An automated multispectral pixel and image classification system using texture analysis and neural networks

Zheng, Yi; Foley, David A.; Kinter, T. M.

doi:10.1109/ultsym.1992.276007

Cited by 2 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Medical ultrasound can provide medical personnel with information about the texture of the target objects [17,18,19] (e.g. arterial walls [20,21,22]), whether certain objects are present or not (e.g.…”

Section: Figure 11 Example Obstetric Ultrasound Imagementioning

confidence: 99%

“…18 The magnitude response of a square root filter (right) designed from the magnitude of the system impulse response(left) …”

mentioning

confidence: 99%

“…18 shows that the square root filter approaches an inverse filter, but any smaller Fourier components are not fully inverted, they are raised only to the power of -½ instead of being raised to the power -1 as the inverse filter does. This makes the filter less sensitive to noise at these frequencies, and provides the motivation for this filter.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Pseudo-inverse filter design for improving the axial resolution of ultrasound images

Young

McLaughlin²

TENCON '97 Brisbane - Australia. Proceedings of IEEE TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologie

View full text Add to dashboard Cite

show abstract

Section: Figure 11 Example Obstetric Ultrasound Imagementioning

confidence: 99%

“…18 The magnitude response of a square root filter (right) designed from the magnitude of the system impulse response(left) …”

mentioning

confidence: 99%

See 1 more Smart Citation

Pseudo-inverse filter design for improving the axial resolution of ultrasound images

Young

McLaughlin²

TENCON '97 Brisbane - Australia. Proceedings of IEEE TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologie

View full text Add to dashboard Cite

show abstract

Differentiation of Intracardiac Tumors and Thrombi by Echocardiography Tissue Characterization: Comparison of an Artificial Neural Network and Human Observers

et al. 2000

View full text Add to dashboard Cite

The feasibility of classifying ultrasound images of intracardiac tumors and thrombi with a neural network-based algorithm was compared with the performance of experienced echocardiographers. The neural network used statistical descriptors of the apparent echocardiographic texture of the masses, and the blinded echocardiographers were given photographic prints of enlarged regions of interest without clinical data. The network classified 66% of the images correctly and the echocardiographers, 83%. The network and echocardiographers agreed in 88% of the images. Human observers usually base their classification of intracardiac masses on clinical data. The echocardiographic texture of tumors is quantitatively different from that of thrombi. This difference can be recognized by a neural network and potentially be useful in assisting with the diagnosis when clinical clues are insufficient.

show abstract

An automated multispectral pixel and image classification system using texture analysis and neural networks

Cited by 2 publications

References 8 publications

Pseudo-inverse filter design for improving the axial resolution of ultrasound images

Pseudo-inverse filter design for improving the axial resolution of ultrasound images

Differentiation of Intracardiac Tumors and Thrombi by Echocardiography Tissue Characterization: Comparison of an Artificial Neural Network and Human Observers

Contact Info

Product

Resources

About