scholarly journals Machine Learning-Based Image Analysis for Accelerating the Diagnosis of Complicated Preneoplastic and Neoplastic Ductal Lesions in Breast Biopsy Tissues

2021 ◽  
Author(s):  
Shinya Sato ◽  
Satoshi Maki ◽  
Takashi Yamanaka ◽  
Daisuke Hoshino ◽  
Yukihide Ota ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
Breast Biopsy ◽  
Ductal Carcinoma ◽  
Pathological Diagnosis ◽  
Comparison Analysis ◽  
Preneoplastic Lesions ◽  
Biopsy Specimens ◽  
Ductal Hyperplasia ◽  
Neoplastic Lesions

Abstract Purpose: Diagnosis of breast preneoplastic and neoplastic lesions is difficult due to their similar morphology in breast biopsy specimens. To diagnose these lesions, pathologists perform immunohistochemical analysis and consult with expert breast pathologists. These additional examinations are time-consuming and expensive. Artificial intelligence (AI)-based image analysis has recently improved, and may help in ordinal pathological diagnosis. Here, we showed the significance of machine learning-based image analysis of breast preneoplastic and neoplastic lesions for facilitating high-throughput diagnosis.Methods: Images were obtained from normal mammary glands, hyperplastic lesions, preneoplastic lesions and neoplastic lesions, such as usual ductal hyperplasia (UDH), columnar cell lesion (CCL), ductal carcinoma in situ (DCIS), and DCIS with comedo necrosis (comedo DCIS) in breast biopsy specimens. The original enhanced convoluted neural network (CNN) system was used for analyzing the pathological images. Results: The AI-based image analysis provided the following area under the curve values (AUC): normal lesion vs. DCIS, 0.9902; DCIS vs. comedo DCIS, 0.9942; normal lesion vs. CCL, 0.9786; and UDH vs. DCIS, 1.000. Multiple comparison analysis showed precision and recall scores similar to those of single comparison analysis. Based on the Gradient-weighted Class Activation Mapping (Grad-CAM) used to visualize the important regions reflecting the result of CNN analysis, the ratio of stromal tissue in the whole weighted area was significantly higher in UDH and CCL than that in DCIS. Conclusions: These analyses may provide a more accurate and rapid pathological diagnosis of patients. Moreover, Grad-CAM identifies uncharted important histological characteristics for newer pathological findings and targets of research for understanding diseases.

Epstein-Barr Virus in Breast Carcinoma in Argentina

2005 ◽  
Vol 129 (3) ◽  
pp. 377-381
Author(s):  
María Victoria Preciado ◽  
Paola Andrea Chabay ◽  
Elena Noemí De Matteo ◽  
Pedro Gonzalez ◽  
Saúl Grinstein ◽  
...  
Keyword(s):  
Breast Carcinoma ◽  
Epstein Barr Virus ◽  
Breast Biopsy ◽  
Immunohistochemical Analysis ◽  
Nuclear Antigen ◽  
Cancer Etiology ◽  
Barr Virus ◽  
Biopsy Specimens ◽  
Ductal Hyperplasia ◽  
Epstein Barr

Abstract Context.—Because the etiology and progression of breast carcinoma remain unclear, novel mechanisms of disease pathogenesis need to be considered. Recent interest has focused on Epstein-Barr virus (EBV), an oncogenic ubiquitous herpesvirus. Investigations of this association could not only broaden understanding of breast cancer etiology but also have implications regarding early detection, treatment, and prevention. Objective.—To assess EBV presence in breast carcinoma in an Argentine series. Design.—Breast biopsy specimens of 69 women with breast carcinoma and fresh tumor tissue of 39 of these women were collected. As controls, 17 biopsy specimens of fibroadenomas, 9 of benign epithelial proliferation, 4 of atypical ductal hyperplasia, and 10 of usual ductal hyperplasia and 8 normal breast tissues from women were studied. The EBV-infected cells were identified by means of immunohistochemical analysis, using a monoclonal antibody against Epstein-Barr virus–encoded nuclear antigen 1 (EBNA-1). Polymerase chain reaction (PCR) was used to amplify EBV DNA, with primers that cover the EBV encoded RNA (EBER) and BamHIW regions. Results.—Nuclear expression of EBNA-1 was observed in tumor epithelial cells in 24 (35%) of the 69 cases. We confirmed both positive and negative immunohistochemical results by PCR in those cases where good quality DNA was also available, detecting amplification fragments of 108 base pairs (bp) from the EBER region and 122 bp from the BamHIW region. Neither immunohistochemical analysis nor PCR detected any positive EBV results in the control samples. Conclusions.—Our results demonstrate the presence and expression of EBV restricted to epithelial tumor cells in a subset of breast carcinomas studied. However, no significant association was observed between EBV expression and worse clinical and pathologic patient characteristics.

Histological Assessment of Breast Lesions Identified Exclusively by Magnetic Resonance

2014 ◽  
Vol 80 (10) ◽  
pp. 944-947
Author(s):  
Victoria O'connor ◽  
Elizabeth Arena ◽  
Joslyn Albright ◽  
Nefertiti Brown ◽  
Ryan O'connor ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Magnetic Resonance ◽  
Breast Biopsy ◽  
Ductal Carcinoma ◽  
Low Grade ◽  
Breast Lesions ◽  
Significant Family History ◽  
Ductal Hyperplasia ◽  
Significant Pathology

Radiologic–pathologic correlation of lesions diagnosed by magnetic resonance (MR) is precluded by insufficient data on histological characteristics of lesions suspicious on MR but not visible on concurrent mammogram or ultrasound. The objective of this study was to describe histological features of breast lesions diagnosed exclusively by MR. The participants underwent MR-guided breast biopsy between 2007 and 2012 for a suspicious lesion not identified by mammography or ultrasound. Histology slides were interpreted retrospectively by a breast pathologist. Of 126 patients (126 lesions), 34 (27%) had new breast cancer, 51 (40.5%) previous breast cancer, and 41 (32.5%) dense breasts or a significant family history of breast cancer. MR identified 23 (18.3%) invasive cancers: 20 were Grade 1 and 17 were ductal. Of the 126 lesions, 16 (13%) were ductal carcinoma in situ (DCIS), four were atypical ductal hyperplasia and atypical lobular hyperplasia (3%), and 68 (54%) were benign. Fifteen biopsies (12%) had no significant pathology. Five DCIS lesions were upgraded to T1 invasive cancers. Approximately 30 per cent of suspicious lesions detected exclusively by MR are invasive or in situ cancers that are predominantly low grade. Further studies are needed to determine if malignant lesions can be prospectively distinguished by MR characteristics.

Nipple Discharge as a Sign of Preneoplastic Lesion and Occult Carcinoma of the Breast: Clinical and Galactographic Study in 103 Consecutive Patients

1979 ◽  
Vol 65 (3) ◽  
pp. 317-324 ◽  
Author(s):  
Sergio Di Pietro ◽  
Gianfranco Coopmans De Yoldi ◽  
Silvana Bergonzi ◽  
Gianstefano Gardani ◽  
Roberto Saccozzi ◽  
...  
Keyword(s):  
Ductal Carcinoma ◽  
Atypical Ductal Hyperplasia ◽  
Nipple Discharge ◽  
Diagnostic Value ◽  
Complete Resection ◽  
Preneoplastic Lesion ◽  
Carcinoma Of The Breast ◽  
Ductal Hyperplasia ◽  
Neoplastic Lesions ◽  
Sclerosing Adenosis

A clinical and galactographic investigation was carried out on 103 patients with hematic, serous-hematic, and serous nipple discharge. The age of the patients ranged from 18 to 72 years. A single papilloma was found in 20 cases, diffuse papillomatosis in 2 cases, atypical ductal hyperplasia in 8 cases, and ductal carcinoma in 4 cases (3 of these were infiltrating and 1 was noninfiltrating associated with a diffuse papillomatosis). Mammography gave no indications of carcinoma in any of the 4 cases. In the remaining 49 patients, pictures of ductal hyperplasia, periductal mastitis or sclerosis, sclerosing adenosis, or ductal ectasia were observed. The various types of lesions were often associated. Lacunae, stenosis, or occlusion of the ducts, evidenced by galactography, correlated well with the histologic findings of proliferative lesions of the ductal epithelium. Nevertheless, in practice, it should be the type of discharge that indicates surgery rather than galactographic or cytologic data, which appeared to have little diagnostic value. The frequency with which preneoplastic (or limit) lesions, and also nonsuspect carcinomas were found in patients with a significant nipple discharge confirm the importance of this symptom for a secondary prevention or early diagnosis of mammary neoplastic lesions originating from galactophorous ducts. Finally, complete resection of the galactophorous ducts must be considered as the best treatment in all patients with a suspicious nipple discharge that requires surgery.

Atypical Ductal Hyperplasia and Ductal Carcinoma In Situ as Revealed by Large-Core Needle Breast Biopsy

2000 ◽  
Vol 175 (5) ◽  
pp. 1341-1346 ◽  
Author(s):  
Marla L. Rosenfield Darling ◽  
Darrell N. Smith ◽  
Susan C. Lester ◽  
Carolyn Kaelin ◽  
Donna-Lee G. Selland ◽  
...  
Keyword(s):  
Ductal Carcinoma In Situ ◽  
Carcinoma In Situ ◽  
Breast Biopsy ◽  
Ductal Carcinoma ◽  
Atypical Ductal Hyperplasia ◽  
Large Core ◽  
Core Needle ◽  
Ductal Hyperplasia

scholarly journals Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas

2005 ◽  
Vol 27 (4) ◽  
pp. 237-244 ◽  
Author(s):  
Hae-Gil Hwang ◽  
Hyun-Ju Choi ◽  
Byeong-Il Lee ◽  
Hye-Kyoung Yoon ◽  
Sang-Hee Nam ◽  
...  
Keyword(s):  
Image Analysis ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Visual Analysis ◽  
Ductal Carcinoma ◽  
Texture Features ◽  
Cancer Tissue ◽  
Histological Sections ◽  
Haar Transform ◽  
Ductal Hyperplasia

Multi-resolution images of histological sections of breast cancer tissue were analyzed using texture features of Haar- and Daubechies transform wavelets. Tissue samples analyzed were from ductal regions of the breast and included benign ductal hyperplasia, ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (CA). To assess the correlation between computerized image analysis and visual analysis by a pathologist, we created a two-step classification system based on feature extraction and classification. In the feature extraction step, we extracted texture features from wavelet-transformed images at 10× magnification. In the classification step, we applied two types of classifiers to the extracted features, namely a statistics-based multivariate (discriminant) analysis and a neural network. Using features from second-level Haar transform wavelet images in combination with discriminant analysis, we obtained classification accuracies of 96.67 and 87.78% for the training and testing set (90 images each), respectively. We conclude that the best classifier of carcinomas in histological sections of breast tissue are the texture features from the second-level Haar transform wavelet images used in a discriminant function.

Nonneoplastic Alterations of the Mammary Epithelium Can Mimic Atypia

2009 ◽  
Vol 133 (5) ◽  
pp. 722-728 ◽  
Author(s):  
Melissa Murray
Keyword(s):  
Differential Diagnosis ◽  
Breast Biopsy ◽  
English Literature ◽  
Mammary Epithelium ◽  
Phase Changes ◽  
Diagnostic Challenge ◽  
Breast Epithelium ◽  
Biopsy Specimens ◽  
Ductal Hyperplasia ◽  
Clinical Consequences

Abstract Context.—The pathologist evaluating breast biopsy specimens sometimes encounters nonneoplastic alterations of the mammary epithelium that raise the differential diagnosis of atypia. Because the identification of atypical ductal hyperplasia of the breast has significant clinical implications, it is important to correctly recognize its nonneoplastic morphologic mimics. Objective.—To highlight a spectrum of physiologic and treatment-related changes that can occur in the mammary epithelium and to discuss the differential diagnosis with true atypia. Data Sources.—A comprehensive review of the published English literature on physiologic and treatment-related changes of the breast epithelium was performed. Conclusions.—Among physiologic alterations of the ductal epithelium, luteal-phase changes and secretory changes can sometimes be overinterpreted as atypical. Treatment-related changes, secondary to chemotherapy and radiation, can pose a major diagnostic challenge and their misinterpretation as neoplastic carries major clinical consequences. Familiarity with the morphology of both physiologic and treatment-related alterations of the mammary epithelium is essential to avoid misdiagnosis.

scholarly journals Atypical Ductal Hyperplasia after Vacuum-Assisted Breast Biopsy: Can We Reduce the Upgrade to Breast Cancer to an Acceptable Rate?

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1120
Author(s):  
Luca Nicosia ◽  
Antuono Latronico ◽  
Francesca Addante ◽  
Rossella De Santis ◽  
Anna Carla Bozzini ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Invasive Carcinoma ◽  
Breast Biopsy ◽  
Ductal Carcinoma ◽  
Atypical Ductal Hyperplasia ◽  
Univariate Analysis ◽  
Surgical Excision ◽  
P Value ◽  
Ductal Hyperplasia

(1) Background: to evaluate which factors can reduce the upgrade rate of atypical ductal hyperplasia (ADH) to in situ or invasive carcinoma in patients who underwent vacuum-assisted breast biopsy (VABB) and subsequent surgical excision. (2) Methods: 2955 VABBs were reviewed; 141 patients with a diagnosis of ADH were selected for subsequent surgical excision. The association between patients’ characteristics and the upgrade rate to breast cancer was evaluated in both univariate and multivariate analyses. (3) Results: the upgrade rates to ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) were, respectively, 29.1% and 7.8%. The pooled upgrade rate to DCIS or IC was statistically lower at univariate analysis, considering the following parameters: complete removal of the lesion (p-value < 0.001); BIRADS ≤ 4a (p-value < 0.001); size of the lesion ≤15 mm (p-value: 0.002); age of the patients <50 years (p-value: 0.035). (4) Conclusions: the overall upgrade rate of ADH to DCIS or IC is high and, as already known, surgery should be recommended. However, ADH cases should always be discussed in multidisciplinary meetings: some parameters appear to be related to a lower upgrade rate. Patients presenting these parameters could be strictly followed up to avoid overtreatment.

scholarly journals Atypical ductal hyperplasia on percutaneous breast biopsy: Scoring system to identify the lowest risk for upgrade

2021 ◽  
Author(s):  
Amanda L Amin ◽  
Onalisa D Winblad ◽  
Allison H Zupon ◽  
Fang Fan ◽  
Ossama Tawfik ◽  
...  
Keyword(s):  
Scoring System ◽  
Breast Biopsy ◽  
Ductal Carcinoma ◽  
Atypical Ductal Hyperplasia ◽  
Surgical Excision ◽  
Low Risk ◽  
Categorical Variables ◽  
Imaging Features ◽  
Continuous Variables ◽  
Ductal Hyperplasia

Abstract Purpose NCCN guidelines recommend surgical excision for all patients with atypical ductal hyperplasia (ADH) on percutaneous biopsy. Improved imaging and biopsy techniques have lower contemporary upgrade rates, challenging standard practice. Methods A retrospective analysis identified 87 percutaneous biopsies diagnosing ADH who underwent surgical excision at a single institution from 01/2008 to 10/2015. Imaging was reviewed for lesion size and residual calcifications. Biopsy slides were reviewed for ADH features. Categorical variables were analyzed using Chi-square and Fisher’s exact tests; continuous variables with T- and Wilcoxon tests. Logistic regression model was used to determine association between odds of upgrade and number of low-risk features. Results Upgrade was identified in 13 cases (14.9%; 11 ductal carcinoma in situ and 2 invasive breast cancer). Imaging features associated with lowest risk of upgrade included imaging size < 1cm (p = 0.004) and > 50% removed by biopsy (p = 0.03). The only pathologic feature significantly associated with upgrade was the presence of micropapillary features (p = 0.10), with lower extent of ADH (1–2 foci, p = 0.12) trending toward significance. Those with the lowest risk of upgrade (0%) had all 4 low risk features (n = 17, 20%). The loss of a low-risk feature increased the odds of upgrade by 189% (OR = 1.89, 95% CI 0.241,0.742, p = 0.001). Conclusion Contemporary imaging and biopsy techniques have resulted in lower upgrade rates for ADH. Patients at lowest risk for upgrade can be identified using a scoring system and may be safely offered active surveillance over surgical excision.

Sign in / Sign up

Export Citation Format

Share Document