Improvement in Radiologists?? Detection of Clustered Microcalcifications on Mammograms

Chan, Heang-Ping; Doi, Kunio; Vyborny, Carl J.; Schmidt, Robert A.; Metz, Charles E.; Lam, Kwok L.; Ogura, Takashi; Wu, Yidong; MacMahon, Heber

doi:10.1097/00004424-199010000-00006

Cited by 358 publications

(149 citation statements)

References 0 publications

Supporting

Mentioning

137

Contrasting

Unclassified

Order By: Relevance

“…These methods can be applied to m ark suspicious areas in mammograms when they are read, in order to reduce detection errors. This approach has turned out to be successful in a num ber o f studies [9][10][11]. H o w ever, neither o f these studies has yet dem onstrated the im pact in a real screening program , w here the fraction of abnorm al cases is only a few percent.…”

Section: Ig Itizationmentioning

confidence: 99%

Computer-assisted reading of mammograms

Karssemeijer

Hendriks

1997

Eur. Radiol.

View full text Add to dashboard Cite

Abstract. Techniques developed in com puter visionand automated pattern recognition can be applied to assist radiologists in reading mammograms. W ith the introduction of direct digital mammography this w ill become a feasible approach. A radiologist in breast cancer screening can use findings of the com puter as a second opinion, or as a pointer to suspicious re gions. This may increase the sensitivity and specificity of screening programs, and it may avoid the need for double reading. In this paper methods which have been developed fo r automated detection of mammo graphie abnorm alities are reviewed. Program s fo r de tecting m icrocalcification clusters and stellate lesions have reached a le ve l of performance which makes app lication in practice viable. Current programs fo r rec ognition of masses and asymmetry perform less well. Large-scale studies still have to demonstrate if rad io l ogists in a screening situation can deal w ith the re la tiv e ly large num ber of false positives w hich are m arked by com puter programs, where the num ber of norm al cases is much higher than in observer experi ments conducted thus far,

show abstract

Section: Ig Itizationmentioning

confidence: 99%

Computer-assisted reading of mammograms

Karssemeijer

Hendriks

1997

Eur. Radiol.

View full text Add to dashboard Cite

show abstract

“…Computer-assisted diagnosis for interpretation of mammograms and chest nadiographs is being explored in several institutions, with the objective of improving the frequency of detection of abnormalities (i.e., enhancing the sensitivity) and reducing the number offalse-positive and suggestive findings (i.e., improving the specificity) [4,5]. Methods of computer diagnosis…”

Section: What Else Ismentioning

confidence: 99%

The information perspective of radiology.

Hendee¹

1992

American Journal of Roentgenology

View full text Add to dashboard Cite

How well an industry such as radiology responds to challenges and adapts to change depends in large measure on how it views itself. The railroad industry has not thrived in the United States, largely because it has viewed itself for decades as a railroad industry. It would have fared better if it had thought of itself as an industry dedicated to efficient and effective transportation of people and products and followed through with the organizational and functional changes necessary to improve its efficiency and effectiveness.As an opposite example, IBM has done very well over the years by conceptualizing its business not as making computers but as facilitating the acquisition and use of information. EastmanKodak has remained strong in the photographic products market because it has presented itself less as a film industry and more as an industry dedicated to memorializing events such as family activities and significant public happenings.The challenge to any industry is to understand and appreciate the fundamental needs and desires of its market and then to develop and characterize products that meet those needs and desires [ii. To attempt to mold the marketplace to one's product line is to court disaster, as was discovered by the U.S. auto industry in the early 1970s when it ignored the growing public demand for smaller, more fuel-efficient cars. To build and maintain a viable position in the marketplace for the long term, an industry must position its product line in response to the market, rather than try to mold the market to its product line.Radiology is an industry with a market that has specific needs and desires. How we in radiology view our discipline defines in large measure how well those needs and desires are satisfied and therefore how well our profession will fare in the future. The question then is: How do we in radiology view our discipline? Perspectives of RadiologyThere are many different perspectives on radiology. Some persons think that radiology is primarily a discipline in which sophisticated imaging technologies are used for the study of human disease and injury. This "technology perspective" focuses on mastering the principles and applications of imaging technologies and sometimes ends up as an infatuation with the technologies themselves. Persons with this orientation may become more interested in the gadgetry of technologies than in how and why the technologies are useful in caring for patients. Those who work in radiology principally because they are enamored with radiology's technologies are the technocrats of the discipline. Some persons define radiology as the process of producing diagnostic images that are helpful in determining what might be wrong with patients. This "image perspective" operates under the assumption that high-quality images are the desined products of the nadiologic process. Persons with this image perspective are devoted to performing comprehensive examinations that yield the highest quality images possible. They are satisfied only with the best pictures and the...

show abstract

“…Microcalcifications are deposited tiny calcium which accumulates in breast tissue [13]. It is shown that 90 % of impalpable ductal carcinomas in situ and 70 % of impalpable minimal carcinomas were visible as microcalcification alone [7]. Advance image processing can improve the odds of mammograms in detecting breast cancer early [28].…”

Section: Introductionmentioning

confidence: 99%

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

2014

View full text Add to dashboard Cite

This work is directed toward the development of a computer-aided diagnosis (CAD) system to detect abnormalities or suspicious areas in digital mammograms and classify them as malignant or nonmalignant. Original mammogram is preprocessed to separate the breast region from its background. To work on the suspicious area of the breast, region of interest (ROI) patches of a fixed size of 128 × 128 are extracted from the original large-sized digital mammograms. For training, patches are extracted manually from a preprocessed mammogram. For testing, patches are extracted from a highly dense area identified by clustering technique. For all extracted patches corresponding to a mammogram, Zernike moments of different orders are computed and stored as a feature vector. A support vector machine (SVM) is used to classify extracted ROI patches. The experimental study shows that the use of Zernike moments with order 20 and SVM classifier gives better results among other studies. The proposed system is tested on Image Retrieval In Medical Application (IRMA) reference dataset and Digital Database for Screening Mammography (DDSM) mammogram database. On IRMA reference dataset, it attains 99 % sensitivity and 99 % specificity, and on DDSM mammogram database, it obtained 97 % sensitivity and 96 % specificity. To verify the applicability of Zernike moments as a fitting texture descriptor, the performance of the proposed CAD system is compared with the S. Sharma · P. Khanna ( ) Pandit Dwarka Prasad Mishra Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Dumna Airport Road, P.O.: Khamaria, Jabalpur, Madhya Pradesh 482 005, India e-mail: pkhanna@iiitdmj.ac.in S. Sharma e-mail: shubhi.sharma@iiitdmj.ac.in other well-known texture descriptors namely gray-level cooccurrence matrix (GLCM) and discrete cosine transform (DCT).

show abstract

Improvement in Radiologists?? Detection of Clustered Microcalcifications on Mammograms

Cited by 358 publications

References 0 publications

Computer-assisted reading of mammograms

Computer-assisted reading of mammograms

The information perspective of radiology.

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

Contact Info

Product

Resources

About