Impact of Breast Density on Computer-Aided Detection for Breast Cancer

Brem, Rachel F.; Hoffmeister, Jeffrey W.; Rapelyea, Jocelyn A.; Zisman, Gilat; Mohtashemi, Kevin; Jindal, Guarav; DiSimio, Martin P.; Rogers, Steven K.

doi:10.2214/ajr.184.2.01840439

Cited by 89 publications

(66 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Also, it is an imperfect exam, with many agreeing that this test has a sensitivity of about 85 to 90% (4,5). In order to improve the effectiveness of this method, systems for computer aided diagnosis (CAD) are arising and according to several authors this is leading to an incremental improvement of detection for this type of cancer by coordinating the work of the radiologist with the implementation of the CAD system (1,4,6).…”

Section: Framing the Issuementioning

confidence: 99%

“…Nevertheless, when cancer cells are found in the lymph nodes of the breast there is a high probability that these spread to the bloodstream and consequently create metastases elsewhere in the body (3,5,16).…”

Section: Breast Cancermentioning

confidence: 99%

“…Thus, and with other studies that demonstrate the importance of breast density to identify breast cancer (5,25,28) arises the need for standardization of the same. The model of classification and standardization presented meets the following criteria:…”

Section: Lexicons and Terminologiesmentioning

confidence: 99%

See 2 more Smart Citations

Using Data Mining Techniques to Support Breast Cancer Diagnosis

Diz

Marreiros

2015

New Contributions in Information Systems and Technologies

View full text Add to dashboard Cite

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method.In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis.In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings.Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix.For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests).The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS ® scale.The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications.The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques. VIII IX ResumoCada vez mais assistimos a um aumento global do número de métodos de apoio a decisão e diagnóstico assistido por computador, aplicados a diversas áreas da medicina.Na área de investigação do cancro da mama muitos são os trabalhos que têm sido desenvolvidos como segunda leitura de modo a reduzir o número de falsos positivos no diagnóstico.Neste estudo é apresentado um conjunto de técnicas de data mining que poderão ser aplicadas a um sistema de apoio à decisão na área do diagnóstico de cancro da mama.Esta abordagem tem por objetivo ajudar os clínicos na identificação de achados mamográficos como microcalcificações, massas e mesmo tecidos normais, de forma a evitar diagnósticos errados.Para isso, neste trabalho é usada uma base de dados fidedigna, de 410 imagens correspondentes a 115 pacientes, contendo análises prévias, realizadas por radiologistas, de microcalcificações, massas e tecidos considerados normais.Ao longo deste trabalho são utilizadas duas técnicas de extração de características, a matriz de coocorrência de níveis de cinza e a matriz de comprimento da linha de níveis de cinza.

show abstract

Section: Framing the Issuementioning

confidence: 99%

Section: Breast Cancermentioning

confidence: 99%

See 1 more Smart Citation

Using Data Mining Techniques to Support Breast Cancer Diagnosis

Diz

Marreiros

2015

New Contributions in Information Systems and Technologies

View full text Add to dashboard Cite

show abstract

“…The FROC curves with the FP marker rates obtained from the normal data set were compared. [52][53][54] because it reflects how the CAD system performs in terms of specificity and whether the CAD system may cause extra efforts for radiologists to double check the marked locations or unnecessary recalls in a screening setting. Furthermore, for CAD systems that set a maximum number of detected objects at the output, estimating the number of FPs using images with lesions can potentially lead to an optimistic bias for the FROC curve because one of the detected objects will likely be the true lesion.…”

Section: Fig 11mentioning

confidence: 99%

Development of a Computer-Aided Diagnosis System for Early Detection of Masses Using Retrospectively Detected Cancers on Prior Mammograms

Wei¹

2007

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing this collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden to Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports (0704-0188), 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS. REPORT DATE (DD-MM-YYYY) 01-06-20072. REPORT TYPE (From -To) Annual DATES COVERED PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) 8. PERFORMING ORGANIZATION REPORT NUMBERUniversity of Michigan Ann Arbor, MI 48109-1274 SPONSORING / MONITORING AGENCY NAME(S) AND ADDRESS(ES) 10. SPONSOR/MONITOR'S ACRONYM(S) U.S. Army Medical Research and Materiel Command Fort Detrick, Maryland 21702-5012 SPONSOR/MONITOR'S REPORT NUMBER(S) DISTRIBUTION / AVAILABILITY STATEMENTApproved for Public Release; Distribution Unlimited 13. SUPPLEMENTARY NOTES -Original contains colored plates: ALL DTIC reproductions will be in black and white. ABSTRACTThe goal of this project is to develop a computer-aided diagnosis (CAD) system for mass detection using advanced computer vision techniques that will be trained with retrospectively detected cancers on prior mammograms. The new CAD system will be combined with our existing CAD system. When fully developed, the new dual CAD system should increase the sensitivity of detecting cancers at the early stage without compromising the sensitivity for other cancers.During this project year, we have performed the following tasks: (1) continue to collect the data sets of digitized film mammograms for testing our CAD system, (2) investigation of a bilateral approach to reduce the false positives (FPs) on single CAD system, (3) develop image processing techniques for improvement of mass detection on prior mammograms, and (4) continue to develop a two-view information fusion method to improve the performance of single CAD system. In summary, we have investigated a number of areas in CAD of mammographic masses and evaluated the new techniques for mass detection on mammograms. We have made progress in three of the tasks proposed in the project. We have found that our new computer-vision techniques can improve the performance of the CAD systems. We will continue the development of the CAD system in the coming years. SUBJECT TERMSBreast cancer, mammography, CAD (4) IntroductionRecent clinical studies have proved that computer-aided diagnosis (CAD) systems are helpful for improving cancer detection by radio...

show abstract

“…Recent studies have shown that the performance of mammographic ComputerAided Detection systems decreases as the density of the breast increases, either decreasing the sensitivity [1,2] or increasing the specificity [3]. Thus, the segmentation of breast density is beneficial not only for estimating the quantity of breast dense tissue, but also for establishing specific abnormalities detection procedures according to the type of tissue (i.e.…”

Section: Introductionmentioning

confidence: 99%

Breast Density Segmentation: A Comparison of Clustering and Region Based Techniques

Torrent

Bardera

Oliver

et al.

Digital Mammography

View full text Add to dashboard Cite

Abstract. This paper presents a comparison of two clustering based algorithms and one region based algorithm for segmenting fatty and dense tissue in mammographic images. This is a crucial step in order to obtain a quantitative measure of the density of the breast. The first algorithm is a multiple thresholding algorithm based on the excess entropy, the second one is based on the Fuzzy C-Means clustering algorithm, and the third one is based on a statistical analysis of the breast. The performance of the algorithms is exhaustively evaluated using a database of full-field digital mammograms containing 150 CC and 150 MLO images and ROC analysis (ground-truth provided by an expert). Results demonstrate that the use of region information is useful to obtain homogeneous region segmentation, although clustering algorithms obtained better sensitivity.

show abstract

Impact of Breast Density on Computer-Aided Detection for Breast Cancer

Cited by 89 publications

References 13 publications

Using Data Mining Techniques to Support Breast Cancer Diagnosis

Using Data Mining Techniques to Support Breast Cancer Diagnosis

Development of a Computer-Aided Diagnosis System for Early Detection of Masses Using Retrospectively Detected Cancers on Prior Mammograms

Breast Density Segmentation: A Comparison of Clustering and Region Based Techniques

Contact Info

Product

Resources

About