Macroscopic inelastic scattering imaging using a hyperspectral line-scanning system identifies invasive breast cancer in lumpectomy and mastectomy specimens.

Significance: Of patients with early-stage breast cancer, 60% to 75% undergo breast-conserving surgery. Of those, 20% or more need a second surgery because of an incomplete tumor resection only discovered days after surgery. An intraoperative imaging technology allowing cancer detection on the margins of breast specimens could reduce re-excision procedure rates and improve patient survival. Aim: We aimed to develop an experimental protocol using hyperspectral line-scanning Raman spectroscopy to image fresh breast specimens from cancer patients. Our objective was to determine whether macroscopic specimen images could be produced to distinguish invasive breast cancer from normal tissue structures. Approach: A hyperspectral inelastic scattering imaging instrument was used to interrogate eight specimens from six patients undergoing breast cancer surgery. Machine learning models trained with a different system to distinguish cancer from normal breast structures were used to produce tissue maps with a field-of-view of 1 cm 2 classifying each pixel as either cancer, adipose, or other normal tissues. The predictive model results were compared with spatially correlated histology maps of the specimens. Results: A total of eight specimens from six patients were imaged. Four of the hyperspectral images were associated with specimens containing cancer cells that were correctly identified by the new ex vivo pathology technique. The images associated with the remaining four specimens had no histologically detectable cancer cells, and this was also correctly predicted by the instrument. Conclusions: We showed the potential of hyperspectral Raman imaging as an intraoperative breast cancer margin assessment technique that could help surgeons improve cosmesis and reduce the number of repeat procedures in breast cancer surgery.

VIRGINAL RECURRENT GIGANTOMASTIA (BREAST HYPERTROPHY). A CASE REPORT.

Virginal gigantomastia (VGM) is a benign disease of the breasts without a clearly established etiology. The treatment of VGM remains a problem. The conservative treatment is not effective while surgery is too traumatic. Most specialists recommend subcutaneous mastectomy with immediate implant reconstruction or reduction mammoplasty. The reduction mammoplasty with adjuvant hormone therapy is a variant of treatment of young patients with a risk of recurrence. We present a case of a patient with VGM who was operated in 2014. Reduction mammoplasty was performed. After 9 years, the patient had a relapse and second surgery, resection of the breasts with reduction mammoplasty. Tissues with cysts, fibrosis, hamartomas, and fibroadenomas were dissected. Histopathology revealed extensive fibrosis with hamartomas and fibroadenomas. The immunohistochemical examination of the breast tissue showed a high level (70%) of estrogen and progesterone receptors expression. We prescribed hormone therapy with tamoxifen 10 mg per day. Dynamic monitoring of the treatment result and control of the disease remission was carried out. Breast-conserving surgery performed in such patients can help alleviate the psychological, social, and physical disorders caused by VGM.

Value of sonoelastography for diagnosis of breast non-mass lesions and comparison with BI-RADS: A systematic review and meta-analysis.

BACKGROUND: Not all the breast lesions were mass-like, some were non-mass-like at ultrasonography. In these lesions, conventional ultrasonography had a high sensitivity but a low specificity. Sonoelastography can evaluate tissue stiffness to differentiate malignant masses from benign ones. Then what about the non-mass lesions? The aim of this study was to evaluate the current accuracy of sonoelastography in the breast non-mass lesions and compare the results with those of the American College of Radiology breast Imaging-Reporting and Data System (BI-RADS). METHODS: An independent literature search of English medical databases, including PubMed, Web of Science, Embase & MEDLINE (Embase.com) and Cochrane Library, was performed by 2 researchers. The accuracy of sonoelastography was calculated and compared with those of BI-RADS. RESULTS: Fourteen relevant studies including 1058 breast non-mass lesions were included. Sonoelastography showed a pooled sensitivity of 0.74 (95% CI: 0.70-0.78), specificity of 0.89 (95% CI: 0.85-0.91), diagnostic odds ratio (DOR) of 25.22 (95% CI: 17.71-35.92), and an area under the curve of 0.9042. Eight articles included both sonoelastography and BI-RADS. The pooled sensitivity, specificity, DOR and AUC were 0.69 versus 0.91 (P < .01), 0.90 versus 0.68 (P < .01), 19.65 versus 29.34 (P > .05), and 0.8685 versus 0.9327 (P > .05), respectively. CONCLUSIONS: Sonoelastography has a higher specificity and a lower sensitivity for differential diagnosis between malignant and benign breast non-mass lesions compared with BI-RADS, although there were no differences in AUC between them.

Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images.

BACKGROUND: Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology but has a high inter-assessor variability with many tumours being classified as intermediate grade, NHG2. Here, we evaluate if DeepGrade, a previously developed model for risk stratification of resected tumour specimens, could be applied to risk-stratify tumour biopsy specimens. METHODS: A total of 11,955,755 tiles from 1169 whole slide images of preoperative biopsies from 896 patients diagnosed with breast cancer in Stockholm, Sweden, were included. DeepGrade, a deep convolutional neural network model, was applied for the prediction of low- and high-risk tumours. It was evaluated against clinically assigned grades NHG1 and NHG3 on the biopsy specimen but also against the grades assigned to the corresponding resection specimen using area under the operating curve (AUC). The prognostic value of the DeepGrade model in the biopsy setting was evaluated using time-to-event analysis. RESULTS: Based on preoperative biopsy images, the DeepGrade model predicted resected tumour cases of clinical grades NHG1 and NHG3 with an AUC of 0.908 (95% CI: 0.88; 0.93). Furthermore, out of the 432 resected clinically-assigned NHG2 tumours, 281 (65%) were classified as DeepGrade-low and 151 (35%) as DeepGrade-high. Using a multivariable Cox proportional hazards model the hazard ratio between DeepGrade low- and high-risk groups was estimated as 2.01 (95% CI: 1.06; 3.79). CONCLUSIONS: DeepGrade provided prediction of tumour grades NHG1 and NHG3 on the resection specimen using only the biopsy specimen. The results demonstrate that the DeepGrade model can provide decision support to identify high-risk tumours based on preoperative biopsies, thus improving early treatment decisions.

Sonographic Evaluation of Nigerian Women with Mammographic Focal Asymmetric Density.

BACKGROUND AND OBJECTIVE: Focal asymmetric breast densities (FABD) present a diagnostic challenge concerning the need for a further histologic workup to rule out malignancy. We therefore aim to correlate ultrasonography and mammographic findings in women with FABD and evaluate the use of ultrasonography as a workup tool. METHODOLOGY: This is a retrospective study of women who underwent targeted breast sonography due to FABD with a mammogram in a private diagnostic centre in Abuja over three years (2016-2018). Demographic details, clinical indication, mammographic and ultrasonography features were documented and statistical analysis was done using SAS software version 9.3 with the statistical level of significance set at 0.05. RESULT: The age range of 44 patients was 32-69 years with a majority (79.5%) presenting for screening mammography. The predominant breast density pattern in those <60 years was heterogeneous (ACR C). FABD in mammography was noted mostly in the upper outer quadrant and retro-areolar regions (34.1 and 38.6%). Ultrasonography findings were normal breast tissue (56.8%), 4 simple cysts, 1 abscess, 4 solid masses, 2 focal fibrocystic changes, and 4 cases of duct ectasia. Twenty-nine (65.9%) of the abnormal cases were on the same side as the mammogram, while all the incongruent cases were recorded in heterogeneously dense breasts (ACR C). Final BIRADS Scores on USS showed that 41(93.2%) of mammographic FABD had normal and benign findings while only 2(4.6%) had sonographic features of malignancy. CONCLUSION: Breast ultrasonography allows for optimal lesion characterization and is a veritable tool in the workup of patients with focal asymmetric breast densities with the majority presenting as normal breast tissue and benign pathologies.

CONTEXTE ET OBJECTIF: Les densités asymétriques mammographiques focales mammographiques, FABD présentent un défi diagnostique en ce qui concerne la nécessité d'un examen histologique supplémentaire pour exclure une tumeur maligne. Nous visons donc à corréler les résultats échographiques et mammographiques chez les femmes ayant une densité mammaire focale asymétrique et à établir la nécessité d'un bilan plus approfondi. METHODOLOGIE: Une étude rétrospective de 44 femmes ayant subi une échographie ciblée du sein en raison de FABD à la mammographie dans un centre de diagnostic privé à Abuja sur trois ans (2016-2018) Les détails démographiques, les présentations cliniques, les caractéristiques mammographiques et échographiques ont été documentés et analysés statistiquement fait à l'aide du logiciel SAS version 9.3 avec un niveau de signification statistique fixé à 0,05. RESULTAT: La tranche d'âge des patients était de 32 à 69 ans (SD 1), la majorité (79,5%) se présentant pour une mammographie de dépistage. Le schéma de densité mammaire prédominant chez les moins de 60 ans était hétérogène (ACR C). FABD en mammographie a presque la même distribution dans le quadrant externe supérieur et les régions rétroaréolaires (38,4 vs 36,8%). Les résultats échographiques étaient: tissu mammaire normal (65,9%), 4 kystes simples, 1 kyste complexe, 4 masses solides, 2 fibrokystiques focales et 4 cas d'ectasie canalaire.29 (65,9%) des cas anormaux étaient du même côté que la mammographie, alors que tous les cas incongruents ont été enregistrés dans des seins denses de manière hétérogène (ACR C). Les scores finaux BIRADS sur USS ont montré que 41 (93,2%) des FABD mammographiques avaient des résultats normaux et bénins, tandis que seulement 2 (4,6%) avaient des caractéristiques échographiques de malignité. CONCLUSION: L'échographie mammaire permet une caractérisation optimale des lésions et constitue un véritable outil dans le bilan des patientes présentant des densités mammaires asymétriques focales dont la majorité se présente comme un tissu mammaire normal et des pathologies bénignes. MOTS CLES: Sein, Asymétrie focale, Échographie, Mammographie.

Repository of MRI-derived models of the breast with single and multiple benign and malignant tumors for microwave imaging research.

The diagnosis of breast cancer through MicroWave Imaging (MWI) technology has been extensively researched over the past few decades. However, continuous improvements to systems are needed to achieve clinical viability. To this end, the numerical models employed in simulation studies need to be diversified, anatomically accurate, and also representative of the cases in clinical settings. Hence, we have created the first open-access repository of 3D anatomically accurate numerical models of the breast, derived from 3.0T Magnetic Resonance Images (MRI) of benign breast disease and breast cancer patients. The models include normal breast tissues (fat, fibroglandular, skin, and muscle tissues), and benign and cancerous breast tumors. The repository contains easily reconfigurable models which can be tumor-free or contain single or multiple tumors, allowing complex and realistic test scenarios needed for feasibility and performance assessment of MWI devices prior to experimental and clinical testing. It also includes an executable file which enables researchers to generate models incorporating the dielectric properties of breast tissues at a chosen frequency ranging from 3 to 10 GHz, thereby ensuring compatibility with a wide spectrum of research requirements and stages of development for any breast MWI prototype system. Currently, our dataset comprises MRI scans of 55 patients, but new exams will be continuously added.

Artificial intelligence-based classification of breast lesion from contrast enhanced mammography: a multicenter study.

PURPOSE: The authors aimed to establish an artificial intelligence (AI)-based method for preoperative diagnosis of breast lesions from contrast enhanced mammography (CEM) and to explore its biological mechanism. MATERIALS AND METHODS: This retrospective study includes 1430 eligible patients who underwent CEM examination from June 2017 to July 2022 and were divided into a construction set (n=1101), an internal test set (n=196), and a pooled external test set (n=133). The AI model adopted RefineNet as a backbone network, and an attention sub-network, named convolutional block attention module (CBAM), was built upon the backbone for adaptive feature refinement. An XGBoost classifier was used to integrate the refined deep learning features with clinical characteristics to differentiate benign and malignant breast lesions. The authors further retrained the AI model to distinguish in situ and invasive carcinoma among breast cancer candidates. RNA-sequencing data from 12 patients were used to explore the underlying biological basis of the AI prediction. RESULTS: The AI model achieved an area under the curve of 0.932 in diagnosing benign and malignant breast lesions in the pooled external test set, better than the best-performing deep learning model, radiomics model, and radiologists. Moreover, the AI model has also achieved satisfactory results (an area under the curve from 0.788 to 0.824) for the diagnosis of in situ and invasive carcinoma in the test sets. Further, the biological basis exploration revealed that the high-risk group was associated with the pathways such as extracellular matrix organization. CONCLUSIONS: The AI model based on CEM and clinical characteristics had good predictive performance in the diagnosis of breast lesions.

A prediction model based on digital breast pathology image information.

BACKGROUND: The workload of breast cancer pathological diagnosis is very heavy. The purpose of this study is to establish a nomogram model based on pathological images to predict the benign and malignant nature of breast diseases and to validate its predictive performance. METHODS: In retrospect, a total of 2,723 H&E-stained pathological images were collected from 1,474 patients at Qingdao Central Hospital between 2019 and 2022. The dataset consisted of 509 benign tumor images (adenosis and fibroadenoma) and 2,214 malignant tumor images (infiltrating ductal carcinoma). The images were divided into a training set (1,907) and a validation set (816). Python3.7 was used to extract the values of the R channel, G channel, B channel, and one-dimensional information entropy from all images. Multivariable logistic regression was used to select variables and establish the breast tissue pathological image prediction model. RESULTS: The R channel value, B channel value, and one-dimensional information entropy of the images were identified as independent predictive factors for the classification of benign and malignant pathological images (P < 0.05). The area under the curve (AUC) of the nomogram model in the training set was 0.889 (95% CI: 0.869, 0.909), and the AUC in the validation set was 0.838 (95% CI: 0.7980.877). The calibration curve results showed that the calibration curve of this nomogram model was close to the ideal curve. The decision curve results indicated that the predictive model curve had a high value for auxiliary diagnosis. CONCLUSION: The nomogram model for the prediction of benign and malignant breast diseases based on pathological images demonstrates good predictive performance. This model can assist in the diagnosis of breast tissue pathological images.

Dynamic contrast-enhanced mammography and breast MRI in the diagnosis of breast cancer and detection of tumor size.

Background/aim: The aim of this study is to evaluate the performance of contrast-enhanced mammography (CEM) and dynamic breast MRI techniques for diagnosing breast lesions, assess the diagnostic accuracy of CEM's using histopathological findings, and compare lesion size measurements obtained from both methods with pathological size. Materials and methods: This prospective study included 120 lesions, of which 70 were malignant, in 104 patients who underwent CEM and MRI within a week. Two radiologists independently evaluated the MR and CEM images in separate sessions, using the BI-RADS classification system. Additionally, the maximum sizes of lesion were measured. Diagnostic accuracy parameters and the receiver operating characteristics (ROC) curves were constructed for the two modalities. The correlation between the maximum diameter of breast lesions observed in MRI, CEM, and pathology was analyzed. Results: The overall diagnostic values for MRI were as follows: sensitivity 97.1%, specificity 60%, positive predictive value (PPV) 77.3%, negative predictive value (NPV) 93.8%, and accuracy 81.7%. Correspondingly, for CEM, the sensitivity, accuracy, specificity, PPV, and NPV were 97.14%, 81.67%, 60%, 77.27%, and 93.75%, respectively. The ROC analysis of CEM revealed an area under the curve (AUC) of 0.907 for observer 1 and 0.857 for observer 2, whereas MRI exhibited an AUC of 0.910 for observer 1 and 0.914 for observer 2. Notably, CEM showed the highest correlation with pathological lesion size (r = 0.660 for observer 1 and r = 0.693 for observer 2, p < 0.001 for both). Conclusion: CEM can be used with high sensitivity and similar diagnostic performance comparable to MRI for diagnosing breast cancer. CEM proves to be a successful diagnostic method for precisely determining tumor size.

Intratumoral Microbiota: Unraveling their Oncogenic Impact on Cancer Progression With Focus on Breast Cancer Therapeutic Outcomes.

The gut microbiota has been implicated in many cancers through the secretion of blood-traveling metabolites or activation of oncogenic signaling. Currently, specific microbial signatures have been detected in the human breast, which are different from other microbial-rich compartments, such as the intestine and skin. Changes in the breast microbiome profile have been shown to positively or negatively correlate with breast cancer development, progression, and therapeutic outcomes. However, studies regarding the role and underlying mechanism of intratumoral microbiota in breast cancer have remained concealed. This review aimed to provide an overview of the role of the intratumoral microbiome in tumorigenesis and tumor progression, and how these intratumoral microbiota affect breast cancer. We also discuss the potential of using the intratumoral microbiome as a biomarker or treatment alternative in breast cancers.

Molecular Pathology of Breast Tumors: Diagnostic and Actionable Genetic Alterations.

Breast cancer is a heterogenous disease with various histologic subtypes, molecular profiles, behaviors, and response to therapy. After the histologic assessment and diagnosis of an invasive breast carcinoma, the use of biomarkers, multigene expression assays and mutation profiling may be used. With improved molecular assays, the identification of somatic genetic alterations in key oncogenes and tumor suppressor genes are playing an increasingly important role in many areas of breast cancer care. This review summarizes the most clinically significant somatic alterations in breast tumors and how this information is used to facilitate diagnosis, provide potential treatment options, and identify mechanisms of resistance.

DAU-Net: Dual attention-aided U-Net for segmenting tumor in breast ultrasound images.

Breast cancer remains a critical global concern, underscoring the urgent need for early detection and accurate diagnosis to improve survival rates among women. Recent developments in deep learning have shown promising potential for computer-aided detection (CAD) systems to address this challenge. In this study, a novel segmentation method based on deep learning is designed to detect tumors in breast ultrasound images. Our proposed approach combines two powerful attention mechanisms: the novel Positional Convolutional Block Attention Module (PCBAM) and Shifted Window Attention (SWA), integrated into a Residual U-Net model. The PCBAM enhances the Convolutional Block Attention Module (CBAM) by incorporating the Positional Attention Module (PAM), thereby improving the contextual information captured by CBAM and enhancing the model's ability to capture spatial relationships within local features. Additionally, we employ SWA within the bottleneck layer of the Residual U-Net to further enhance the model's performance. To evaluate our approach, we perform experiments using two widely used datasets of breast ultrasound images and the obtained results demonstrate its capability in accurately detecting tumors. Our approach achieves state-of-the-art performance with dice score of 74.23% and 78.58% on BUSI and UDIAT datasets, respectively in segmenting the breast tumor region, showcasing its potential to help with precise tumor detection. By leveraging the power of deep learning and integrating innovative attention mechanisms, our study contributes to the ongoing efforts to improve breast cancer detection and ultimately enhance women's survival rates. The source code of our work can be found here: https://github.com/AyushRoy2001/DAUNet.

Cylindroma of the Breast: A Rare Differential for Breast Cancer on Core Biopsies, Case Report and Review of Literature.

Breast cancers of either ductal or lobular pathology make up the vast majority of breast malignancies. Other cancers occur rarely in the breast. Benign pathology can at times mimic breast cancers on imaging and initial needle biopsies. We report a rare breast pathology of cylindroma. Cylindromas are usually benign, rare dermatologic lesions most commonly associated with head or neck locations. They more commonly occur as sporadic and solitary masses. Less commonly is an autosomal-dominant multi-centric form of this disease. Malignant cylindromas are very rare. We present a patient with findings of a cylindroma of the breast after excision. This was initially felt to be concerning for breast cancer on imaging and core biopsy. Treatment of cylindromas of the breast is excision. Sentinel lymph node dissection is not indicated, nor are adjuvant therapies when identified in the breast. This lesion needs to be included in the differential diagnosis for breast cancer. If cylindromas can be accurately diagnosed preoperatively, this would negate the need for consideration of axillary nodal surgery and adjuvant therapies.

Functional hemodynamic imaging markers for the prediction of pathological outcomes in breast cancer patients treated with neoadjuvant chemotherapy.

Significance: Achieving pathologic complete response (pCR) after neoadjuvant chemotherapy (NACT) is a significant predictor of increased likelihood of survival in breast cancer patients. Early prediction of pCR is of high clinical value as it could allow personalized adjustment of treatment regimens in non-responding patients for improved outcomes. Aim: We aim to assess the association between hemoglobin-based functional imaging biomarkers derived from diffuse optical tomography (DOT) and the pathological outcome represented by pCR at different timepoints along the course of NACT. Approach: Twenty-two breast cancer patients undergoing NACT were enrolled in a multimodal DOT and X-ray digital breast tomosynthesis (DBT) imaging study in which their breasts were imaged at different compression levels. Logistic regressions were used to study the associations between DOT-derived imaging markers evaluated after the first and second cycles of chemotherapy, respectively, with pCR status determined after the conclusion of NACT at the time of surgery. Receiver operating characteristic curve analysis was also used to explore the predictive performance of selected DOT-derived markers. Results: Normalized tumor HbT under half compression was significantly lower in the pCR group compared to the non-pCR group after two chemotherapy cycles (p=0.042). In addition, the change in normalized tumor StO2 upon reducing compression from full to half mammographic force was identified as another potential indicator of pCR at an earlier time point, i.e., after the first chemo cycle (p=0.038). Exploratory predictive assessments showed that AUCs using DOT-derived functional imaging markers as predictors reach as high as 0.75 and 0.71, respectively, after the first and second chemo cycle, compared to AUCs of 0.50 and 0.53 using changes in tumor size measured on DBT and MRI. Conclusions: These findings suggest that breast DOT could be used to assist response assessment in women undergoing NACT, a critical but unmet clinical need, and potentially enable personalized adjustments of treatment regimens.

Structured illumination microscopy for cancer identification in diagnostic breast biopsies.

Breast cancer is the second most common cancer diagnosed in women in the US with almost 280,000 new cases anticipated in 2023. Currently, on-site pathology for location guidance is not available during the collection of breast biopsies or during surgical intervention procedures. This shortcoming contributes to repeat biopsy and re-excision procedures, increasing the cost and patient discomfort during the cancer management process. Both procedures could benefit from on-site feedback, but current clinical on-site evaluation techniques are not commonly used on breast tissue because they are destructive and inaccurate. Ex-vivo microscopy is an emerging field aimed at creating histology-analogous images from non- or minimally-processed tissues, and is a promising tool for addressing this pain point in clinical cancer management. We investigated the ability structured illumination microscopy (SIM) to generate images from freshly-obtained breast tissues for structure identification and cancer identification at a speed compatible with potential on-site clinical implementation. We imaged 47 biopsies from patients undergoing a guided breast biopsy procedure using a customized SIM system and a dual-color fluorescent hematoxylin & eosin (H&E) analog. These biopsies had an average size of 0.92 cm2 (minimum 0.1, maximum 4.2) and had an average imaging time of 7:29 (minimum 0:22, maximum 37:44). After imaging, breast biopsies were submitted for standard histopathological processing and review. A board-certified pathologist returned a binary diagnostic accuracy of 96% when compared to diagnoses from gold-standard histology slides, and key tissue features including stroma, vessels, ducts, and lobules were identified from the resulting images.

Improvement of Phased Antenna Array Applied in Focused Microwave Breast Hyperthermia.

Focused microwave breast hyperthermia (FMBH) employs a phased antenna array to perform beamforming that can focus microwave energy at targeted breast tumors. Selective heating of the tumor endows the hyperthermia treatment with high accuracy and low side effects. The effect of FMBH is highly dependent on the applied phased antenna array. This work investigates the effect of polarizations of antenna elements on the microwave-focusing results by simulations. We explore two kinds of antenna arrays with the same number of elements using different digital realistic human breast phantoms. The first array has all the elements' polarization in the vertical plane of the breast, while the second array has half of the elements' polarization in the vertical plane and the other half in the transverse plane, i.e., cross polarization. In total, 96 sets of different simulations are performed, and the results show that the second array leads to a better focusing effect in dense breasts than the first array. This work is very meaningful for the potential improvement of the antenna array for FMBH, which is of great significance for the future clinical applications of FMBH. The antenna array with cross polarization can also be applied in microwave imaging and sensing for biomedical applications.

Yield of MR-directed US for MRI-detected breast findings: how often can we avoid MR biopsy?

PURPOSE: To evaluate the yield of MR-directed ultrasound for MRI detected breast findings. METHODS: This retrospective study included 857 consecutive patients who had a breast MRI between January 2017-December 2020 and received a BI-RADS 4 assessment. Only exams recommended for MR-directed ultrasound were included in the study, yielding 765 patients. Findings were characterized by presence or absence of a sonographic correlate. Utilizing the electronic medical record, for those with a sonographic correlate, the size, location, and morphology were noted. Imaging guided (Ultrasound and MRI) pathology results as well as excisional pathology results were recorded. A multivariable logistical regression analysis was used to investigate the clinical utility of MR-directed ultrasound. RESULTS: There were 1262 MRI-detected BI-RADS category 4 findings in 765 patients. Of the 1262 findings, MR-directed ultrasound was performed on 852 (68 %). Of these, 291/852 (34 %) had an ultrasound correlate, including 143/291 (49 %) benign lesions, 81/291 (28 %) malignant lesions, 16/291 (5 %) with high-risk pathology and 51/291 (18 %) unknown due to lost to follow-up. Of those findings with ultrasound correlates, 173/291 (59 %) represented masses, 69/291 (24 %) were regions of non-mass enhancement, 22/291 (7.6 %) were foci and 27/291 (9.3 %) fell into the category of other which included lymph node, cysts, and scar tissue. Masses were significantly more likely to be identified on MR-directed ultrasound (p < 0.0001) compared to foci. CONCLUSION: The yield of MR-directed ultrasound is significantly higher for masses, than foci and non-mass enhancement, which should be taken into consideration when recommending an MR-directed ultrasound.

Optimising the diagnostic accuracy of First post-contrAst SubtracTed breast MRI (FAST MRI) through interpretation-training: a multicentre e-learning study, mapping the learning curve of NHS Breast Screening Programme (NHSBSP) mammogram readers using an enriched dataset.

BACKGROUND: Abbreviated breast MRI (FAST MRI) is being introduced into clinical practice to screen women with mammographically dense breasts or with a personal history of breast cancer. This study aimed to optimise diagnostic accuracy through the adaptation of interpretation-training. METHODS: A FAST MRI interpretation-training programme (short presentations and guided hands-on workstation teaching) was adapted to provide additional training during the assessment task (interpretation of an enriched dataset of 125 FAST MRI scans) by giving readers feedback about the true outcome of each scan immediately after each scan was interpreted (formative assessment). Reader interaction with the FAST MRI scans used developed software (RiViewer) that recorded reader opinions and reading times for each scan. The training programme was additionally adapted for remote e-learning delivery. STUDY DESIGN: Prospective, blinded interpretation of an enriched dataset by multiple readers. RESULTS: 43 mammogram readers completed the training, 22 who interpreted breast MRI in their clinical role (Group 1) and 21 who did not (Group 2). Overall sensitivity was 83% (95%CI 81-84%; 1994/2408), specificity 94% (95%CI 93-94%; 7806/8338), readers' agreement with the true outcome kappa = 0.75 (95%CI 0.74-0.77) and diagnostic odds ratio = 70.67 (95%CI 61.59-81.09). Group 1 readers showed similar sensitivity (84%) to Group 2 (82% p = 0.14), but slightly higher specificity (94% v. 93%, p = 0.001). Concordance with the ground truth increased significantly with the number of FAST MRI scans read through the formative assessment task (p = 0.002) but by differing amounts depending on whether or not a reader had previously attended FAST MRI training (interaction p = 0.02). Concordance with the ground truth was significantly associated with reading batch size (p = 0.02), tending to worsen when more than 50 scans were read per batch. Group 1 took a median of 56 seconds (range 8-47,466) to interpret each FAST MRI scan compared with 78 (14-22,830, p < 0.0001) for Group 2. CONCLUSIONS: Provision of immediate feedback to mammogram readers during the assessment test set reading task increased specificity for FAST MRI interpretation and achieved high diagnostic accuracy. Optimal reading-batch size for FAST MRI was 50 reads per batch. Trial registration (25/09/2019): ISRCTN16624917.

Fibrocystic Change.

Fibrocystic changes are commonly seen in clinically symptomatic patients and during imaging workup of screening-detected findings. The term "fibrocystic changes" encompasses a broad spectrum of specific benign pathologic entities. Recognition of classically benign findings of fibrocystic changes, including cysts and layering calcifications, can prevent unnecessary follow-ups and biopsies. Imaging findings such as solid masses, nonlayering calcifications, and architectural distortion may require core needle biopsy for diagnosis. In these cases, understanding the varied appearances of fibrocystic change aids determination of radiologic-pathologic concordance. Management of fibrocystic change is typically conservative.

Deep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study.

BACKGROUND: Patients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70-80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies. MATERIALS AND METHODS: This retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients. RESULTS: A 95% sensitivity for the "higher stage disease" class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively. CONCLUSION: Deep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.