A priori prediction of breast cancer response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivative and molecular subtype.

The purpose of this study was to investigate the performances of the tumor response prediction prior to neoadjuvant chemotherapy based on quantitative ultrasound, tumour core-margin, texture derivative analyses, and molecular parameters in a large cohort of patients (n = 208) with locally advanced and earlier-stage breast cancer and combined them to best determine tumour responses with machine learning approach. Two multi-features response prediction algorithms using a k-nearest neighbour and support vector machine were developed with leave-one-out and hold-out cross-validation methods to evaluate the performance of the response prediction models. In a leave-one-out approach, the quantitative ultrasound-texture analysis based model attained good classification performance with 80% of accuracy and AUC of 0.83. Including molecular subtype in the model improved the performance to 83% of accuracy and 0.87 of AUC. Due to limited number of samples in the training process, a model developed with a hold-out approach exhibited a slightly higher bias error in classification performance. The most relevant features selected in predicting the response groups are core-to-margin, texture-derivative, and molecular subtype. These results imply that that baseline tumour-margin, texture derivative analysis methods combined with molecular subtype can potentially be used for the prediction of ultimate treatment response in patients prior to neoadjuvant chemotherapy.

How Does Diagnostic Accuracy Evolve with Increased Breast MRI Experience?

Introduction: Our institution is part of a provincial program providing annual breast MRI screenings to high-risk women. We assessed how MRI experience, background parenchymal enhancement (BPE), and the amount of fibroglandular tissue (FGT) affect the biopsy-proven predictive value (PPV3) and accuracy for detecting suspicious MRI findings. Methods: From all high-risk screening breast MRIs conducted between 1 July 2011 and 30 June 2020, we reviewed all BI-RADS 4/5 observations with pathological tissue diagnoses. Overall and annual PPV3s were computed. Radiologists with fewer than ten observations were excluded from performance analyses. PPV3s were computed for each radiologist. We assessed how MRI experience, BPE, and FGT impacted diagnostic accuracy using logistic regression analyses, defining positive cases as malignancies alone (definition A) or malignant or high-risk lesions (definition B). Findings: There were 536 BI-RADS 4/5 observations with tissue diagnoses, including 77 malignant and 51 high-risk lesions. A total of 516 observations were included in the radiologist performance analyses. The average radiologist's PPV3 was 16 ± 6% (definition A) and 25 ± 8% (definition B). MRI experience in years correlated significantly with positive cases (definition B, OR = 1.05, p = 0.03), independent of BPE or FGT. Diagnostic accuracy improved exponentially with increased MRI experience (definition B, OR of 1.27 and 1.61 for 5 and 10 years, respectively, p = 0.03 for both). Lower levels of BPE significantly correlated with increased odds of findings being malignant, independent of FGT and MRI experience. Summary: More extensive MRI reading experience improves radiologists' diagnostic accuracy for high-risk or malignant lesions, even in MRI studies with increased BPE.

Breast ductography: to do or not to do? A pictorial essay.

Nipple discharge is a frequent breast disease clinical presentation. Although most cases of nipple discharge are physiologic, pathologic nipple discharge is not uncommon. Eight to 15% of pathological nipple discharge is associated with malignancy, requiring investigation. Some specialists believe that ductography is a challenging procedure that is better to be substituted by other methods, such as MRI. However, an experienced physician can perform ductography quickly and easily and still play an essential role in some clinical scenarios. Conventional imaging, such as mammography and sonography, commonly fails to detect the underlying causes of pathological nipple discharge. MRI has limitations of low specificity, cost, lengthy exam duration, accessibility, and patient factors such as claustrophobia. In addition, we can make a specific diagnosis and appropriate treatment by coupling ductography with other methods, such as ultrasound-guided or stereotactic biopsy. This study aims to present the ductography technique, possible findings, and the clinical settings where ductography is useful.Critical relevance statement Although ductography is currently less used in breast imaging, it still plays an essential role in some clinical scenarios. These clinical scenarios include pathological nipple discharge with negative conventional imaging, contraindicated MRI, unavailable MRI, unremarkable MRI results, and multiple MRI findings.Key points• Conventional imaging commonly fails to detect the underlying causes of pathological nipple discharge.• MRI in the setting of nipple discharge has some limitations.• Ductography still plays an essential role in some clinical scenarios.• Coupling ductography with other methods helps make a specific diagnosis.

Novel MRI-guided focussed ultrasound stimulated microbubble radiation enhancement treatment for breast cancer.

Preclinical studies have demonstrated focused ultrasound (FUS) stimulated microbubble (MB) rupture leads to the activation of acid sphingomyelinase-ceramide pathway in the endothelial cells. When radiotherapy (RT) is delivered concurrently with FUS-MB, apoptotic pathway leads to increased cell death resulting in potent radiosensitization. Here we report the first human trial of using magnetic resonance imaging (MRI) guided FUS-MB treatment in the treatment of breast malignancies. In the phase 1 prospective interventional study, patients with breast cancer were treated with fractionated RT (5 or 10 fractions) to the disease involving breast or chest wall. FUS-MB treatment was delivered before 1st and 5th fractions of RT (within 1 h). Eight patients with 9 tumours were treated. All 7 evaluable patients with at least 3 months follow-up treated for 8 tumours had a complete response in the treated site. The maximum acute toxicity observed was grade 2 dermatitis in 1 site, and grade 1 in 8 treated sites, at one month post RT, which recovered at 3 months. No RT-related late effect or FUS-MB related toxicity was noted. This study demonstrated safety of combined FUS-MB and RT treatment. Promising response rates suggest potential strong radiosensitization effects of the investigational modality.Trial registration: clinicaltrials.gov, identifier NCT04431674.

Pseudoangiomatous stromal hyperplasia of the breast, imaging and clinical perspective: A review.

Pseudoangiomatous stromal hyperplasia (PASH) is a benign breast pathology, which most commonly presents incidentally along with other breast pathologies. The etiology and pathogenesis of PASH are still unknown; however, there is some evidence suggesting PASH is hormone dependent. The clinical history, presentation, and imaging appearance of PASH are variable. Clinically, PASH has a wide spectrum of presentations, from being silent to gigantomastia. On imaging, PASH demonstrates various benign to suspicious features. Here we summarize PASH's clinical presentation, histopathology, imaging features, and management.

Correlation of Mammographic Microcalcifications with Final Surgical Pathology After Neoadjuvant Chemotherapy for Breast Cancer.

INTRODUCTION: Imaging guidelines for post-neoadjuvant chemotherapy (NAC) breast cancer patients lack specificity on appropriateness and utility of individual modalities for surgical planning. Microcalcifications confound mammographic interpretation. We examined the correlation between the mammographic extent of microcalcifications present post-NAC, corresponding magnetic resonance imaging (MRI) lesions, and definitive surgical pathology. METHODS: In this retrospective cohort study, patients with calcifications on mammography were collected from a database of consecutive breast cancer patients receiving NAC. The primary objective was to determine the correlation between maximum dimension of post-NAC calcifications with surgical pathology (invasive disease, tumor bed, and ductal carcinoma in situ [DCIS]), stratified by tumor receptor subgroup. Secondarily, we examined the correlation of residual disease with MRI mass enhancement (ME) and non-ME (NME). Pearson's correlation coefficient was used to evaluate statistical significance (strong: R2 ≥70%; moderate: R2=25-70%; weak: R2 ≤25%). RESULTS: Overall, 186 patients met the inclusion criteria. Mammographic calcifications correlated poorly with invasive disease (R2 = 10.8%), overestimating by 57%. In patients with calcifications on mammography, MRI ME and NME correlated weakly with the maximum dimension of invasive disease and DCIS. In triple-negative breast cancer (TNBC) patients, invasive disease correlated strongly with the maximum dimension of calcifications (R2 = 83%) and moderately with ME (R2 = 37.7%) and NME (R2 = 28.4%). CONCLUSION: Overall, current imaging techniques correlate poorly and overestimate final surgical pathology. This poor correlation may lead to uncertainty in the extent of required surgical excision and the exclusion of potential candidates for non-surgical management in ongoing trials. TNBCs would be good candidates for these trials given the stronger observed correlations between pathology and imaging.

Machine learning analysis of breast ultrasound to classify triple negative and HER2+ breast cancer subtypes.

OBJECTIVES: Early diagnosis of triple-negative (TN) and human epidermal growth factor receptor 2 positive (HER2+) breast cancer is important due to its increased risk of micrometastatic spread necessitating early treatment and for guiding targeted therapies. This study aimed to evaluate the diagnostic performance of machine learning (ML) classification of newly diagnosed breast masses into TN versus non-TN (NTN) and HER2+ versus HER2 negative (HER2-) breast cancer, using radiomic features extracted from grayscale ultrasound (US) b-mode images. MATERIALS AND METHODS: A retrospective chart review identified 88 female patients who underwent diagnostic breast US imaging, had confirmation of invasive malignancy on pathology and receptor status determined on immunohistochemistry available. The patients were classified as TN, NTN, HER2+ or HER2- for ground-truth labelling. For image analysis, breast masses were manually segmented by a breast radiologist. Radiomic features were extracted per image and used for predictive modelling. Supervised ML classifiers included: logistic regression, k-nearest neighbour, and Naïve Bayes. Classification performance measures were calculated on an independent (unseen) test set. The area under the receiver operating characteristic curve (AUC), sensitivity (%), and specificity (%) were reported for each classifier. RESULTS: The logistic regression classifier demonstrated the highest AUC: 0.824 (sensitivity: 81.8%, specificity: 74.2%) for the TN sub-group and 0.778 (sensitivity: 71.4%, specificity: 71.6%) for the HER2 sub-group. CONCLUSION: ML classifiers demonstrate high diagnostic accuracy in classifying TN versus NTN and HER2+ versus HER2- breast cancers using US images. Identification of more aggressive breast cancer subtypes early in the diagnostic process could help achieve better prognoses by prioritizing clinical referral and prompting adequate early treatment.

Impact of COVID-19 and Socioeconomic Factors on Delays in High-Risk MRI Breast Cancer Screening.

The purpose of this study is to investigate if there was a delay in high-risk MRI breast cancer screening in our local region, if this delay is ongoing despite COVID-19 vaccinations, and if demographic and socioeconomic factors are associated with these delays. Six-hundred and sixty-five high-risk breast patients from 23 January 2018-30 September 2021 were included. Delays were determined by comparing the time in between each patients' MRI screening exams prior to the COVID-19 pandemic to the time in between MRI screening exams during the height of the COVID-19 pandemic as well as the time in between exams when our patients started receiving vaccinations. Delays were analyzed via logistical regression with demographic and socioeconomic factors to determine if there was an association between these factors and delays. Significant time delays in between MRI screening exams were found between the pre-COVID timeframe compared to during the height of COVID. Significant time delays also persisted during the timeframe after patients started getting vaccinations. There were no associations with delays and socioeconomic or demographic factors. Significant time delays were found in between MRI high-risk breast cancer screening examinations due to the COVID-19 pandemic. These delays were not exacerbated by demographic or socioeconomic factors.

BI-RADS BERT and Using Section Segmentation to Understand Radiology Reports.

Radiology reports are one of the main forms of communication between radiologists and other clinicians, and contain important information for patient care. In order to use this information for research and automated patient care programs, it is necessary to convert the raw text into structured data suitable for analysis. State-of-the-art natural language processing (NLP) domain-specific contextual word embeddings have been shown to achieve impressive accuracy for these tasks in medicine, but have yet to be utilized for section structure segmentation. In this work, we pre-trained a contextual embedding BERT model using breast radiology reports and developed a classifier that incorporated the embedding with auxiliary global textual features in order to perform section segmentation. This model achieved 98% accuracy in segregating free-text reports, sentence by sentence, into sections of information outlined in the Breast Imaging Reporting and Data System (BI-RADS) lexicon, which is a significant improvement over the classic BERT model without auxiliary information. We then evaluated whether using section segmentation improved the downstream extraction of clinically relevant information such as modality/procedure, previous cancer, menopausal status, purpose of exam, breast density, and breast MRI background parenchymal enhancement. Using the BERT model pre-trained on breast radiology reports, combined with section segmentation, resulted in an overall accuracy of 95.9% in the field extraction tasks. This is a 17% improvement, compared to an overall accuracy of 78.9% for field extraction with models using classic BERT embeddings and not using section segmentation. Our work shows the strength of using BERT in the analysis of radiology reports and the advantages of section segmentation by identifying the key features of patient factors recorded in breast radiology reports.

Early Changes in Quantitative Ultrasound Imaging Parameters during Neoadjuvant Chemotherapy to Predict Recurrence in Patients with Locally Advanced Breast Cancer.

BACKGROUND: This study was conducted to explore the use of quantitative ultrasound (QUS) in predicting recurrence for patients with locally advanced breast cancer (LABC) early during neoadjuvant chemotherapy (NAC). METHODS: Eighty-three patients with LABC were scanned with 7 MHz ultrasound before starting NAC (week 0) and during treatment (week 4). Spectral parametric maps were generated corresponding to tumor volume. Twenty-four textural features (QUS-Tex1) were determined from parametric maps acquired using grey-level co-occurrence matrices (GLCM) for each patient, which were further processed to generate 64 texture derivatives (QUS-Tex1-Tex2), leading to a total of 95 features from each time point. Analysis was carried out on week 4 data and compared to baseline (week 0) data. ∆Week 4 data was obtained from the difference in QUS parameters, texture features (QUS-Tex1), and texture derivatives (QUS-Tex1-Tex2) of week 4 data and week 0 data. Patients were divided into two groups: recurrence and non-recurrence. Machine learning algorithms using k-nearest neighbor (k-NN) and support vector machines (SVMs) were used to generate radiomic models. Internal validation was undertaken using leave-one patient out cross-validation method. RESULTS: With a median follow up of 69 months (range 7-118 months), 28 patients had disease recurrence. The k-NN classifier was the best performing algorithm at week 4 with sensitivity, specificity, accuracy, and area under curve (AUC) of 87%, 75%, 81%, and 0.83, respectively. The inclusion of texture derivatives (QUS-Tex1-Tex2) in week 4 QUS data analysis led to the improvement of the classifier performances. The AUC increased from 0.70 (0.59 to 0.79, 95% confidence interval) without texture derivatives to 0.83 (0.73 to 0.92) with texture derivatives. The most relevant features separating the two groups were higher-order texture derivatives obtained from scatterer diameter and acoustic concentration-related parametric images. CONCLUSIONS: This is the first study highlighting the utility of QUS radiomics in the prediction of recurrence during the treatment of LABC. It reflects that the ongoing treatment-related changes can predict clinical outcomes with higher accuracy as compared to pretreatment features alone.

Missed Breast Cancers on MRI in High-Risk Patients: A Retrospective Case-Control Study.

Purpose: To determine if MRI features and molecular subtype influence the detectability of breast cancers on MRI in high-risk patients. Methods and Materials: Breast cancers in a high-risk population of 104 patients were diagnosed following MRI describing a BI-RADS 4-5 lesion. MRI characteristics at the time of diagnosis were compared with previous MRI, where a BI-RADS 1-2-3 lesion was described. Results: There were 77 false-negative MRIs. A total of 51 cancers were overlooked and 26 were misinterpreted. There was no association found between MRI characteristics, the receptor type and the frequency of missed cancers. The main factors for misinterpreted lesions were multiple breast lesions, prior biopsy/surgery and long-term stability. Lesions were mostly overlooked because of their small size and high background parenchymal enhancement. Among missed lesions, 50% of those with plateau kinetics on initial MRI changed for washout kinetics, and 65% of initially progressively enhancing lesions then showed plateau or washout kinetics. There were more basal-like tumours in BRCA1 carriers (50%) than in non-carriers (13%), p = 0.0001, OR = 6.714, 95% CI = [2.058-21.910]. The proportion of missed cancers was lower in BRCA carriers (59%) versus non-carriers (79%), p < 0.05, OR = 2.621, 95% CI = [1.02-6.74]. Conclusions: MRI characteristics or molecular subtype do not influence breast cancer detectability. Lesions in a post-surgical breast should be assessed with caution. Long-term stability does not rule out malignancy and multimodality evaluation is of added value. Lowering the biopsy threshold for lesions with an interval change in kinetics for a type 2 or 3 curve should be considered. There was a higher rate of interval cancers in BRCA 1 patients attributed to lesions more aggressive in nature.

A rare presentation of tuberculous adenitis mimicking metastatic breast lymphadenopathy.

Tuberculosis (TB) remains in 2022 a significant public health issue as it remains endemic in some areas of the globe, with a high prevalence in underdeveloped countries (Pujani, Khan, Hassan, Jetley, Raina, Breast Dis., 35(3): 195-198, 2015. doi:10.3233/BD-150405. PMID: 26406543). Pulmonary TB is the most common form, but TB can also have extrapulmonary manifestations like tubercular lymphadenopathy. Tuberculous lymphadenitis is the most extrapulmonary tuberculosis. It used to be called scrofula in the past coming from the Latin meaning breeding sow (Kokosali, Lloyd, Dent Update, 33(5): 306-308, 311, 2006. doi:10.12968/denu.2006.33.5.306. PMID: 16841612; Oberhelman, Watchmaker, Phillips, JAMA Dermatol, 155(5): 610, 2019. doi:10.1001/jamadermatol.2018.5651. PMID: 30942835). It is a common cause of peripheral lymphadenitis, seen mostly in the developing countries, but also reemerging among intravenous drugs users and immunocompromised population. Cervical nodes are the most commonly detected nodes in tuberculous lymphadenitis, accounting for 63% of the cases, followed by mediastinal (27%) and axillary nodes (8%) (Ahuja, Ying, Evans, King, Metreweli, Clin Radiol, 50(6): 391-395, 1995. doi:10.1016/s0009-9260(05)83136-8. PMID: 7789023). Tuberculous lymphadenitis affects predominantly the young population and children. There is also a slight female predilection. As to our knowledge, there have not been any reported cases as post-menopausal axillary tuberculous lymphadenitis, and it is the focus of this article.

Radiomics in predicting recurrence for patients with locally advanced breast cancer using quantitative ultrasound.

BACKGROUND: The purpose of the study was to investigate the role of pre-treatment quantitative ultrasound (QUS)-radiomics in predicting recurrence for patients with locally advanced breast cancer (LABC). MATERIALS AND METHODS: A prospective study was conducted in patients with LABC (n = 83). Primary tumours were scanned using a clinical ultrasound device before starting treatment. Ninety-five imaging features were extracted-spectral features, texture, and texture-derivatives. Patients were determined to have recurrence or no recurrence based on clinical outcomes. Machine learning classifiers with k-nearest neighbour (KNN) and support vector machine (SVM) were evaluated for model development using a maximum of 3 features and leave-one-out cross-validation. RESULTS: With a median follow up of 69 months (range 7-118 months), 28 patients had disease recurrence (local or distant). The best classification results were obtained using an SVM classifier with a sensitivity, specificity, accuracy and area under curve of 71%, 87%, 82%, and 0.76, respectively. Using the SVM model for the predicted non-recurrence and recurrence groups, the estimated 5-year recurrence-free survival was 83% and 54% (p = 0.003), and the predicted 5-year overall survival was 85% and 74% (p = 0.083), respectively. CONCLUSIONS: A QUS-radiomics model using higher-order texture derivatives can identify patients with LABC at higher risk of disease recurrence before starting treatment.

MRI texture features from tumor core and margin in the prediction of response to neoadjuvant chemotherapy in patients with locally advanced breast cancer.

BACKGROUND: Radiomics involving quantitative analysis of imaging has shown promises in oncology to serve as non-invasive biomarkers. We investigated whether pre-treatment T2-weighted magnetic resonance imaging (MRI) can be used to predict response to neoadjuvant chemotherapy (NAC) in breast cancer. MATERIALS AND METHODS: MRI scans were obtained for 102 patients with locally advanced breast cancer (LABC). All patients were treated with standard regimens of NAC as decided by the treating oncologist, followed by surgery and adjuvant treatment according to standard institutional practice. The primary tumor was segmented, and 11 texture features were extracted using the grey-level co-occurrence matrices analysis of the T2W-images from tumor cores and margins. Response assessment was done using clinical-pathological responses with patients classified into binary groups: responders and non-responders. Machine learning classifiers were used to develop a radiomics model, and a leave-one-out cross-validation technique was used to assess the performance. RESULTS: 7 features were significantly (p < 0.05) different between the two response groups. The best classification accuracy was obtained using a k-nearest neighbor (kNN) model with sensitivity, specificity, accuracy, and area under curve of 63, 93, 87, and 0.78, respectively. CONCLUSIONS: Pre-treatment T2-weighted MRI texture features can predict NAC response with reasonable accuracy.

Adequacy of invasive and in situ breast carcinoma margins in radioactive seed and wire-guided localization lumpectomies.

Image-guided preoperative localizations help surgeons to completely resect nonpalpable breast cancers. The objective of this study is to compare the adequacy of specimen margins for both invasive breast cancer (IBC) and ductal carcinoma in situ (DCIS) after radioactive seed localization (RSL) vs wire-guided localization (WGL). We retrospectively reviewed 600 cases at a single Canadian academic center from January 2014 to September 2017, comparing surgical margins, re-excisions and reoperations, localization accuracy and major complications (migration, accidental deployment, vasovagal reaction), as well as operative duration between RSL and WGL cases. IBC margins were positive in 7% of RSL and 6% of WGL cases (P = .57). Tumor size (P = .039) and association with DCIS (P = .036) predicted positive margins in invasive carcinoma. DCIS margins were positive in 6% and 8%, and close (≤2 mm) in 37% and 36% of cases (P = .45) for RSL and RSL cases respectively. The presence of extensive intraductal component predicted positive DCIS margins (P < .0001). There was no significant difference between intraoperative re-excisions (P = .54), localization accuracy (P = .34), and operation duration (P = .81). Reoperation for lumpectomies and mastectomies was marginally higher for WGL than RSL (P = .049). There were 11 (4%) WGL and no RSL complications (P = .03). Overall, positive margins for IBC, close or positive margins for DCIS, intraoperative re-excision, localization accuracy, and operation duration were similar between RSL and WGL. The reoperation rate was higher in WGL than RSL, which may reflect practice changes over time. RSL was safer than WGL with lower complication rates.

Budget Impact Analysis of Preoperative Radioactive Seed Localization.

BACKGROUND: This study models costs in implementing a radioactive seed localization (RSL) program for nonpalpable breast lesions at a large Canadian tertiary hospital to replace existing wire-guided localization (WGL). METHODS: All direct and indirect operating costs of localization per lesion from the hospital's perspective were determined by retrospectively reviewing patient data and costs from January 2014 to December 2016. A budget impact analysis and sensitivity analysis were performed to calculate the mean cost per lesion, the minimum and maximum cost per lesion, operational costs, and initial costs. RESULTS: There were 265 WGL lesions in 2014 and 170 RSL lesions in 2016 included in cost calculation. The mean cost per localization was $185 CAD for WGL ($148-$311) and $283 CAD ($245-$517) for RSL using preloaded seeds, adjusted to 2016 Canadian dollars. The annual operational expenditure including all localizations and overhead costs was $49,835 for WGL and $80,803 for RSL. Initial costs for RSL were $22,000, including external training and new equipment purchases. CONCLUSIONS: Our budget impact analysis shows that RSL using preloaded radioactive seeds was more expensive than WGL when considering per-lesion localization costs and specific costs related to radiation safety. Manually loading radioactive seed could be a cost-saving alternative to purchasing preloaded seeds. Our breakdown of costs can provide a framework for other centres to determine which localization method best suit their departments.

Computational Radiology in Breast Cancer Screening and Diagnosis Using Artificial Intelligence.

Breast cancer screening has been shown to significantly reduce mortality in women. The increased utilization of screening examinations has led to growing demands for rapid and accurate diagnostic reporting. In modern breast imaging centers, full-field digital mammography (FFDM) has replaced traditional analog mammography, and this has opened new opportunities for developing computational frameworks to automate detection and diagnosis. Artificial intelligence (AI), and its subdomain of deep learning, is showing promising results and improvements on diagnostic accuracy, compared to previous computer-based methods, known as computer-aided detection and diagnosis.In this commentary, we review the current status of computational radiology, with a focus on deep neural networks used in breast cancer screening and diagnosis. Recent studies are developing a new generation of computer-aided detection and diagnosis systems, as well as leveraging AI-driven tools to efficiently interpret digital mammograms, and breast tomosynthesis imaging. The use of AI in computational radiology necessitates transparency and rigorous testing. However, the overall impact of AI to radiology workflows will potentially yield more efficient and standardized processes as well as improve the level of care to patients with high diagnostic accuracy.