Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling

Diagnostic performance of Kaiser score in the evaluation of breast cancer using MRI: A systematic review and meta-analysis

PURPOSE

To assess the performance of Kaiser score (KS) in detecting and characterizing breast cancer on magnetic resonance imaging (MRI).

METHODS

The protocol was pre-registered at (https://osf.io/83c6j/). We performed a comprehensive search in PubMed, Embase, Cochrane Library, and Web of Science until 30 October 2024 for studies that used KS for detection of breast cancer on MRI. The risk of bias in the included studies was evaluated utilizing Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Diagnostic values of area under the curve (AUC), sensitivity, specificity, positive and negative likelihood ratios, and diagnostic odds ratio were calculated using a random-effects bivariate model. Meta-regression was used to explore the source of heterogeneity when I2 was ≥ 50 %. P-value < 0.05 was considered statistically significant.

RESULTS

A total of 29 studies with 7918 patients and 8451 breast lesions were included. The pooled sensitivity, specificity, and AUC of KS for detecting malignant breast lesions on MRI were 95 % (95 % CI = 94 % to 96 %), 70 % (95 % CI = 64 % to 75 %), and 0.94 (95 % CI = 0.91 to 0.96), while for Breast Imaging Reporting and Data System (BI-RADS), they were 97 % (95 % CI = 92 % to 99 %), 46 % (95 % CI = 30 % to 62 %), and 0.89 (95 % CI = 0.86 to 0.91). Sensitivity difference was not statistically significant (p-value = 0.803), but specificity difference was significant (p-value = 0.001). Also, KS demonstrated slightly better diagnostic accuracy for mass lesions with a sensitivity of 96 % (95 % CI = 94 % to 97 %), specificity of 69 % (95 % CI = 60 % to 77 %), and AUC of 0.96 (95 % CI = 0.94 to 0.97) compared to non-mass lesions with 93 % (95 % CI = 88 % to 96 %), 68 % (95 % CI = 58 % to 77 %), and 0.91 (95 % CI = 0.88 to 0.94) values, respectively. KS showed better performance in larger lesions.

CONCLUSION

The KS's superior diagnostic performance compared to BI-RADS, particularly its ability to avoid unnecessary biopsies, makes it valuable for diagnostic and clinical decision-making.

What Is the Added Value of DWI Compared With Structured Assessment of BI-RADS Criteria by the Kaiser Score? A Systematic Review and Meta-analysis

OBJECTIVE

This systematic review and meta-analysis investigated the added value of DWI compared with the structured assessment of BI-RADS criteria using the Kaiser score.

MATERIALS AND METHODS

Articles published in English until May 2024 were included. Two independent reviewers extracted data on the characteristics of studies evaluating the added value of DWI to distinguish benign from malignant breast lesions compared with structured assessment of the BI-RADS criteria. Using bivariate random-effects models, the sensitivity and specificity were calculated. I2 statistics, Deek's funnel plot asymmetry test for publication bias, and meta-regression were applied for the data analysis.

RESULTS

Five studies comprising 1005 malignant and 846 benign lesions were eligible for data synthesis. The pooled sensitivity and specificity estimates of structured BI-RADS assessment were 95.7% (95% confidence interval [CI], 92.6%-97.5%) and 68.7% (95% CI, 60.9%-75.6%), respectively. Adding DWI to the structured BI-RADS assessment achieved a pooled sensitivity of 94.4% (95% CI, 90.5%-96.7%) and a pooled specificity of 74.9% (95% CI, 68.8%-80.2%). Adding DWI to the structured BI-RADS assessment significantly changed neither the sensitivity ( P = 0.52) nor the specificity ( P = 0.20).

CONCLUSIONS

This systematic review and meta-analysis revealed only a limited, statistically nonsignificant added value of DWI compared with the structured assessment of BI-RADS criteria using the Kaiser score.

Breast lesions on MRI in mass and non-mass enhancement: Kaiser score and modified Kaiser score + for readers of variable experience

OBJECTIVES

To compare the diagnostic performance of three readers using BI-RADS and Kaiser score (KS) based on mass and non-mass enhancement (NME) lesions.

METHODS

A total of 630 lesions, 393 malignant and 237 benign, 458 mass and 172 NME, were analyzed. Three radiologists with 3 years, 6 years, and 13 years of experience made diagnoses. 596 cases had diffusion-weighted imaging, and the apparent diffusion coefficient (ADC) was measured. For lesions with ADC > 1.4 × 10-3 mm2/s, the KS was reduced by 4 as the modified KS +, and the benefit was assessed.

RESULTS

When using BI-RADS, AUC was 0.878, 0.915, and 0.941 for mass, and 0.771, 0.838, 0.902 for NME for Reader-1, 2, and 3, respectively, better for mass than for NME. The diagnostic accuracy of KS was improved compared to BI-RADS for less experienced readers. For Reader-1, AUC was increased from 0.878 to 0.916 for mass (p = 0.005) and from 0.771 to 0.822 for NME (p = 0.124). Based on the cut-off value of BI-RADS ≥ 4B and KS ≥ 5 as malignant, the sensitivity of KS by Readers-1 and -2 was significantly higher for both Mass and NME. When ADC was considered to change to modified KS +, the AUC and the accuracy for all three readers were improved, showing higher specificity with slightly degraded sensitivity.

CONCLUSION

The benefit of KS compared to BI-RADS was most noticeable for the less experienced readers in improving sensitivity. Compared to KS, KS + can improve specificity for all three readers. For NME, the KS and KS + criteria need to be further improved.

CLINICAL RELEVANCE STATEMENT

KS provides an intuitive method for diagnosing lesions on breast MRI. BI-RADS and KS face greater difficulties in evaluating NME compared to mass lesions. Adding ADC to the KS can improve specificity with slightly degraded sensitivity.

KEY POINTS

KS provides an intuitive method for interpreting breast lesions on MRI, most helpful for novice readers. KS, compared to BI-RADS, improved sensitivity in both mass and NME groups for less experienced readers. NME lesions were considered during the development of the KS flowchart, but may need to be better defined.

Assessment of the contribution of the ADC value to the Kaiser score in the differential diagnosis of breast lesions with non-mass enhancement morphology on MRI

PURPOSE

To investigate the effectiveness of diffusion-weighted imaging (DWI) as a supplementary tool to the Kaiser score (KS) in diagnosing breast cancer in non-mass enhancement (NME) lesions using breast magnetic resonance imaging (MRI).

METHODS

This single-center, retrospective study analyzed 360 cases with NME on MRI images. Two breast radiologists independently evaluated each lesion using the Kaiser score (KS) and apparent diffusion coefficient (ADC) values, without knowledge of the pathological outcomes. NME lesions with a KS above 4 and an ADC value below 1.3 × 10-3mm2/s were classified as malignant. Inter-rater reliability was determined using Cohen's Kappa (κ) statistics. The diagnostic performance of KS, DWI, and their combination was assessed by calculating sensitivity, specificity, and the area under the curve (AUC), and the results were compared across the benign and malignant groups.

RESULTS

The diagnostic performance of KS surpassed that of DWI in predicting the malignancy of NMEs (p = 0.003). The sensitivity of KS alone was 93 %; however, when ADC data was incorporated, the sensitivity decreased to 86 %, with no significant difference observed (p = 0.060). The specificity of the combined KS and ADC (94 %) was significantly higher than that of KS alone (89 %) and DWI alone (73 %) (p < 0.001).

CONCLUSION

Our findings indicated that although the combination of KS and ADC increased specificity and reduced unnecessary biopsies, the resulting decrease in sensitivity was unacceptable. Therefore, KS alone is superior to the KS-ADC combination in detecting malignancy in NME lesions.

Application of the Kaiser score on contrast-enhanced mammography in the differential diagnosis of breast lesions: comparison with breast magnetic resonance imaging

Background

The Kaiser score (KS) as a clinical decision rule has been proven capable of enhancing the diagnostic efficiency for suspicious breast lesions and obviating unnecessary benign biopsies. However, the consistency of KS in contrast-enhanced mammography (CEM-KS) and KS on magnetic resonance imaging (MRI-KS) is still unclear. This study aimed to evaluate and compare the diagnostic efficacy and agreement of CEM-KS and MRI-KS for suspicious breast lesions.

Methods

This retrospective study included 207 patients from April 2019 to June 2022. The radiologists assigned a diagnostic category to all lesions using the Breast Imaging Reporting and Data System (BI-RADS). Subsequently, they were asked to assign a final diagnostic category for each lesion according to the KS. The diagnostic performance was evaluated by the area under the receiver operating characteristic curve (AUC). The agreement in terms of the kinetic curve and the KS categories for CEM and MRI were evaluated via the Cohen kappa coefficient.

Results

The AUC was higher for the CEM-KS category assignment than for the CEM-BI-RADS category assignment (0.856 vs. 0.776; P=0.047). The AUC was higher for MRI-KS than for MRI-BI-RADS (0.841 vs. 0.752; P =0.015). The AUC of CEM-KS was not significantly different from that of MRI-KS (0.856 vs. 0.841; P=0.538). The difference between the AUCs for CEM-BI-RADS and MRI-BI-RADS was not statistically significant (0.776 vs. 0.752; P=0.400). The kappa agreement for the characterization of suspicious breast lesions using CEM-KS and MRI-KS was 0.885.

Conclusions

The KS substantially improved the diagnostic performance of suspicious breast lesions, not only in MRI but also in CEM. CEM-KS and MRI-KS showed similar diagnostic performance and almost perfect agreement for the characterization of suspicious breast lesions. Therefore, CEM holds promise as an alternative when breast MRI is not available or contraindicated.

Enhancing the Kaiser score for lesion characterization in unenhanced breast MRI

PURPOSE

To adapt the methodology of the Kaiser score, a clinical decision rule for lesion characterization in breast MRI, for unenhanced protocols.

METHOD

In this retrospective IRB-approved cross-sectional study, we included 93 consecutive patients who underwent breast MRI between 2021 and 2023 for further work-up of BI-RADS 0, 3-5 in conventional imaging or for staging purposes (BI-RADS 6). All patients underwent biopsy for histologic verification or were followed for a minimum of 12 months. MRI scans were conducted using 1.5 T or 3 T scanners using dedicated breast coils and a protocol in line with international recommendations including DWI and ADC. Lesion characterization relied solely on T2w and DWI/ADC-derived features (such as lesion type, margins, shape, internal signal, surrounding tissue findings, ADC value). Statistical analysis was done using decision tree analysis aiming to distinguish benign (histology/follow-up) from malignant outcomes.

RESULTS

We analyzed a total of 161 lesions (81 of them non-mass) with a malignancy rate of 40%. Lesion margins (spiculated, irregular, or circumscribed) were identified as the most important criterion within the decision tree, followed by the ADC value as second most important criterion. The resulting score demonstrated a strong diagnostic performance with an AUC of 0.840, providing both rule-in and rule-out criteria. In an independent test set of 65 lesions the diagnostic performance was verified by two readers (AUC 0.77 and 0.87, kappa: 0.62).

CONCLUSIONS

We developed a clinical decision rule for unenhanced breast MRI including lesion margins and ADC value as the most important criteria, achieving high diagnostic accuracy.

Machine learning and new insights for breast cancer diagnosis

Breast cancer (BC) is the most prominent form of cancer among females all over the world. The current methods of BC detection include X-ray mammography, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography and breast thermographic techniques. More recently, machine learning (ML) tools have been increasingly employed in diagnostic medicine for its high efficiency in detection and intervention. The subsequent imaging features and mathematical analyses can then be used to generate ML models, which stratify, differentiate and detect benign and malignant breast lesions. Given its marked advantages, radiomics is a frequently used tool in recent research and clinics. Artificial neural networks and deep learning (DL) are novel forms of ML that evaluate data using computer simulation of the human brain. DL directly processes unstructured information, such as images, sounds and language, and performs precise clinical image stratification, medical record analyses and tumour diagnosis. Herein, this review thoroughly summarizes prior investigations on the application of medical images for the detection and intervention of BC using radiomics, namely DL and ML. The aim was to provide guidance to scientists regarding the use of artificial intelligence and ML in research and the clinic.

Using the Kaiser Score as a clinical decision rule for breast lesion classification: Does computer-assisted curve type analysis improve diagnosis?

PURPOSE

We aimed to investigate the effect of using visual or automatic enhancement curve type assessment on the diagnostic performance of the Kaiser Score (KS), a clinical decision rule for breast MRI.

METHOD

This IRB-approved retrospective study analyzed consecutive conventional BI-RADS 0, 4 or 5 patients who underwent biopsy after 1.5T breast MRI according to EUSOBI recommendations between 2013 and 2015. The KS includes five criteria (spiculations; signal intensity (SI)-time curve type; margins of the lesion; internal enhancement; and presence of edema) resulting in scores from 1 (=lowest) to 11 (=highest risk of breast cancer). Enhancement curve types (Persistent, Plateau or Wash-out) were assessed by two radiologists independently visually and using a pixel-wise color-coded computed parametric map of curve types. KS diagnostic performance differences between readings were compared by ROC analysis.

RESULTS

In total 220 lesions (147 benign, 73 malignant) including mass (n = 148) and non-mass lesions (n = 72) were analyzed. KS reading performance in distinguishing benign from malignant lesions did not differ between visual analysis and parametric map (P = 0.119; visual: AUC 0.875, sensitivity 95 %, specificity 63 %; and map: AUC 0.901, sensitivity 97 %, specificity 65 %). Additionally, analyzing mass and non-mass lesions separately, showed no difference between parametric map based and visual curve type-based KS analysis as well (P = 0.130 and P = 0.787).

CONCLUSIONS

The performance of the Kaiser Score is largely independent of the curve type assessment methodology, confirming its robustness as a clinical decision rule for breast MRI in any type of breast lesion in clinical routine.

Improved Differential Diagnosis Based on BI-RADS Descriptors and Apparent Diffusion Coefficient for Breast Lesions: A Multiparametric MRI Analysis as Compared to Kaiser Score

RATIONALE AND OBJECTIVES

To develop the nomogram utilizing the American College of Radiology BI-RADS descriptors, clinical features, and apparent diffusion coefficient (ADC) to differentiate benign from malignant breast lesions.

MATERIALS AND METHODS

A total of 341 lesions (161 malignant and 180 benign) were included. Clinical data and imaging features were reviewed. Univariable and multivariable logistic regression analyses were performed to determine the independent variables. ADC as a continuous or classified into binary form with a cutoff value of 1.30 × 10-3 mm2/s, incorporated other independent predictors to construct two nomograms, respectively. Receiver operating curve and calibration plot was employed to test the models' discriminative ability. The diagnostic performance between the developed model and the Kaiser score (KS) was also compared.

RESULTS

In both models, high patient age, the presence of root sign, time-intensity curves (TICs) types (plateau and washout), heterogenous internal enhancement, the presence of peritumoral edema, and ADC were independently associated with malignancy. The AUCs of two multivariable models (AUC, 0.957; 95% CI: 0.929-0.976 and AUC, 0.958; 95% CI: 0.931-0.976) were significantly higher than that of the KS (AUC, 0.919, 95% CI: 0.885-0.946; both P < 0.001). At the same sensitivity of 95.7%, our models showed an increase in specificity by 5.56% (P = 0.076) and 6.11% (P = 0.035), respectively, as compared to the KS.

CONCLUSION

The models incorporating MRI features (root sign, TIC, margins, internal enhancement, and presence of edema), quantitative ADC value, and patient age showed improved diagnostic performance and might have avoided more unnecessary biopsies in comparison with the KS, although further external validation is required.

Diagnostic value of Kaiser score combined with breast vascular assessment from breast MRI for the characterization of breast lesions

Objectives

The Kaiser scoring system for breast magnetic resonance imaging is a clinical decision-making tool for diagnosing breast lesions. However, the Kaiser score (KS) did not include the evaluation of breast vascularity. Therefore, this study aimed to use KS combined with breast vascular assessment, defined as KS^*, and investigate the effectiveness of KS^* in differentiating benign from malignant breast lesions.

Methods

This retrospective study included 223 patients with suspicious breast lesions and pathologically verified results. The histopathological diagnostic criteria were according to the fifth edition of the WHO classification of breast tumors. The KS^* was obtained after a joint evaluation combining the original KS and breast vasculature assessment. The receiver operating characteristic (ROC) curve was used for comparing differences in the diagnostic performance between KS^* and KS, and the area under the receiver operating characteristic (AUC) was compared.

Results

There were 119 (53.4%) benign and 104 (46.6%) malignant lesions in total. The overall sensitivity, specificity, and accuracy of increased ipsilateral breast vascularity were 69.2%, 76.5%, and 73.1%, respectively. The overall sensitivity, specificity, and accuracy of AVS were 82.7%, 76.5%, and 79.4%, respectively. For all lesions included the AUC of KS^* was greater than that of KS (0.877 vs. 0.858, P = 0.016). The largest difference in AUC was observed in the non-mass subgroup (0.793 vs. 0.725, P = 0.029).

Conclusion

Ipsilaterally increased breast vascularity and a positive AVS sign were significantly associated with malignancy. KS combined with breast vascular assessment can effectively improve the diagnostic ability of KS for breast lesions, especially for non-mass lesions.

Combination of ultrafast dynamic contrast-enhanced MRI-based radiomics and artificial neural network in assessing BI-RADS 4 breast lesions: Potential to avoid unnecessary biopsies

Objectives

To investigate whether combining radiomics extracted from ultrafast dynamic contrast-enhanced MRI (DCE-MRI) with an artificial neural network enables differentiation of MR BI-RADS 4 breast lesions and thereby avoids false-positive biopsies.

Methods

This retrospective study consecutively included patients with MR BI-RADS 4 lesions. The ultrafast imaging was performed using Differential sub-sampling with cartesian ordering (DISCO) technique and the tenth and fifteenth postcontrast DISCO images (DISCO-10 and DISCO-15) were selected for further analysis. An experienced radiologist used freely available software (FAE) to perform radiomics extraction. After principal component analysis (PCA), a multilayer perceptron artificial neural network (ANN) to distinguish between malignant and benign lesions was developed and tested using a random allocation approach. ROC analysis was performed to evaluate the diagnostic performance.

Results

173 patients (mean age 43.1 years, range 18-69 years) with 182 lesions (95 benign, 87 malignant) were included. Three types of independent principal components were obtained from the radiomics based on DISCO-10, DISCO-15, and their combination, respectively. In the testing dataset, ANN models showed excellent diagnostic performance with AUC values of 0.915-0.956. Applying the high-sensitivity cutoffs identified in the training dataset demonstrated the potential to reduce the number of unnecessary biopsies by 63.33%-83.33% at the price of one false-negative diagnosis within the testing dataset.

Conclusions

The ultrafast DCE-MRI radiomics-based machine learning model could classify MR BI-RADS category 4 lesions into benign or malignant, highlighting its potential for future application as a new tool for clinical diagnosis.