Management of Architectural Distortion on Digital Breast Tomosynthesis With Nonmalignant Pathology at Biopsy

A Comprehensive Assessment of Radial Scars on Core Needle Biopsy in Patients with or without Breast Cancer: Upgrade Rate and Implications on Management

BACKGROUND

Radial scars/radial sclerosing lesions (RS) are benign breast lesions identified on core needle biopsy (CNB) which can upgrade to malignancy at excision. There is limited data on RS detection and upgrade rates with more sensitive imaging such as magnetic resonance imaging (MRI) and none during their detection for breast cancer workup and its implication on patient treatment decisions.

METHODS

A retrospective institutional study of RS diagnosed on CNB between January 2008 and December 2017 was conducted. Clinicopathologic and radiologic features of RS, patient treatment decisions, upgrade rates and long-term follow-up were examined.

RESULTS

We identified 133 patients with RS on CNB, of whom 106 opted for surgery for an upgrade rate to malignancy of 1.9%, 2 patients. Radial scar was diagnosed on mammogram in 60%, MRI in 25% and ultrasound in 15% of patients. In this cohort, 32 patients had their RS detected during breast cancer workup (coexistent group) and they were more likely to have their radial scar detected by MRI (60% vs. 14%, P < .001) and undergo more extensive surgery (94% vs. 75%, P = .02). Among the 27 patients electing observation of their RS, only one (3.7%) developed breast cancer.

CONCLUSIONS

Our results show an extremely low upgrade rate to malignancy of RS, regardless if there is coexisting breast cancer elsewhere. Despite this, RS still prompted more extensive surgical excisions. The findings do not support excision of RS even among breast cancer patients when identified at a separate site from their cancer.

Evaluation of architectural distortion with contrast-enhanced mammography

Architectural distortion (AD) is the third most common abnormality detected on mammograms. In the absence of an accurate non-invasive tool to evaluate ADs, clinical management often requires surgical excision for histological diagnosis. This problem is expected to worsen with the growing use of digital breast tomosynthesis (DBT) and the resultant increasing detection of ADs. There is therefore a great clinical need for a diagnostic imaging tool to complement non-enhanced mammography for the evaluation of AD. Contrast-enhanced mammography (CEM) is an emerging breast imaging method that uses contrast media and the principle of dual-energy subtraction to evaluate vascularity of suspicious breast lesions. CEM, a cost-effective alternative to breast magnetic resonance imaging (MRI), can be used to evaluate AD by juxtaposing CEM images with non-enhanced mammograms for comparison. In this review, the authors aim to provide readers with an overview of the interpretation of AD on CEM using imaging examples. Relevant imaging features of CEM and their respective significance will be matched with information from a literature review. Finally, the authors would like to highlight the added value of CEM in relevant clinical applications in the assessment of AD.

Third International Consensus Conference on lesions of uncertain malignant potential in the breast (B3 lesions)

The heterogeneous group of B3 lesions in the breast harbors lesions with different malignant potential and progression risk. As several studies about B3 lesions have been published since the last Consensus in 2018, the 3rd International Consensus Conference discussed the six most relevant B3 lesions (atypical ductal hyperplasia (ADH), flat epithelial atypia (FEA), classical lobular neoplasia (LN), radial scar (RS), papillary lesions (PL) without atypia, and phyllodes tumors (PT)) and made recommendations for diagnostic and therapeutic approaches. Following a presentation of current data of each B3 lesion, the international and interdisciplinary panel of 33 specialists and key opinion leaders voted on the recommendations for further management after core-needle biopsy (CNB) and vacuum-assisted biopsy (VAB). In case of B3 lesion diagnosis on CNB, OE was recommended in ADH and PT, whereas in the other B3 lesions, vacuum-assisted excision was considered an equivalent alternative to OE. In ADH, most panelists (76%) recommended an open excision (OE) after diagnosis on VAB, whereas observation after a complete VAB-removal on imaging was accepted by 34%. In LN, the majority of the panel (90%) preferred observation following complete VAB-removal. Results were similar in RS (82%), PL (100%), and FEA (100%). In benign PT, a slim majority (55%) also recommended an observation after a complete VAB-removal. VAB with subsequent active surveillance can replace an open surgical intervention for most B3 lesions (RS, FEA, PL, PT, and LN). Compared to previous recommendations, there is an increasing trend to a de-escalating strategy in classical LN. Due to the higher risk of upgrade into malignancy, OE remains the preferred approach after the diagnosis of ADH.

Pathologic Outcomes in Single Versus Multiple Areas of Architectural Distortion on Digital Breast Tomosynthesis

BACKGROUND. Digital breast tomosynthesis (DBT) has led to increased detection of architectural distortion (AD). Management of patients with multiple areas of AD is not established. OBJECTIVE. The purpose of this article is to compare pathologic outcomes between single and multiple areas of AD identified on DBT. METHODS. This retrospective study included 402 patients (mean age, 56 years) who underwent image-guided core needle biopsy of AD visualized on DBT between April 7, 2017, and April 16, 2019. Patients were classified as having a single or multiple areas of AD according to the presence of distinct areas of AD described in the clinical radiology reports. The pathologic diagnosis for each AD was on the basis of the most aggressive pathology identified on either biopsy or surgical excision, if performed. Patients with single and multiple areas of AD were compared. RESULTS. The sample included 372 patients with a single AD (145 benign, 121 high risk, 105 malignant, one other) and 30 patients with multiple visualized ADs, including 66 biopsied ADs (10 benign, 35 high risk, 21 malignant). At pathologic assessment on a per-lesion basis, multiple compared with single ADs showed higher frequency of high-risk pathology (53.0% vs 32.5%, p = .002) but no difference in frequency of malignancy (31.8% vs 28.2%, p = .56). In multivariable analysis of a range of patient-related characteristics, the presence of single versus multiple areas of AD was not independently associated with malignancy (p = .51). In patients with multiple areas of AD, the most aggressive pathology (benign, high risk, or malignant) across all ADs was not associated with the number of ADs (p = .73). In 8 of 24 patients with at least two ipsilateral biopsied ADs, the ipsilateral areas varied in terms of most aggressive pathology; in 5 of 10 patients with contralateral biopsied ADs, the contralateral areas varied in most aggressive pathology. CONCLUSION. The presence of multiple areas of AD, compared with a single AD, was significantly more likely to yield high-risk pathology but was not significantly different in yield of malignancy. In patients with multiple ADs, multiple ipsilateral or contralateral ADs commonly varied in pathologic classification (benign, high risk, or malignant). CLINICAL IMPACT. These findings may help guide management of AD visualized by DBT, including multiple ADs. For patients with multiple areas of AD, biopsy of all areas may be warranted given variation in pathologic diagnoses.

Identification and diagnosis of mammographic malignant architectural distortion using a deep learning based mask regional convolutional neural network

Background

Architectural distortion (AD) is a common imaging manifestation of breast cancer, but is also seen in benign lesions. This study aimed to construct deep learning models using mask regional convolutional neural network (Mask-RCNN) for AD identification in full-field digital mammography (FFDM) and evaluate the performance of models for malignant AD diagnosis.

Methods

This retrospective diagnostic study was conducted at the Second Affiliated Hospital of Guangzhou University of Chinese Medicine between January 2011 and December 2020. Patients with AD in the breast in FFDM were included. Machine learning models for AD identification were developed using the Mask RCNN method. Receiver operating characteristics (ROC) curves, their areas under the curve (AUCs), and recall/sensitivity were used to evaluate the models. Models with the highest AUCs were selected for malignant AD diagnosis.

Results

A total of 349 AD patients (190 with malignant AD) were enrolled. EfficientNetV2, EfficientNetV1, ResNext, and ResNet were developed for AD identification, with AUCs of 0.89, 0.87, 0.81 and 0.79. The AUC of EfficientNetV2 was significantly higher than EfficientNetV1 (0.89 vs. 0.78, P=0.001) for malignant AD diagnosis, and the recall/sensitivity of the EfficientNetV2 model was 0.93.

Conclusion

The Mask-RCNN-based EfficientNetV2 model has a good diagnostic value for malignant AD.

Diagnosis of architectural distortion on digital breast tomosynthesis using radiomics and deep learning

Purpose

To implement two Artificial Intelligence (AI) methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images.

Materials and Methods

A total of 298 patients were identified from a retrospective review, and all of them had confirmed pathological diagnoses, 175 malignant and 123 benign. The BI-RADS scores of DBT were obtained from the radiology reports, classified into 2, 3, 4A, 4B, 4C, and 5. The architectural distortion areas on craniocaudal (CC) and mediolateral oblique (MLO) views were manually outlined as the region of interest (ROI) for the radiomics analysis. Features were extracted using PyRadiomics, and then the support vector machine (SVM) was applied to select important features and build the classification model. Deep learning was performed using the ResNet50 algorithm, with the binary output of malignancy and benignity. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was utilized to localize the suspicious areas. The predicted malignancy probability was used to construct the ROC curves, compared by the DeLong test. The binary diagnosis was made using the threshold of ≥ 0.5 as malignant.

Results

The majority of malignant lesions had BI-RADS scores of 4B, 4C, and 5 (148/175 = 84.6%). In the benign group, a substantial number of patients also had high BI-RADS ≥ 4B (56/123 = 45.5%), and the majority had BI-RADS ≥ 4A (102/123 = 82.9%). The radiomics model built using the combined CC+MLO features yielded an area under curve (AUC) of 0.82, the sensitivity of 0.78, specificity of 0.68, and accuracy of 0.74. If only features from CC were used, the AUC was 0.77, and if only features from MLO were used, the AUC was 0.72. The deep-learning model yielded an AUC of 0.61, significantly lower than all radiomics models (p<0.01), which was presumably due to the use of the entire image as input. The Grad-CAM could localize the architectural distortion areas.

Conclusion

The radiomics model can achieve a satisfactory diagnostic accuracy, and the high specificity in the benign group can be used to avoid unnecessary biopsies. Deep learning can be used to localize the architectural distortion areas, which may provide an automatic method for ROI delineation to facilitate the development of a fully-automatic computer-aided diagnosis system using combined AI strategies.