariate analyses with P <  0.05. The diagnostic efficacy of radiologists and radiomic model were compared by area under the receiver-operating characteristic curve (AUC), sensitivity, specificity and accuracy.

RESULTS

In univariate analyses, patient's age, menopausal state, intratumor hemorrhage, tumor margin and uterine endometrial cavity were associated with pathological results, P <  0.05. Patient's age, tumor margin and uterine endometrial cavity remained significant in a multivariable model, P <  0.05. Diagnosis efficacy of radiologists based on MRI reached an AUC of 0.752, sensitivity of 58.6%, specificity of 91.8%, and accuracy of 79.5%. The optimal radiomic model reached an AUC of 0.830, sensitivity of 76.0%, average specificity of 73.2%, and accuracy of 73.9%.

CONCLUSIONS

Ill-defined tumor margin and interrupted uterine endometrial cavity of older women were predictors of uterine sarcoma. Radiomic analysis was feasible. Optimal radiomic model showed comparable diagnostic efficacy with experienced radiologists.

Feasibility of an ADC-based radiomics model for predicting pelvic lymph node metastases in patients with stage IB-IIA cervical squamous cell carcinoma

OBJECTIVES

To investigate the prediction value of a radiomics model based on apparent diffusion coefficient (ADC) maps for pelvic lymph node metastasis (PLNM) in patients with stage IB-IIA cervical squamous cell carcinoma (CSCC).

METHODS

A total of 153 stage IB-IIA CSCC patients who underwent preoperative MRI including DWI from January 2015 to October 2017 were retrospectively studied and divided into a training cohort ( n = 102) and a validation cohort ( n = 51). Radiomics features were extracted from the ADC maps. The one-way ANOVA method, Mann-Whitney U test and Pearson's correlation analysis were used for selecting radiomics features. Logistic regression analyses were used to develop the model. ROC analyses were used to evaluate the prediction performance of the model.

RESULTS

Clinical stage, tumor diameter, and MR-reported lymph node (LN) status were significantly associated with LN status ( p < 0.05 for both the training and validation cohorts). The radiomics model, which incorporated clinical stage, MR-reported LN status, and grey-level non-uniformity, showed good predictive performance in the training group (AUC 0.864; 95% CI, 0.782 - 0.924) and the validation group (AUC 0.870; 95% CI, 0.747 - 0.948). The performance of the radiomics model was significantly better than that of each predictive factor alone.

CONCLUSION

The presented radiomics model, a non-invasive preoperative prediction tool, has the potential to have more predictive efficacy than clinical and radiological factors for differentiating between metastatic and non-metastatic lymph nodes.

ADVANCES IN KNOWLEDGE

A radiomics model derived from the ADC maps of primary lesions demonstrated good performance for predicting PLNM in stage IB-IIA CSCC patients and may help to improve clinical decision-making.

Preoperative prediction of pelvic lymph nodes metastasis in early-stage cervical cancer using radiomics nomogram developed based on T2-weighted MRI and diffusion-weighted imaging

OBJECTIVE

To explore an MRI-based radiomics nomogram for preoperatively predicting of pelvic lymph node (PLN) metastasis in patients with early-stage cervical cancer (ECC).

METHODS

Ninety-six patients with ECC were enrolled in this study. All patients underwent T2WI and DWI scans before radical hysterectomy with PLN dissection surgery. Radiomics features extracted from T2WI and DWI were selected by least absolute shrinkage and selection operation regression for further radimoics signature calculation. The discrimination of this radiomics signature for PLN metastasis was then assessed using a support vector machine (SVM) model. Subsequently, a radiomics nomogram was constructed based on the radiomics signature and clinicopathologic risk factors using a multivariable logistic regression method. The performance of the radiomics nomogram for the preoperative prediction of PLN metastasis was evaluated for discrimination and calibration.

RESULTS

The radiomics signatures demonstrated a good discrimination for PLN metastasis. A radiomics signature derived from joint T2WI and DWI yielded higher AUC than the signatures derived from T2WI or DWI alone. The radiomics nomogram integrating the radiomics signature with clinicopathologic risk factors showed a significant improvement over the nomogram based only on clinicopathologic risk factors in the primary cohort(C-index, 0.893 vs. 0.616; P = 4.311×10^-5) and validation cohort(C-index, 0.922 vs. 0.799; P = 3.412 ×10^-2).The calibration curves also showed good agreement.

CONCLUSIONS

The radiomics nomogram based on joint T2WI and DWI demonstrated an improved prediction ability for PLN metastasis in ECC. This noninvasive and convenient tool may be used to facilitate preoperative identification of PLN metastasis in patients with ECC.

Preoperative Prediction of Axillary Lymph Node Metastasis in Breast Cancer Using Mammography-Based Radiomics Method

It is difficult to accurately assess axillary lymph nodes metastasis and the diagnosis of axillary lymph nodes in patients with breast cancer is invasive and has low-sensitivity preoperatively. This study aims to develop a mammography-based radiomics nomogram for the preoperative prediction of ALN metastasis in patients with breast cancer. This study enrolled 147 patients with clinicopathologically confirmed breast cancer and preoperative mammography. Features were extracted from each patient's mammography images. The least absolute shrinkage and selection operator regression method was used to select features and build a signature in the primary cohort. The performance of the signature was assessed using support vector machines. We developed a nomogram by incorporating the signature with the clinicopathologic risk factors. The nomogram performance was estimated by its calibration ability in the primary and validation cohorts. The signature was consisted of 10 selected ALN-status-related features. The AUC of the signature from the primary cohort was 0.895 (95% CI, 0.887-0.909) and 0.875 (95% CI, 0.698-0.891) for the validation cohort. The C-Index of the nomogram from the primary cohort was 0.779 (95% CI, 0.752-0.793) and 0.809 (95% CI, 0.794-0.833) for the validation cohort. Our nomogram is a reliable and non-invasive tool for preoperative prediction of ALN status and can be used to optimize current treatment strategy for breast cancer patients.

Diffusion-weighted imaging of the breast: current status as an imaging biomarker and future role

Diffusion-weighted imaging (DWI) of the breast is a MRI sequence that shows several advantages when compared to the dynamic contrast-enhanced sequence: it does not need intravenous contrast, it is relatively quick and easy to implement (artifacts notwithstanding). In this review, the current applications of DWI for lesion characterization and prognosis as well as for response evaluation are analyzed from the point of view of the necessary steps to become a useful surrogate of underlying biological processes (tissue architecture and cellularity): from the proof of concept, to the proof of mechanism, the proof of principle and finally the proof of effectiveness. Future applications of DWI in screening, DWI modeling and radiomics are also discussed.

The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges

Medical imaging can assess the tumor and its environment in their entirety, which makes it suitable for monitoring the temporal and spatial characteristics of the tumor. Progress in computational methods, especially in artificial intelligence for medical image process and analysis, has converted these images into quantitative and minable data associated with clinical events in oncology management. This concept was first described as radiomics in 2012. Since then, computer scientists, radiologists, and oncologists have gravitated towards this new tool and exploited advanced methodologies to mine the information behind medical images. On the basis of a great quantity of radiographic images and novel computational technologies, researchers developed and validated radiomic models that may improve the accuracy of diagnoses and therapy response assessments. Here, we review the recent methodological developments in radiomics, including data acquisition, tumor segmentation, feature extraction, and modelling, as well as the rapidly developing deep learning technology. Moreover, we outline the main applications of radiomics in diagnosis, treatment planning and evaluations in the field of oncology with the aim of developing quantitative and personalized medicine. Finally, we discuss the challenges in the field of radiomics and the scope and clinical applicability of these methods.

An Intelligent Clinical Decision Support System for Preoperative Prediction of Lymph Node Metastasis in Gastric Cancer

PURPOSE

The aim of this study was to develop and validate a computational clinical decision support system (DSS) on the basis of CT radiomics features for the prediction of lymph node (LN) metastasis in gastric cancer (GC) using machine learning-based analysis.

METHODS

Clinicopathologic and CT imaging data were retrospectively collected from 490 patients who were diagnosed with GC between January 2002 and December 2016. Radiomics features were extracted from venous-phase CT images. Relevant features were selected, ranked, and modeled using a support vector machine classifier in 326 training and validation data sets. A model test was performed independently in a test set (n = 164). Finally, a head-to-head comparison of the diagnostic performance of the DSS and that of the conventional staging criterion was performed.

RESULTS

Two hundred ninety-seven of the 490 patients examined had histopathologic evidence of LN metastasis, yielding a 60.6% metastatic rate. The area under the curve for predicting LN+ was 0.824 (95% confidence interval, 0.804-0.847) for the DSS in the training and validation data and 0.764 (95% confidence interval, 0.699-0.833) in the test data. The calibration plots showed good concordance between the predicted and observed probability of LN+ using the DSS approach. The DSS was better able to predict LN metastasis than the conventional staging criterion in the training and validation data (accuracy 76.4% versus 63.5%) and in the test data (accuracy 71.3% versus 63.2%) CONCLUSIONS: A DSS based on 13 "worrisome" radiomics features appears to be a promising tool for the preoperative prediction of LN status in patients with GC.

Development and Validation of Nomograms Predictive of Axillary Nodal Status to Guide Surgical Decision-Making in Early-Stage Breast Cancer

Purpose: To develop and validate nomogram models using noninvasive imaging parameters with related clinical variables to predict the extent of axillary nodal involvement and stratify treatment options based on the essential cut-offs for axillary surgery according to the ACOSOG Z0011 criteria.

Materials and Methods: From May 2007 to December 2017, 1799 patients who underwent preoperative breast and axillary magnetic resonance imaging (MRI) were retrospectively studied. Patients with data on axillary ultrasonography (AUS) were enrolled. The MRI images were interpreted according to Breast Imaging Reporting and Data system (BI-RADS). Using logistic regression analyses, nomograms were developed to visualize the associations between the predictors and each lymph node (LN) status endpoint. Predictive performance was assessed based on the area under the receiver operating characteristic curve (AUC). Bootstrap resampling was performed for internal validation. Goodness-of-fit of the models was evaluated using the Hosmer-Lemeshow test.

Results: Of 397 early breast cancer patients, 200 (50.4%) had disease-free axilla, 119 (30.0%) had 1 or 2 positive LNs, and 78 (19.6%) had ≥3 positive LNs. Patient age, MRI features (mass margin, LN margin, presence/absence of LN hilum, and LN symmetry/asymmetry), and AUS descriptors (presence of cortical thickening or hilum) were identified as predictors of nodal disease. Nomograms with these predictors showed good calibration and discrimination; the AUC was 0.809 for negative axillary node (N0) vs. any LN metastasis, 0.749 for 1 or 2 involved nodes vs. N0, and 0.874 for ≥3 nodes vs. ≤2 metastatic nodes. The predictive ability of the 3 nomograms with additional pathological variables was significantly greater.

Conclusion: The nomograms could predict the extent of ALN metastasis and facilitate decision-making preoperatively.

Development and validation of a magnetic resonance imaging-based model for the prediction of distant metastasis before initial treatment of nasopharyngeal carcinoma: A retrospective cohort study

Background

We aimed to identify a magnetic resonance imaging (MRI)-based model for assessment of the risk of individual distant metastasis (DM) before initial treatment of nasopharyngeal carcinoma (NPC).

Methods

This retrospective cohort analysis included 176 patients with NPC. Using the PyRadiomics platform, we extracted the imaging features of primary tumors in all patients who did not exhibit DM before treatment. Subsequently, we used minimum redundancy-maximum relevance and least absolute shrinkage and selection operator algorithms to select the strongest features and build a logistic model for DM prediction. The independent statistical significance of multiple clinical variables was tested using multivariate logistic regression analysis.

Findings

In total, 2780 radiomic features were extracted. A DM MRI-based model (DMMM) comprising seven features was constructed for the classification of patients into high- and low-risk groups in a training cohort and validated in an independent cohort. Overall survival was significantly shorter in the high-risk group than in the low-risk group (P < 0·001). A radiomics nomogram based on radiomic features and clinical variables was developed for DM risk assessment in each patient, and it showed a significant predictive ability in the training [area under the curve (AUC), 0·827; 95% confidence interval (CI), 0.754–0.900] and validation (AUC, 0.792; 95% CI, 0.633–0.952) cohorts.

Interpretation

DMMM can serve as a visual prognostic tool for DM prediction in NPC, and it can improve treatment decisions by aiding in the differentiation of patients with high and low risks of DM.

Fund

This research received financial support from the National Natural Science Foundation of China (81571664, 81871323, 81801665, 81771924, 81501616, 81671851, and 81527805); the National Natural Science Foundation of Guangdong Province (2018B030311024); the Science and Technology Planning Project of Guangdong Province (2016A020216020); the Scientific Research General Project of Guangzhou Science Technology and Innovation Commission (201707010328); the China Postdoctoral Science Foundation (2016M600145); and the National Key R&D Program of China (2017YFA0205200, 2017YFC1308700, and 2017YFC1309100).

T2 -based MRI Delta-radiomics improve response prediction in soft-tissue sarcomas treated by neoadjuvant chemotherapy

BACKGROUND

Standard of care for patients with high-grade soft-tissue sarcoma (STS) are being redefined since neoadjuvant chemotherapy (NAC) has demonstrated a positive effect on patients' outcome. Yet response evaluation in clinical trials still relies on RECIST criteria.

PURPOSE

To investigate the added value of a Delta-radiomics approach for early response prediction in patients with STS undergoing NAC.

STUDY TYPE

Retrospective.

POPULATION

Sixty-five adult patients with newly-diagnosed, locally-advanced, histologically proven high-grade STS of trunk and extremities. All were treated by anthracycline-based NAC followed by surgery and had available MRI at baseline and after two chemotherapy cycles.

FIELD STRENGTH/SEQUENCE

Pre- and postcontrast enhanced T₁ -weighted imaging (T₁ -WI), turbo spin echo T₂ -WI at 1.5 T.

ASSESSMENT

A threshold of <10% viable cells on surgical specimens defined good response (Good-HR). Two senior radiologists performed a semantic analysis of the MRI. After 3D manual segmentation of tumors at baseline and early evaluation, and standardization of voxel-sizes and intensities, absolute changes in 33 texture and shape features were calculated.

STATISTICAL TESTS

Classification models based on logistic regression, support vector machine, k-nearest neighbors, and random forests were elaborated using crossvalidation (training and validation) on 50 patients ("training cohort") and was validated on 15 other patients ("test cohort").

RESULTS

Sixteen patients were good-HR. Neither RECIST status (P = 0.112) nor semantic radiological variables were associated with response (range of P-values: 0.134-0.490) except an edema decrease (P = 0.003), although 14 shape and texture features were (range of P-values: 0.002-0.037). On the training cohort, the highest diagnostic performances were obtained with random forests built on three features: Δ_Histogram_Entropy, Δ_Elongation, Δ_Surrounding_Edema, which provided: area under the curve the receiver operating characteristic = 0.86, accuracy = 88.1%, sensitivity = 94.1%, and specificity = 66.3%. On the test cohort, this model provided an accuracy of 74.6% but 3/5 good-HR were systematically ill-classified.

DATA CONCLUSION

A T₂ -based Delta-radiomics approach might improve early response assessment in STS patients with a limited number of features.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:497-510.

Computerized evaluation scheme to detect metastasis in sentinel lymph nodes using contrast-enhanced computed tomography before breast cancer surgery

Sentinel lymph node (SLN) biopsy for evaluating lymph node metastasis during breast cancer surgery is associated with several problems, such as the consequent increase in operation time and the possibility of abrupt changes in the treatment plan during the operation. Although it is desirable to distinguish SLNs with and without cancer metastasis before surgery, there is no established examination for this purpose. This study aimed to develop a computerized scheme for evaluating metastasis in SLNs by analyzing computed tomography lymphography images and the three-dimensional versions of these images. Our database consisted of computed tomography lymphography images from 100 patients with breast cancer. Three subjective features of the nodes were assessed in the three-dimensional images: (1) the shape of the lymphoduct, (2) degree of signal enhancement in the nodes, and (3) shape of the nodes. Six objective features were also assessed in the computed tomography lymphography images: (4) the long axis, (5) area, (6) standard deviation of the signal values, (7) mean signal values, (8) maximum signal value, and (9) minimum signal value. Support vector machines were employed to evaluate cancer metastasis in SLNs. For the input, six of the nine features were selected in a stepwise method. The classification accuracy, sensitivity, and specificity were 98.0% (98/100), 97.8% (44/45), and 98.2% (54/55), respectively. The positive and negative predictive values were 97.8% (44/45) and 98.2% (54/55), respectively. This computerized method exhibited high classification accuracy and will be useful in determining the need for lymph node dissection before breast cancer surgery.

A New Challenge for Radiologists: Radiomics in Breast Cancer

INTRODUCTION

Over the last decade, the field of medical imaging experienced an exponential growth, leading to the development of radiomics, with which innumerable quantitative features are obtained from digital medical images, providing a comprehensive characterization of the tumor. This review aims to assess the role of this emerging diagnostic tool in breast cancer, focusing on the ability of radiomics to predict malignancy, response to neoadjuvant chemotherapy, prognostic factors, molecular subtypes, and risk of recurrence.

EVIDENCE ACQUISITION

A literature search on PubMed and on Cochrane database websites to retrieve English-written systematic reviews, review articles, meta-analyses, and randomized clinical trials published from August 2013 up to July 2018 was carried out.

RESULTS

Twenty papers (19 retrospective and 1 prospective studies) conducted with different conventional imaging modalities were included.

DISCUSSION

The integration of quantitative information with clinical, histological, and genomic data could enable clinicians to provide personalized treatments for breast cancer patients. Current limitations of a routinely application of radiomics are represented by the limited knowledge of its basics concepts among radiologists and by the lack of efficient and standardized systems of feature extraction and data sharing.

Preoperative prediction of sentinel lymph node metastasis in breast cancer by radiomic signatures from dynamic contrast-enhanced MRI

BACKGROUND

Sentinel lymph node (SLN) status is an important prognostic factor for patients with breast cancer, which is currently determined in clinical practice by invasive SLN biopsy.

PURPOSE

To noninvasively predict SLN metastasis in breast cancer using dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) intra- and peritumoral radiomics features combined with or without clinicopathologic characteristics of the primary tumor.

STUDY TYPE

Retrospective.

POPULATION

A total of 163 breast cancer patients (55 positive SLN and 108 negative SLN).

FIELD STRENGTH/SEQUENCE

1.5T, T₁ -weighted DCE-MRI.

ASSESSMENT

A total of 590 radiomic features were extracted for each patient from both intratumoral and peritumoral regions of interest. To avoid overfitting, the dataset was randomly separated into a training set (∼67%) and a validation set (∼33%). The prediction models were built with the training set using logistic regression on the most significant radiomic features in the training set combined with or without clinicopathologic characteristics. The prediction performance was further evaluated in the independent validation set.

STATISTICAL TESTS

Mann-Whitney U-test, Spearman correlation, least absolute shrinkage selection operator (LASSO) regression, logistic regression, and receiver operating characteristic (ROC) analysis were performed.

RESULTS

Combining radiomic features with clinicopathologic characteristics, six features were automatically selected in the training set to establish the prediction model of SLN metastasis. In the independent validation set, the area under ROC curve (AUC) was 0.869 (NPV = 0.886). Using radiomic features alone in the same procedure, 4 features were selected and the validation set AUC was 0.806 (NPV = 0.824).

DATA CONCLUSION

This is the first attempt to demonstrate the feasibility of using DCE-MRI radiomics to predict SLN metastasis in breast cancer. Clinicopathologic characteristics improved the prediction performance. This study provides noninvasive methods to evaluate SLN status for guiding further treatment of breast cancer patients, and can potentially benefit those with negative SLN, by eliminating unnecessary invasive lymph node removal and the associated complications, which is a step further towards precision medicine.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:131-140.

A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for Change

The adoption of enterprise digital imaging, along with the development of quantitative imaging methods and the re-emergence of statistical learning, has opened the opportunity for more personalized cancer treatments through transformative data science research. In the last 5 years, accumulating evidence has indicated that noninvasive advanced imaging analytics (i.e., radiomics) can reveal key components of tumor phenotype for multiple lesions at multiple time points over the course of treatment. Many groups using homegrown software have extracted engineered and deep quantitative features on 3-dimensional medical images for better spatial and longitudinal understanding of tumor biology and for the prediction of diverse outcomes. These developments could augment patient stratification and prognostication, buttressing emerging targeted therapeutic approaches. Unfortunately, the rapid growth in popularity of this immature scientific discipline has resulted in many early publications that miss key information or use underpowered patient data sets, without production of generalizable results. Quantitative imaging research is complex, and key principles should be followed to realize its full potential. The fields of quantitative imaging and radiomics in particular require a renewed focus on optimal study design and reporting practices, standardization, interpretability, data sharing, and clinical trials. Standardization of image acquisition, feature calculation, and statistical analysis (i.e., machine learning) are required for the field to move forward. A new data-sharing paradigm enacted among open and diverse participants (medical institutions, vendors and associations) should be embraced for faster development and comprehensive clinical validation of imaging biomarkers. In this review and critique of the field, we propose working principles and fundamental changes to the current scientific approach, with the goal of high-impact research and development of actionable prediction models that will yield more meaningful applications of precision cancer medicine.

Diffusion-weighted breast imaging

Magnetic resonance imaging (MRI) of the breast represents one of the most sensitive imaging modalities in breast cancer detection. Diffusion-weighted imaging (DWI) is a sequence variation introduced as a complementary MRI technique that relies on mapping the diffusion process of water molecules thereby providing additional information about the underlying tissue. Since water diffusion is more restricted in most malignant tumors than in benign ones owing to the higher cellularity of the rapidly proliferating neoplasia, DWI has the potential to contribute to the identification and characterization of suspicious breast lesions. Thus, DWI might increase the diagnostic accuracy of breast MRI and its clinical value. Future applications including optimized DWI sequences, technical developments in MR devices, and the application of radiomics/artificial intelligence algorithms may expand the potential of DWI in breast imaging beyond its current supplementary role.

A new approach to predict lymph node metastasis in solid lung adenocarcinoma: a radiomics nomogram

Background

Lymph node metastasis (LNM) of lung cancer is an important factor related to survival and recurrence. The association between radiomics features of lung cancer and LNM remains unclear. We developed and validated a radiomics nomogram to predict LNM in solid lung adenocarcinoma.

Methods

A total of 159 eligible patients with solid lung adenocarcinoma were divided into training (n=106) and validation cohorts (n=53). Radiomics features were extracted from venous-phase CT images. We built a radiomics nomogram using a multivariate logistic regression model combined with CT-reported lymph node (LN) status. The performance of the radiomics nomogram was evaluated using the area under curve (AUC) of receiver operating characteristic curve. We performed decision curve analysis (DCA) within training and validation cohorts to assess the clinical usefulness of the nomogram.

Results

Fourteen radiomics features were chosen from 94 candidate features to build a radiomics signature that significantly correlated with LNM. The model showed good calibration and discrimination in the training cohort, with an AUC of 0.871 (95% CI: 0.804-0.937), sensitivity of 85.71% and specificity of 77.19%. In the validation cohort, AUC was 0.856 (95% CI: 0.745-0.966), sensitivity was 91.66%, and specificity was 82.14%. DCA demonstrated that the nomogram was clinically useful. The nomogram also showed good predictive ability in patients at high risk for LNM in the CT-reported LN negative (cN0) subgroup.

Conclusions

The radiomics nomogram, based on preoperative CT images, can be used as a noninvasive method to predict LNM in patients with solid lung adenocarcinoma.

Rapid review: radiomics and breast cancer

PURPOSE

To perform a rapid review of the recent literature on radiomics and breast cancer (BC).

METHODS

A rapid review, a streamlined approach to systematically identify and summarize emerging studies was done (updated 27 September 2017). Clinical studies eligible for inclusion were those that evaluated BC using a radiomics approach and provided data on BC diagnosis (detection or characterization) or BC prognosis (response to therapy, morbidity, mortality), or provided data on technical challenges (software application: open source, repeatability of results). Descriptive statistics, results, and radiomics quality score (RQS) are presented.

RESULTS

N = 17 retrospective studies, all published after 2015, provided BC-related radiomics data on 3928 patients evaluated with a radiomics approach. Most studies were done for diagnosis and/or characterization (65%, 11/17) or to aid in prognosis (41%, 7/17). The mean number of radiomics features considered was 100. Mean RQS score was 11.88 ± 5.8 (maximum value 36). The RQS criteria related to validation, gold standard, potential clinical utility, cost analysis, and open science data had the lowest scores. The majority of studies n = 16/17 (94%) provided correlation with histological outcomes and staging variables or biomarkers. Only 4/17 (23%) studies provided evidence of correlation with genomic data. Magnetic resonance imaging (MRI) was used in most studies n = 14/17 (82%); however, ultrasound (US), mammography, or positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (18F FDG PET/CT) was also used. Much heterogeneity was found for software usage.

CONCLUSIONS

The study of radiomics in BC patients is a new and emerging translational research topic. Radiomics in BC is frequently done to potentially improve diagnosis and characterization, mostly using MRI. Substantial quality limitations were found; high-quality prospective and reproducible studies are needed to further potential application.