Automated detection of breast cancer in false-negative screening MRI studies from women at increased risk

Early Detection of Breast Cancer in MRI Using AI

RATIONALE AND OBJECTIVES

To develop and evaluate an AI algorithm that detects breast cancer in MRI scans up to one year before radiologists typically identify it, potentially enhancing early detection in high-risk women.

MATERIALS AND METHODS

A convolutional neural network (CNN) AI model, pre-trained on breast MRI data, was fine-tuned using a retrospective dataset of 3029 MRI scans from 910 patients. These contained 115 cancers that were diagnosed within one year of a negative MRI. The model aimed to identify these cancers, with the goal of predicting cancer development up to one year in advance. The network was fine-tuned and tested with 10-fold cross-validation. Mean age of patients was 52 years (range, 18-88 years), with average follow-up of 4.3 years (range 1-12 years).

RESULTS

The AI detected cancers one year earlier with an area under the ROC curve of 0.72 (0.67-0.76). Retrospective analysis by a radiologist of the top 10% highest risk MRIs as ranked by the AI could have increased early detection by up to 30%. (35/115, CI:22.2-39.7%, 30% sensitivity). A radiologist identified a visual correlate to biopsy-proven cancers in 83 of prior-year MRIs (83/115, CI: 62.1-79.4%). The AI algorithm identified the anatomic region where cancer would be detected in 66 cases (66/115, CI:47.8-66.5%); with both agreeing in 54 cases (54/115, CI:%37.5-56.4%).

CONCLUSION

This novel AI-aided re-evaluation of "benign" breasts shows promise for improving early breast cancer detection with MRI. As datasets grow and image quality improves, this approach is expected to become even more impactful.

'Earlier than Early' Detection of Breast Cancer in Israeli BRCA Mutation Carriers Applying AI-Based Analysis to Consecutive MRI Scans

Female BRCA1/BRCA2 (=BRCA) pathogenic variants (PVs) carriers are at a substantially higher risk for developing breast cancer (BC) compared with the average risk population. Detection of BC at an early stage significantly improves prognosis. To facilitate early BC detection, a surveillance scheme is offered to BRCA PV carriers from age 25-30 years that includes annual MRI based breast imaging. Indeed, adherence to the recommended scheme has been shown to be associated with earlier disease stages at BC diagnosis, more in-situ pathology, smaller tumors, and less axillary involvement. While MRI is the most sensitive modality for BC detection in BRCA PV carriers, there are a significant number of overlooked or misinterpreted radiological lesions (mostly enhancing foci), leading to a delayed BC diagnosis at a more advanced stage. In this study we developed an artificial intelligence (AI)-network, aimed at a more accurate classification of enhancing foci, in MRIs of BRCA PV carriers, thus reducing false-negative interpretations. Retrospectively identified foci in prior MRIs that were either diagnosed as BC or benign/normal in a subsequent MRI were manually segmented and served as input for a convolutional network architecture. The model was successful in classification of 65% of the cancerous foci, most of them triple-negative BC. If validated, applying this scheme routinely may facilitate 'earlier than early' BC diagnosis in BRCA PV carriers.

Automatic Detection and Segmentation of Breast Cancer on MRI Using Mask R-CNN Trained on Non-Fat-Sat Images and Tested on Fat-Sat Images

RATIONALE AND OBJECTIVES

Computer-aided methods have been widely applied to diagnose lesions on breast magnetic resonance imaging (MRI). The first step was to identify abnormal areas. A deep learning Mask Regional Convolutional Neural Network (R-CNN) was implemented to search the entire set of images and detect suspicious lesions.

MATERIALS AND METHODS

Two DCE-MRI datasets were used, 241 patients acquired using non-fat-sat sequence for training, and 98 patients acquired using fat-sat sequence for testing. All patients have confirmed unilateral mass cancers. The tumor was segmented using fuzzy c-means clustering algorithm to serve as the ground truth. Mask R-CNN was implemented with ResNet-101 as the backbone. The neural network output the bounding boxes and the segmented tumor for evaluation using the Dice Similarity Coefficient (DSC). The detection performance, and the trade-off between sensitivity and specificity, was analyzed using free response receiver operating characteristic.

RESULTS

When the precontrast and subtraction image of both breasts were used as input, the false positive from the heart and normal parenchymal enhancements could be minimized. The training set had 1469 positive slices (containing lesion) and 9135 negative slices. In 10-fold cross-validation, the mean accuracy = 0.86 and DSC = 0.82. The testing dataset had 1568 positive and 7264 negative slices, with accuracy = 0.75 and DSC = 0.79. When the obtained per-slice results were combined, 240 of 241 (99.5%) lesions in the training and 98 of 98 (100%) lesions in the testing datasets were identified.

CONCLUSION

Deep learning using Mask R-CNN provided a feasible method to search breast MRI, localize, and segment lesions. This may be integrated with other artificial intelligence algorithms to develop a fully automatic breast MRI diagnostic system.

Automatic breast lesion detection in ultrafast DCE-MRI using deep learning

PURPOSE

We propose a deep learning-based computer-aided detection (CADe) method to detect breast lesions in ultrafast DCE-MRI sequences. This method uses both the 3D spatial information and temporal information obtained from the early-phase of the dynamic acquisition.

METHODS

The proposed CADe method, based on a modified 3D RetinaNet model, operates on ultrafast T1 weighted sequences, which are preprocessed for motion compensation, temporal normalization, and are cropped before passing into the model. The model is optimized to enable the detection of relatively small breast lesions in a screening setting, focusing on detection of lesions that are harder to differentiate from confounding structures inside the breast.

RESULTS

The method was developed based on a dataset consisting of 489 ultrafast MRI studies obtained from 462 patients containing a total of 572 lesions (365 malignant, 207 benign) and achieved a detection rate, sensitivity, and detection rate of benign lesions of 0.90 (0.876-0.934), 0.95 (0.934-0.980), and 0.81 (0.751-0.871) at four false positives per normal breast with 10-fold cross-testing, respectively.

CONCLUSIONS

The deep learning architecture used for the proposed CADe application can efficiently detect benign and malignant lesions on ultrafast DCE-MRI. Furthermore, utilizing the less visible hard-to-detect lesions in training improves the learning process and, subsequently, detection of malignant breast lesions.

Texture Analysis of DCE-MRI Intratumoral Subregions to Identify Benign and Malignant Breast Tumors

Purpose

To evaluate the potential of the texture features extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) intratumoral subregions to distinguish benign from malignant breast tumors.

Materials and Methods

A total of 299 patients with pathologically verified breast tumors who underwent breast DCE-MRI examination were enrolled in this study, including 124 benign cases and 175 malignant cases. The whole tumor area was semi-automatically segmented on the basis of subtraction images of DCE-MRI in Matlab 2018b. According to the time to peak of the contrast agent, the whole tumor area was partitioned into three subregions: early, moderate, and late. A total of 467 texture features were extracted from the whole tumor area and the three subregions, respectively. Patients were divided into training (n = 209) and validation (n = 90) cohorts by different MRI scanners. The least absolute shrinkage and selection operator (LASSO) method was used to select the optimal feature subset in the training cohort. The Kolmogorov-Smirnov test was first performed on texture features selected by LASSO to test whether the samples followed a normal distribution. Two machine learning methods, decision tree (DT) and support vector machine (SVM), were used to establish classification models with a 10-fold cross-validation method. The performance of the classification models was evaluated with receiver operating characteristic (ROC) curves.

Results

In the training cohort, the areas under the ROC curve (AUCs) for the DT_Whole model and SVM_Whole model were 0.744 and 0.806, respectively. In contrast, the AUCs of the DT_Early model (P = 0.004), DT_Late model (P = 0.015), SVM_Early model (P = 0.002), and SVM_Late model (P = 0.002) were significantly higher: 0.863 (95% CI, 0.808-0.906), 0.860 (95% CI, 0.806-0.904), 0.934 (95% CI, 0.891-0.963), and 0.921 (95% CI, 0.876-0.954), respectively. The SVM_Early model and SVM_Late model achieved better performance than the DT_Early model and DT_Late model (P = 0.003, 0.034, 0.008, and 0.026, respectively). In the validation cohort, the AUCs for the DT_Whole model and SVM_Whole model were 0.670 and 0.708, respectively. In comparison, the AUCs of the DT_Early model (P = 0.006), DT_Late model (P = 0.043), SVM_Early model (P = 0.001), and SVM_Late model (P = 0.007) were significantly higher: 0.839 (95% CI, 0.747-0.908), 0.784 (95% CI, 0.601-0.798), 0.890 (95% CI, 0.806-0.946), and 0.865 (95% CI, 0.777-0.928), respectively.

Conclusion

The texture features from intratumoral subregions of breast DCE-MRI showed potential in identifying benign and malignant breast tumors.

Using Deep Learning to Improve Nonsystematic Viewing of Breast Cancer on MRI

OBJECTIVE

To investigate the feasibility of using deep learning to identify tumor-containing axial slices on breast MRI images.

METHODS

This IRB-approved retrospective study included consecutive patients with operable invasive breast cancer undergoing pretreatment breast MRI between January 1, 2014, and December 31, 2017. Axial tumor-containing slices from the first postcontrast phase were extracted. Each axial image was subdivided into two subimages: one of the ipsilateral cancer-containing breast and one of the contralateral healthy breast. Cases were randomly divided into training, validation, and testing sets. A convolutional neural network was trained to classify subimages into "cancer" and "no cancer" categories. Accuracy, sensitivity, and specificity of the classification system were determined using pathology as the reference standard. A two-reader study was performed to measure the time savings of the deep learning algorithm using descriptive statistics.

RESULTS

Two hundred and seventy-three patients with unilateral breast cancer met study criteria. On the held-out test set, accuracy of the deep learning system for tumor detection was 92.8% (648/706; 95% confidence interval: 89.7%-93.8%). Sensitivity and specificity were 89.5% and 94.3%, respectively. Readers spent 3 to 45 seconds to scroll to the tumor-containing slices without use of the deep learning algorithm.

CONCLUSION

In breast MR exams containing breast cancer, deep learning can be used to identify the tumor-containing slices. This technology may be integrated into the picture archiving and communication system to bypass scrolling when viewing stacked images, which can be helpful during nonsystematic image viewing, such as during interdisciplinary tumor board meetings.

Breast MRI: False-Negative Results and Missed Opportunities

Breast MRI is the most sensitive modality for the detection of breast cancer. However, false-negative cases may occur, in which the cancer is not visualized at MRI and is instead diagnosed with another imaging modality. The authors describe the causes of false-negative breast MRI results, which can be categorized broadly as secondary to perceptual errors or cognitive errors, or nonvisualization secondary to nonenhancement of the tumor. Tips and strategies to avoid these errors are discussed. Perceptual errors occur when an abnormality is not prospectively identified, yet the examination is technically adequate. Careful development of thorough search patterns is critical to avoid these errors. Cognitive errors occur when an abnormality is identified but misinterpreted or mischaracterized as benign. The radiologist may avoid these errors by utilizing all available prior examinations for comparison, viewing images in all planes to better assess the margins and shapes of abnormalities, and appropriately integrating all available information from the contrast-enhanced, T2-weighted, and T1-weighted images as well as the clinical history. Despite this, false-negative cases are inevitable, as certain subtypes of breast cancer, including ductal carcinoma in situ, invasive lobular carcinoma, and certain well-differentiated invasive cancers, may demonstrate little to no enhancement at MRI, owing to differences in angiogenesis and neovascularity. MRI is a valuable diagnostic tool in breast imaging. However, MRI should continue to be used as a complementary modality, with mammography and US, in the detection of breast cancer. ^©RSNA, 2021.

Recognition of Heterogeneous Edges in Multiwavelength Transmission Images Based on the Weighted Constraint Decision Method

Multiwavelength light transmission imaging provides a possibility for early detection of breast cancer. However, due to strong scattering during the transmission process of breast tissue analysis, the transmitted image signal is weak and the image is blurred and this makes heterogeneous edge detection difficult. This paper proposes a method based on the weighted constraint decision (WCD) method to eliminate the erosion and checkerboard effects in image histogram equalization (HE) enhancement and to improve the recognition of heterogeneous edge. Multiwavelength transmission images of phantom are acquired on the designed experimental system and the mask image with high signal-to-noise ratio (SNR) is obtained by frame accumulation and an Otsu thresholding model. Then, during image enhancement the image is divided into low-gray-level (LGL) and high-gray-level (HGL) regions according to the distribution of light intensity in image. And the probability density distribution of gray level in the LGL and HGL regions are redefined respectively according to the WCD method. Finally, the reconstructed image is obtained based on the modified HE. The experimental results show that compared with traditional image enhancement methods, the WCD method proposed in this paper can greatly improve the contrast between heterogeneous region and normal region. Moreover, the correlation between the original image data is maintained to the greatest extent, so that the edge of the heterogeneity can be detected more accurately. In conclusion, the WCD method not only accurately identifies the edge of heterogeneity in multiwavelength transmission images, but it also could improve the clinical application of multiwavelength transmission images in the early detection of breast cancer.

Screening in patients with increased risk of breast cancer (part 1): pros and cons of MRI screening

Screening plays an important role in women with a high risk of breast cancer. Given this population's high incidence of breast cancer and younger age of onset compared to the general population, it is recommended that screening starts earlier. There is ample evidence that magnetic resonance imaging (MRI) is the most sensitive diagnostic tool, and American and the European guidelines both recommend annual MRI screening (with supplementary annual mammography) as the optimum screening modality. Nevertheless, the current guidelines do not totally agree about the recommendations for MRI screening in some subgroups of patients. The first part of this article on screening in women with increased risk of breast cancer reviews the literature to explain and evaluate the advantages of MRI screening compared to screening with mammography alone: increased detection of smaller cancers with less associated lymph node involvement and a reduction in the rate of interval cancers, which can have an impact on survival and mortality (with comparable effects to other preventative measures). At the same time, however, we would like to reflect on the drawbacks of MRI screening that affect its applicability.

Artificial intelligence in the interpretation of breast cancer on MRI

Advances in both imaging and computers have led to the rise in the potential use of artificial intelligence (AI) in various tasks in breast imaging, going beyond the current use in computer-aided detection to include diagnosis, prognosis, response to therapy, and risk assessment. The automated capabilities of AI offer the potential to enhance the diagnostic expertise of clinicians, including accurate demarcation of tumor volume, extraction of characteristic cancer phenotypes, translation of tumoral phenotype features to clinical genotype implications, and risk prediction. The combination of image-specific findings with the underlying genomic, pathologic, and clinical features is becoming of increasing value in breast cancer. The concurrent emergence of newer imaging techniques has provided radiologists with greater diagnostic tools and image datasets to analyze and interpret. Integrating an AI-based workflow within breast imaging enables the integration of multiple data streams into powerful multidisciplinary applications that may lead the path to personalized patient-specific medicine. In this article we describe the goals of AI in breast cancer imaging, in particular MRI, and review the literature as it relates to the current application, potential, and limitations in breast cancer. Level of Evidence: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2020;51:1310-1324.

Multireader Study on the Diagnostic Accuracy of Ultrafast Breast Magnetic Resonance Imaging for Breast Cancer Screening

OBJECTIVES

Breast cancer screening using magnetic resonance imaging (MRI) has limited accessibility due to high costs of breast MRI. Ultrafast dynamic contrast-enhanced breast MRI can be acquired within 2 minutes. We aimed to assess whether screening performance of breast radiologist using an ultrafast breast MRI-only screening protocol is as good as performance using a full multiparametric diagnostic MRI protocol (FDP).

MATERIALS AND METHODS

The institutional review board approved this study, and waived the need for informed consent. Between January 2012 and June 2014, 1791 consecutive breast cancer screening examinations from 954 women with a lifetime risk of more than 20% were prospectively collected. All women were scanned using a 3 T protocol interleaving ultrafast breast MRI acquisitions in a full multiparametric diagnostic MRI protocol consisting of standard dynamic contrast-enhanced sequences, diffusion-weighted imaging, and T2-weighted imaging. Subsequently, a case set was created including all biopsied screen-detected lesions in this period (31 malignant and 54 benign) and 116 randomly selected normal cases with more than 2 years of follow-up. Prior examinations were included when available. Seven dedicated breast radiologists read all 201 examinations and 153 available priors once using the FDP and once using ultrafast breast MRI only in 2 counterbalanced and crossed-over reading sessions.

RESULTS

For reading the FDP versus ultrafast breast MRI alone, sensitivity was 0.86 (95% confidence interval [CI], 0.81-0.90) versus 0.84 (95% CI, 0.78-0.88) (P = 0.50), specificity was 0.76 (95% CI, 0.74-0.79) versus 0.82 (95% CI, 0.79-0.84) (P = 0.002), positive predictive value was 0.40 (95% CI, 0.36-0.45) versus 0.45 (95% CI, 0.41-0.50) (P = 0.14), and area under the receiver operating characteristics curve was 0.89 (95% CI, 0.82-0.96) versus 0.89 (95% CI, 0.82-0.96) (P = 0.83). Ultrafast breast MRI reading was 22.8% faster than reading FDP (P < 0.001). Interreader agreement is significantly better for ultrafast breast MRI (κ = 0.730; 95% CI, 0.699-0.761) than for the FDP (κ = 0.665; 95% CI, 0.633-0.696).

CONCLUSIONS

Breast MRI screening using only an ultrafast breast MRI protocol is noninferior to screening with an FDP and may result in significantly higher screening specificity and shorter reading time.

The added value of mammography in different age-groups of women with and without BRCA mutation screened with breast MRI

Background

Breast magnetic resonance imaging (MRI) is the most sensitive imaging method for breast cancer detection and is therefore offered as a screening technique to women at increased risk of developing breast cancer. However, mammography is currently added from the age of 30 without proven benefits. The purpose of this study is to investigate the added cancer detection of mammography when breast MRI is available, focusing on the value in women with and without BRCA mutation, and in the age groups above and below 50 years.

Methods

This retrospective single-center study evaluated 6553 screening rounds in 2026 women at increased risk of breast cancer (1 January 2003 to 1 January 2014). Risk category (BRCA mutation versus others at increased risk of breast cancer), age at examination, recall, biopsy, and histopathological diagnosis were recorded. Cancer yield, false positive recall rate (FPR), and false positive biopsy rate (FPB) were calculated using generalized estimating equations for separate age categories (< 40, 40–50, 50–60, ≥ 60 years). Numbers of screens needed to detect an additional breast cancer with mammography (NSN) were calculated for the subgroups.

Results

Of a total of 125 screen-detected breast cancers, 112 were detected by MRI and 66 by mammography: 13 cancers were solely detected by mammography, including 8 cases of ductal carcinoma in situ. In BRCA mutation carriers, 3 of 61 cancers were detected only on mammography, while in other women 10 of 64 cases were detected with mammography alone. While 77% of mammography-detected-only cancers were detected in women ≥ 50 years of age, mammography also added more to the FPR in these women. Below 50 years the number of mammographic examinations needed to find an MRI-occult cancer was 1427.

Conclusions

Mammography is of limited added value in terms of cancer detection when breast MRI is available for women of all ages who are at increased risk. While the benefit appears slightly larger in women over 50 years of age without BRCA mutation, there is also a substantial increase in false positive findings in these women.

The frequency of missed breast cancers in women participating in a high-risk MRI screening program

Purpose

To evaluate the frequency of missed cancers on breast MRI in women participating in a high-risk screening program.

Methods

Patient files from women who participated in an increased risk mammography and MRI screening program (2003–2014) were coupled to the Dutch National Cancer Registry. For each cancer detected, we determined whether an MRI scan was available (0–24 months before cancer detection), which was reported to be negative. These negative MRI scans were in consensus re-evaluated by two dedicated breast radiologists, with knowledge of the cancer location. Cancers were scored as invisible, minimal sign, or visible. Additionally, BI-RADS scores, background parenchymal enhancement, and image quality (IQ; perfect, sufficient, bad) were determined. Results were stratified by detection mode (mammography, MRI, interval cancers, or cancers in prophylactic mastectomies) and patient characteristics (presence of BRCA mutation, age, menopausal state).

Results

Negative prior MRI scans were available for 131 breast cancers. Overall 31% of cancers were visible at the initially negative MRI scan and 34% of cancers showed a minimal sign. The presence of a BRCA mutation strongly reduced the likelihood of visible findings in the last negative MRI (19 vs. 46%, P < 0.001). Less than perfect IQ increased the likelihood of visible findings and minimal signs in the negative MRI (P = 0.021).

Conclusion

This study shows that almost one-third of cancers detected in a high-risk screening program are already visible at the last negative MRI scan, and even more in women without BRCA mutations. Regular auditing and double reading for breast MRI screening is warranted.

Fully automated detection of breast cancer in screening MRI using convolutional neural networks

Current computer-aided detection (CADe) systems for contrast-enhanced breast MRI rely on both spatial information obtained from the early-phase and temporal information obtained from the late-phase of the contrast enhancement. However, late-phase information might not be available in a screening setting, such as in abbreviated MRI protocols, where acquisition is limited to early-phase scans. We used deep learning to develop a CADe system that exploits the spatial information obtained from the early-phase scans. This system uses three-dimensional (3-D) morphological information in the candidate locations and the symmetry information arising from the enhancement differences of the two breasts. We compared the proposed system to a previously developed system, which uses the full dynamic breast MRI protocol. For training and testing, we used 385 MRI scans, containing 161 malignant lesions. Performance was measured by averaging the sensitivity values between 1/8-eight false positives. In our experiments, the proposed system obtained a significantly ([Formula: see text]) higher average sensitivity ([Formula: see text]) compared with that of the previous CADe system ([Formula: see text]). In conclusion, we developed a CADe system that is able to exploit the spatial information obtained from the early-phase scans and can be used in screening programs where abbreviated MRI protocols are used.