Breast Dynamic Contrast-enhanced Magnetic Resonance Research Articles

The Predictive Role of Mammography, Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging and Diffusion-Weighted Imaging in Hormone Receptor Status of Pure Ductal Carcinoma In Situ Lesions.

The aim of this retrospective study was to analyze the predictive capabilities of preoperative mammography, dynamic contrast-enhanced-magnetic resonance imaging (DCE-MRI), and diffusion-weighted imaging (DWI) in determining hormone receptor (HRc) status for pure ductal carcinoma in situ (DCIS) lesions. The study included a total of 79 patients who underwent preoperative mammography (MG) and MRI between December 2018 and December 2023 and were subsequently diagnosed with pure DCIS after surgery. The correlation between MG, DCE-MRI, and DWI features and estrogen receptor (ER) and progesterone receptor (PR) status was examined. Among the lesions, 44 were double HRc-positive (ER and PR-positive), 13 were single HRc-positive (ER-positive and PR-negative or ER-negative and PR-positive) and 22 were double HRc-negative (ER and PR-negative). The presence of symptom (p = 0.029), the presence of comedo necrosis (p = 0.005) and high histological grade (p<0.001) were found to be associated with ER and PR negativity. Amorphous microcalcifications were more commonly observed in the double HRc-negative group, while linear calcifications were more prevalent in both double and single HRc-positive groups (p = 0.020). Non-mass enhancement (NME) with a linear distribution was significantly more common in double HRc-negative lesions (38%), and NME with a segmental distribution in both double (43%) and single (50%) receptor-positive lesions (p = 0.042). Evaluation of DWI findings revealed that a higher lesion-to-normal breast parenchyma apparent diffusion coefficient (ADC) ratio statistically increased the probability of HRc positivity (p = 0.033). Certain clinicopathological, mammography, and MRI features, along with the lesion-to-normal breast parenchyma ADC ratio, can serve as predictors for HRc status in DCIS lesions.

Molecular subtypes of breast cancer identified by dynamically enhanced MRI radiomics: the delayed phase cannot be ignored

ObjectivesTo compare the diagnostic performance of intratumoral and peritumoral features from different contrast phases of breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) by building radiomics models for differentiating molecular subtypes of breast cancer.MethodsThis retrospective study included 377 patients with pathologically confirmed breast cancer. Patients were divided into training set (n = 202), validation set (n = 87) and test set (n = 88). The intratumoral volume of interest (VOI) and peritumoral VOI were delineated on primary breast cancers at three different DCE-MRI contrast phases: early, peak, and delayed. Radiomics features were extracted from each phase. After feature standardization, the training set was filtered by variance analysis, correlation analysis, and least absolute shrinkage and selection (LASSO). Using the extracted features, a logistic regression model based on each tumor subtype (Luminal A, Luminal B, HER2-enriched, triple-negative) was established. Ten models based on intratumoral or/plus peritumoral features from three different phases were developed for each differentiation.ResultsRadiomics features extracted from delayed phase DCE-MRI demonstrated dominant diagnostic performance over features from other phases. However, the differences were not statistically significant. In the full fusion model for differentiating different molecular subtypes, the most frequently screened features were those from the delayed phase. According to the Shapley additive explanation (SHAP) method, the most important features were also identified from the delayed phase.ConclusionsThe intratumoral and peritumoral radiomics features from the delayed phase of DCE-MRI can provide additional information for preoperative molecular typing. The delayed phase of DCE-MRI cannot be ignored.Critical relevance statementRadiomics features extracted and radiomics models constructed from the delayed phase of DCE-MRI played a crucial role in molecular subtype classification, although no significant difference was observed in the test cohort.Key PointsThe molecular subtype of breast cancer provides a basis for setting treatment strategy and prognosis.The delayed-phase radiomics model outperformed that of early-/peak-phases, but no differently than other phases or combinations.Both intra- and peritumoral radiomics features offer valuable insights for molecular typing.Graphical

Abstract PO1-07-07: Radiomics features for distinguishing true recurrence versus new primary tumor following breast-conserving treatment

Abstract Background Despite modern surgical and irradiation techniques, ipsilateral breast tumor recurrence (IBTR) accounts for 5-15% of all cancer recurrences in women treated with breast conservative treatment. Historically, the methods to define true recurrence (TR) and new primary tumor (NP) for IBTR mainly rely on clinical and pathological criteria, limiting the accuracy of the discerption and causing misclassification. This study aimed to develop a preoperative, noninvasive model for distinguishing IBTR by integrating clinicopathological review with paired dynamic contrast-enhanced breast magnetic resonance imaging (DCE-MRI) at diagnosis and following in-breast recurrence. MethodsWe retrospectively extracted radiomics features from MRI to develop a radiomic cohort of IBTR (n =46), among which all patients underwent paired preoperative DCE-MRI. This radiomic cohort was divided into a training cohort (n =27) and a validation cohort (n =19) with stratified random sampling. Classification of IBTR as TR or NP on the basis of tumor location, histologic subtype, estrogen receptor, and HER2 status was set as the gold standard. The least absolute shrinkage and selection operator (LASSO) regression and logistic regression were utilized to perform radiomics feature selection and model training, respectively. The clinical utility of the model was determined via decision curve analysis (DCA). Results We selected three radiomics features (first-order feature Kurtosis from the first postcontrast phase on IBTR DCE-MRI, GLCM feature Imc2 from the first postcontrast phase on IBTR DCE-MRI, and the delta feature Correlation from the precontrast phase of the change between IBTR and primary tumor DCE-MRI) to develop an IBTR-classification predicting radiomic model, which performed well in the validation cohort (AUC 0.867, 95% confidence interval (CI) 0.694-1). Further investigation for sensitivity (73.3%) and specificity (100%) verified a favorable concordance between the radiomic classification and the conventional standard, with a diagnostic accuracy of 79%. Conclusions: Our study demonstrated the feasibility of the radiomics model in predicting IBTR classification and provided preoperative information about the nature of “recurrence”. This might have important implications in surgical approaches and multidisciplinary care for IBTR. Further efforts are needed to improve the reproducibility of radiomics features and models in multiple centers. Citation Format: Feilin Qu, Guan-Hua Su, Jin-Hui Li, Chao You, Zhi-Ming Shao. Radiomics features for distinguishing true recurrence versus new primary tumor following breast-conserving treatment [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-07-07.

Simulation of time-intensity curve based on k-space filling in breast dynamic contrast-enhanced three-dimensional magnetic resonance imaging.

This study elucidated the effects of a three-dimensional k-space trajectory incorporating the partial Fourier (PF) technique on a time-intensity curve (TIC) in a dynamic contrast-enhanced magnetic resonance imaging of a typical malignant breast tumor using a digital phantom. Images were obtained from the Cancer Imaging Archive Open Data for Breast Cancer, and 1-min scans with high temporal resolution were analyzed. The order of the k-space trajectory was set as Linear (sequential), Low-High (centric), PF (62.5%; Z-, Y-, and both directions), and Low-High Radial. k0 (center of the k-space) timing and TIC shape were affected by the chosen k-space trajectory and implementation of the PF technique. A small TIC gradient was obtained using a Low-High Radial order. If the k-space filling method (particularly the radial method) produces a gentle TIC gradient, misinterpretation could arise during the assessment of tumor malignancy status.

Morfo-dinamske i funkcionalne karakteristike MRI dojki u proceni duktlanog karcinoma in situ i invazivnog duktalnog karcinoma kod postmenopauzalnih ispitanica

Introduction: Most frequent histologic types of breast cancer include invasive ductal carcinoma (IDC) and its most common precursor: ductal carcinoma in situ (DCIS). Based on morpho-dynamic and functional parameters: lesion size, initial signal intensity enhancement (wash-in), time-intensity curve (TIC) type, apparent diffusion coefficient (ADC), and positive enhancement integral (PEI), breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows the differentiation between IDC and in situ lesions in postmenopausal female patients. Methods: A single-center retrospective study included 40 postmenopausal female patients with histopathologically confirmed diagnosis (DCIS n1 =20; IDC n2 =20), examined with full diagnostic protocol (FDP) on 1.5T and 3T MRI scanners. The SPSS 21.0 software package was used for the statistical analysis of the defined parameters in two predefined subgroups. Results: Tumor size was significantly larger (p&lt;0.001) in patients with DCIS. The IDC group showed significantly higher wash-in and PEI values (p&lt;0.001). ADC was significantly higher (p&lt;0.001) in DCIS. There was a statistically significant difference (p&lt;0.05) in the TIC type distribution: TIC type 2 was predominant in patients with DCIS, while the TIC type 3 was predominant in patients with IDC. Conclusion: Based on predefined morpho-dynamic and functional parameters, breast MRI may allow the differentiation between the two types of breast ductal carcinoma: IDC and DCIS. However, histopathological confirmation remains the "golden standard" in differentiation, taking the nature of the disease into account.

Preoperative Dynamic Contrast-Enhanced and Diffusion-Weighted Breast Magnetic Resonance Imaging Findings for Prediction of Lymphovascular Invasion of the Lesions in Node-Negative Invasive Breast Cancer.

Purpose: Our single-centre retrospective study aimed to investigate the relationship between preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) findings and apparent diffusion coefficient (ADC) values and lymphovascular invasion (LVI) status of the lesions in patients with clinically-radiologically lymph node-negative invasive breast cancer. Methods: A total of 250 breast lesions diagnosed in preoperative magnetic resonance imaging were identified. All patients were divided into 2 subgroups: LVI-negative and LVI-positive according to the pathological findings of surgical specimens. The 2 groups' DCE-MRI findings, ADC values, and histopathological results of lesions were compared. Results: LVI was detected in 100 of 250 lesions. Younger age than 45 years and larger lesion size than 20 mm were found to be associated with the presence of LVI (P < .001). High histological and nuclear grade (P = .001), HER2-enriched molecular subtype (P = .001), and Ki-67 positivity (P = .016) were significantly associated with LVI. The LVI positivity rate was significantly higher in the lesions with medium-rapid initial phase kinetic curve and washout delayed phase kinetic curve (P = .001). The presence of LVI was significantly associated with the presence of peritumoural edema, sentinel lymph node metastasis, adjacent vessel sign, and increased whole breast vascularity (P < .001). When diffusion-weighted imaging findings were evaluated, it was determined that tumoural ADC values lower than 1068 × 10-6 mm2/second (P = .002) and peritumoural-tumoural ADC ratios higher than 1.5 (P = .001) statistically increased the probability of LVI. Conclusion: The patient's age, various histopathological and DCE-MRI findings, tumoural ADC value, and peritumoural-tumoural ADC ratio may be useful in the preoperative prediction of LVI status in breast cancer lesions.

Efficient estimation of pharmacokinetic parameters from breast dynamic contrast-enhanced MRI based on a convolutional neural network for predicting molecular subtypes

Objective. Tracer kinetic models allow for estimating pharmacokinetic (PK) parameters, which are related to pathological characteristics, from breast dynamic contrast-enhanced magnetic resonance imaging. However, existing tracer kinetic models subject to inaccuracy are time-consuming for PK parameters estimation. This study aimed to accurately and efficiently estimate PK parameters for predicting molecular subtypes based on convolutional neural network (CNN). Approach. A CNN integrating global and local features (GL-CNN) was trained using synthetic data where known PK parameters map was used as the ground truth, and subsequently used to directly estimate PK parameters (volume transfer constant K trans and flux rate constant K ep) map. The accuracy assessed by the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and concordance correlation coefficient (CCC) was compared between the GL-CNN and Tofts-based PK parameters in synthetic data. Radiomic features were calculated from the PK parameters map in 208 breast tumors. A random forest classifier was constructed to predict molecular subtypes using a discovery cohort (n = 144). The diagnostic performance evaluated on a validation cohort (n = 64) using the area under the receiver operating characteristic curve (AUC) was compared between the GL-CNN and Tofts-based PK parameters. Main results. The average PSNR (48.8884), SSIM (0.9995), and CCC (0.9995) between the GL-CNN-based K trans map and ground truth were significantly higher than those between the Tofts-based K trans map and ground truth. The GL-CNN-based K trans obtained significantly better diagnostic performance (AUCs = 0.7658 and 0.8528) than the Tofts-based K trans for luminal B and HER2 tumors. The GL-CNN method accelerated the computation by speed approximately 79 times compared to the Tofts method for the whole breast of all patients. Significance. Our results indicate that the GL-CNN method can be used to accurately and efficiently estimate PK parameters for predicting molecular subtypes.

Discrimination of benign and malignant breast lesions on dynamic contrast-enhanced magnetic resonance imaging using deep learning.

To evaluate the capability of deep transfer learning (DTL) and fine-tuning methods in differentiating malignant from benign lesions in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). The diagnostic efficiencies of the VGG19, ResNet50, and DenseNet201 models were tested under the same dataset. The model with the highest performance was selected and modified utilizing three fine-tuning strategies (S1-3). Fifty additional lesions were selected to form the validation set to verify the generalization abilities of these models. The accuracy (Ac) of the different models in the training and test sets, as well as the precision (Pr), recall rate (Rc), F1 score (), and area under the receiver operating characteristic curve (AUC), were primary performance indicators. Finally, the kappa test was used to compare the degree of agreement between the DTL models and pathological diagnosis in differentiating malignant from benign breast lesions. The Pr, Rc, f1, and AUC of VGG19 (86.0%, 0.81, 0.81, and 0.81, respectively) were higher than those of DenseNet201 (70.0%, 0.61, 0.63, and 0.61, respectively) and ResNet50 (61.0%, 0.59, 0.59, and 0.59). After fine-tuning, the Pr, Rc, f1, and AUC of S1 (87.0%, 0.86, 0.86, and 0.86, respectively) were higher than those of VGG19. Notably, the degree of agreement between S1 and pathological diagnosis in differentiating malignant from benign breast lesions was 0.720 (κ = 0.720), which was higher than that of DenseNet201 (κ = 0.440), VGG19 (κ = 0.640), and ResNet50 (κ = 0.280). The VGG19 model is an effective method for identifying benign and malignant breast lesions on DCE-MRI, and its performance can be further improved via fine-tuning. Overall, our findings insinuate that this technique holds potential clinical application value.

U-Net breast lesion segmentations for breast dynamic contrast-enhanced magnetic resonance imaging.

Given the dependence of radiomic-based computer-aided diagnosis artificial intelligence on accurate lesion segmentation, we assessed the performances of 2D and 3D U-Nets in breast lesion segmentation on dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) relative to fuzzy c-means (FCM) and radiologist segmentations. Using 994 unique breast lesions imaged with DCE-MRI, three segmentation algorithms (FCM clustering, 2D and 3D U-Net convolutional neural networks) were investigated. Center slice segmentations produced by FCM, 2D U-Net, and 3D U-Net were evaluated using radiologist segmentations as truth, and volumetric segmentations produced by 2D U-Net slices and 3D U-Net were compared using FCM as a surrogate reference standard. Fivefold cross-validation by lesion was conducted on the U-Nets; Dice similarity coefficient (DSC) and Hausdorff distance (HD) served as performance metrics. Segmentation performances were compared across different input image and lesion types. 2D U-Net outperformed 3D U-Net for center slice (DSC, HD ) and volume segmentations (DSC, HD ). 2D U-Net outperformed FCM in center slice segmentation (DSC ). The use of second postcontrast subtraction images showed greater performance than first postcontrast subtraction images using the 2D and 3D U-Net (DSC ). Additionally, mass segmentation outperformed nonmass segmentation from first and second postcontrast subtraction images using 2D and 3D U-Nets (DSC, HD ). Results suggest that 2D U-Net is promising in segmenting mass and nonmass enhancing breast lesions from first and second postcontrast subtraction MRIs and thus could be an effective alternative to FCM or 3D U-Net.

Quantitative evaluation of Kaiser score in diagnosing breast dynamic contrast-enhanced magnetic resonance imaging for patients with high-grade background parenchymal enhancement.

High-grade background parenchymal enhancement (BPE), including moderate and marked, poses a considerable challenge for the diagnosis of breast disease due to its tendency to increase the rate of false positives and false negatives. The purpose of our study was to explore whether the Kaiser score can be used for more accurate assessment of benign and malignant lesions in high-grade BPE compared with the Breast Imaging Reporting and Data System (BI-RADS). A retrospective review was conducted on consecutive breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) scans from 2 medical centers. Included were patients who underwent DCE-MRI demonstrating high-grade BPE and who had a pathology-confirmed diagnosis. Excluded were patients who had received neoadjuvant chemotherapy or who had undergone biopsy prior to MRI examination. Two physicians with more than 7 years of experience specializing in breast imaging diagnosis jointly reviewed breast magnetic resonance (MR) images. The Kaiser score was used to determine the sensitivity, specificity, and positive predictive value (PPV), and negative predictive value (NPV) of the BI-RADS from different BPE groups and different enhancement types. The performance of the Kaiser score and BI-RADS were compared according to diagnostic accuracy. A total of 126 cases of high-grade BPE from 2 medical centers were included in this study. The Kaiser score had a higher specificity and PPV than did the BI-RADS (87.5% vs. 46.3%) as well as a higher PPV (94.3% vs. 79.8%). The value of diagnostic accuracy and 95% confidence interval (CI) for the Kaiser score (accuracy 0.928; 95% CI: 0.883-0.973) was larger than that for BI-RADS (accuracy 0.810; 95% CI: 0.741-0.879). Moreover, the Kaiser score had a significantly higher value of diagnostic accuracy for both mass and non-mass enhancement, especially mass lesions (Kaiser score: accuracy 0.947, 95% CI: 0.902-0.992; BI-RADS: accuracy 0.821, 95% CI: 0.782-0.860), with a P value of 0.006. The Kaiser score is a useful diagnostic tool for the evaluation of high-grade BPE lesions, with a higher specificity, PPV, and diagnostic accuracy as compared to the BI-RADS.

Breast Tumor Segmentation in DCE-MRI With Tumor Sensitive Synthesis.

Segmenting breast tumors from dynamic contrast-enhanced magnetic resonance (DCE-MR) images is a critical step for early detection and diagnosis of breast cancer. However, variable shapes and sizes of breast tumors, as well as inhomogeneous background, make it challenging to accurately segment tumors in DCE-MR images. Therefore, in this article, we propose a novel tumor-sensitive synthesis module and demonstrate its usage after being integrated with tumor segmentation. To suppress false-positive segmentation with similar contrast enhancement characteristics to true breast tumors, our tumor-sensitive synthesis module can feedback differential loss of the true and false breast tumors. Thus, by following the tumor-sensitive synthesis module after the segmentation predictions, the false breast tumors with similar contrast enhancement characteristics to the true ones will be effectively reduced in the learned segmentation model. Moreover, the synthesis module also helps improve the boundary accuracy while inaccurate predictions near the boundary will lead to higher loss. For the evaluation, we build a very large-scale breast DCE-MR image dataset with 422 subjects from different patients, and conduct comprehensive experiments and comparisons with other algorithms to justify the effectiveness, adaptability, and robustness of our proposed method.

A quantitative heterogeneity analysis approach to molecular subtype recognition of breast cancer in dynamic contrast-enhanced magnetic imaging images from radiomics data.

Breast cancer is a major cause of mortality among women worldwide. Dynamic contrast-enhanced breast magnetic resonance imaging (DCE-MRI) is a good imaging technique that can show temporal information about the kinetics of the contrast agent in suspicious breast lesions as well as acceptable spatial resolution. Computer-aided detection systems assist in the detection of lesions through medical image processing techniques combined with computerized analysis and calculation, which in turn helps radiologists recognize molecular subtypes of breast lesions that will be beneficial for better treatment plan decisions. In this paper, a computer-aided diagnosis method is proposed to automatically locate breast cancer lesions and identify molecular subtypes of breast cancer with heterogeneity analysis from radiomics data. A fast region-based convolutional network (Faster R-CNN) framework is first applied to images to detect breast cancer lesions. Then, the heterogeneous regions of every breast cancer lesion are extracted. Based on the multiple visual and kinetic radiomics features extracted from the heterogeneous regions, a temporal bag of visual word model is proposed, which takes into account the dynamic characteristics of both lesion and heterogeneous regions in images over time. The recognition task of molecular subtypes of breast lesions is realized based on a stacking classification model. At the genetic level, breast cancer is divided into four molecular subtypes, namely, luminal epithelial type A (Luminal A), luminal epithelial type B (Luminal B), HER-2 overexpression and basal cell type. The experimental results show that the precision of the four subtypes is 93%, 94%, 83%, 86%; the recall is 96%, 80%, 91%, 94%; and the F1-score is 95%, 86%, 87%. The experimental results denote the influence of heterogeneous regions on the recognition task. The DCE-MRI-based approach to identify molecular typing of breast cancer for noninvasive diagnosis will contribute to the development of breast cancer treatment, improved outcomes and reduced mortality.

Can Supine Breast Magnetic Resonance Imaging After a Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging Provide Information for Supine Procedures?

A retrospective analysis was conducted on 75 lesions in 50 patients with pathologically proven breast cancer who underwent MRI in prone and supine positions between December 2019 and December 2020. The transverse, anteroposterior, and craniocaudal dimensions (in millimeters) of the tumor in the x -, y -, and z -axes were measured. Distances from the center of the tumor to the chest wall and the adjacent skin were measured on transverse and reformatted sagittal images. In cases where multifocal lesions were present, the transverse, anteroposterior, and craniocaudal distances between the tumor centers in the x -, y -, and z -axes were measured. Differences between measurements in supine and prone MRI were evaluated with the Mann-Whitney U and the Wilcoxon tests. P values of less than 0.05 were considered to indicate a statistically significant difference. The analysis revealed 31 MRIs with 1 and 20 with multifocal lesions. The x -axis dimension of the lesions in prone and supine positions did not significantly differ ( P = 0.198) between the 2 positions. A significant difference in the y - and z -axes dimensions was observed between the prone and supine position ( P = 0.00 for both). The distance from the tumor to the chest wall and the adjacent skin showed significant difference ( P = 0.00 for both). For multifocal lesions, the distance between the lesions showed a significant difference on the y -axis ( P = 0.00). This study showed a significant difference in the tumor size, location, and tumor-to-tumor distances due to change of patient position, from the standard prone MRI to the supine position in the operating room, resulting in distortion, spatial repositioning, and convergence of the lesions. Supine MRI may be considered in providing a less extensive surgery.

Classification of Breast Lesions on DCE-MRI Data Using a Fine-Tuned MobileNet

It is crucial to diagnose breast cancer early and accurately to optimize treatment. Presently, most deep learning models used for breast cancer detection cannot be used on mobile phones or low-power devices. This study intended to evaluate the capabilities of MobileNetV1 and MobileNetV2 and their fine-tuned models to differentiate malignant lesions from benign lesions in breast dynamic contrast-enhanced magnetic resonance images (DCE-MRI).

Tumor-Attentive Segmentation-Guided GAN for Synthesizing Breast Contrast-Enhanced MRI Without Contrast Agents.

Breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a sensitive imaging technique critical for breast cancer diagnosis. However, the administration of contrast agents poses a potential risk. This can be avoided if contrast-enhanced MRI can be obtained without using contrast agents. Thus, we aimed to generate T1-weighted contrast-enhanced MRI (ceT1) images from pre-contrast T1 weighted MRI (preT1) images in the breast. We proposed a generative adversarial network to synthesize ceT1 from preT1 breast images that adopted a local discriminator and segmentation task network to focus specifically on the tumor region in addition to the whole breast. The segmentation network performed a related task of segmentation of the tumor region, which allowed important tumor-related information to be enhanced. In addition, edge maps were included to provide explicit shape and structural information. Our approach was evaluated and compared with other methods in the local (n = 306) and external validation (n = 140) cohorts. Four evaluation metrics of normalized mean squared error (NRMSE), Pearson cross-correlation coefficients (CC), peak signal-to-noise ratio (PSNR), and structural similarity index map (SSIM) for the whole breast and tumor region were measured. An ablation study was performed to evaluate the incremental benefits of various components in our approach. Our approach performed the best with an NRMSE 25.65, PSNR 54.80 dB, SSIM 0.91, and CC 0.88 on average, in the local test set. Performance gains were replicated in the validation cohort. We hope that our method will help patients avoid potentially harmful contrast agents. Clinical and Translational Impact Statement-Contrast agents are necessary to obtain DCE-MRI which is essential in breast cancer diagnosis. However, administration of contrast agents may cause side effects such as nephrogenic systemic fibrosis and risk of toxic residue deposits. Our approach can generate DCE-MRI without contrast agents using a generative deep neural network. Thus, our approach could help patients avoid potentially harmful contrast agents resulting in an improved diagnosis and treatment workflow for breast cancer.

Radiomics of dynamic contrast-enhanced magnetic resonance imaging parametric maps and apparent diffusion coefficient maps to predict Ki-67 status in breast cancer.

This study was aimed at evaluating whether a radiomics model based on the entire tumor region from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parametric maps and apparent diffusion coefficient (ADC) maps could indicate the Ki-67 status of patients with breast cancer. This retrospective study enrolled 205 women with breast cancer who underwent clinicopathological examination. Among them, 93 (45%) had a low Ki-67 amplification index (Ki-67 positivity< 14%), and 112 (55%) had a high Ki-67 amplification index (Ki-67 positivity ≥ 14%). Radiomics features were extracted from three DCE-MRI parametric maps and ADC maps calculated from two different b values of diffusion-weighted imaging sequences. The patients were randomly divided into a training set (70% of patients) and a validation set (30% of patients). After feature selection, we trained six support vector machine classifiers by combining different parameter maps and used 10-fold cross-validation to predict the expression level of Ki-67. The performance of six classifiers was evaluated with receiver operating characteristic (ROC) analysis, sensitivity, and specificity in both cohorts. Among the six classifiers constructed, a radiomics feature set combining three DCE-MRI parametric maps and ADC maps yielded an area under the ROC curve (AUC) of 0.839 (95% confidence interval [CI], 0.768-0.895) within the training set and 0.795 (95% CI, 0.674-0.887) within the independent validation set. Additionally, the AUC value, compared with that for a single parameter map, was moderately increased by combining features from the three parametric maps. Radiomics features derived from the DCE-MRI parametric maps and ADC maps have the potential to serve as imaging biomarkers to determine Ki-67 status in patients with breast cancer.

Differentiation of breast lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using deep transfer learning based on DenseNet201.

In order to achieve better performance, artificial intelligence is used in breast cancer diagnosis. In this study, we evaluated the efficacy of different fine-tuning strategies of deep transfer learning (DTL) based on the DenseNet201 model to differentiate malignant from benign lesions on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). We collected 4260 images of benign lesions and 4140 images of malignant lesions of the breast pertaining to pathologically confirmed cases. The benign and malignant groups was randomly divided into a training set and a testing set at a ratio of 9:1. A DTL model based on the DenseNet201 model was established, and the effectiveness of 4 fine-tuning strategies (S0: strategy 0, S1: strategy; S2: strategy; and S3: strategy) was compared. Additionally, DCE-MRI images of 48 breast lesions were selected to verify the robustness of the model. Ten images were obtained for each lesion. The classification was considered correct if more than 5 images were correctly classified. The metrics for model performance evaluation included accuracy (Ac) in the training and testing sets, precision (Pr), recall rate (Rc), f1 score (f1), and area under the receiver operating characteristic curve (AUROC) in the validation set. The Ac of the 4 fine-tuning strategies reached 100.00% in the training set. The S2 strategy exhibited good convergence in the testing set. The Ac of S2 was 98.01% in the testing set, which was higher than those of S0 (93.10%), S1 (90.45%), and S3 (93.90%). The average classification Pr, Rc, f1, and AUROC of S2 in the validation set were (89.00%, 80.00%, 0.81, and 0.79, respectively) higher than those of S0 (76.00%, 67.00%, 0.69, and 0.65, respectively), S1 (60.00%, 60.00%, 0.60, 0.66, and respectively), and S3 (77.00%, 73.00%, 0.74, 0.72, respectively). The degree of coincidence between S2 and the histopathological method for differentiating between benign and malignant breast lesions was high (κ = 0.749). The S2 strategy can improve the robustness of the DenseNet201 model in relatively small breast DCE-MRI datasets, and this is a reliable method to increase the Ac of discriminating benign from malignant breast lesions on DCE-MRI.

Prediction of the histologic upgrade of ductal carcinoma in situ using a combined radiomics and machine learning approach based on breast dynamic contrast-enhanced magnetic resonance imaging.

To investigate whether support vector machine (SVM) trained with radiomics features based on breast magnetic resonance imaging (MRI) could predict the upgrade of ductal carcinoma in situ (DCIS) diagnosed by core needle biopsy (CNB) after surgical excision. This retrospective study included a total of 349 lesions from 346 female patients (mean age, 54 years) diagnosed with DCIS by CNB between January 2011 and December 2017. Based on histological confirmation after surgery, the patients were divided into pure (n = 198, 56.7%) and upgraded DCIS (n = 151, 43.3%). The entire dataset was randomly split to training (80%) and test sets (20%). Radiomics features were extracted from the intratumor region-of-interest, which was semi-automatically drawn by two radiologists, based on the first subtraction images from dynamic contrast-enhanced T1-weighted MRI. A least absolute shrinkage and selection operator (LASSO) was used for feature selection. A 4-fold cross validation was applied to the training set to determine the combination of features used to train SVM for classification between pure and upgraded DCIS. Sensitivity, specificity, accuracy, and area under the receiver-operating characteristic curve (AUC) were calculated to evaluate the model performance using the hold-out test set. The model trained with 9 features (Energy, Skewness, Surface Area to Volume ratio, Gray Level Non Uniformity, Kurtosis, Dependence Variance, Maximum 2D diameter Column, Sphericity, and Large Area Emphasis) demonstrated the highest 4-fold mean validation accuracy and AUC of 0.724 (95% CI, 0.619-0.829) and 0.742 (0.623-0.860), respectively. Sensitivity, specificity, accuracy, and AUC using the test set were 0.733 (0.575-0.892) and 0.7 (0.558-0.842), 0.714 (0.608-0.820) and 0.767 (0.651-0.882), respectively. Our study suggested that the combined radiomics and machine learning approach based on preoperative breast MRI may provide an assisting tool to predict the histologic upgrade of DCIS.

Impact of continuous learning on diagnostic breast MRI AI: evaluation on an independent clinical dataset.

Purpose: We demonstrate continuous learning and assess its impact on the performance of artificial intelligence of breast dynamic contrast-enhanced magnetic resonance imaging in the task of distinguishing malignant from benign lesions on an independent clinical test dataset. Approach: The study included 1979 patients with 1990 lesions who underwent breast MR imaging during 2015, 2016, and 2017, retrospectively collected under an IRB-approved protocol; there were 1494 malignant and 496 benign lesions based on histopathology. AI was conducted in the task of distinguishing malignant and benign lesions, and independent testing was performed to assess the effect of increasing the numbers of training cases. Five training sets mimicking clinical implementation of continuous AI learning included cases from (1)first quarter of 2015, (2)first half of 2015, (3)all 2015, (4)all 2015 and first half of 2016, and (5)all 2015 and 2016. All classifiers were evaluated on the 2017 independent test set. The area under the ROC curve (AUC) served as the performance metric and was calculated over all lesions in the test set, as well as only mass lesions and only non-mass enhancements. The Mann-Kendall test was used to determine if continuous learning resulted in a positive trend in classification performance. was considered to be statistically significant. Results: Over the continuous training period, the selected feature subsets tended to become more similar and stable. Performance of the five training conditions on the independent test dataset yielded AUCs of 0.86 (95% CI: [0.83,0.90]), 0.87 (95% CI: [0.83,0.90]), 0.88 (95% CI: [0.84,0.91]), 0.89 (95% CI: [0.85,0.92]), and 0.89 (95% CI: [0.86,0.92]). The Mann-Kendall test indicated a statistically significant positive trend ( ) in classification performance with continuous learning. Conclusions: Improved diagnostic performance over time was observed when continuous learning of AI was implemented on an independent clinical test dataset.

Post-Processing Bias Field Inhomogeneity Correction for Assessing Background Parenchymal Enhancement on Breast MRI as a Quantitative Marker of Treatment Response.

Background parenchymal enhancement (BPE) of breast fibroglandular tissue (FGT) in dynamic contrast-enhanced breast magnetic resonance imaging (MRI) has shown an association with response to neoadjuvant chemotherapy (NAC) in patients with breast cancer. Fully automated segmentation of FGT for BPE calculation is a challenge when image artifacts are present. Low spatial frequency intensity nonuniformity due to coil sensitivity variations is known as bias or inhomogeneity and can affect FGT segmentation and subsequent BPE measurement. In this study, we utilized the N4ITK algorithm for bias correction over a restricted bilateral breast volume and compared the contralateral FGT segmentations based on uncorrected and bias-corrected images in three MRI examinations at pre-treatment, early treatment and inter-regimen timepoints during NAC. A retrospective analysis of 2 cohorts was performed: one with 735 patients enrolled in the multi-center I-SPY 2 TRIAL and the sub-cohort of 340 patients meeting a high-quality benchmark for segmentation. Bias correction substantially increased the FGT segmentation quality for 6.3–8.0% of examinations, while it substantially decreased the quality for no examination. Our results showed improvement in segmentation quality and a small but statistically significant increase in the resulting BPE measurement after bias correction at all timepoints in both cohorts. Continuing studies are examining the effects on pCR prediction.