Association of distant recurrence-free survival with algorithmically extracted MRI characteristics in breast cancer

Time-to-Event Endpoints in Imaging Biomarker Studies

Time-to-event endpoints are widely used as measures of patients' well-being and indicators of prognosis. In imaging-based biomarker studies, there are increasingly more studies that focus on examining imaging biomarkers' prognostic or predictive utilities on those endpoints, whether in a trial or an observational study setting. In this educational review article, we briefly introduce some basic concepts of time-to-event endpoints and point out potential pitfalls in the context of imaging biomarker research in hope of improving radiologists' understanding of related subjects. Besides, we have included some review and discussions on the benefits of using time-to-event endpoints and considerations on selecting overall survival or progression-free survival for primary analysis. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 3.

Machine learning radiomics of magnetic resonance imaging predicts recurrence-free survival after surgery and correlation of LncRNAs in patients with breast cancer: a multicenter cohort study

BACKGROUND

Several studies have indicated that magnetic resonance imaging radiomics can predict survival in patients with breast cancer, but the potential biological underpinning remains indistinct. Herein, we aim to develop an interpretable deep-learning-based network for classifying recurrence risk and revealing the potential biological mechanisms.

METHODS

In this multicenter study, 1113 nonmetastatic invasive breast cancer patients were included, and were divided into the training cohort (n = 698), the validation cohort (n = 171), and the testing cohort (n = 244). The Radiomic DeepSurv Net (RDeepNet) model was constructed using the Cox proportional hazards deep neural network DeepSurv for predicting individual recurrence risk. RNA-sequencing was performed to explore the association between radiomics and tumor microenvironment. Correlation and variance analyses were conducted to examine changes of radiomics among patients with different therapeutic responses and after neoadjuvant chemotherapy. The association and quantitative relation of radiomics and epigenetic molecular characteristics were further analyzed to reveal the mechanisms of radiomics.

RESULTS

The RDeepNet model showed a significant association with recurrence-free survival (RFS) (HR 0.03, 95% CI 0.02-0.06, P < 0.001) and achieved AUCs of 0.98, 0.94, and 0.92 for 1-, 2-, and 3-year RFS, respectively. In the validation and testing cohorts, the RDeepNet model could also clarify patients into high- and low-risk groups, and demonstrated AUCs of 0.91 and 0.94 for 3-year RFS, respectively. Radiomic features displayed differential expression between the two risk groups. Furthermore, the generalizability of RDeepNet model was confirmed across different molecular subtypes and patient populations with different therapy regimens (All P < 0.001). The study also identified variations in radiomic features among patients with diverse therapeutic responses and after neoadjuvant chemotherapy. Importantly, a significant correlation between radiomics and long non-coding RNAs (lncRNAs) was discovered. A key lncRNA was found to be noninvasively quantified by a deep learning-based radiomics prediction model with AUCs of 0.79 in the training cohort and 0.77 in the testing cohort.

CONCLUSIONS

This study demonstrates that machine learning radiomics of MRI can effectively predict RFS after surgery in patients with breast cancer, and highlights the feasibility of non-invasive quantification of lncRNAs using radiomics, which indicates the potential of radiomics in guiding treatment decisions.

MRI-based radiomics approach for the prediction of recurrence-free survival in triple-negative breast cancer after breast-conserving surgery or mastectomy

To explore the value of a radiomics signature and develop a nomogram combined with a radiomics signature and clinical factors for predicting recurrence-free survival in triple-negative breast cancer patients. We enrolled 151 patients from the cancer imaging archive who underwent preoperative contrast-enhanced magnetic resonance imaging. They were assigned to training, validation and external validation cohorts. Image features with coefficients not equal to zero in the 10-fold cross-validation were selected to generate a radiomics signature. Based on the optimal cutoff value of the radiomics signature determined by maximally selected log-rank statistics, patients were stratified into high- and low-risk groups in the training and validation cohorts. Kaplan-Meier survival analysis was performed for both groups. Kaplan-Meier survival distributions in these groups were compared using log-rank tests. Univariate and multivariate Cox regression analyses were used to construct clinical and combined models. Concordance index was used to assess the predictive performance of the 3 models. Calibration of the combined model was assessed using calibration curves. Four image features were selected to generate the radiomics signature. The Kaplan-Meier survival distributions of patients in the 2 groups were significantly different in the training (P < .001) and validation cohorts (P = .001). The C-indices of the radiomics model, clinical model, and combined model in the training and validation cohorts were 0.772, 0.700, 0.878, and 0.744, 0.574, 0.777, respectively. The C-indices of the radiomics model, clinical model, and combined model in the external validation cohort were 0.778, 0.733, 0.822, respectively. The calibration curves of the combined model showed good calibration. The radiomics signature can predict recurrence-free survival of patients with triple-negative breast cancer and improve the predictive performance of the clinical model.

Radiomic signatures based on pretreatment 18F-FDG PET/CT, combined with clinicopathological characteristics, as early prognostic biomarkers among patients with invasive breast cancer

Purpose

The aim of this study was to investigate the predictive role of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the prognostic risk stratification of patients with invasive breast cancer (IBC). To achieve this, we developed a clinicopathologic-radiomic-based model (C-R model) and established a nomogram that could be utilized in clinical practice.

Methods

We retrospectively enrolled a total of 91 patients who underwent preoperative 18F-FDG PET/CT and randomly divided them into training (n=63) and testing cohorts (n=28). Radiomic signatures (RSs) were identified using the least absolute shrinkage and selection operator (LASSO) regression algorithm and used to compute the radiomic score (Rad-score). Patients were assigned to high- and low-risk groups based on the optimal cut-off value of the receiver operating characteristic (ROC) curve analysis for both Rad-score and clinicopathological risk factors. Univariate and multivariate Cox regression analyses were performed to determine the association between these variables and progression-free survival (PFS) or overall survival (OS). We then plotted a nomogram integrating all these factors to validate the predictive performance of survival status.

Results

The Rad-score, age, clinical M stage, and minimum standardized uptake value (SUVmin) were identified as independent prognostic factors for predicting PFS, while only Rad-score, age, and clinical M stage were found to be prognostic factors for OS in the training cohort. In the testing cohort, the C-R model showed superior performance compared to single clinical or radiomic models. The concordance index (C-index) values for the C-R model, clinical model, and radiomic model were 0.816, 0.772, and 0.647 for predicting PFS, and 0.882, 0.824, and 0.754 for OS, respectively. Furthermore, decision curve analysis (DCA) and calibration curves demonstrated that the C-R model had a good ability for both clinical net benefit and application.

Conclusion

The combination of clinicopathological risks and baseline PET/CT-derived Rad-score could be used to evaluate the prognosis in patients with IBC. The predictive nomogram based on the C-R model further enhanced individualized estimation and allowed for more accurate prediction of patient outcomes.

How Radiomics Can Improve Breast Cancer Diagnosis and Treatment

Recent technological advances in the field of artificial intelligence hold promise in addressing medical challenges in breast cancer care, such as early diagnosis, cancer subtype determination and molecular profiling, prediction of lymph node metastases, and prognostication of treatment response and probability of recurrence. Radiomics is a quantitative approach to medical imaging, which aims to enhance the existing data available to clinicians by means of advanced mathematical analysis using artificial intelligence. Various published studies from different fields in imaging have highlighted the potential of radiomics to enhance clinical decision making. In this review, we describe the evolution of AI in breast imaging and its frontiers, focusing on handcrafted and deep learning radiomics. We present a typical workflow of a radiomics analysis and a practical "how-to" guide. Finally, we summarize the methodology and implementation of radiomics in breast cancer, based on the most recent scientific literature to help researchers and clinicians gain fundamental knowledge of this emerging technology. Alongside this, we discuss the current limitations of radiomics and challenges of integration into clinical practice with conceptual consistency, data curation, technical reproducibility, adequate accuracy, and clinical translation. The incorporation of radiomics with clinical, histopathological, and genomic information will enable physicians to move forward to a higher level of personalized management of patients with breast cancer.

Development and Validation of an MRI Radiomics-Based Signature to Predict Histological Grade in Patients with Invasive Breast Cancer

Background

Histological grade is an important factor in the overall prognosis of patients with invasive breast cancer. Therefore, the non-invasive assessment of histological grade in breast cancer patients is an increasing concern for clinicians. We aimed to establish an MRI-based radiomics model for preoperative prediction of invasive breast cancer histological grade.

Methods

We enrolled 901 patients with invasive breast cancer and pre-operative MRI. Patients were randomly divided into the training cohort (n=630) and validation cohort (n=271) with a ratio of 7:3. A radiomics signature was constructed by extracting radiomics features from MRI images and was developed according to multivariate logistic regression analysis. The diagnostic performance of the radiomics model was assessed using receiver operating characteristic (ROC) curve analysis.

Results

Of the 901 patients, 618 (68.6%) were histological grade 1 or 2 while 283 (31.4%) were histological grade 3. The area under the ROC curve (AUC) of the radiomics model for the prediction of the histological grade was 0.761 (95% CI 0.728–0.794) in the training cohort and 0.722 (95% CI 0.664–0.777) in the validation cohort. The decision curve analysis (DCA) demonstrated the radiomics model’s clinical application value.

Conclusion

This is a preliminary study suggesting that the development of an MRI-based radiomics model can predict the histological grade of invasive breast cancer.

Prediction for Distant Metastasis of Breast Cancer Using Dynamic Contrast-Enhanced Magnetic Resonance Imaging Images under Deep Learning

This research aimed to explore the effect of using magnetic resonance imaging (MRI) radiomic features to establish a model for predicting distant metastasis under dynamic contrast-enhanced MRI imaging with deep learning algorithms. The deep learning algorithm was used to segment the images. A total of 96 cases with 100 lesions were included in the metastatic group, including 2 cases of bifocal breast cancer and 2 cases of multifocal breast cancer. There were 192 cases in the nonmetastatic group, with 197 lesions, including 5 cases of multifocal breast cancer. After dynamic contrast-enhancement, the morphological features and grayscale statistical features were extracted from the lesions to establish a prediction model through sum-sum check and feature dimension reduction. The accuracy, sensitivity, specificity, and area under receiver operator characteristic curve (AUC) of prediction models based only on imaging features were compared with those created by combining radiomic features with clinical and pathological features. The created predictive model based on radiomic features for distant metastases in breast cancer showed a sensitivity of 66.7%, a specificity of 84.2%, an accuracy of 78.3%, and an AUC of 0.744. The sensitivity of the prediction model for distant metastasis of breast cancer was 67.7%, the specificity was 86.8%, the accuracy was 80.5%, and the AUC was 0.763. Bone, lung, and liver were the most common distant metastatic sites of breast cancer. Under the dynamic contrast-enhanced MRI of deep learning, the prediction model combining radiomic features with clinical and pathological features showed better predictive performance.

Validated algorithms for identifying timing of second event of oropharyngeal squamous cell carcinoma using real-world data

BACKGROUND

Understanding occurrence and timing of second events (recurrence and second primary cancer) is essential for cancer specific survival analysis. However, this information is not readily available in administrative data.

METHODS

Alberta Cancer Registry, physician claims, and other administrative data were used. Timing of second event was estimated based on our developed algorithm. For validation, the difference, in days between the algorithm estimated and the chart-reviewed timing of second event. Further, the result of Cox-regression modeling cancer-free survival was compared to chart review data.

RESULTS

Majority (74.3%) of the patients had a difference between the chart-reviewed and algorithm-estimated timing of second event falling within the 0-60 days window. Kaplan-Meier curves generated from the estimated data and chart review data were comparable with a 5-year second-event-free survival rate of 75.4% versus 72.5%.

CONCLUSION

The algorithm provided an estimated timing of second event similar to that of the chart review.

Development and Validation of Noninvasive MRI-Based Signature for Preoperative Prediction of Early Recurrence in Perihilar Cholangiocarcinoma

BACKGROUND

Cholangiocarcinoma is a type of hepatobiliary tumor. For perihilar cholangiocarcinoma (pCCA), patients who experience early recurrence (ER) have a poor prognosis. Preoperative accurate prediction of postoperative ER can avoid unnecessary operation; however, prediction is challenging.

PURPOSE

To develop a novel signature based on clinical and/or MRI radiomics features of pCCA to preoperatively predict ER.

STUDY TYPE

Retrospective.

POPULATION

One hundred eighty-four patients (median age, 61.0 years; interquartile range: 53.0-66.8 years) including 115 men and 69 women.

FIELD STRENGTH/SEQUENCE

A 1.5 T; volumetric interpolated breath-hold examination (VIBE) sequence.

ASSESSMENT

The models were developed from the training set (128 patients) and validated in a separate testing set (56 patients). The contrast-enhanced arterial and portal vein phase MR images of hepatobiliary system were used for extracting radiomics features. The correlation analysis, least absolute shrinkage and selection operator (LASSO) logistic regression (LR), backward stepwise LR were mainly used for radiomics feature selection and modeling (Model^radiomic ). The univariate and multivariate backward stepwise LR were used for preoperative clinical predictors selection and modeling (Model^clinic ). The radiomics and preoperative clinical predictors were combined by multivariate LR method to construct clinic-radiomics nomogram (Model^combine ).

STATISTICAL TESTS

Chi-squared (χ² ) test or Fisher's exact test, Mann-Whitney U-test or t-test, Delong test. Two tailed P < 0.05 was considered statistically significant.

RESULTS

Based on the comparison of area under the curves (AUC) using Delong test, Model^clinic and Model^combine had significantly better performance than Model^radiomic and tumor-node-metastasis (TNM) system in training set. In the testing set, both Model^clinic and Model^combine had significantly better performance than TNM system, whereas only Model^combine was significantly superior to Model^radiomic . However, the AUC values were not significantly different between Model^clinic and Model^combine (P = 0.156 for training set and P = 0.439 for testing set).

DATA CONCLUSION

A noninvasive model combining the MRI-based radiomics signature and clinical variables is potential to preoperatively predict ER for pCCA.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 4.

Magnetic Resonance Imaging-Based Radiomics Features Associated with Depth of Invasion Predicted Lymph Node Metastasis and Prognosis in Tongue Cancer

Background

Adequate safe margin in tongue cancer radical surgery is one of the most important prognostic factors. However, the role of peritumoral tissues in predicting lymph node metastasis (LNM) and prognosis using radiomics analysis remains unclear.

Purpose

To investigate whether magnetic resonance imaging (MRI)‐based radiomics analysis with peritumoral extensions contributes toward the prediction of LNM and prognosis in tongue cancer.

Study type

Retrospective.

Population

Two hundred and thirty‐six patients (38.56% female) with tongue cancer (training set, N = 157; testing set, N = 79; 37.58% and 40.51% female for each).

Field Strength/Sequence

1.5 T; T2‐weighted turbo spin‐echo images.

Assessment

Radiomics models (R_prim, R_prim+3, R_prim+5, R_prim+10, R_prim+15) were developed with features extracted from the primary tumor without or with peritumoral extensions (3, 5, 10, and 15 mm, respectively). Clinicopathological characteristics selected from univariate analysis, including MRI‐reported LN status, radiological extrinsic lingual muscle invasion, and pathological depth of invasion (DOI) were further incorporated into radiomics models to develop combined radiomics models (CR_prim, CR_prim+3, CR_prim+5, CR_prim+10, CR_prim+15). Finally, the model performance was validated in the testing set. DOI was measured from the adjacent normal mucosa to the deepest point of tumor invasion.

Statistical Tests

Chi‐square test, regression analysis, receiver operating characteristic curve (ROC) analysis, decision analysis, spearman correlation analysis. The Delong test was used to compare area under the ROC (AUC). P < 0.05 was considered statistically significant.

Results

Of all the models, the CR_prim+10 reached the highest AUC of 0.995 in the training set and 0.872 in the testing set. Radiomics features were significantly correlated with pathological DOI (correlation coefficients, −0.157 to −0.336). The CR_prim+10 was an independent indicator for poor disease‐free survival (hazard ratio, 5.250) and overall survival (hazard ratio, 17.464) in the testing set.

Data Conclusion

Radiomics analysis with a 10‐mm peritumoral extension had excellent power to predict LNM and prognosis in tongue cancer.

Predicting cancer outcomes with radiomics and artificial intelligence in radiology

The successful use of artificial intelligence (AI) for diagnostic purposes has prompted the application of AI-based cancer imaging analysis to address other, more complex, clinical needs. In this Perspective, we discuss the next generation of challenges in clinical decision-making that AI tools can solve using radiology images, such as prognostication of outcome across multiple cancers, prediction of response to various treatment modalities, discrimination of benign treatment confounders from true progression, identification of unusual response patterns and prediction of the mutational and molecular profile of tumours. We describe the evolution of and opportunities for AI in oncology imaging, focusing on hand-crafted radiomic approaches and deep learning-derived representations, with examples of their application for decision support. We also address the challenges faced on the path to clinical adoption, including data curation and annotation, interpretability, and regulatory and reimbursement issues. We hope to demystify AI in radiology for clinicians by helping them to understand its limitations and challenges, as well as the opportunities it provides as a decision-support tool in cancer management.

Radiomics- Quantitative Biomarker Analysis for Breast Cancer Diagnosis and Prediction: A Review

BACKGROUND

Cancer of the breast has become a global problem for women's health. Though concerns regarding early detection and accurate diagnosis were raised, an effort is required for precision medicine as well as personalized treatment. In the past years, the area of medicinal imaging has seen an unprecedented growth that leads to an advancement of radiomics, which provides countless quantitative biomarkers extracted from modern diagnostic images, including a detailed tumor characterization of breast malignancy.

DISCUSSION

In this research, we presented the methodology and implementation of radiomics, together with its future trends and challenges by the basis of published papers. Radiomics could distinguish between malignant from benign tumors, predict prognostic factors, molecular subtypes of breast carcinoma, treatment response to neoadjuvant chemotherapy (NAC), and recurrence survival. The incorporation of quantitative knowledge with clinical, histopathological and genomic information will enable physicians to afford customized care of treatment for patients with breast cancer.

CONCLUSION

Our research was intended to help physicians and radiologists learn fundamental knowledge about radiomics and also to work collaboratively with researchers to explore evidence for further usage in clinical practice.

The Impact of Preoperative Radiomics Signature on the Survival of Breast Cancer Patients With Residual Tumors After NAC

Background

Residual cancer cells remaining after chemotherapy may have more aggressive behavior that promotes recurrence or metastasis, and which patients would benefit from subsequent additional treatment is controversial. The purpose of our study was to evaluate the prognostic value of the preoperative radiomics features of computed tomography (CT) imaging in breast cancer (BC) patients with residual tumors after neoadjuvant chemotherapy (NAC).

Methods

Post-NAC CT images were reviewed from 114 patients who had received breast surgery and had residual breast tumors. The association of the 110 radiomics features derived from CT images with 5-year disease-free survival (DFS) was assessed by log-rank test in the training cohort, resulting in 13 prognostic radiomics features.

Results

We constructed a radiomics signature consisting of four selected features by using least absolute shrinkage and selection operator (LASSO) Cox regression analysis, which performed well in the discrimination with an area under the curve (AUC) of 0.78 (95% CI, 0.67–0.89) and 0.73 (95% CI, 0.59–0.87) in the training and validation cohorts, respectively. Radiomics nomogram, incorporating the radiomics signature with the conventional clinical variables, also performed well in the two cohorts (training cohort: AUC, 0.84; validation cohort: AUC, 0.82). Moreover, we found that the high-risk patients determined by our radiomics nomogram could benefit from postoperative adjuvant chemotherapy, while the low-risk and total patient groups could not.

Conclusions

Our novel radiomics nomogram is a promising and favorable prognostic biomarker for preoperatively predicting survival outcomes and may aid in clinical decision-making in BC patients with residual tumors after NAC.

Heterogeneity of enhancement kinetics in dynamic contrast-enhanced MRI and implication of distant metastasis in invasive breast cancer

AIM

To investigate the heterogeneity of enhancement kinetics for breast tumour in order to demonstrate the predictive power of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) features for distant metastasis (DM) in invasive breast cancer.

MATERIALS AND METHODS

Time-signal intensity curve (TIC) patterns from 128 patients with invasive breast cancer were analysed by a pixel-based DCE-MRI analysis. This MRI technique enabled pixels with varying TIC patterns (persistent, plateau, washout and non-enhancement) to be categorised semi-automatically and the percentage of different TIC patterns in each breast tumour to be calculated. The percentage of TIC patterns was compared between the DM and non-DM groups. DM-free survival was estimated using Kaplan-Meier survival analysis.

RESULTS

This study demonstrated a larger percentage of persistent TIC and non-enhancement TIC was associated with DM in invasive breast cancer. The cut-off values of persistent TIC and non-enhancement TIC were 22.5% and 2.5%. Combining TIC patterns and traditional predictors (tumour size and axillary lymph node status) can improve the prediction efficiency. The multivariable model yielded an area under the receiver operating characteristic curve (AUC) of 0.87 with 0.70 sensitivity and 0.87 specificity in leave-one-out cross-validation (LOOCV). These predictors showed significant differences in DM-free survival by Kaplan-Meier analysis.

CONCLUSION

This study shows that breast tumours with higher heterogeneity are more likely to metastasise, and pixel-based TIC analysis has utility in predicting distant metastasis of invasive breast cancer.

Radiogenomics of magnetic resonance imaging and a new multi-gene classifier for predicting recurrence prognosis in estrogen receptor-positive breast cancer: A preliminary study

To examine the correlation of qualitative and quantitative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) results with 95-gene classifier or Curebest 95-gene classifier Breast (95GC) results for recurrence prediction in estrogen receptor-positive breast cancer (ERPBC).This retrospective study included 78 ERPBC patients (age range, 24-74 years) classified into high- (n = 33) and low- (n = 45) risk groups for recurrence based on 95GC and who underwent DCE-MRI between July 2006 and November 2012. For qualitative evaluation, mass shape, margin, and internal enhancement based on BI-RADS MRI lexicon and multiplicity were determined by consensus interpretation by 2 breast radiologists. For quantitative evaluation, mass size, volume ratios of the DCE-MRI kinetics, and both the kurtosis and the skewness of the intensity histogram for the whole mass in the initial and delayed phases were determined. Differences between the 2 risk-groups were analyzed using univariate logistic regression analyses and multiple logistic regression analyses. Receiver-operating characteristic curve cut-off values were used to define the groups.As for the qualitative findings, the difference between the 2 groups was not significant. For the quantitative data, the volume ratio of "medium" in the initial phase differed significantly between the 2 groups (P = .049). The volume ratio of "medium" (P = .006) and of "slow-persistent" (P = .005), and the delayed phase kurtosis (P = .012) in the univariate logistic regression analyses, and in the multiple logistic regression, volume ratio of "medium" >38.9% and delayed phase kurtosis >3.31 were identified as significant high-risk indicators (odds ratio, 5.83 and 3.55; 95% confidence interval, 1.58 to 21.42 and 1.24 to 10.15; P = .008 and P = .018, respectively).A high volume ratio of "medium" in the initial phase and/or high kurtosis in the delayed phase for quantitative evaluation could predict high ERPBC recurrence risk based on 95GC.