Differentiation of Malignancy and Idiopathic Granulomatous Mastitis Presenting as Non-mass Lesions on MRI: Radiological, Clinical, Radiomics, and Clinical-Radiomics Models

RATIONALE AND OBJECTIVES

To investigate the effectiveness of machine learning-based clinical, radiomics, and combined models in differentiating idiopathic granulomatous mastitis (IGM) from malignancy, both presenting as non-mass enhancement (NME) lesions on magnetic resonance imaging (MRI), and to compare these models with radiological evaluation.

MATERIAL AND METHODS

A total of 178 patients (69 IGM and 109 breast cancer patients) with NME on breast MRI evaluated between March 2018 and April 2022, were included in this two-center study. Age, skin changes, presence of fistula, and abscess were recorded from hospital records. Two experienced radiologists evaluated MRI images according to the breast imaging reporting and data system 2013 lexicon. Lesions were segmented independently on T2-weighted, apparent diffusion coefficient, and post-contrast-T1-weighted sequences. Data were split into training and external testing sets. Machine learning models were built using Light GBM (light gradient-boosting machine). Radiological, clinical, radiomics, and clinical-radiomics models were created and compared. Decision curve analysis was performed. Quality of reporting and that of methodology were evaluated using CLEAR and METRICS tools.

RESULTS

IGM group was younger (p = 0.014). Abscesses (p < 0.001), fistulas (p < 0.001), and skin changes (p < 0.001) were significantly more common in the IGM group. No significant difference was detected in terms of lesion size (p = 0.213). In the evaluation of NME, the lowest performance belonged to the radiologists' evaluation (AUC for training, 0.740; for testing, 0.737), while the highest AUC was achieved by the model developed by combined clinical and radiomics features (AUC for training, 0.979; for testing, 0.942).

CONCLUSION

Our study has shown that the machine learning-based clinical-radiomics model might have the potential to accurately discriminate IGM and malignant lesions in evaluating NME areas.

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists' interpretations at various levels

PURPOSE

To evaluate the diagnostic performance of deep learning using the Residual Networks 50 (ResNet50) neural network constructed from different segmentations for distinguishing malignant and benign non-mass enhancement (NME) on breast magnetic resonance imaging (MRI) and conduct a comparison with radiologists with various levels of experience.

MATERIALS AND METHODS

A total of 84 consecutive patients with 86 lesions (51 malignant, 35 benign) presenting NME on breast MRI were analyzed. Three radiologists with different levels of experience evaluated all examinations, based on the Breast Imaging-Reporting and Data System (BI-RADS) lexicon and categorization. For the deep learning method, one expert radiologist performed lesion annotation manually using the early phase of dynamic contrast-enhanced (DCE) MRI. Two segmentation methods were applied: a precise segmentation was carefully set to include only the enhancing area, and a rough segmentation covered the whole enhancing region, including the intervenient non-enhancing area. ResNet50 was implemented using the DCE MRI input. The diagnostic performance of the radiologists' readings and deep learning were then compared using receiver operating curve analysis.

RESULTS

The ResNet50 model from precise segmentation achieved diagnostic accuracy equivalent [area under the curve (AUC) = 0.91, 95% confidence interval (CI) 0.90, 0.93] to that of a highly experienced radiologist (AUC = 0.89, 95% CI 0.81, 0.96; p = 0.45). Even the model from rough segmentation showed diagnostic performance equivalent to a board-certified radiologist (AUC = 0.80, 95% CI 0.78, 0.82 vs. AUC = 0.79, 95% CI 0.70, 0.89, respectively). Both ResNet50 models from the precise and rough segmentation exceeded the diagnostic accuracy of a radiology resident (AUC = 0.64, 95% CI 0.52, 0.76).

CONCLUSION

These findings suggest that the deep learning model from ResNet50 has the potential to ensure accuracy in the diagnosis of NME on breast MRI.

Magnetic resonance imaging diagnosis of non-mass enhancement of the breast

Breast Imaging Reporting and Data System magnetic resonance imaging (BI-RADS-MRI) classifies lesions as mass, non-mass enhancement (NME), or focus. BI-RADS ultrasound does not currently have the concept of non-mass. Additionally, knowing the concept of NME in MRI is significant. Thus, this study aimed to provide a narrative review of NME diagnosis in breast MRI. Lexicons are defined with distribution (focal, linear, segmental, regional, multiple regions, and diffuse) and internal enhancement patterns (homogenous, heterogeneous, clumped, and clustered ring) in the case of NME. Among these, linear, segmental, clumped, clustered ring, and heterogeneous are the terms that suggest malignancy. Hence, a hand search was conducted for reports of malignancy frequencies. The malignancy frequency in NME is widely distributed, ranging from 25 to 83.6%, and the frequency of each finding varies. Latest techniques, such as diffusion-weighted imaging and ultrafast dynamic MRI, are attempted to differentiate NME. Additionally, attempts are made in the preoperative setting to determine the concordance of lesion spread based on findings and the presence of invasion.

A review of MRI (CT)/US fusion imaging in treatment of breast cancer

The ultrasound fusion imaging system is a diagnostic device developed in Japan that utilizes ultrasound and magnetic positioning/navigation. A position sensor with a probe reads spatial location information from a magnetic field generator and by synchronously displaying ultrasound images and magnetic resonance (MR)/computed tomography (CT) images in real time. Lesions that are difficult to observe via ultrasonography alone, such as non-mass enhancement, can be identified. Furthermore, lesions that are difficult to identify with ultrasound alone indicated for MRI-guided biopsy under the National Health Insurance Scheme can be identified using ultrasound fusion technology, thereby enabling tissue biopsy to be performed under ultrasound guidance. Using this ultrasound fusion technology, not only non-mass enhancement but also small lesions that are difficult to identify using ultrasound alone can be detected, thus ensuring that a more accurate preoperative imaging diagnosis is established, and leading to safer, more reassuring examinations and surgical procedures. In this paper, we outline the use of this ultrasound fusion technology and fusion techniques in the treatment of breast cancer.

Limited value of multiparametric MRI with dynamic contrast-enhanced and diffusion-weighted imaging in non-mass enhancing breast tumors

PURPOSE

To investigate the diagnostic value of multiparametric MRI (mpMRI) including dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) in non-mass enhancing breast tumors.

METHOD

Patients who underwent mpMRI, who were diagnosed with a suspicious non-mass enhancement (NME) on DCE-MRI (BI-RADS 4/5), and who subsequently underwent image-guided biopsy were retrospectively included. Two radiologists independently evaluated all NMEs, on both DCE-MR images and high-b-value DW images. Different mpMRI reading approaches were evaluated: 1) with a fixed apparent diffusion coefficient (ADC) threshold (<1.3 malignant, ≥1.3 benign) based on the recommendation by the European Society of Breast Imaging (EUSOBI); 2) with a fixed ADC threshold (<1.5 malignant, ≥1.5 benign) based on recently published trial data; 3) with an ADC threshold adapted to the assigned BI-RADS classification using a previously published reading method; and 4) with individually determined best thresholds for each reader.

RESULTS

The final study sample consisted of 66 lesions in 66 patients. DCE-MRI alone had the highest sensitivity for breast cancer detection (94.8-100 %), outperforming all mpMRI reading approaches (R1 74.4-87.1 %, R2 71.7-94.8 %) and DWI alone (R1 74.4 %, R2 79.4 %). The adapted approach achieved the best specificity for both readers (85.1 %), resulting in the best diagnostic accuracy for R1 (86.5 %) but a moderate diagnostic accuracy for R2 (77.2 %).

CONCLUSION

mpMRI has limited added diagnostic value to DCE-MRI in the assessment of NME.

An artificial intelligence system using maximum intensity projection MR images facilitates classification of non-mass enhancement breast lesions

OBJECTIVES

To build an artificial intelligence (AI) system to classify benign and malignant non-mass enhancement (NME) lesions using maximum intensity projection (MIP) of early post-contrast subtracted breast MR images.

METHODS

This retrospective study collected 965 pure NME lesions (539 benign and 426 malignant) confirmed by histopathology or follow-up in 903 women. The 754 NME lesions acquired by one MR scanner were randomly split into the training set, validation set, and test set A (482/121/151 lesions). The 211 NME lesions acquired by another MR scanner were used as test set B. The AI system was developed using ResNet-50 with the axial and sagittal MIP images. One senior and one junior radiologist reviewed the MIP images of each case independently and rated its Breast Imaging Reporting and Data System category. The performance of the AI system and the radiologists was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

The AI system yielded AUCs of 0.859 and 0.816 in the test sets A and B, respectively. The AI system achieved comparable performance as the senior radiologist (p = 0.558, p = 0.041) and outperformed the junior radiologist (p < 0.001, p = 0.009) in both test sets A and B. After AI assistance, the AUC of the junior radiologist increased from 0.740 to 0.862 in test set A (p < 0.001) and from 0.732 to 0.843 in test set B (p < 0.001).

CONCLUSION

Our MIP-based AI system yielded good applicability in classifying NME lesions in breast MRI and can assist the junior radiologist achieve better performance.

KEY POINTS

• Our MIP-based AI system yielded good applicability in the dataset both from the same and a different MR scanner in predicting malignant NME lesions. • The AI system achieved comparable diagnostic performance with the senior radiologist and outperformed the junior radiologist. • This AI system can assist the junior radiologist achieve better performance in the classification of NME lesions in MRI.

Evaluation of an MRI/US fusion technique for the detection of non-mass enhancement of breast lesions detected by MRI yet occult on conventional B-mode second-look US

PURPOSE

The aim of this study was to verify the utility of second-look ultrasound (US) using real-time virtual sonography (RVS), a magnetic resonance imaging (MRI)/US fusion technique, in identifying MRI-detected breast lesions with non-mass enhancement (NME).

METHODS

Consecutive patients who had one or more NME lesions detected by MRI yet occult on the subsequent second-look US in conventional B (cB)-mode imaging were enrolled in the study between June 2015 and April 2020. Supine MRI of the lesions was performed and, using its data, second-look US using RVS was performed.

RESULTS

Twenty patients with 21 NME lesions were included. The overall median lesion size on prone MRI was 23 mm (range, 5-63 mm). Supine MRI identified all the 21 NME lesions, and second-look US using RVS successfully detected 18 (86%) of them. RVS-guided biopsy was performed for histopathological evaluation, showing that nine of the 18 lesions were benign and the other nine malignant. Of the nine malignant lesions, two (22%) were invasive cancer and seven (78%) were ductal carcinoma in situ. In four of five patients who underwent prone MRI for preoperative evaluation, the diagnosis was benign and surgery was conducted as originally planned. In the other patient, the diagnosis was malignant and contralateral breast-conserving surgery was added. Three (14%) of the 21 NME lesions had no RVS correlates and were judged to be benign after 24-month follow-up.

CONCLUSION

The results suggest that second-look US using RVS helps identify MRI-detected NME lesions that are occult on cB-mode second-look US.

Additive value of texture analysis based on breast MRI for distinguishing between benign and malignant non-mass enhancement in premenopausal women

BACKGROUND

Non-mass enhancement (NME) is a diagnostic dilemma and highly reliant on the experience of the radiologists. Texture analysis (TA) could serve as an objective method to quantify lesion characteristics. However, it remains unclear what role TA plays in a predictive model based on routine MRI characteristics. The purpose of this study was to explore the value of TA in distinguishing between benign and malignant NME in premenopausal women.

METHODS

Women in whom NME was histologically proven (n = 147) were enrolled (benign: 58; malignant: 89) was retrospective. Then, 102 and 45 patients were classified as the training and validation groups, respectively. Scanning sequences included Fat-suppressed T2-weighted and fat-suppressed contrast-enhanced T1-weighted which were acquired on a 1.5T MRI system. Clinical and routine MR characteristics (CRMC) were evaluated by two radiologists according to the Breast Imaging and Reporting and Data system (2013). Texture features were extracted from all post-contrast sequences in the training group. The combination model was built and then assessed in the validation group. Pearson's chi-square test and Mann-Whitney U test were used to compare categorical variables and continuous variables, respectively. Logistic regression analysis and receiver operating characteristic curve were employed to assess the diagnostic performance of CRMC, TA, and their combination model in NME diagnosis.

RESULTS

The combination model showed superior diagnostic performance in differentiating between benign and malignant NME compared to that of CRMC or TA alone (AUC, 0.887 vs 0.832 vs 0.74). Moreover, compared to CRMC, the model showed high specificity (72.5% vs 80%). The results obtained in the validation group confirmed the model was promising.

CONCLUSIONS

With the combined use of TA and CRMC could afford an improved diagnostic performance in differentiating between benign and malignant NME.

Utility and Diagnostic Performance of Automated Breast Ultrasound System in Evaluating Pure Non-Mass Enhancement on Breast Magnetic Resonance Imaging

Objective

To compare the utility and diagnostic performance of automated breast ultrasound system (ABUS) with that of hand-held ultrasound (HHUS) in evaluating pure non-mass enhancement (NME) lesions on breast magnetic resonance imaging (MRI).

Materials and Methods

One hundred twenty-six consecutive MRI-visible pure NME lesions of 122 patients with breast cancer were assessed from April 2016 to March 2017. Two radiologists reviewed the preoperative breast MRI, ABUS, and HHUS images along with mammography (MG) findings. The NME correlation rate and diagnostic performance of ABUS were compared with that of HHUS, and the imaging features associated with ABUS visibility were analyzed.

Results

Among 126 pure NME lesions, 100 (79.4%) were malignant and 26 (20.6%) were benign. The overall correlation rate was 87.3% (110/126) in ABUS and 92.9% (117/126) in HHUS. The sensitivity and specificity were 87% and 50% for ABUS and 92% and 42.3% for HHUS, respectively, with no significant differences (p = 0.180 and 0.727, respectively). Malignant NME was more frequently visualized than benign NME lesions on ABUS (93% vs. 65.4%, p = 0.001). Significant factors associated with the visibility of ABUS were the size of NME lesions on MRI (p < 0.001), their distribution pattern (p < 0.001), and microcalcifications on MG (p = 0.027).

Conclusion

ABUS evaluation of pure NME lesions on MRI in patients with breast cancer is a useful technique with high visibility, especially in malignant lesions. The diagnostic performance of ABUS was comparable with that of conventional HHUS in evaluating NME lesions.

Limited role of DWI with apparent diffusion coefficient mapping in breast lesions presenting as non-mass enhancement on dynamic contrast-enhanced MRI

BACKGROUND

Available data proving the value of DWI for breast cancer diagnosis is mainly for enhancing masses; DWI may be less sensitive and specific in non-mass enhancement (NME) lesions. The objective of this study was to assess the diagnostic accuracy of DWI using different ROI measurement approaches and ADC metrics in breast lesions presenting as NME lesions on dynamic contrast-enhanced (DCE) MRI.

METHODS

In this retrospective study, 95 patients who underwent multiparametric MRI with DCE and DWI from September 2007 to July 2013 and who were diagnosed with a suspicious NME (BI-RADS 4/5) were included. Twenty-nine patients were excluded for lesion non-visibility on DWI (n = 24: 12 benign and 12 malignant) and poor DWI quality (n = 5: 1 benign and 4 malignant). Two readers independently assessed DWI and DCE-MRI findings in two separate randomized readings using different ADC metrics and ROI approaches. NME lesions were classified as either benign (> 1.3 × 10^-3 mm²/s) or malignant (≤ 1.3 × 10^-3 mm²/s). Histopathology was the standard of reference. ROC curves were plotted, and AUCs were determined. Concordance correlation coefficient (CCC) was measured.

RESULTS

There were 39 malignant (59%) and 27 benign (41%) lesions in 66 (65 women, 1 man) patients (mean age, 51.8 years). The mean ADC value of the darkest part of the tumor (Dptu) achieved the highest diagnostic accuracy, with AUCs of up to 0.71. Inter-reader agreement was highest with Dptu ADC max (CCC 0.42) and lowest with the point tumor (Ptu) ADC min (CCC = - 0.01). Intra-reader agreement was highest with Wtu ADC mean (CCC = 0.44 for reader 1, 0.41 for reader 2), but this was not associated with the highest diagnostic accuracy.

CONCLUSIONS

Diagnostic accuracy of DWI with ADC mapping is limited in NME lesions. Thirty-one percent of lesions presenting as NME on DCE-MRI could not be evaluated with DWI, and therefore, DCE-MRI remains indispensable. Best results were achieved using Dptu 2D ROI measurement and ADC mean.

Grading system to categorize breast MRI using BI-RADS 5th edition: a statistical study of non-mass enhancement descriptors in terms of probability of malignancy

PURPOSE

To analyze the association of breast non-mass enhancement descriptors in the BI-RADS 5th edition with malignancy, and to establish a grading system and categorization of descriptors.

MATERIALS AND METHODS

This study was approved by our institutional review board. A total of 213 patients were enrolled. Breast MRI was performed with a 1.5-T MRI scanner using a 16-channel breast radiofrequency coil. Two radiologists determined internal enhancement and distribution of non-mass enhancement by consensus. Corresponding pathologic diagnoses were obtained by either biopsy or surgery. The probability of malignancy by descriptor was analyzed using Fisher's exact test and multivariate logistic regression analysis. The probability of malignancy by category was analyzed using Fisher's exact and multi-group comparison tests.

RESULTS

One hundred seventy-eight lesions were malignant. Multivariate model analysis showed that internal enhancement (homogeneous vs others, p < 0.001, heterogeneous and clumped vs clustered ring, p = 0.003) and distribution (focal and linear vs segmental, p < 0.001) were the significant explanatory variables. The descriptors were classified into three grades of suspicion, and the categorization (3, 4A, 4B, 4C, and 5) by sum-up grades showed an incremental increase in the probability of malignancy (p < 0.0001).

CONCLUSION

The three-grade criteria and categorization by sum-up grades of descriptors appear valid for non-mass enhancement.

Magnetic resonance imaging characteristics of granulomatous mastitis

Granulomatous mastitis (GM) is a benign chronic inflammatory condition of the breast. This study was performed to determine the utility of magnetic resonance imaging (MRI) in differentiating GM from malignancy. MRI findings in 12 women with clinical or histopathologically-proven GM were retrospectively reviewed. Non-mass enhancement on MRI was present in all 12 patients with clustered ring enhancement being the most common pattern (n=7, 58%). Architectural distortion (n=10, 83%), skin thickening (n=10, 83%) and focal skin enhancement (n=10, 83%) were also very common. MRI features of GM are often identical to features considered suspicious for malignancy on MRI.