Quantitative comparison of clustered microcalcifications in for-presentation and for-processing mammograms in full-field digital mammography

Wang, Juan; Nishikawa, Robert M.; Yang, Yongyi

doi:10.1002/mp.12316

Cited by 6 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have already investigated and compared the use of for‐presentation and for‐processing images for mammographic percent density estimation, but little has been done for microcalcification detection. Recently, however, Wang et al . investigated the feasibility of using for‐presentation images in computerized analysis and diagnosis of microcalcification lesions.…”

Section: Discussionmentioning

confidence: 99%

Detection of potential microcalcification clusters using multivendor for‐presentation digital mammograms for short‐term breast cancer risk estimation

et al. 2019

View full text Add to dashboard Cite

PurposeWe explore using the number of potential microcalcification clusters detected in for‐presentation mammographic images (the images which are typically accessible to large epidemiological studies) a marker of short‐term breast cancer risk.MethodsWe designed a three‐step algorithm for detecting potential microcalcification clusters in for‐presentation digital mammograms. We studied association with short‐term breast cancer risk using a nested case control design, with a mammography screening cohort as a source population. In total, 373 incident breast cancer cases (diagnosed at least 3 months after a negative screen at study entry) and 1466 matched controls were included in our study. Conditional logistic regression Wald tests were used to test for association with the presence of microcalcifications at study entry. We compared results of these analyses to those obtained using a Computer‐aided Diagnosis (CAD) software (VuComp) on corresponding for‐processing images (images which are used clinically, but typically not saved).ResultsWe found a moderate agreement between our measure of potential microcalcification clusters on for‐presentation images and a CAD measure on for‐processing images. Similar evidence of association with short‐term breast cancer risk was found (P = 1×10−10 and P = 9×10−09, for our approach on for‐presentation images and for the CAD measure on for‐processing images, respectively) and interestingly both measures contributed independently to association with a short‐term risk (P = 9×10−03 for the CAD measure, adjusted for our proposed method and P = 1×10−04 for our proposed method, adjusted for the CAD measure).ConclusionMeaningful measurement of potential microcalcifications, in the context of short‐term breast cancer risk assessment, is feasible for for‐presentation images across a range of vendors. Our algorithm for for‐presentation images performs similarly to a CAD algorithm on for‐processing images, hence our algorithm can be a useful tool for research on microcalcifications and their role on breast cancer risk, based on large‐scale epidemiological studies with access to for‐presentation images.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection of potential microcalcification clusters using multivendor for‐presentation digital mammograms for short‐term breast cancer risk estimation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To summarize the detection performance, we conducted a free-response receiver operating characteristic (FROC) analysis of the MC detection results. An FROC curve is a plot of the true-positive (TP) fraction of the MCs detected versus the average number of FPs per unit image region (1 cm 2 in area) with the decision threshold varied over an operating range [45]. For clarity, this is referred to as MC-based FROC analysis .…”

Section: Methodsmentioning

confidence: 99%

“…In the MC-based FROC analysis, the TP fraction was computed from the average of the TP fractions of the ROIs with clustered MCs, whereas the FP rate was computed from both the ROIs with and without any MCs [46]. In the detector output, a detected object was treated as a TP when at least 40% of its area overlaps with that of a true MC or its distance to the center of a true MC is no larger than 0.3 mm; otherwise it was counted as an FP [45].…”

Section: Methodsmentioning

confidence: 99%

A context-sensitive deep learning approach for microcalcification detection in mammograms

Wang

Yang

2018

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

A challenging issue in computerized detection of clustered microcalcifications (MCs) is the frequent occurrence of false positives (FPs) caused by local image patterns that resemble MCs. We develop a context-sensitive deep neural network (DNN), aimed to take into account both the local image features of an MC and its surrounding tissue background, for MC detection. The DNN classifier is trained to automatically extract the relevant image features of an MC as well as its image context. The proposed approach was evaluated on a set of 292 mammograms using free-response receiver operating characteristic (FROC) analysis on the accuracy both in detecting individual MCs and in detecting MC clusters. The results demonstrate that the proposed approach could achieve significantly higher FROC curves when compared to two MC-based detectors. It indicates that incorporating image context information in MC detection can be beneficial for reducing the FPs in detections.

show abstract

“…The calcifications in the mammography appear as small white spots. There are two different types of calcifications, microcalcifications and macrocalcifications [6]. The macrocalcifications are large and coarse, mostly benign and associated with the age.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the Cluster Prominence Feature for Detecting Calcifications in Mammograms

Cruz-Bernal

Flores-Barranco

Almanza-Ojeda

et al. 2018

Journal of Healthcare Engineering

View full text Add to dashboard Cite

In mammograms, a calcification is represented as small but brilliant white region of the digital image. Earlier detection of malignant calcifications in patients provides high expectation of surviving to this disease. Nevertheless, white regions are difficult to see by visual inspection because a mammogram is a gray-scale image of the breast. To help radiologists in detecting abnormal calcification, computer-inspection methods of mammograms have been proposed; however, it remains an open important issue. In this context, we propose a strategy for detecting calcifications in mammograms based on the analysis of the cluster prominence (cp) feature histogram. The highest frequencies of the cp histogram describe the calcifications on the mammography. Therefore, we obtain a function that models the behaviour of the cp histogram using the Vandermonde interpolation twice. The first interpolation yields a global representation, and the second models the highest frequencies of the histogram. A weak classifier is used for obtaining a final classification of the mammography, that is, with or without calcifications. Experimental results are compared with real DICOM images and their corresponding diagnosis provided by expert radiologists, showing that the cp feature is highly discriminative.

show abstract

Quantitative comparison of clustered microcalcifications in for-presentation and for-processing mammograms in full-field digital mammography

Cited by 6 publications

References 52 publications

Detection of potential microcalcification clusters using multivendor for‐presentation digital mammograms for short‐term breast cancer risk estimation

Detection of potential microcalcification clusters using multivendor for‐presentation digital mammograms for short‐term breast cancer risk estimation

A context-sensitive deep learning approach for microcalcification detection in mammograms

Analysis of the Cluster Prominence Feature for Detecting Calcifications in Mammograms

Contact Info

Product

Resources

About