Search

Purpose: To evaluate the total biopsy and positive biopsy rates in women at high risk of breast cancer compared to the general population. Methods: The study group consisted of 330 BRCA mutation carriers attending the dedicated multidisciplinary breast cancer clinic of a tertiary medical center in Israel. Clinical, genetic, and biopsy data were retrieved from the central healthcare database and the medical files. Patients who were at age 50 years or older during follow-up were matched 1:10 to women in the general population referred for routine breast cancer screening at the same age, as recommended in the international guidelines. The groups were compared for rate of biopsy studies performed and percentage of positive biopsy results. Matched analysis was performed to correct for confounders. Results: The matched analysis revealed that the total biopsy rate per 1000 follow-up-years was 61.7 in the study group and 22.7 in the control group (p Citation Format: Adi Pomerantz, Daliah Tsoref, Ahuva Grubstein, Sonya Wadhawker, Yael Rapson, Itay Gadiel, Hadar Goldvaser, Ariel Hammerman, Tzipora Shochat, Eran Sharon, Rinat Yerushalmi. Rate of breast biopsy referrals in BRCA mutation carriers: A retrospective comparative study and matched analysis [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P2-11-16.

Objectives In the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring of patients with COVID-19. We propose a deep learning model for detection of COVID-19 from CXRs, as well as a tool for retrieving similar patients according to the model’s results on their CXRs. For training and evaluating our model, we collected CXRs from inpatients hospitalized in four different hospitals. Methods In this retrospective study, 1384 frontal CXRs, of COVID-19 confirmed patients imaged between March and August 2020, and 1024 matching CXRs of non-COVID patients imaged before the pandemic, were collected and used to build a deep learning classifier for detecting patients positive for COVID-19. The classifier consists of an ensemble of pre-trained deep neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, and vgg16, and is enhanced by data augmentation and lung segmentation. We further implemented a nearest-neighbors algorithm that uses DNN-based image embeddings to retrieve the images most similar to a given image. Results Our model achieved accuracy of 90.3%, (95% CI: 86.3–93.7%) specificity of 90% (95% CI: 84.3–94%), and sensitivity of 90.5% (95% CI: 85–94%) on a test dataset comprising 15% (350/2326) of the original images. The AUC of the ROC curve is 0.96 (95% CI: 0.93–0.97). Conclusion We provide deep learning models, trained and evaluated on CXRs that can assist medical efforts and reduce medical staff workload in handling COVID-19. Key Points • A machine learning model was able to detect chest X-ray (CXR) images of patients tested positive for COVID-19 with accuracy and detection rate above 90%. • A tool was created for finding existing CXR images with imaging characteristics most similar to a given CXR, according to the model’s image embeddings. Supplementary Information The online version contains supplementary material available at 10.1007/s00330-021-08050-1.

Women who carry the BRCA mutation are at high lifetime risk of breast cancer, but there is no consensus regarding an effective and safe chemoprevention strategy. A large body of evidence suggests that 3,3-diindolylmethane (DIM), a dimer of indole-3-carbinol found in cruciferous vegetables, can potentially prevent carcinogenesis and tumor development. The primary aim of this prospective single-arm study was to investigate the effect of DIM supplementation on breast density, a recognized predictive factor of breast cancer risk. Participants were 23 healthy female BRCA carriers (median age 47 years; 78% postmenopausal) who were treated with oral DIM 100 mg × 1/day for 1 year. The amount of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) on magnetic resonance imaging (MRI) performed before and after the intervention was scored by two independent expert radiologists using the Breast Imaging and Reporting Data System. The results showed a decrease in the average score for FGT amount from 2.8 ± 0.8 at the onset to 2.65 ± 0.84 after 1 year (P = 0.031), with no significant change in BPE (P = 0.429). A group of DIM-untreated age- and menopausal-status-matched women from the BRCA clinic did not show a significant change in FGT amount (P = 0.33) or BPE (P = 0.814) in a parallel year. Mean estradiol level decreased from 159 to 102 pmol/l (P = 0.01), and mean testosterone level decreased from 0.42 to 0.31 pmol/l (P = 0.007). Side effects were grade 1. In conclusion, 1 year’s supplementation with DIM 100 mg × 1/day in BRCA carriers was associated with a significant decline in FGT amount on MRI. Larger randomized studies are warranted to corroborate these findings., The impact of 1 year’s supplementation with oral 3,3-diindolylmethane 100 mg × 1/day on breast density and estrogen metabolism was evaluated in 23 healthy BRCA carriers. MRI showed a significant decrease in average Breast Imaging and Reporting Data System score for fibroglandular tissue from before to after treatment.

PurposeTo evaluate the total biopsy and positive biopsy rates in women at high risk of breast cancer compared to the general population.MethodsThe study group consisted of 330 women with pathogenic variants (PVs) inBRCA1/2attending the dedicated multidisciplinary breast cancer clinic of a tertiary medical center in Israel. Clinical, genetic, and biopsy data were retrieved from the central healthcare database and the medical files. Patients aged 50 years or older during follow-up were matched 1:10 to women in the general population referred for routine breast cancer screening at the same age, as recommended by international guidelines. The groups were compared for rate of biopsy studies performed and percentage of positive biopsy results. Matched analysis was performed to correct for confounders.ResultsThe total biopsy rate per 1000 follow-up years was 61.7 in the study group and 22.7 in the control group (p p p ConclusionWomen aged 50 + years with PVs inBRCA1/2attending a dedicated clinic have a 2.7 times higher biopsy rate per 1000 follow-up years, a 13.2 times higher positive biopsy rate per 1000 follow-up years, and a 4.9 times higher positive biopsy percentage than same-aged women in the general population.

Purpose To evaluate the total biopsy and positive biopsy rates in women at high risk of breast cancer compared to the general population. Methods The study group consisted of 330 BRCA mutation carriers attending the dedicated multidisciplinary breast cancer clinic of a tertiary medical center in Israel. Clinical, genetic, and biopsy data were retrieved from the central healthcare database and the medical files. Patients who were at age 50 years or older during follow-up were matched 1:10 to women in the general population referred for routine breast cancer screening at the same age, as recommended in the international guidelines. The groups were compared for rate of biopsy studies performed and percentage of positive biopsy results. Matched analysis was performed to correct for confounders. Results The matched analysis revealed that the total biopsy rate per 1000 follow-up-years was 61.7 in the study group and 22.7 in the control group (p p p BRCA mutation carriers who attend a dedicated clinic, have a 2.7 times higher biopsy rate per 1000 follow-up-years, a 13.2 times higher positive biopsy rate per 1000 follow-up-years, and a 4.9 times higher positive biopsy percentage compared with women in the general population.

Breast cancer is the most common malignancy in women. Mammographic findings such as microcalcifications and masses, as well as morphologic features of masses in sonographic scans, are the main diagnostic targets for tumor detection. However, improved specificity of these imaging modalities is required. A leading alternative target is neoangiogenesis. When pathological, it contributes to the development of numerous types of tumors, and the formation of metastases. Hence, demonstrating neoangiogenesis by visualization of the microvasculature may be of great importance. Super resolution ultrasound localization microscopy enables imaging of the microvasculature at the capillary level. Yet, challenges such as long reconstruction time, dependency on prior knowledge of the system Point Spread Function (PSF), and separability of the Ultrasound Contrast Agents (UCAs), need to be addressed for translation of super-resolution US into the clinic. In this work we use a deep neural network architecture that makes effective use of signal structure to address these challenges. We present in vivo human results of three different breast lesions acquired with a clinical US scanner. By leveraging our trained network, the microvasculature structure is recovered in a short time, without prior PSF knowledge, and without requiring separability of the UCAs. Each of the recoveries exhibits a different structure that corresponds with the known histological structure. This study demonstrates the feasibility of in vivo human super resolution, based on a clinical scanner, to increase US specificity for different breast lesions and promotes the use of US in the diagnosis of breast pathologies.

In the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in the diagnosis and monitoring of patients with COVID-19. Machine learning solutions have been shown to be useful for X-ray analysis and classification in a range of medical contexts. The purpose of this study is to create and evaluate a machine learning model for diagnosis of COVID-19, and to provide a tool for searching for similar patients according to their X-ray scans. In this retrospective study, a classifier was built using a pre-trained deep learning model (ReNet50) and enhanced by data augmentation and lung segmentation to detect COVID-19 in frontal CXR images collected between January 2018 and July 2020 in four hospitals in Israel. A nearest-neighbors algorithm was implemented based on the network results that identifies the images most similar to a given image. The model was evaluated using accuracy, sensitivity, area under the curve (AUC) of receiver operating characteristic (ROC) curve and of the precision-recall (P-R) curve. The dataset sourced for this study includes 2362 CXRs, balanced for positive and negative COVID-19, from 1384 patients (63 +/- 18 years, 552 men). Our model achieved 89.7% (314/350) accuracy and 87.1% (156/179) sensitivity in classification of COVID-19 on a test dataset comprising 15% (350 of 2326) of the original data, with AUC of ROC 0.95 and AUC of the P-R curve 0.94. For each image we retrieve images with the most similar DNN-based image embeddings; these can be used to compare with previous cases., Elisha Goldstein, Daphna Keidar, and Daniel Yaron have made an equal contribution and are equal first authors, listed alphabetically

Background: With approximately 1.6 million annual procedures in the United States and 3 million world-wide, needle biopsy is considered the Gold Standard for breast cancer diagnosis and treatment planning. Overdiagnosis can result in unnecessary treatment, cost, and anxiety, while underdiagnosis can delay treatment and diminish outcomes. A 2015 study published in JAMA1 found nearly 25% discordance between pathology diagnosis and expert review, most pronounced in cases of DCIS, Atypia and in patients with dense breasts. It has been well established that physiologic differences between benign and malignant tissues are reflected in their electrical properties.2,3,4 Access to real-time tissue properties during the biopsy procedure has the potential for increasing accuracy by enabling the most suspicious tissue to be sampled, and by providing the tissue characterization to pathology for comparison with histologic findings. Through research made possible by the European Union’s Horizon 2020 research award, this feasibility study sought to determine if five 0.8mm miniaturized, flexible RF sensors (Dune Medical Devices, Alpharetta, GA) mounted within the sample cavity of a 14-gauge biopsy needle can accurately measure and map the electrical properties of multiple breast tissue types. Methods: Between March, 2018 and March, 2019, 44 patients undergoing mastectomy or lumpectomy at three medical centers in Israel were enrolled in the study. The biopsy needle was applied to freshly excised specimens, with continuous readings by the sensors. An average of 8.1 cores (ranging from 2-10) were obtained from each specimen. Cores were oriented and analyzed by standard histopathology. Based on histology, the dielectric properties of the various tissue types were derived, and the ability of the device to differentiate between malignant and non-malignant tissue was assessed. Results: A total of 357 cores from 44 specimens were analyzed. Ease of use and quality of tissue samples were equivalent to that of a standard biopsy needle. The dielectric properties of three tissue groups: Fat, Healthy non-Fat, and Malignant, in the low radiofrequency range were measured, showing distinct differences between the various types. Feature sizes larger than 0.8 mm were analyzed. The differentiation ability between tissue types was characterized using sensitivity and specificity of 85% and 99% respectively. Conclusions: Miniature, flexible RF sensors can be incorporated onto a biopsy needle. Although this study utilized a 14-gauge core needle, the 0.8mm sensor size allows for configuration within both vacuum-assisted and core biopsy needles of various gauges. The dielectric properties of breast tissue can be assessed in real-time during the biopsy procedure. These results show promise in differentiating between breast tissue types, specifically cancerous and benign, enabling more accurate tissue sampling and subsequent diagnosis. Improving the accuracy of breast biopsies should provide immediate clinical impact by reducing overstaging and subsequent unneeded treatment, procedures and cost, as well as reducing understaging of breast cancer which results in delayed diagnosis and missed cancer. Forward-looking, real-time tissue characterization during biopsy could prove especially beneficial should newer protocols currently under trial, such as active surveillance for low risk DCIS5 and omission of surgery for exceptional responders of neoadjuvant chemotherapy,6 become treatment options. The ability to mount the sensors to minimally invasive treatment devices will lay the foundation for expanding the technology to other cancer types, with the potential for precision delivery of new targeted drugs, radiation and ablation therapies at the site of the cancer. Citation Format: Noemi Weisenberg, Avihai Lachman, Lisa Cadena, Inbal Shimens, Olga Shmain, Ahuva Grubstein, Yael Rapson, Hana Cernik, Debora Kidron, Tania Zehavi, Evgeny Edelstein, Vladimir Kravtsov, Tatiana Kogan, Meirav Wolff Bar, Judith Diment, Ilana Haas, Patricia Malinger, Eran Sharon, Yehudit Birnbaum, Ada Magen, Yael Sobol, Osnat Givon Madhala, Sonya Wadhawker, Tanir M Allweis. Feasibility of incorporating miniaturized, flexible radiofrequency (RF) sensors in a breast biopsy needle for accurate real-time characterization of benign and malignant tissue [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr OT3-04-01.

Background: The aim of this study was to characterize the signs of invasive lobular carcinoma of the breast on digital breast tomosynthesis (DBT) imaging. Patients and Methods: The study group included 23 women with pathologically proven invasive lobular carcinoma of the breast for whom both digital mammography (DM) and DBT images were available. The images were read jointly by 2 experienced breast radiologists. Findings were recorded according to the descriptors in the Breast Imaging and Reporting Data System lexicon and correlated with the detailed pathology results. Results: In 21 of the 23 patients, the combination of DM and DBT yielded pathologic findings (91%). Architectural distortions or spiculations were demonstrated in 87% of cases. The addition of DBT to DM improved lesion detection by more clearly depicting both the lesion margins and architectural distortions. Only 2 lesions were occult by both DM and DBT, including 1 lesion in a peripheral location that was not incorporated in the standard mediolateral oblique and craniocaudal views. Conclusion: DBT improves the detection of invasive lobular carcinoma lesions by more clearly depicting architectural distortions and spiculations.

Introduction: Tubular adenomas are rare benign epithelial neoplasms of the breast resembling fibroadenomas on both imaging and pathology. We aimed at characterizing and differentiating these lesions on contrast enhanced mammography and MRI.Material and methods: Out of all percutaneous breast biopsies performed at the Rabin medical center between the years 2010-2019, five cases which also had contrast-based imaging including contrast enhanced mammography and MRI were retrieved. Morphology and enhancement patterns of the lesions were analyzed by two dedicated breast radiologists.Results: The contrast imaging characteristics of all lesions were enhancing masses measuring 4-17 mm. The shape of the lesions was oval, borders well circumscribed, on both CEM and MRI. CEM revealed marked homogenous enhancement. MRI enhancement patterns of the small tumors showed homogenous enhancement, whereas the larger mass showed a more heterogeneous enhancement. Kinetic curves on MRI were of rapid marked enhancement.Conclusion: Tubular adenomas diverge pathologically from known enhancement patterns of fibroadenomas.