The role of MRI and clinicopathologic features in predicting the invasive component of biopsy-confirmed ductal carcinoma in situ

Florid Lobular Carcinoma In Situ: Imaging Characteristics and Pathologic Upgrade Rates on Surgical Excision

Background: Florid lobular carcinoma in situ is an uncommon lobular neoplasia variant that is frequently associated with invasive carcinoma. However, there remains a paucity of information to guide management. The authors aimed to study imaging features associated with pathologic upgrade rates for patients with florid lobular carcinoma in situ identified on core biopsy undergoing surgical excision. Methods: Patients with florid lobular carcinoma in situ on core biopsy were selected from an institutional pathology database. Patients were excluded if pleomorphic lobular carcinoma in situ was also present on core biopsy. Clinical, radiologic, and pathologic features for each case were reviewed focusing on imaging features which led to core biopsy and those associated with pathologic upgrade on surgical excision. Results: Eighteen cases of florid lobular carcinoma in situ underwent surgical excision. Upgrade rates on surgical excision were higher in cases with suspicious calcifications (8/11, 73%, p=0.049) compared to those without (1/7, 14.3%) and in cases with larger breast lesions (p=0.011). The overall upgrade rate was 50% (9/18), 89% (8/9) with invasive lobular carcinoma and 11% (1/9) with ductal carcinoma in situ. Of the 8 cases with upgrade to invasive lobular carcinoma, 7/8 (87.5%) were Stage I cancers and only 1/8 (12.5%) had macroscopic lymph node involvement and was upgraded to Stage II. Conclusion: Florid lobular carcinoma in situ on core biopsy had an upgrade rate on surgical excision of 50% overall, with 89% of these cases upgraded to invasive lobular carcinoma. Pathologic upgrade was seen more frequently with suspicious calcifications and larger breast lesions. These findings can help guide surgical management of this uncommon lobular neoplasia variant including planning extent of excision and consideration for lymph node evaluation.

Adding contrast-enhanced ultrasound can improve the predictive ability of breast conventional ultrasound and mammography for pathological upgrade of biopsy-confirmed ductal carcinoma in situ

OBJECTIVES

To evaluate the added value of contrast-enhanced ultrasound (CEUS) on top of breast conventional imaging for predicting the upgrading of ductal carcinoma in situ (DCIS) to invasive cancer after surgery.

METHODS

This retrospective study enrolled 140 biopsy-proven DCIS lesions in 138 patients and divided them into two groups based on postoperative histopathology: non-upgrade and upgrade groups. Conventional ultrasound (US), mammography (MMG), CEUS and clinicopathological (CL) features were reviewed and compared between the two groups. The predictive performance of different models (with and without CEUS features) for histologic upgrade were compared to calculate the added value of CEUS.

RESULTS

Fifty-nine (42.1 %) lesions were histologically upgraded to invasive cancer after surgery. By logistic regression analyses, we found that high-grade DCIS at biopsy (P=0.004), ultrasonographic lesion size > 20 mm (P=0.007), mass-like lesion on US (P=0.030), the presence of suspicious calcification on MMG (P=0.014), the presence of perfusion defect (P=0.005) and the area under TIC>1021.34 ml (P<0.001) on CEUS were six independent factors predicting concomitant invasive components after surgery. The CL+US+MMG model made with the four predictors in the clinicopathologic, US and MMG categories yielded an area under the receiver operating curve (AUROC) value of 0.759 (95 % CI: 0.680-0.828) in predicting histological upgrade. The combination model built by adding the two CEUS predictors to the CL+US+MMG model showed higher predictive efficacy than the CL+US+MMG model (P=0.018), as the AUROC value was improved to 0.861 (95 % CI: 0.793-0.914).

CONCLUSIONS

The addition of contrast-enhanced ultrasound to breast conventional imaging could improve the preoperative prediction of an upgrade to invasive cancer from CNB -proven DCIS lesions.

Clinical and Imaging Characteristics of Contrast-enhanced Mammography and MRI to Distinguish Microinvasive Carcinoma from Ductal Carcinoma In situ

RATIONALE AND OBJECTIVES

The prognosis of ductal carcinoma in situ with microinvasion (DCISM) is more similar to that of small invasive ductal carcinoma (IDC) than to pure ductal carcinoma in situ (DCIS). It is particularly important to accurately distinguish between DCISM and DCIS. The present study aims to compare the clinical and imaging characteristics of contrast-enhanced mammography (CEM) and magnetic resonance imaging (MRI) between DCISM and pure DCIS, and to identify predictive factors of microinvasive carcinoma, which may contribute to a comprehensive understanding of DCISM in clinical diagnosis and support surveillance strategies, such as surgery, radiation, and other treatment decisions.

MATERIALS AND METHODS

Forty-seven female patients diagnosed with DCIS were included in the study from May 2019 to August 2023. Patients were further divided into two groups based on pathological diagnosis: DCIS and DCISM. Clinical and imaging characteristics of these two groups were analyzed statistically. The independent clinical risk factors were selected using multivariate logistic regression and used to establish the logistic model [Logit(P)]. The diagnostic performance of independent predictors was assessed and compared using receiver operating characteristic (ROC) analysis and DeLong's test.

RESULTS

In CEM, the maximum cross-sectional area (CSAmax), the percentage signal difference between the enhancing lesion and background in the craniocaudal and mediolateral oblique projection (%RSCC, and %RSMLO) were found to be significantly higher for DCISM compared to DCIS (p = 0.001; p < 0.001; p = 0.008). Additionally, there were noticeable statistical differences in the patterns of enhancement morphological distribution (EMD) and internal enhancement pattern (IEP) between DCIS and DCISM (p = 0.047; p = 0.008). In MRI, only CSAmax (p = 0.012) and IEP (p = 0.020) showed significant statistical differences. The multivariate regression analysis suggested that CSAmax (in CEM or MR) and %RSCC were independent predictors of DCISM (all p < 0.05). The area under the curve (AUC) of CSAmax (CEM), %RSCC (CEM), Logit(P) (CEM), and CSAmax (MR) were 0.764, 0.795, 0.842, and 0.739, respectively. There were no significant differences in DeLong's test for these values (all p > 0.10). DCISM was significantly associated with high nuclear grade, comedo type, high axillary lymph node (ALN) metastasis, and high Ki-67 positivity compared to DCIS (all p < 0.05).

CONCLUSION

The tumor size (CSAmax), enhancement index (%RS), and internal enhancement pattern (IEP) were highly indicative of DCISM. DCISM tends to express more aggressive pathological features, such as high nuclear grade, comedo-type necrosis, ALN metastasis, and Ki-67 overexpression. As with MRI, CEM has the capability to help predict when DCISM is accompanying DCIS.

The utility of ultrafast MRI and conventional DCE-MRI for predicting histologic aggressiveness in patients with breast cancer

BACKGROUND

Prediction of histologic prognostic markers is important for determining management strategy and predicting prognosis.

PURPOSE

To identify important features of ultrafast and conventional dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) that can predict histopathologic prognostic markers in patients with breast cancer.

MATERIAL AND METHODS

Preoperative MRI scans of 158 consecutive women (mean age = 54.0 years; age range = 29-86 years) with 163 breast cancers between February 2021 and August 2022 were retrospectively reviewed. Inter-observer agreements for ultrafast MRI parameters were analyzed by two radiologists. The qualitative and quantitative MRI parameters were correlated with histopathologic prognostic markers including molecular subtypes and histologic invasiveness.

RESULTS

Inter-observer agreements for ultrafast MRI parameters were excellent (intraclass correlation coefficients of area under the kinetic curve [AUC], maximum slope [MS], maximum enhancement [ME], and slope = 0.987, 0.844, 0.822, and 0.760, respectively). Triple-negative breast cancers (TNBC) were significantly associated with rim enhancement (odds ratio [OR] = 9.4, P = 0.003) and peritumoral edema (OR = 17.9, P = 0.002), compared to luminal cancers. Invasive cancers were associated with lesion type-mass, increased delayed washout, angiovolume, ME, slope, MS, and AUC, compared to in situ cancers. In regression analysis, the combination of MS (>46.2%/s) (OR = 5.7, P = 0.046) and delayed washout (>17.5%) (OR = 17.6, P = 0.01), and that of AUC (>27,410.3) (OR = 9.6, P = 0.04), delayed washout (>17.5%) (OR = 8.9, P = 0.009), and lesion-type mass (OR = 4.6, P = 0.04) were predictive of histologic invasiveness.

CONCLUSION

Conventional DCE-MRI with ultrafast imaging can provide useful information for predicting histologic underestimation and aggressive molecular subtype. MS and AUC on ultrafast MRI can be potential imaging markers for predicting histologic upgrade from DCIS to invasive cancer with high reliability.

Correlations of Imaging and Therapy in Breast Cancer Based on Molecular Patterns: An Important Issue in the Diagnosis of Breast Cancer

Breast cancer is a global health issue affecting countries worldwide, imposing a significant economic burden due to expensive treatments and medical procedures, given the increasing incidence. In this review, our focus is on exploring the distinct imaging features of known molecular subtypes of breast cancer, underlining correlations observed in clinical practice and reported in recent studies. The imaging investigations used for assessment include screening modalities such as mammography and ultrasonography, as well as more complex investigations like MRI, which offers high sensitivity for loco-regional evaluation, and PET, which determines tumor metabolic activity using radioactive tracers. The purpose of this review is to provide a better understanding as well as a revision of the imaging differences exhibited by the molecular subtypes and histopathological types of breast cancer.

Could breast multiparametric MRI discriminate between pure ductal carcinoma in situ and microinvasive carcinoma?

BACKGROUND

Ductal carcinoma in situ (DCIS) is often reclassified as invasive cancer in the final pathology report of the surgical specimen. It is of significant clinical relevance to acknowledge the possibility of underestimating invasive disease when utilizing preoperative biopsies for a DCIS diagnosis. In cases where such histologic upgrades occur, it is imperative to consider them in the preoperative planning process, including the potential inclusion of sentinel lymph node biopsy due to the risk of axillary lymph node metastasis.

PURPOSE

To assess the capability of breast multiparametric magnetic resonance imaging (MP-MRI) in differentiating between pure DCIS and microinvasive carcinoma (MIC).

MATERIAL AND METHODS

Between January 2018 and November 2022, this retrospective study enrolled patients with biopsy-proven DCIS who had undergone preoperative breast MP-MRI. We assessed various MP-MRI features, including size, morphology, margins, internal enhancement pattern, extent of disease, presence of peritumoral edema, time-intensity curve value, diffusion restriction, and ADC value. Subsequently, a logistic regression analysis was conducted to explore the association of these features with the pathological outcome.

RESULTS

Of 129 patients with biopsy-proven DCIS, 36 had foci of micro-infiltration on surgical specimens and eight were diagnosed with invasive ductal carcinoma (IDC). The presence of micro-infiltration foci was significantly associated with several MP-MRI features, including tumor size (P <0.001), clustered ring enhancement (P <0.001), segmental distribution (P <0.001), diffusion restriction (P = 0.005), and ADC values <1.3 × 10-3 mm2/s (P = 0.004).

CONCLUSION

Breast MP-MRI has the potential to predict the presence of micro-infiltration foci in biopsy-proven DCIS and may serve as a valuable tool for guiding therapeutic planning.

Evolving Treatment Paradigms for Low-Risk Ductal Carcinoma In Situ: Imaging Needs

Ductal carcinoma in situ (DCIS) is a nonobligate precursor to invasive cancer that classically presents as asymptomatic calcifications on screening mammography. The increase in DCIS diagnoses with organized screening programs has raised concerns about overdiagnosis, while a patientcentric push for more personalized care has increased awareness about DCIS overtreatment. The standard of care for most new DCIS diagnoses is surgical excision, but nonsurgical management via active monitoring is gaining attention, and multiple clinical trials are ongoing. Imaging, along with demographic and pathologic information, is a critical component of active monitoring efforts. Commonly used imaging modalities including mammography, ultrasound, and MRI, as well as newer modalities such as contrast-enhanced mammography and dedicated breast PET, can provide prognostic information to risk stratify patients for DCIS active monitoring eligibility. Furthermore, radiologists will be responsible for closely surveilling patients on active monitoring and identifying if invasive progression occurs. Active monitoring is a paradigm shift for DCIS care, but the success or failure will rely heavily on the interpretations and guidance of radiologists.

Quantitative peritumoral magnetic resonance imaging fingerprinting improves machine learning-based prediction of overall survival in colorectal cancer

Aim

To investigate magnetic resonance imaging (MRI)-based peritumoral texture features as prognostic indicators of survival in patients with colorectal liver metastasis (CRLM).

Methods

From 2007-2015, forty-eight patients who underwent MRI within 3 months prior to initiating treatment for CRLM were identified. Clinicobiological prognostic variables were obtained from electronic medical records. Ninety-four metastatic hepatic lesions were identified on T1-weighted post-contrast images and volumetrically segmented. A total of 112 radiomic features (shape, first-order, texture) were derived from a 10 mm region surrounding each segmented tumor. A random forest model was applied, and performance was tested by receiver operating characteristic (ROC). Kaplan-Meier analysis was utilized to generate the survival curves.

Results

Forty-eight patients (male:female = 23:25, age 55.3 years ± 18 years) were included in the study. The median lesion size was 25.73 mm (range 8.5-103.8 mm). Microsatellite instability was low in 40.4% (38/94) of tumors, with Ki-ras2 Kirsten rat sarcoma viral oncogene homolog (KRAS) mutation detected in 68 out of 94 (72%) tumors. The mean survival was 35 months ± 21 months, and local disease progression was observed in 35.5% of patients. Univariate regression analysis identified 42 texture features [8 first order, 5 gray level dependence matrix (GLDM), 5 gray level run time length matrix (GLRLM), 5 gray level size zone matrix (GLSZM), 2 neighboring gray tone difference matrix (NGTDM), and 17 gray level co-occurrence matrix (GLCM)] independently associated with metastatic disease progression (P < 0.03). The random forest model achieved an area under the curve (AUC) of 0.88.

Conclusions

MRI-based peritumoral heterogeneity features may serve as predictive biomarkers for metastatic disease progression and patient survival in CRLM.

A clinical radiomics nomogram preoperatively to predict ductal carcinoma in situ with microinvasion in women with biopsy-confirmed ductal carcinoma in situ: a preliminary study

PURPOSE

To predict ductal carcinoma in situ with microinvasion (DCISMI) based on clinicopathologic, conventional breast magnetic resonance imaging (MRI), and dynamic contrast enhanced MRI (DCE-MRI) radiomics signatures in women with biopsy-confirmed ductal carcinoma in situ (DCIS).

METHODS

Eighty-six women with eighty-seven biopsy-proven DCIS who underwent preoperative MRI and underwent surgery were retrospectively identified. Clinicopathologic, conventional MRI, DCE-MRI radiomics, combine (based on conventional MRI and DCE-MRI radiomics), traditional (based on clinicopathologic and conventional MRI) and mixed (based on clinicopathologic, conventional MRI and DCE-MRI radiomics) models were constructed by logistic regression (LR) with a 3-fold cross-validation, all evaluated using receiver operating characteristic (ROC) curve analysis. A clinical radiomics nomogram was then built by incorporating the Radiomics score, significant clinicopathologic and conventional MRI features of mixed model.

RESULTS

The area under the curves (AUCs) of clinicopathologic, conventional MRI, DCE-MRI radiomics, traditional, combine, and mixed model were 0.76 (95% confidence interval [CI] 0.59-0.94), 0.77 (95%CI 0.59-0.95), 0.74 (95%CI 0.55-0.93), 0.87 (95%CI 0.73-1), 0.8 (95%CI 0.63-0.96), and 0.93 (95%CI 0.84-1) in the validation cohort, respectively. The clinical radiomics nomogram based on mixed model showed higher AUCs than both clinicopathologic and DCE-MRI radiomics models in training/test (all P < 0.05) set and showed the greatest overall net benefit for upstaging according to decision curve analysis (DCA).

CONCLUSION

A nomogram constructed by combining clinicopathologic, conventional MRI features and DCE-MRI radiomics signatures may be useful in predicting DCISMI from DICS preoperatively.

An MRI-Based Radiomics Nomogram to Distinguish Ductal Carcinoma In Situ with Microinvasion From Ductal Carcinoma In Situ of Breast Cancer

RATIONALE AND OBJECTIVES

Accurate preoperative differentiation between ductal carcinoma in situ with microinvasion (DCISM) and ductal carcinoma in situ (DCIS) could facilitate treatment optimization and individualized risk assessment. The present study aims to build and validate a radiomics nomogram based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) that could distinguish DCISM from pure DCIS breast cancer.

MATERIALS AND METHODS

MR images of 140 patients obtained between March 2019 and November 2022 at our institution were included. Patients were randomly divided into a training (n = 97) and a test set (n = 43). Patients in both sets were further split into DCIS and DCISM subgroups. The independent clinical risk factors were selected by multivariate logistic regression to establish the clinical model. The optimal radiomics features were chosen by the least absolute shrinkage and selection operator, and a radiomics signature was built. The nomogram model was constructed by integrating the radiomics signature and independent risk factors. The discrimination efficacy of our nomogram was assessed by using calibration and decision curves.

RESULTS

Six features were selected to construct the radiomics signature for distinguishing DCISM from DCIS. The radiomics signature and nomogram model exhibited better calibration and validation performance in the training (AUC 0.815, 0.911, 95% confidence interval [CI], 0.703-0.926, 0.848-0.974) and test (AUC 0.830, 0.882, 95% CI, 0.672-0.989, 0.764-0.999) sets than in the clinical factor model (AUC 0.672, 0.717, 95% CI, 0.544-0.801, 0.527-0.907). The decision curve also demonstrated that the nomogram model exhibited good clinical utility.

CONCLUSION

The proposed noninvasive MRI-based radiomics nomogram model showed good performance in distinguishing DCISM from DCIS.

Active Surveillance for Atypical Ductal Hyperplasia and Ductal Carcinoma In Situ

Atypical ductal hyperplasia (ADH) and ductal carcinoma in situ (DCIS) are relatively common breast lesions on the same spectrum of disease. Atypical ductal hyperblasia is a nonmalignant, high-risk lesion, and DCIS is a noninvasive malignancy. While a benefit of screening mammography is early cancer detection, it also leads to increased biopsy diagnosis of noninvasive lesions. Previously, treatment guidelines for both entities included surgical excision because of the risk of upgrade to invasive cancer after surgery and risk of progression to invasive cancer for DCIS. However, this universal management approach is not optimal for all patients because most lesions are not upgraded after surgery. Furthermore, some DCIS lesions do not progress to clinically significant invasive cancer. Overtreatment of high-risk lesions and DCIS is considered a burden on patients and clinicians and is a strain on the health care system. Extensive research has identified many potential histologic, clinical, and imaging factors that may predict ADH and DCIS upgrade and thereby help clinicians select which patients should undergo surgery and which may be appropriate for active surveillance (AS) with imaging. Additionally, multiple clinical trials are currently underway to evaluate whether AS for DCIS is feasible for a select group of patients. Recent advances in MRI, artificial intelligence, and molecular markers may also have an important role to play in stratifying patients and delineating best management guidelines. This review article discusses the available evidence regarding the feasibility and limitations of AS for ADH and DCIS, as well as recent advances in patient risk stratification.

Outcomes and imaging features of microinvasive carcinoma and ductal carcinoma in situ: Matched cohort study

INTRODUCTION

The purpose of this study is to investigate the differences in clinical outcomes between microinvasive carcinoma (mIC) and ductal carcinoma in situ (DCIS) and compare the imaging features of both using mammography, US and MRI.

MATERIALS AND METHODS

This retrospective study was approved by our institutional review board. Between January 2011 and December 2013, 516 women with mIC or DCIS confirmed by surgery were included. Patients were matched with propensity score matching to compare recurrence-free survival (RFS). RFS was compared using a Cox proportional hazards model. Imaging features were also compared between the two groups.

RESULTS

Among 516 women, 219 mIC and 297 DCIS tumors were identified. After matching, 132 women were allocated to each group. The mean follow-up duration was 80.2 months. In the matched cohort, no statistically significant association was observed between the DCIS and mIC groups in terms of total recurrence (hazard ratio [HR]: 1.7; 95% confidence interval [CI]: 0.8-4.0; P = 0.19), local-regional recurrence (HR: 3.4; 95% CI: 0.9-12.3, P = 0.07), or contralateral recurrence (HR: 0.9; 95% CI: 0.3-2.8, P = 0.89). Non-mass lesions at US (P = 0.004), moderate or marked background parenchymal enhancement (P = 0.04), and higher peak enhancement (P = 0.02) at MRI were more commonly seen in the mIC group than in the DCIS group.

CONCLUSION

Microinvasive carcinomas are distinct from DCIS in terms of imaging features, but no statistically significant association in recurrence survival.

Preoperative Breast MRI: Current Evidence and Patient Selection

Breast MRI is the most sensitive imaging modality for the assessment of newly diagnosed breast cancer extent and can detect additional mammographically and clinically occult breast cancers in the ipsilateral and contralateral breasts. Nonetheless, appropriate use of breast MRI in the setting of newly diagnosed breast cancer remains debated. Though highly sensitive, MRI is less specific and may result in false positives and overestimation of disease when MRI findings are not biopsied prior to surgical excision. Furthermore, improved anatomic depiction of breast cancer on MRI has not consistently translated to improved clinical outcomes, such as lower rates of re-excision or breast cancer recurrence, though there is a paucity of well-designed studies examining these issues. In addition, current treatment paradigms have been developed in the absence of this more accurate depiction of disease span, which likely has limited the value of MRI. These issues have led to inconsistent and variable utilization of preoperative MRI across practice settings and providers. In this review, we discuss the history of breast MRI and its current use and recommendations with a focus on the preoperative setting. We review the evidence surrounding the use of preoperative MRI in the evaluation of breast malignancies and discuss the data on breast MRI in the setting of specific patient factors often used to determine breast MRI eligibility, such as age, index tumor phenotype, and breast density. Finally, we review the impact of breast MRI on surgical outcomes (re-excision and mastectomy rates) and long-term breast recurrence and survival outcomes.

Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms

The prediction of an occult invasive component in ductal carcinoma in situ (DCIS) before surgery is of clinical importance because the treatment strategies are different between pure DCIS without invasive component and upgraded DCIS. We demonstrated the potential of using deep learning models for differentiating between upgraded versus pure DCIS in DCIS diagnosed by core-needle biopsy. Preoperative axial dynamic contrast-enhanced magnetic resonance imaging (MRI) data from 352 lesions were used to train, validate, and test three different types of deep learning models. The highest performance was achieved by Recurrent Residual Convolutional Neural Network using Regions of Interest (ROIs) with an accuracy of 75.0% and area under the receiver operating characteristic curve (AUC) of 0.796. Our results suggest that the deep learning approach may provide an assisting tool to predict the histologic upgrade of DCIS and provide personalized treatment strategies to patients with underestimated invasive disease.

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

Objective

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.

Materials and methods

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.

Results

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.

Conclusion

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.

Diffusion-weighted Breast MRI in Prediction of Upstaging in Women with Biopsy-proven Ductal Carcinoma in Situ

Background Accurate preoperative prediction of upstaging in women with biopsy-proven ductal carcinoma in situ (DCIS) is important for surgical planning, but published models using predictive MRI features remain lacking. Purpose To develop and validate a predictive model based on preoperative breast MRI to predict upstaging in women with biopsy-proven DCIS and to select high-risk women who may benefit from sentinel lymph node biopsy at initial surgery. Materials and methods Consecutive women with biopsy-proven DCIS who underwent preoperative 3.0-T breast MRI including dynamic contrast-enhanced (DCE) MRI and diffusion-weighted imaging (DWI) and who underwent surgery between June 2019 and March 2020 were retrospectively identified (development set) from an academic medical center. The apparent diffusion coefficients of lesions from DWI, lesion size and morphologic features on DCE MRI scans, mammographic findings, age, symptoms, biopsy method, and DCIS grade at biopsy were collected. The presence of invasive cancer and axillary metastases was determined with surgical pathology. A predictive model for upstaging was developed by using multivariable logistic regression and validated in a subsequent prospective internal validation set recruited between July 2020 and April 2021. Results Fifty-seven (41%) of 140 women (mean age, 53 years ± 11 [SD]) in the development set and 43 (41%) of 105 women (mean age, 53 years ± 10) in the validation set were upstaged after surgery. The predictive model combining DWI and clinical-pathologic factors showed the areas under the receiver operating characteristic curve at 0.87 (95% CI: 0.80, 0.92) in the development set and 0.76 (95% CI: 0.67, 0.84) in the validation set. The predicted probability of invasive cancer showed good interobserver agreement (intraclass correlation coefficient, 0.79); the positive predictive value was 85% (28 of 33), and the negative predictive value was 92% (22 of 24). Conclusion A predictive model based on diffusion-weighted breast MRI identified women at high risk of upstaging. © RSNA, 2022 Online supplemental material is available for this article See also the editorial by Baltzer in this issue.

Improving ductal carcinoma in situ classification by convolutional neural network with exponential linear unit and rank-based weighted pooling

Ductal carcinoma in situ (DCIS) is a pre-cancerous lesion in the ducts of the breast, and early diagnosis is crucial for optimal therapeutic intervention. Thermography imaging is a non-invasive imaging tool that can be utilized for detection of DCIS and although it has high accuracy (~ 88%), it is sensitivity can still be improved. Hence, we aimed to develop an automated artificial intelligence-based system for improved detection of DCIS in thermographs. This study proposed a novel artificial intelligence based system based on convolutional neural network (CNN) termed CNN-BDER on a multisource dataset containing 240 DCIS images and 240 healthy breast images. Based on CNN, batch normalization, dropout, exponential linear unit and rank-based weighted pooling were integrated, along with L-way data augmentation. Ten runs of tenfold cross validation were chosen to report the unbiased performances. Our proposed method achieved a sensitivity of 94.08 ± 1.22%, a specificity of 93.58 ± 1.49 and an accuracy of 93.83 ± 0.96. The proposed method gives superior performance than eight state-of-the-art approaches and manual diagnosis. The trained model could serve as a visual question answering system and improve diagnostic accuracy.

Contrast-Enhanced Mammographic Features of In Situ and Invasive Ductal Carcinoma Manifesting Microcalcifications Only: Help to Predict Underestimation?

BACKGROUND

The contrast-enhanced mammographic features of ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) manifesting microcalcifications only on mammograms were evaluated to determine whether they could predict IDC underestimation.

METHODS

We reviewed patients who underwent mammography-guided biopsy on suspicious breast microcalcifications only and received contrast-enhanced spectral mammography (CESM) within 2 weeks before the biopsy. Those patients who were proven to have cancers (DCIS or IDC) by biopsy and subsequently had surgical treatment in our hospital were included for analysis. The presence or absence, size, morphology and texture of enhancement on contrast-enhanced spectral mammography were reviewed by consensus of two radiologists.

RESULTS

A total of 49 patients were included for analysis. Forty patients (81.6%) showed enhancement, including 18 (45%) DCIS and 22 (55%) IDC patients. All nine unenhanced cancers were pure DCIS. Pure DCIS showed 72.22% nonmass enhancement and 83.33% pure ground glass enhancement. IDC showed more mass (72.2% vs. 27.8%) and solid enhancements (83.33% vs. 16.67%). The cancer and texture of enhancement were significantly different between pure DCIS and IDC, with moderate diagnostic performance for the former (p-value < 0.01, AUC = 0.66, sensitivity = 93%, specificity = 39%) and the latter (p-value < 0.01, AUC = 0.74, sensitivity = 65%, specificity = 83%). Otherwise, pure DCIS showed a significant difference in enhanced texture compared with upgraded IDC and IDC (p = 0.0226 and 0.0018, respectively).

CONCLUSIONS

Nonmass and pure ground glass enhancements were closely related to pure DCIS, and cases showing mass and unpurified solid enhancements should be suspected as IDC. Unenhanced DCIS with microcalcifications only has a low DCIS upgrade rate. The CESM-enhanced features could feasibly predict IDC underestimation.

Breast MRI in DCIS size estimation, breast-conserving surgery and oncoplastic breast surgery

The impact of MRI on improving surgical outcomes in DCIS is debated. Here, we explore the utility of MRI in the investigation and management of DCIS in three key areas. Firstly, we highlight that MRI is likely to be a more accurate predictor of actual tumour size than conventional imaging. Secondly, we examine mastectomy rates and reoperation rates across the literature and suggest that surgical outcomes do not differ between pre-operative MRI and conventional imaging groups, despite improved size estimation on MRI. Finally, we examine the rapidly developing field of oncoplastic breast surgery and highlight a paucity of data in determining the usefulness of pre-operative MRI in this field, despite this being an oncologically safe alternative with improved patient outcomes and satisfaction.

Clinical and imaging characteristics of breast ductal carcinoma in situ with microinvasion

Background

We analyzed the clinical and imaging characteristics of patients with breast ductal carcinoma in situ with microinvasion (DCISM) and breast ductal carcinoma in situ (DCIS).

Methods

We analyzed the records of 40 patients diagnosed with DCISM and 61 patients with DCIS who were hospitalized at Shengjing Hospital (Shenyang, China) from January 2009 to June 2016. The size, hardness, and degree of calcification of tumors were determined by mammography and ultrasonography.

Results

In all, 37 DCISM patients and 45 DCIS patients showed clinical palpable masses (92.5% vs 73.77%, P = 0.018). Mammography showed that the mean size of tumor was larger in DCISM patients than that of DCIS patients (3.13 ± 1.51 vs 2.68 ± 1.77, P = 0.030). Ultrasound examination revealed calcification shadows in the solid tumor mass in 17 DCISM cases and 11 DCIS patients (42.5 vs 18.03%, P = 0.007). Furthermore, estrogen receptor positivity and progesterone receptor positivity were more common in DCIS patients (32.5% vs 54.10%, P = 0.033; 22.5% vs 45.90%, P = 0.017), and the percentage of menopausal patients were higher in DCISM patients than that of DCIS patients (70.00% vs 47.54%, P = 0.026).

Conclusion

Clinically palpable and calcified tumor masses on sonography are more commonly encountered in DCISM lesions.