Combined B-mode and Nakagami Images for Improved Discrimination of Breast Masses using Deep Learning

Muhtadi, Sabiq; Haque, Syed Tousiful; Gallippi, Caterina M.

doi:10.1109/ius54386.2022.9957624

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to enhance classification performance, the conventionally used average pixel value from the tumor region of Nakagami parametric images, which has been shown to be effective for breast tumor characterization across several studies, 28 , 30 , 33 – 36 was incorporated with the best performing texture feature sets. These average pixel values were obtained from the tumor region of Nakagami parametric images generated with the standard window (SL = 3), as in this case stable estimation of Nakagami parameters is important.…”

Section: Discussionmentioning

confidence: 99%

“…These parametric images have been widely applied for the characterization of breast lesions 32 – 36 However, these research works have been limited to use of the average pixel value within the tumor region of the Nakagami parametric images for breast lesion characterization. On the other hand, Nakagami parametric images are less susceptible to system and operator dependencies and are known to contain tissue features that are not visible on standard ultrasound B-mode images 23 , 32 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Texture quantified from ultrasound Nakagami parametric images is diagnostically relevant for breast tumor characterization

et al. 2023

View full text Add to dashboard Cite

We evaluate texture quantified from ultrasound Nakagami parametric images for non-invasive characterization of breast tumors, as Nakagami images can more faithfully represent intrinsic tumor characteristics than standard B-mode images.Approach: Parametric images were formed using sliding windows applied to ultrasound envelope data. To analyze the trade-off between spatial resolution and stability of estimated Nakagami parameters for texture quantification, two different window sizes were used for image formation: (i) the standard square window with sides equal to three times the pulse length of incident ultrasound, and (ii) a smaller square window with sides equal to exactly the pulse length. Texture was quantified from two different regions of interest (ROIs) consisting of the tumor core and a 5 mm surrounding margin. A total of 186 texture features were analyzed for each ROI, and feature selection was used to identify the most relevant feature sets for breast tumor characterization.Results: Texture quantified from parametric images formed using the two different windows did not outperform each other by a significant margin. However, when the mean pixel value within the tumor region of the parametric images was incorporated with the texture features, texture quantified from the tumor core and surrounding margin of images formed using the standard square window thoroughly outperformed other considerations for breast lesion characterization. The highest performing set of texture and mean value features yielded a significant AUC of 0.94, along with sensitivity of 90.38% and specificity of 89.58%. Conclusions:We establish that texture quantified from ultrasound Nakagami parametric images are diagnostically relevant and may be used to characterize breast lesions effectively.

show abstract