Prediction of pathologic complete response on MRI in patients with breast cancer receiving neoadjuvant chemotherapy according to molecular subtypes

Prediction model for individualized precision surgery in breast cancer patients with complete response on MRI and residual calcifications on mammography after neoadjuvant chemotherapy

BACKGROUND

Identifying whether there is residual carcinoma in remaining suspicious calcifications after neoadjuvant chemotherapy (NAC) in breast cancer patients can provide crucial information for surgeons in determining the most appropriate surgical approach. Therefore, we investigated factors predicting calcifications without residual carcinoma (ypCalc_0) or with residual carcinoma (ypCalc_ca) and aimed to develop a prediction model for patients exhibiting residual suspicious calcifications on mammography but complete response on MRI after NAC.

METHODS

This retrospective study included breast cancer patients undergoing NAC, showing residual suspicious mammographic calcifications but complete response on MRI between January 2019 and December 2020 (development set) and between January 2021 and December 2022 (validation set). Multivariable logistic regression analysis identified significant factors associated with ypCalc_0. The prediction model, developed using a decision tree and factors from logistic regression analysis, was validated in the validation set.

RESULTS

The development set included 134 women (mean age, 50.6 years; 91 with ypCalc_0 and 43 with ypCalc_ca) and validation set included 146 women (mean age, 51.0 years; 108 with ypCalc_0 and 38 with ypCalc_ca). Molecular subtype (P = .0002) and high Ki-67 (P = .02) emerged as significant independent factors associated with ypCalc_0 in the development set. The prediction model, incorporating hormone receptor (HR)-/human epidermal growth factor receptor 2 (HER2)+ with high Ki-67 as ypCalc_0 predictors, and HR+/HER2- cancers or HR+/HER2+ or triple-negative (TN) cancers with low Ki-67, as ypCalc_ca predictors, achieved an area under receiver operating characteristic curve of 0.844 (95% CI 0.774-0.914) in the validation set.

CONCLUSION

Minimized surgery may be considered for managing residual calcifications in HR-/HER2+ with high Ki-67 cancers, while complete excision is recommended for HR+/HER2- breast cancers or for HR+/HER2+or TN breast cancers with low Ki-67.

Comparison of radiomics-based machine-learning classifiers for the pretreatment prediction of pathologic complete response to neoadjuvant therapy in breast cancer

Background

Machine learning classifiers are increasingly used to create predictive models for pathological complete response (pCR) in breast cancer after neoadjuvant therapy (NAT). Few studies have compared the effectiveness of different ML classifiers. This study evaluated radiomics models based on pre- and post-contrast first-phase T1 weighted images (T1WI) in predicting breast cancer pCR after NAT and compared the performance of ML classifiers.

Methods

This retrospective study enrolled 281 patients undergoing NAT from the Duke-Breast-Cancer-MRI dataset. Radiomic features were extracted from pre- and post-contrast first-phase T1WI images. The Synthetic Minority Oversampling Technique (SMOTE) was applied, then the dataset was randomly divided into training and validation groups (7:3). The radiomics model was built using selected optimal features. Support vector machine (SVM), random forest (RF), decision tree (DT), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were classifiers. Receiver operating characteristic curves were used to assess predictive performance.

Results

LightGBM performed best in predicting pCR [area under the curve (AUC): 0.823, 95% confidence interval (CI) [0.743-0.902], accuracy 74.0%, sensitivity 85.0%, specificity 67.2%]. During subgroup analysis, RF was most effective in pCR prediction in luminal breast cancers (AUC: 0.914, 95% CI [0.847-0.981], accuracy 87.0%, sensitivity 85.2%, specificity 88.1%). In triple-negative breast cancers, LightGBM performed best (AUC: 0.836, 95% CI [0.708-0.965], accuracy 78.6%, sensitivity 68.2%, specificity 90.0%).

Conclusion

The LightGBM-based radiomics model performed best in predicting pCR in patients with breast cancer. RF and LightGBM showed promising results for luminal and triple-negative breast cancers, respectively.

Radiological, pathological and surgical outcomes after neoadjuvant endocrine treatment in patients with ER-positive/HER2-negative breast cancer with a clinical high risk and a low-risk 70-gene signature

OBJECTIVE

This study aims to evaluate the response to and surgical benefits of neoadjuvant endocrine therapy (NET) in ER+/HER2-breast cancer patients who are clinically high risk, but genomic low risk according to the 70-gene signature (MammaPrint).

METHODS

Patients with ER+/HER2-invasive breast cancer with a clinical high risk according to MINDACT, who had a genomic low risk according to the 70-gene signature and were treated with NET between 2015 and 2023 in our center, were retrospectively analyzed. RECIST 1.1 criteria were used to assess radiological response using MRI or ultrasound. Surgical specimens were evaluated to assess pathological response. Two breast cancer surgeons independently scored the eligibility of breast conserving therapy (BCS) pre- and post- NET.

RESULTS

Of 72 included patients, 23 were premenopausal (100% started with tamoxifen of which 4 also received OFS) and 49 were postmenopausal (98% started with an aromatase inhibitor). Overall, 8 (11%) showed radiological complete response. Only 1 (1.4%) patient had a pathological complete response (RCB-0) and 68 (94.4%) had a pathological partial response (RCB-1 or RCB-2). Among the 26 patients initially considered for mastectomy, 14 (53.8%) underwent successful BCS. In all 20 clinical node-positive patients, a marked axillary lymph node was removed to assess response. Four out of 20 (20%) patients had a pathological complete response of the axilla.

CONCLUSION

The study showed that a subgroup of patients with a clinical high risk and a genomic low risk ER+/HER2-breast cancer benefits from NET resulting in BCS instead of a mastectomy. Additionally, NET may enable de-escalation in axillary treatment.

Breast surgery after neoadjuvant chemotherapy in patients with lobular carcinoma: surgical and oncologic outcome

INTRODUCTION

Breast cancer patients with invasive lobular carcinoma (ILC) have an increased risk of positive margins after surgery and often show little response to neoadjuvant chemotherapy (NAC). We aimed to investigate surgical outcomes in patients with ILC treated with NAC.

METHODS

In this retrospective cohort study, all breast cancer patients with ILC treated with NAC who underwent surgery at the Netherlands Cancer Institute from 2010 to 2019 were selected. Patients with mixed type ILC in pre-NAC biopsies were excluded if the lobular component was not confirmed in the surgical specimen. Main outcomes were tumor-positive margins and re-excision rate. Associations between baseline characteristics and tumor-positive margins were assessed, as were complications, locoregional recurrence rate (LRR), recurrence-free survival (RFS), and overall survival (OS).

RESULTS

We included 191 patients. After NAC, 107 (56%) patients had breast conserving surgery (BCS) and 84 (44%) patients underwent mastectomy. Tumor-positive margins were observed in 67 (35%) patients. Fifty five (51%) had BCS and 12 (14%) underwent mastectomy (p value < 0.001). Re-excision was performed in 35 (33%) patients with BCS and in 4 (5%) patients with mastectomy. Definitive surgery was mastectomy in 107 (56%) patients and BCS in 84 (44%) patients. Tumor-positive margins were associated with cT ≥ 3 status (OR 4.62, 95% CI 1.26-16.98, p value 0.021) in the BCS group. Five-year LRR (4.7%), RFS (81%), and OS (93%) were not affected by type of surgery after NAC.

CONCLUSION

Although 33% of ILC breast cancer patients undergoing BCS after NAC required re-excision for positive resection margins, it is considered safe given that five-year RFS remained excellent and LRR and OS did not differ by extent of surgery.

Optimizing surgical strategy in locally advanced breast cancer: a comparative analysis between preoperative MRI and postoperative pathology after neoadjuvant chemotherapy

PURPOSE

In the treatment of breast cancer, neo-adjuvant chemotherapy is often used as systemic treatment followed by tumor excision. In this context, planning the operation with regard to excision margins relies on tumor size measured by MRI. The actual tumor size can be determined through pathologic evaluation. The aim of this study is to investigate the correlation and agreement between pre-operative MRI and postoperative pathological evaluation.

METHODS

One hundred and ninety-three breast cancer patients that underwent neo-adjuvant chemotherapy and subsequent breast surgery were retrospectively included between January 2013 and July 2016. Preoperative tumor diameters determined with MRI were compared with postoperative tumor diameters determined by pathological analysis. Spearman correlation and Bland-Altman agreement methods were used. Results were subjected to subgroup analysis based on histological subtype (ER, HER2, ductal, lobular).

RESULTS

The correlation between tumor size at MRI and pathology was 0.63 for the whole group, 0.39 for subtype ER + /HER2-, 0.51 for ER + /HER2 + , 0.63 for ER-/HER2 +, and 0.85 for ER-/HER2-. The mean difference and limits of agreement (LoA) between tumor size measured MRI vs. pathological assessment was 4.6 mm (LoA -27.0-36.3 mm, n = 195). Mean differences and LoA for subtype ER + /HER2- was 7.6 mm (LoA -31.3-46.5 mm, n = 100), for ER + /HER2 + 0.9 mm (LoA -8.5-10.2 mm, n = 33), for ER-/HER2+ -1.2 mm (LoA -5.1-7.5 mm, n = 21), and for ER-/HER- -0.4 mm (LoA -8.6-7.7 mm, n = 41).

CONCLUSION

HER2 + and ER-/HER2- tumor subtypes showed clear correlation and agreement between preoperative MRI and postoperative pathological assessment of tumor size. This suggests that MRI evaluation could be a suitable predictor to guide the surgical approach. Conversely, correlation and agreement for ER + /HER2- and lobular tumors was poor, evidenced by a difference in tumor size of up to 5 cm. Hence, we demonstrate that histological tumor subtype should be taken into account when planning breast conserving surgery after NAC.

The accuracy of MRI in detecting pathological complete response following neoadjuvant chemotherapy in different breast cancer subtypes

BACKGROUND

Pathological complete response (pCR) following neo-adjuvant chemotherapy (NACT) for breast cancer is associated with improved disease-free and overall survival in certain breast cancer subtypes. Magnetic Resonance Imaging (MRI) is increasingly used as standard to assess treatment response in patients receiving NACT. The aim of this study was to determine the clinical utility of MRI in accurately predicting pCR post-NACT.

METHODS

A single-centre, retrospective study was conducted in breast cancer patients, who received NACT between 2013 and 2020. Patients who had an MRI before and after NACT were included. Pathological and MRI radiological response rates to NACT were analyzed and MRI accuracy assessed in detecting pCR according to breast cancer subtype.

RESULTS

One hundred and sixty-seven patients were included in the study. Forty-one of the 167 patients achieved pCR (24.6 %), with the highest proportion in HR- HER2+ subgroup (58.3 %), followed by triple negative breast cancer (TNBC) (35 %). Only 22.2 % and 10.5 % of patients with HR + HER2+ and HR + HER2-respectively achieved pCR. The overall accuracy of MRI in predicting pCR after NACT was 77.3 %. The greatest accuracy was in TNBC (87.5 %) with a specificity and positive predictive value (PPV) of 100 % and the highest number of correctly diagnosed complete responses (14 of 40). MRI was less accurate in predicting response rates in HR + HER2- (PPV 91.2 %) and HR + HER2+ groups (PPV 90.5 %). MRI performed significantly better in predicting complete response in TNBC compared to HR + HER2-subtype (p = 0.0057).

CONCLUSION

MRI is a clinically useful adjunct in assessing pCR following NACT and appears to predict pathological response more accurately in TNBC compared to HR + HER2-breast cancer subtypes. This has significant clinical implications in terms of surgical planning, adjuvant treatment options and prognosis.

Impact of Imaging Biomarkers and AI on Breast Cancer Management: A Brief Review

Breast cancer stands out as the most frequently identified malignancy, ranking as the fifth leading cause of global cancer-related deaths. The American College of Radiology (ACR) introduced the Breast Imaging Reporting and Data System (BI-RADS) as a standard terminology facilitating communication between radiologists and clinicians; however, an update is now imperative to encompass the latest imaging modalities developed subsequent to the 5th edition of BI-RADS. Within this review article, we provide a concise history of BI-RADS, delve into advanced mammography techniques, ultrasonography (US), magnetic resonance imaging (MRI), PET/CT images, and microwave breast imaging, and subsequently furnish comprehensive, updated insights into Molecular Breast Imaging (MBI), diagnostic imaging biomarkers, and the assessment of treatment responses. This endeavor aims to enhance radiologists' proficiency in catering to the personalized needs of breast cancer patients. Lastly, we explore the augmented benefits of artificial intelligence (AI), machine learning (ML), and deep learning (DL) applications in segmenting, detecting, and diagnosing breast cancer, as well as the early prediction of the response of tumors to neoadjuvant chemotherapy (NAC). By assimilating state-of-the-art computer algorithms capable of deciphering intricate imaging data and aiding radiologists in rendering precise and effective diagnoses, AI has profoundly revolutionized the landscape of breast cancer radiology. Its vast potential holds the promise of bolstering radiologists' capabilities and ameliorating patient outcomes in the realm of breast cancer management.

A Diagnostic Dilemma: New Enhancing Suspicious Findings on Breast MRI Following Neoadjuvant Chemotherapy

OBJECTIVE

Evaluate the incidence and outcome of new enhancing findings on breast MRI after neoadjuvant chemotherapy (NAC).

METHODS

This IRB-approved retrospective review included women with breast cancer undergoing MRI to evaluate NAC response at our institution from January 1, 1998 to March 3, 2021. Post-NAC MRIs given BI-RADS 4 or 5 with new enhancing findings were identified. Patients were excluded if they lacked pretreatment MRI or insufficient follow-up, or if the finding was a satellite of the primary tumor. Medical records and imaging studies were reviewed to identify patients and to find characteristics and outcomes.

RESULTS

Over the study period, 2880 post-NAC breast MRIs were performed. Of 128 post-NAC MRIs given BI-RADS 4 or 5 (4.4%), 35 new suspicious findings were found on 32 MRIs, incidence rate 1.1% (32/2880). Most were characterized as nonmass enhancement (17/35, 49%), followed by mass (11/35, 31%), and then focus (7/35, 20%), with an average maximum dimension of 1.3 cm (range 0.3-7.1 cm). New findings were ipsilateral to the index cancer in 20/35 (57%) of cases. Of the 35 suspicious findings, 22 underwent image-guided biopsy (62%), 1 was surgically excised (3%), 7 underwent mastectomy (20%), 5 were stable or resolved on follow-up (8%), and none were malignant. Thirty-three were benign (94%), and two were benign high-risk lesions (atypical ductal hyperplasia, radial scar) (6%).

CONCLUSION

New suspicious breast MRI findings after NAC are uncommon with a low likelihood of malignancy. Further study is warranted using multi-institutional data for this low incidence finding.

Preoperative Partial Breast Irradiation in Patients with Low-Risk Breast Cancer: A Systematic Review of Literature

BACKGROUND

Preoperative instead of standard postoperative partial breast irradiation (PBI) after breast-conserving surgery (BCS) has the advantage of reducing the irradiated breast volume, toxicity, and number of radiotherapy sessions and can allow tumor downstaging. In this review, we assessed tumor response and clinical outcomes after preoperative PBI.

PATIENTS AND METHODS

We conducted a systematic review of studies on preoperative PBI in patients with low-risk breast cancer using the databases Ovid Medline, Embase.com, Web of Science (Core Collection), and Scopus (PROSPERO registration CRD42022301435). References of eligible manuscripts were checked for other relevant manuscripts. The primary outcome measure was pathologic complete response (pCR).

RESULTS

A total of eight prospective and one retrospective cohort study were identified (n = 359). In up to 42% of the patients, pCR was obtained and this increased after a longer interval between radiotherapy and BCS (0.5-8 months). After a maximum median follow-up of 5.0 years, three studies on external beam radiotherapy reported low local recurrence rates (0-3%) and overall survival of 97-100%. Acute toxicity consisted mainly of grade 1 skin toxicity (0-34%) and seroma (0-31%). Late toxicity was predominantly fibrosis grade 1 (46-100%) and grade 2 (10-11%). Cosmetic outcome was good to excellent in 78-100% of the patients.

CONCLUSIONS

Preoperative PBI showed a higher pCR rate after a longer interval between radiotherapy and BCS. Mild late toxicity and good oncological and cosmetic outcomes were reported. In the ongoing ABLATIVE-2 trial, BCS is performed at a longer interval of 12 months after preoperative PBI aiming to achieve a higher pCR rate.

Abbreviated Versus Full-Protocol MRI for Breast Cancer Neoadjuvant Chemotherapy Response Assessment: Diagnostic Performance by General and Breast Radiologists

BACKGROUND. Abbreviated protocols could allow wider adoption of MRI in patients undergoing breast cancer neoadjuvant chemotherapy (NAC). However, abbreviated MRI has been explored primarily in screening settings. OBJECTIVE. The purpose of this article was to compare diagnostic performance of abbreviated MRI and full-protocol MRI for evaluation of breast cancer NAC response, stratifying by radiologists' breast imaging expertise. METHODS. This retrospective study included 203 patients with breast cancer (mean age, 52.1 ± 11.2 [SD] years) from two hospitals who underwent MRI before NAC initiation and after NAC completion before surgical resection from March 2017 to April 2021. Abbreviated MRI was extracted from full-protocol MRI and included the axial T2-weighted sequence and precontrast and single early postcontrast T1-weighted sequences. Three general radiologists and three breast radiologists independently interpreted abbreviated and full-protocol MRI in separate sessions, identifying enhancing lesions to indicate residual tumor and measuring lesion size. The reference standard was presence and size of residual tumor on pathologic assessment of post-NAC surgical specimens. RESULTS. A total of 50 of 203 patients had pathologic complete response (pCR). Intraobserver and interobserver agreement for abbreviated and full-protocol MRI for general and breast radiologists ranged from substantial to nearly perfect (κ = 0.70-0.81). Abbreviated MRI compared with full-protocol MRI showed no significant difference for general radiologists in sensitivity (54.7% vs 57.3%, p > .99), specificity (92.8% vs 95.6%, p = .29), or accuracy (83.4% vs 86.2%, p = .30), nor for breast radiologists in sensitivity (60.0% vs 61.3%, p > .99), specificity (94.6% vs 97.4%, p = .22), or accuracy (86.0% vs 88.5%, p = .30). Sensitivity, specificity, and accuracy were not significantly different between protocols for any reader individually (p > .05). Mean difference in residual tumor size on MRI relative to pathology for abbreviated protocol ranged for general radiologists from -0.19 to 0.03 mm and for breast radiologists from -0.15 to -0.05 mm, and for full protocol ranged for general radiologists from 0.57 to 0.65 mm and for breast radiologists from 0.66 to 0.79 mm. CONCLUSION. Abbreviated compared with full-protocol MRI showed similar intraobserver and interobserver agreement and no significant difference in diagnostic performance. Full-protocol MRI but not abbreviated MRI slightly overestimated pathologic tumor sizes. CLINICAL IMPACT. Abbreviated protocols may facilitate use of MRI for post-NAC response assessment by general and breast radiologists.

Assessment of malignant risk stratification for microcalcifications interpreted as “amorphous” morphology on mammography: A study based on the 5th edition of breast Imaging Reporting and Data System

PURPOSE

To investigate the malignant risk stratification of microcalcifications interpreted as amorphous morphology on mammography according to the coexistence of punctate microcalcifications based on the 5th edition of the Breast Imaging Reporting and Data System.

METHOD

Between March 2013 and September 2020, 367 microcalcifications interpreted as amorphous morphology on mammography with surgical biopsies were included. The amorphous microcalcifications were classified into a predominantly punctate group (A, <50% of amorphous), a predominantly amorphous group (B, >50% of amorphous), and an only amorphous group (C, 100% of amorphous). The distribution was classified into diffuse, regional, grouped, and linear/segmental. The reference standard was the pathology. The positive predictive values (PPV) were calculated and compared using the Chi-square's test or Fisher's exact test and Kruskal-Wallis test.

RESULTS

The overall PPV of microcalcifications interpreted as having an amorphous morphology was 5.2%. The PPV across groups significantly increased in proportion to the amorphous morphology, with 1.0% in group A, 5.6% in group B, and 23.3% in group C (p <.001). Furthermore, the PPV between group A and groups B plus C (10.1%) and groups A plus B (2.8%) and group C were significantly different (p <.001). The PPV of distribution was 0% for diffuse, 4.9% for regional, 5.0% for grouped, and 11.1% for linear/segmental distributions, without statistical significance.

CONCLUSIONS

Pure amorphous microcalcifications are suitable for category 4B. However, when they coexist with punctate morphology, the malignant risk decreases suitable for category 4A or lower. When amorphous microcalcifications coexist with a predominantly punctate morphology, follow-up should be considered.

Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using radiomics of pretreatment dynamic contrast-enhanced MRI

PURPOSE

To investigate if the pretreatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-based radiomics machine learning predicts the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer patients.

METHODS

Seventy-eight breast cancer patients who underwent DCE-MRI before NAC and confirmed as pCR or non-pCR were enrolled. Early enhancement mapping images of pretreatment DCE-MRI were created using subtraction formula as follows: Early enhancement mapping = (Signal _{1 min} - Signal _pre)/Signal _pre. Images of the whole tumors were manually segmented and radiomics features extracted. Five prediction models were built using five scenarios that included clinical information, subjective radiological findings, first order texture features, second order texture features, and their combinations. In texture analysis workflow, the corresponding variables were identified by mutual information for feature selection and random forest was used for model prediction. In five models, the area under the receiver operating characteristic curves (AUC) to predict the pCR and several metrics for model evaluation were analyzed.

RESULTS

The best diagnostic performance based on F-score was achieved when both first and second order texture features with clinical information and subjective radiological findings were used (AUC = 0.77). The second best diagnostic performance was achieved with an AUC of 0.76 for first order texture features followed by an AUC of 0.76 for first and second order texture features.

CONCLUSIONS

Pretreatment DCE-MRI can improve the prediction of pCR in breast cancer patients when all texture features with clinical information and subjective radiological findings are input to build the prediction model.

Breast cancer diagnosis in an early stage using novel deep learning with hybrid optimization technique

Breast cancer is one of the primary causes of death that is occurred in females around the world. So, the recognition and categorization of initial phase breast cancer are necessary to help the patients to have suitable action. However, mammography images provide very low sensitivity and efficiency while detecting breast cancer. Moreover, Magnetic Resonance Imaging (MRI) provides high sensitivity than mammography for predicting breast cancer. In this research, a novel Back Propagation Boosting Recurrent Wienmed model (BPBRW) with Hybrid Krill Herd African Buffalo Optimization (HKH-ABO) mechanism is developed for detecting breast cancer in an earlier stage using breast MRI images. Initially, the MRI breast images are trained to the system, and an innovative Wienmed filter is established for preprocessing the MRI noisy image content. Moreover, the projected BPBRW with HKH-ABO mechanism categorizes the breast cancer tumor as benign and malignant. Additionally, this model is simulated using Python, and the performance of the current research work is evaluated with prevailing works. Hence, the comparative graph shows that the current research model produces improved accuracy of 99.6% with a 0.12% lower error rate.