Detection of architectural distortion in mammograms acquired prior to the detection of breast cancer using texture and fractal analysis

2008 ◽  
Author(s):  
Shormistha Prajna ◽  
Rangaraj M. Rangayyan ◽  
Fábio J. Ayres ◽  
J. E. Leo Desautels
Keyword(s):  
Breast Cancer ◽  
Fractal Analysis ◽  
Architectural Distortion

Automatic detection of various patterns of calcification distribution on mammograms: a graph convolution network approach (Preprint)

2021 ◽  
Author(s):  
Melissa Min-Szu Yao ◽  
Hao Du ◽  
Mikael Hartman ◽  
Wing P. Chan ◽  
Mengling Feng
Keyword(s):  
Breast Cancer ◽  
Breast Imaging ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Automatic Detection ◽  
Ground Truth ◽  
Architectural Distortion ◽  
Breast Cancers ◽  
Convolutional Network ◽  
Mammographic Images

UNSTRUCTURED Purpose: To develop a novel artificial intelligence (AI) model algorithm focusing on automatic detection and classification of various patterns of calcification distribution in mammographic images using a unique graph convolution approach. Materials and methods: Images from 200 patients classified as Category 4 or 5 according to the American College of Radiology Breast Imaging Reporting and Database System, which showed calcifications according to the mammographic reports and diagnosed breast cancers. The calcification distributions were classified as either diffuse, segmental, regional, grouped, or linear. Excluded were mammograms with (1) breast cancer as a single or combined characterization such as a mass, asymmetry, or architectural distortion with or without calcifications; (2) hidden calcifications that were difficult to mark; or (3) incomplete medical records. Results: A graph convolutional network-based model was developed. 401 mammographic images from 200 cases of breast cancer were divided based on calcification distribution pattern: diffuse (n = 24), regional (n = 111), group (n = 201), linear (n = 8) or segmental (n = 57). The classification performances were measured using metrics including precision, recall, F1 score, accuracy and multi-class area under receiver operating characteristic curve. The proposed achieved precision of 0.483 ± 0.015, sensitivity of 0.606 (0.030), specificity of 0.862 ± 0.018, F1 score of 0.527 ± 0.035, accuracy of 60.642% ± 3.040% and area under the curve of 0.754 ± 0.019, finding method to be superior compared to all baseline models. The predicted linear and diffuse classifications were highly similar to the ground truth, and the predicted grouped and regional classifications were also superior compared to baseline models. Conclusion: The proposed deep neural network framework is an AI solution to automatically detect and classify calcification distribution patterns on mammographic images highly suspected of showing breast cancers. Further study of the AI model in an actual clinical setting and additional data collection will improve its performance.

scholarly journals Scale-Specific Multifractal Medical Image Analysis

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Boris Braverman ◽  
Mauro Tambasco
Keyword(s):  
Breast Cancer ◽  
Fractal Analysis ◽  
Large Scale ◽  
Medical Images ◽  
Medical Image Analysis ◽  
Cancer Tissue ◽  
Clinical Value ◽  
Box Counting ◽  
Dependent Parameter ◽  
Single Number

Fractal geometry has been applied widely in the analysis of medical images to characterize the irregular complex tissue structures that do not lend themselves to straightforward analysis with traditional Euclidean geometry. In this study, we treat the nonfractal behaviour of medical images over large-scale ranges by considering their box-counting fractal dimension as a scale-dependent parameter rather than a single number. We describe this approach in the context of the more generalized Rényi entropy, in which we can also compute the information and correlation dimensions of images. In addition, we describe and validate a computational improvement to box-counting fractal analysis. This improvement is based on integral images, which allows the speedup of any box-counting or similar fractal analysis algorithm, including estimation of scale-dependent dimensions. Finally, we applied our technique to images of invasive breast cancer tissue from 157 patients to show a relationship between the fractal analysis of these images over certain scale ranges and pathologic tumour grade (a standard prognosticator for breast cancer). Our approach is general and can be applied to any medical imaging application in which the complexity of pathological image structures may have clinical value.

scholarly journals Posterior breast cancer: Mammographic and ultrasonographic features

2013 ◽  
Vol 70 (11) ◽  
pp. 1034-1038
Author(s):  
Ana Jankovic ◽  
Mirjan Nadrljanski ◽  
Vesna Plesinac-Karapandzic ◽  
Nebojsa Ivanovic ◽  
Zoran Radojicic ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Imaging ◽  
Color Doppler ◽  
Lobular Carcinoma ◽  
Architectural Distortion ◽  
Breast Cancers ◽  
Significant Difference ◽  
Diagnostic Mammography ◽  
Anatomical Localization ◽  
Mass Lesions

Background/Aim. Posterior breast cancers are located in the prepectoral region of the breast. Owing to this distinctive anatomical localization, physical examination and mammographic or ultrasonographic evaluation can be difficult. The purpose of the study was to assess possibilities of diagnostic mammography and breast ultrasonography in detection and differentiation of posterior breast cancers. Methods. The study included 40 women with palpable, histopathological confirmed posterior breast cancer. Mammographic and ultrasonographic features were defined according to Breast Imaging Reporting and Data System (BI-RADS) lexicon. Results. Based on standard two-view mammography 87.5%, of the cases were classified as BI-RADS 4 and 5 categories, while after additional mammographic views all the cases were defined as BIRADS 4 and 5 categories. Among 96 mammographic descriptors, the most frequent were: spiculated mass (24.0%), architectural distortion (16.7%), clustered microcalcifications (12.6%) and focal asymmetric density (12.6%). The differentiation of the spiculated mass was significantly associated with the possibility to visualize the lesion at two-view mammography (p = 0.009), without the association with lesion diameter (p = 0.083) or histopathological type (p = 0.055). Mammographic signs of invasive lobular carcinoma were significantly different from other histopathological types (architectural distortion, p = 0.003; focal asymmetric density, p = 0.019; association of four or five subtle signs of malignancy, p = 0.006). All cancers were detectable by ultrasonography. Mass lesions were found in 82.0% of the cases. Among 153 ultrasonographic descriptors, the most frequent were: irregular mass (15.7%), lobulated mass (7.2%), abnormal color Doppler signals (20.3%), posterior acoustic attenuation (18.3%). Ultrasonographic BI-RADS 4 and 5 categories were defined in 72.5% of the cases, without a significant difference among various histopathological types (p = 0.109). Conclusion. Standard two-view mammography followed by additional mammographic projections is an effective way to demonstrate the spiculated mass and to classify the prepectoral lesion as category BI-RADS 4 or 5. Additional ultrasonography can overcome the mimicry of invasive lobular breast carcinoma at mammography.

scholarly journals Perceptual learning of lesions in mammograms induced by response feedback during training

2019 ◽  
Author(s):  
Sebastian M. Frank ◽  
Andrea Qi ◽  
Daniela Ravasio ◽  
Yuka Sasaki ◽  
Eric Rosen ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Perceptual Learning ◽  
Early Breast Cancer ◽  
Clinical Applications ◽  
Architectural Distortion ◽  
Trained Subjects ◽  
General Consensus ◽  
Response Feedback ◽  
Determining Factor

AbstractDetecting subtle lesions in mammograms indicative of early breast cancer usually requires years of experience. Well-designed training paradigms could be a strong tool for promoting perceptual learning (PL) with rapid and long-lasting improvement in detectability of these subtle mammographic lesions. Given that PL occurs without feedback about the accuracy of subjects’ responses, the role of feedback has been completely ignored in clinical applications of PL. However, in this study, we found that the contents of the feedback profoundly and differentially influence the formation and retention of PL to detect calcification and architectural distortion lesions, two types of mammographic lesions that are frequently missed in mammographic screenings. We trained subjects to detect one type of lesion in a mammogram and manipulated the content of the response feedback during training for 3 groups (no feedback, correctness only, and both correctness and location of the lesion). We found that PL occurred for both lesions when both correctness and location feedback were provided. PL also occurred for calcifications but not for distortions when only correctness was provided. No learning occurred without feedback for either lesion. A retest conducted six months later showed that PL was retained only in the group with both correctness and location feedback for both types of lesions. In contrast to the general consensus of basic PL studies, our results demonstrate that the content of the response feedback is a determining factor in forming and retaining PL to detect mammographic lesions.

scholarly journals Mammographic architectural distortion caused by cyst aspiration

2019 ◽  
Vol 8 (6) ◽  
pp. 205846011985935
Author(s):  
Noel Miner ◽  
Kenneth Meng
Keyword(s):  
Breast Cancer ◽  
Cancer Screening ◽  
Breast Cancer Screening ◽  
Architectural Distortion ◽  
Underlying Malignancy ◽  
Cyst Aspiration ◽  
Screening Technology

Improvement in breast cancer screening technology has increased the detection of architectural distortion, which can often indicate underlying malignancy; however, there are also many benign causes of architectural distortion. We present a case of architectural distortion caused by cyst aspiration, representing a novel, benign cause.

Functional (PET/CT) compared to conventional (mammography [M], sonography [US], MRI) imaging: Defining novel assessment modalities for inflammatory breast cancer (IBC)

2007 ◽  
Vol 25 (18_suppl) ◽  
pp. 600-600
Author(s):  
W. T. Yang ◽  
H. T. Le-Petross ◽  
A. Gonzalez-Angulo ◽  
H. Macapinlac ◽  
H. Macapinlac ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Imaging Modality ◽  
Distant Metastases ◽  
Sudden Onset ◽  
Cancer Center ◽  
Architectural Distortion ◽  
Mri Imaging ◽  
Nodal Disease ◽  
Eligibility Criteria ◽  
Pet Ct

600 Background: IBC is an aggressive frequently lethal form of breast cancer that is defined by sudden onset breast erythema often without an associated clinical or radiological breast mass. Tissue diagnosis remains problematic due to inability to define an area for biopsy. The aim of this study was to compare conventional [M, US, MRI] vs. functional imaging [PET/CT] in detecting a primary breast parenchymal lesion (BPL) at initial presentation of IBC. Methods: Patients (pts) with a new clinical diagnosis of IBC evaluated at the M. D. Anderson Cancer Center between January 2003 to December 2006 who had M, US, MRI, or PET/CT were included in this study. The visibility of a BPL and skin abnormality on each imaging modality was compared. Regional (axillary, supraclavicular, internal mammary) nodal disease confirmed by pathology was assessed at US and PET/CT. The presence of metastatic disease at diagnosis with PET/CT was documented. Results: Sixty-seven pts met eligibility criteria. Median age was 51 years, (range, 25 to 78). Of these, 61 (91%) had M, 62 (93%) had US, 21 (31%) had MRI, and 13 (19%) had PET/CT. By M, no BPL (mass or calcifications) was observed in 16% (10/61), skin-only abnormality (SOA) in 14% (9/61), and a BPL in 84% (51/61). By US, no BPL (mass or architectural distortion) and SOA were noted in 6% (4/62), and a PBL in 94% (58/62). By MRI, 21/21 (100%) showed malignant enhancing BPL and skin thickening. By PET/CT, 100% (13/13) showed hypermetabolic BPL and skin thickening. Pathologically confirmed regional nodal disease was diagnosed in 96% (59/62) by US and in 69% (9/13) by PET/CT. Distant metastases in the bone and lung were diagnosed in 15% (2/13) by PET/CT, one of which was visible on bone scan. Conclusions: MRI and PET/CT showed a primary BPL in all cases of IBC while conventional imaging (M and US) failed to reveal a BPL amenable to biopsy in up to 16%. US can diagnose regional nodal disease to facilitate loco-regional therapeutic planning. PET/CT provides additional information on distant metastasis and should be considered in the initial staging of IBC. No significant financial relationships to disclose.

Outcome of mammography examination among asymptomatic women.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e13558-e13558
Author(s):  
Hadijat Oluseyi Kolade-Yunusa
Keyword(s):  
Breast Cancer ◽  
Early Detection ◽  
Early Stage ◽  
Imaging Modality ◽  
Positive Outcome ◽  
Radiology Department ◽  
Architectural Distortion ◽  
Cross Sectional ◽  
Mammographic Examination ◽  
Asymptomatic Women

e13558 Background: Early detection of breast cancer is important in reducing mortality, morbidity and high socio-economic burden associated with it. Mammography is currently the primary imaging modality used as a screening tool to detect early breast cancer in women experiencing no symptoms as they are most curable in the early stage. The aim of the study is to determine the mammographic outcome in asymptomatic women who presented for mammographic breast examination in Abuja,Nigeria. Methods: This descriptive cross-sectional study comprises of 113 asymptomatic women who presented for mammographic examination at the Radiology department of University of Abuja Teaching Hospital, Gwagwalada from March 2015 to December 2018. Two basic views (craniocaudal and mediolateral views) of the breast were obtained using EXR-650 machine.Additional views were obtained when necessary. Images of the breast were review by radiologist. Results: The mean age of study population was 40.72 ±10.45years with age range of 35 and 65 years. The mammographic outcome among asymptomatic women who had mammographic examination was negative in 69(61.1%) women and positive in 44(38.9%). The differences observed between the positive and negative mammographic outcome was statistically significant p = 0.01. The positive outcome noted in mammograms of women examined were: benign mass in 18(15.9%) women; 9(8.0%) had benign calcification; 7(6.2%) showed architectural distortion; 5(4.4%) was inconclusive; focal asymmetry in 3(2.6%); and suspicious mass in 2(1.8%). Conclusions: Mammogram is an important tool for screening and diagnoses of breast pathologies. In this study, screening of women reveals various benign and malignant breast changes which necessitate early interventions. Early detection of breast cancer save lives. [Table: see text]

Digital Image Processing and Machine Learning Techniques for the Detection of Architectural Distortion in Prior Mammograms

2012 ◽  
pp. 23-65 ◽  
Author(s):  
Shantanu Banik ◽  
Rangaraj M. Rangayyan ◽  
J. E. Leo Desautels
Keyword(s):  
Breast Cancer ◽  
Phase Portrait ◽  
Interval Cancer ◽  
Gabor Filters ◽  
Bayesian Classifier ◽  
Angular Spread ◽  
Architectural Distortion ◽  
Screening Mammograms ◽  
Prior Mammograms ◽  
Receiver Operating

Architectural distortion is a subtle but important early sign of breast cancer. The purpose of this study is to develop methods for the detection of sites of architectural distortion in prior mammograms of interval-cancer cases. Screening mammograms obtained prior to the detection of cancer could contain subtle signs of early stages of breast cancer, in particular architectural distortion. The methods for the detection of architectural distortion are based upon Gabor filters, phase portrait analysis, a novel method for the analysis of the angular spread of power, fractal analysis via Fractal Dimension (FD), structural analysis of texture via Laws’ texture energy measures derived from geometrically transformed regions of interest (ROIs), and statistical analysis of texture using Haralick’s 14 texture features. The application of Gabor filters and linear phase portrait modeling was used to detect initial candidates of sites of architectural distortion; 4,224 ROIs, including 301 true-positive ROIs related to architectural distortion, were automatically obtained from 106 prior mammograms of 56 interval-cancer cases and from 52 mammograms of 13 normal cases. For each ROI, the FD, three measures of angular spread of power, 10 Laws’ measures, and 14 Haralick’s features were computed. The areas under the receiver operating characteristic curves obtained using the features selected by stepwise logistic regression and the leave-one-ROI-out method are 0.76 with the Bayesian classifier, 0.75 with Fisher linear discriminate analysis, and 0.78 with a single-layer feed forward neural network. Free-response receiver operating characteristics indicated sensitivities of 0.80 and 0.90 at 5.8 and 8.1 false positives per image, respectively, with the Bayesian classifier and the leave-one-image-out method. The methods have shown good potential in detecting architectural distortion in mammograms of interval-cancer cases.

The Analysis of Preoperative Wire Localization in Breast Conserving Surgery and Predictors of Surgical Margin Status

2021 ◽  
Vol 104 (10) ◽  
pp. 1617-1625
Keyword(s):  
Breast Cancer ◽  
Early Stage ◽  
Tumor Resection ◽  
Surgical Margin ◽  
Breast Conserving Surgery ◽  
Margin Status ◽  
Positive Surgical Margin ◽  
Architectural Distortion ◽  
Wire Localization ◽  
Large Tumor

Background: At present, the breast conserving therapy (BCT) is considered a treatment of choice for early-stage breast cancer. BCT aims to achieve complete tumor resection with adequate margin and offers better cosmetic outcome. Objective: To describe the experience with preoperative wire localization technique for early breast cancer and analysis of factors affecting positive margin status. Materials and Methods: The authors retrospectively reviewed 190 patients with 206 malignant breast lesions treated by breast conserving surgery (BCS) after mammographic- or ultrasound- guided wire localization. Patient age, lesion type such as mass, mass with calcifications, calcifications alone, and architectural distortion, BI-RADS assessment categories, size, location, modalities of imaging guidance, number of wires used, radiological and surgical margin status, pathological diagnosis, and tumor focality were recorded. Results: A 14.56% of positive surgical margin rate was observed. Mixed-effects logistic regression analysis showed larger lesion size was a significant predictor for positive surgical margin status at larger than 1.5 cm versus 1.0 cm or smaller (p=0.033). Conclusion: The present study data suggested that larger tumor size is the only significant predictor for positive surgical margin status. To deal with non-palpable large tumor, surgeon and radiologist should pay particular attention to achieve adequate surgical margin. Keywords: Wire localization; Breast conserving surgery; Surgical margin status; Specimen radiography

Sign in / Sign up

Export Citation Format

Share Document