Prediction of near-term risk of developing breast cancer using computerized features from bilateral mammograms

Sun, Wenqing; Lure, Fleming; Wu, Teresa; Zhang, Jianying; Wang, Benjamin Y.; Saltzstein, Edward C.; Qian, Wei

doi:10.1016/j.compmedimag.2014.03.001

Cited by 31 publications

(17 citation statements)

References 41 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiment 1 asked if the abnormality signal was based on a disruption in the usual bilateral symmetry of the breasts. Studies have noted that asymmetry can be a strong indicator for developing breast cancer (27,28). Indeed, research has suggested that bilateral mammographic density asymmetry could be a significantly stronger risk factor for breast cancer development in the near-term than either woman's age or mean mammographic density (29).…”

mentioning

confidence: 99%

A half-second glimpse often lets radiologists identify breast cancer cases even when viewing the mammogram of the opposite breast

Evans

Haygood

Cooper

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

137

View full text Add to dashboard Cite

Humans are very adept at extracting the "gist" of a scene in a fraction of a second. We have found that radiologists can discriminate normal from abnormal mammograms at above-chance levels after a half-second viewing (d′ ∼ 1) but are at chance in localizing the abnormality. This pattern of results suggests that they are detecting a global signal of abnormality. What are the stimulus properties that might support this ability? We investigated the nature of the gist signal in four experiments by asking radiologists to make detection and localization responses about briefly presented mammograms in which the spatial frequency, symmetry, and/or size of the images was manipulated. We show that the signal is stronger in the higher spatial frequencies. Performance does not depend on detection of breaks in the normal symmetry of left and right breasts. Moreover, above-chance classification is possible using images from the normal breast of a patient with overt signs of cancer only in the other breast. Some signal is present in the portions of the parenchyma (breast tissue) that do not contain a lesion or that are in the contralateral breast. This signal does not appear to be a simple assessment of breast density but rather the detection of the abnormal gist may be based on a widely distributed image statistic, learned by experts. The finding that a global signal, related to disease, can be detected in parenchyma that does not contain a lesion has implications for improving breast cancer detection.gist processing | medical image perception | attention | mammography R apid extraction of scene "gist" (1-4) is a very useful aspect of routine visual perception that allows us to allocate our time and attention intelligently when confronted with new visual information (Can I find food here? Is there danger here?). The signals that we extract on our first glimpse of a scene are imperfect but not random. Experts often anecdotally report gistlike experiences with complex images in their domain of expertise. For instance, we have shown that radiologists can distinguish normal from abnormal mammograms at above-chance levels in as little as a quarter of a second, whereas nonexperts cannot (5). The gist of abnormality appears to be a global signal. Radiologists can detect it but cannot even crudely localize the abnormality under these conditions.Detecting the gist of breast cancer might be more than a curiosity, if that signal could be used to improve performance in breast cancer screening. Screening mammography can reduce mortality through early diagnosis of disease (6). Breast cancer is the most prevalent cancer in women and is the second leading cause of cancer deaths in women (7). In North America, screening mammography has a false negative rate of 20 to 30% (8, 9) and a recall rate of about 10% (10). With a disease prevalence of about 0.3% (11), the vast majority of those recalled will not have cancer. Thus, there is significant room for improvement.It has been argued for many years that an initial, global processing step is an i...

show abstract

mentioning

confidence: 99%

A half-second glimpse often lets radiologists identify breast cancer cases even when viewing the mammogram of the opposite breast

Evans

Haygood

Cooper

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

137

View full text Add to dashboard Cite

show abstract

“…The study results demonstrated a statistically significant (positive) associations (with AUC = 0.767 ± 0.019) between the modelgenerated risk prediction scores and the actual near-term risk of a woman having an image-detectable breast abnormality that may lead to the development of breast cancer in the next subsequent examination. This study is also different from the previously reported near-term risk prediction studies 23,25 that used the image features directly computed from the original image of the whole breast area. In this study, we tested and implemented a new multiscaled feature analysis method and systematically investigated the correlations of a large number of texture features on the multiscaled regions with the risk of cancer development.…”

Section: Discussionmentioning

confidence: 74%

“…The details of these algorithms can be found in our previous publications. 23,31,32 Once the breast region was identified, we performed a kclass fuzzy c means (FCM) clustering to partite it into several subregions and each one has relatively homogeneous density values. Instead of stratifying breast areas into dense and fatty regions only, 30,[33][34][35] more subregions were extracted and analyzed from the original breast depicted on mammogram.…”

Section: B Mammographic Subregions Segmentationmentioning

confidence: 99%

“…In our previous research, we have designed and implemented a prototype of breast cancer risk assessment approach using mammographic density information. 23 In this study, we proposed and tested two new approaches. First, instead of extracting the features from the whole breast area, we calculated the features at different scales of subregions on each mammogram.…”

Section: Introductionmentioning

confidence: 99%

“…[20][21][22] Some schemes have also been developed and tested to predict breast cancer risk using computed mammographic image features. [23][24][25] Most of these studies used the computational features extracted from whole breast or dense region of the breast. All the reported PPVs for risk analysis systems are relatively low, most of the PPVs are below 0.6, and the accuracy is still clinically unacceptable.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using multiscale texture and density features for near-term breast cancer risk analysis

et al. 2015

Self Cite

View full text Add to dashboard Cite

Purpose: To help improve efficacy of screening mammography by eventually establishing a new optimal personalized screening paradigm, the authors investigated the potential of using the quantitative multiscale texture and density feature analysis of digital mammograms to predict near-term breast cancer risk. Methods: The authors' dataset includes digital mammograms acquired from 340 women. Among them, 141 were positive and 199 were negative/benign cases. The negative digital mammograms acquired from the "prior" screening examinations were used in the study. Based on the intensity value distributions, five subregions at different scales were extracted from each mammogram. Five groups of features, including density and texture features, were developed and calculated on every one of the subregions. Sequential forward floating selection was used to search for the effective combinations. Using the selected features, a support vector machine (SVM) was optimized using a tenfold validation method to predict the risk of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) was used as the performance assessment index. Results: From a total number of 765 features computed from multiscale subregions, an optimal feature set of 12 features was selected. Applying this feature set, a SVM classifier yielded performance of AUC = 0.729 ± 0.021. The positive predictive value was 0.657 (92 of 140) and the negative predictive value was 0.755 (151 of 200). Conclusions:The study results demonstrated a moderately high positive association between risk prediction scores generated by the quantitative multiscale mammographic image feature analysis and the actual risk of a woman having an image-detectable breast cancer in the next subsequent examinations. C 2015 American Association of Physicists in Medicine. [http://dx

show abstract

Human lung cancer classification and comprehensive analysis using different machine learning techniques

Priyadarshini,

Ali,

Sivanandam

et al. 2024

Microscopy Res & Technique

View full text Add to dashboard Cite

Lung cancer is the most common causes of death among all cancer‐related diseases. A lung scan examination of the patient is the primary diagnostic technique. This scan analysis pertains to an MRI, CT, or X‐ray. The automated classification of lung cancer is difficult due to the involvement of multiple steps in imaging patients' lungs. In this manuscript, human lung cancer classification and comprehensive analysis using different machine learning techniques is proposed. Initially, the input images are gathered using lung cancer dataset. The proposed method processes these images using image‐processing techniques, and further machine learning techniques are utilized for categorization. Seven different classifiers including the k‐nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), multinomial naive Bayes (MNB), stochastic gradient descent (SGD), random forest (RF), and multi‐layer perceptron (MLP) classifier are used, which classifies the lung cancer as malignant and benign. The performance of the proposed approach is examined using performances metrics, like positive predictive value, accuracy, sensitivity, and f‐score are evaluated. Among them, the performance of the MLP classifier provides 25.34%, 45.39%, 15.39%, 41.28%, 22.17%, and 12.12% higher accuracy than other KNN, SVM, DT, MNB, SGD, and RF respectively.Research Highlights Lung cancer is a leading cause of cancer‐related death. Imaging (MRI, CT, and X‐ray) aids diagnosis. Automated classification of lung cancer faces challenges due to complex imaging steps. This study proposes human lung cancer classification using diverse machine learning techniques. Input images from lung cancer dataset undergo image processing and machine learning. Classifiers like k‐nearest neighbors, support vector machine, decision tree, multinomial naive Bayes, stochastic gradient descent, random forest, and multi‐layer perceptron (MLP) classify cancer types; MLP excels in accuracy.

show abstract

Prediction of near-term risk of developing breast cancer using computerized features from bilateral mammograms

Cited by 31 publications

References 41 publications

A half-second glimpse often lets radiologists identify breast cancer cases even when viewing the mammogram of the opposite breast

A half-second glimpse often lets radiologists identify breast cancer cases even when viewing the mammogram of the opposite breast

Using multiscale texture and density features for near-term breast cancer risk analysis

Human lung cancer classification and comprehensive analysis using different machine learning techniques

Contact Info

Product

Resources

About