Automatic BI-RADS Description of Mammographic Masses

Narváez, Fabián; Díaz, Gabriel; Romero, Eduardo

doi:10.1007/978-3-642-13666-5_91

Cited by 9 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main obstacle in making such a system completely automatic is the lesion detection module, since the accuracy of feature calculation is Table 1 Comparative results of the semantic descriptors estimation using competing methods. The hamming loss (6) is used as the quality measure (a value of 1 corresponds to perfect prediction).…”

Section: Discussionmentioning

confidence: 99%

“…The ROI from where the visual features are calculated is obtained by a semiautomatic active contour-type lesion boundary detection method. We compared our method with the somewhat competing approaches of Narvaez et al [6] and Wei et al [7], which are essentially k-nearest neighbors (KNN) approaches, and of Burnside et al [8] and Rubin et al [9], which perform each semantic descriptor estimation independently using a classifier. The performance measure we used is the Hamming loss defined in (6) with equal weights, averaged over the testing set of images, and over the 10 random subsampling experiments.…”

Section: Methodsmentioning

confidence: 99%

“…Semantic descriptors have been primarily used in content based information retrieval (CBIR) for automatic retrieval of similar cases. In [6] the BI-RADS lexicon is used to extract texture characteristics associated with image regions obtained from a human reader mammography reports. The method searches similar regions by automatically computing the Mahalanobis distance of feature vectors that describe the main shape and texture characteristics of the selected regions.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

From medical image to automatic medical report generation

Kisilev¹,

Walach²,

Barkan³

et al. 2015

IBM J. Res. & Dev.

View full text Add to dashboard Cite

We present a novel method for automatic breast radiology report generation from image data. We formalize this problem as learning to map a set of diverse image measurements to a set of discrete semantic descriptor values that represent the standard radiology lexicon. We use a structured learning framework to model individual semantic descriptors and their relationships. The parameters of the learned model are efficiently learned based on a training set of images using the structured support vector machine (SVM). The output report for a new image is generated in the form of a set of radiological lexicon descriptors. If the proposed method is used in a computer aided diagnosis (CAD) system, radiologists should be able to easily understand the diagnosis decision of the system since the system output is the standard radiological lexicon used to make a diagnosis. We applied the method to breast imaging modalities, sonography, and mammography. Our experiments indicate that our method generalizes better than competing approaches. Although the proposed method is tested for breast imaging report generation, it should be useful in general doctors' practice, wherein there is a predefined set of medical descriptors to be acquired by a doctor during image investigation.

show abstract

Section: Discussionmentioning

confidence: 99%