Partner: Michael Andre

University of California (US)

Recent publications
1.Byra M., Galperin M., Ojeda-Fournier H., Olson L., O Boyle M., Comstock C., Andre M., Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion, Medical Physics, ISSN: 0094-2405, DOI: 10.1002/mp.13361, Vol.46, No.2, pp.746-755, 2019
Abstract:

Purpose: We propose a deep learning-based approach to breast mass classification in sonography and compare it with the assessment of four experienced radiologists employing breast imaging reporting and data system 4th edition lexicon and assessment protocol. Methods: Several transfer learning techniques are employed to develop classifiers based on a set of 882 ultrasound images of breast masses. Additionally, we introduce the concept of a matching layer. The aim of this layer is to rescale pixel intensities of the grayscale ultrasound images and convert those images to red, green, blue (RGB) to more efficiently utilize the discriminative power of the convolutional neural network pretrained on the ImageNet dataset. We present how this conversion can be determined during fine-tuning using back-propagation. Next, we compare the performance of the transfer learning techniques with and without the color conversion. To show the usefulness of our approach, we additionallyevaluate it using two publiclyavailable datasets. Results: Color conversion increased the areas under the receiver operating curve for each transfer learning method. For the better-performing approach utilizing the fine-tuning and the matching layer, the area under the curve was equal to 0.936 on a test set of 150 cases. The areas under the curves for the radiologists reading the same set of cases ranged from 0.806 to 0.882. In the case of the two separate datasets, utilizing the proposed approach we achieved areas under the curve of around 0.890. Conclusions: The concept of the matching layer is generalizable and can be used to improve the overall performance of the transfer learning techniques using deep convolutional neural networks. When fully developed as a clinical tool, the methods proposed in this paper have the potential to help radiologists with breast mass classification in ultrasound. © 2018 American Association of Physicists in Medicine [https://doi.org/10.1002/mp.13361]

Keywords:

BI-RADS, breast mass classification, convolutional neural networks, transfer learning, ultrasound imaging

Affiliations:
Byra M.-IPPT PAN
Galperin M.-Almen Laboratories, Inc. (US)
Ojeda-Fournier H.-University of California (US)
Olson L.-University of California (US)
O Boyle M.-University of California (US)
Comstock C.-Memorial Sloan-Kettering Cancer Center (US)
Andre M.-University of California (US)
2.Byra M., Wan L., Wong J.H., Du J., Shah SB., Andre M.P., Chang E.Y., Quantitative ultrasound and b-mode image texture featurescorrelate with collagen and myelin content in human ulnarnerve fascicles, ULTRASOUND IN MEDICINE AND BIOLOGY, ISSN: 0301-5629, DOI: 10.1016/j.ultrasmedbio.2019.02.019, Vol.45, No.7, pp.1830-1840, 2019
Abstract:

We investigate the usefulness of quantitative ultrasound and B-mode texture features for characterization of ulnar nerve fascicles. Ultrasound data were acquired from cadaveric specimens using a nominal 30-MHz probe. Next, the nerves were extracted to prepare histology sections. Eighty-five fascicles were matched between the B-mode images and the histology sections. For each fascicle image, we selected an intra-fascicular region of interest. We used histology sections to determine features related to the concentration of collagen and myelin and ultrasound data to calculate the backscatter coefficient (–24.89 ± 8.31 dB), attenuation coefficient (0.92 ± 0.04 db/cm-MHz), Nakagami parameter (1.01 ± 0.18) and entropy (6.92 ± 0.83), as well as B-mode texture features obtained via the gray-level co-occurrence matrix algorithm. Significant Spearman rank correlations between the combined collagen and myelin concentrations were obtained for the backscatter coefficient (R = –0.68), entropy (R = –0.51) and several texture features. Our study indicates that quantitative ultrasound may potentially provide information on structural components of nerve fascicles.

Keywords:

NerveQuantitative ultrasoundHigh frequencyHistologyPattern recognitionTexture analysis

Affiliations:
Byra M.-IPPT PAN
Wan L.-University of California (US)
Wong J.H.-University of California (US)
Du J.-University of California (US)
Shah SB.-University of California (US)
Andre M.P.-University of California (US)
Chang E.Y.-University of California (US)