Quantitative Ultrasound and B-Mode Image Texture Features Correlate with Collagen and Myelin Content in Human Ulnar Nerve Fascicles

Byra, Michał; Wan, Lidi; Wong, Jonathan; Du, Jiang; Shah, Sameer B.; André, Michael P.; Chang, Eric Y.

doi:10.1016/j.ultrasmedbio.2019.02.019

Cited by 18 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fourth, the machine and imaging settings in this study were inconsistent, which may affect the ultrasomics features (29,30).…”

Section: Discussionmentioning

confidence: 95%

See 1 more Smart Citation

Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma

Zheng

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

BackgroundThe typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhanced in the arterial phase and washed out during the portal venous and late phases. However, atypical variations make a differential diagnosis both challenging and crucial. We aimed to investigate whether machine learning-based ultrasonic signatures derived from CEUS images could improve the diagnostic performance in differentiating focal nodular hyperplasia (FNH) and atypical hepatocellular carcinoma (aHCC).Patients and MethodsA total of 226 focal liver lesions, including 107 aHCC and 119 FNH lesions, examined by CEUS were reviewed retrospectively. For machine learning-based ultrasomics, 3,132 features were extracted from the images of the baseline, arterial, and portal phases. An ultrasomics signature was generated by a machine learning model. The predictive model was constructed using the support vector machine method trained with the following groups: ultrasomics features, radiologist’s score, and combination of ultrasomics features and radiologist’s score. The diagnostic performance was explored using the area under the receiver operating characteristic curve (AUC).ResultsA total of 14 ultrasomics features were chosen to build an ultrasomics model, and they presented good performance in differentiating FNH and aHCC with an AUC of 0.86 (95% confidence interval [CI]: 0.80, 0.89), a sensitivity of 76.6% (95% CI: 67.5%, 84.3%), and a specificity of 80.5% (95% CI: 70.6%, 85.9%). The model trained with a combination of ultrasomics features and the radiologist’s score achieved a significantly higher AUC (0.93, 95% CI: 0.89, 0.96) than that trained with the radiologist’s score (AUC: 0.84, 95% CI: 0.79, 0.89, P < 0.001). For the sub-group of HCC with normal AFP value, the model trained with a combination of ultrasomics features, and the radiologist’s score remain achieved the highest AUC of 0.92 (95% CI: 0.87, 0.96) compared to that with the ultrasomics features (AUC: 0.86, 95% CI: 0.74, 0.89, P < 0.001) and radiologist’s score (AUC: 0.86, 95% CI: 0.79, 0.91, P < 0.001).ConclusionsMachine learning-based ultrasomics performs as well as the staff radiologist in predicting the differential diagnosis of FNH and aHCC. Incorporating an ultrasomics signature into the radiologist’s score improves the diagnostic performance in differentiating FNH and aHCC.

show abstract

“…Fourth, the machine and imaging settings in this study were inconsistent, which may affect the ultrasomics features (29,30).…”

Section: Discussionmentioning

confidence: 95%

“…All outcomes were based on the features extracted by one radiologist, which may not be generalizable to all radiologists. Fourth, the machine and imaging settings in this study were inconsistent, which may affect the ultrasomics features ( 29 , 30 ).…”

Section: Discussionmentioning

confidence: 95%

Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma

Zheng

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…46 This is the only study in the literature that has investigated characteristics of HRUS fascicles with HCS confirmation; however, no reference to our study can be made as the aim of the study was different and only selected fascicles were analysed. 46 Group analysis showed significantly shorter interfascicular distances in the FC group compared to the FF group on HRUS. On HRUS images, the analysis showed significantly larger fascicle CSA in the FC group compared to the FF.…”

Section: Discussionmentioning

confidence: 99%

Median and ulnar nerve fascicle imaging using MR microscopy and high‐resolution ultrasound

Snoj

Serša

Matičič

et al. 2022

Journal of Neuroimaging

View full text Add to dashboard Cite

Background and Purpose: Understanding nerve microanatomy is important as different neuropathies and some nerve neoplasms present with fascicle enlargement. The aim of our study was to gain clinically oriented knowledge on nerve fascicular anatomy using imaging modalities.Methods: On a cadaveric upper extremity, high-resolution ultrasound (HRUS) scan with 22 MHz probe was performed. Sections of the median and ulnar nerves were excised at the level of the distal arm and after magnetic resonance microscopy (MRM), histological cross-sections (HCS) were prepared. Cross-referencing of the MRM and HRUS images with HCS was performed. Fascicle and nerve contouring was performed with morphometric software in order to assess nerve and fascicular cross-sectional area (CSA), fascicle count, and interfascicular distances. Based on fascicle differentiation, factual fascicle (FF) group and fascicular cluster (FC) group were defined.Results: On the cross-referenced imaging material, fascicles were differentiated in 92.7% on MRM and in 57.3% on HRUS. High to very high positive correlation among imaging material was observed for the fascicle CSA. FF depiction was 30.1% on HRUS. In comparison to the FF group, the FC group had significantly larger fascicle CSA and shorter interfascicular distances. Discussion:The findings of our study contribute to understanding of fascicle depiction on imaging modalities. HRUS offers good visualization of fascicles. The capability of differentiating fascicles is modality specific and depends on the fascicle CSA and the amount of interfascicular epineurium.

show abstract

“…Quantitative US parameters, such as the backscatter coefficient, can be used to assess tissue brightness in a scanner‐independent way that would not require the normalization of the median nerve brightness level based on surrounding tissues. In the case of the peripheral nerves, we recently applied these techniques, for instance, to characterization of cadaveric ulnar nerves …”

Section: Discussionmentioning

confidence: 99%

Assessing the Performance of Morphologic and Echogenic Features in Median Nerve Ultrasound for Carpal Tunnel Syndrome Diagnosis

Byra

Hentzen

et al. 2019

J of Ultrasound Medicine

Self Cite

View full text Add to dashboard Cite

Objectives-To assess the feasibility of using ultrasound (US) image features related to the median nerve echogenicity and shape for carpal tunnel syndrome (CTS) diagnosis.Methods-In 31 participants (21 healthy participants and 10 patients with CTS), US images were collected with a 30-MHz transducer from median nerves at the wrist crease in 2 configurations: a neutral position and with wrist extension. Various morphologic features, including the cross-sectional area (CSA), were calculated to assess the nerve shape. Carpal tunnel syndrome commonly results in loss of visualization of the nerve fascicular pattern on US images. To assess this phenomenon, we developed a nerve-tissue contrast index (NTI) method. The NTI is a ratio of average brightness levels of surrounding tissue and the median nerve, both calculated on the basis of a US image. The area under the curve (AUC) from a receiver operating characteristic curve analysis and t test were used to assess the usefulness of the features for differentiation of patients with CTS from control participants.Results-We obtained significant differences in the CSA and NTI parameters between the patients with CTS and control participants (P < .01), with the corresponding highest AUC values equal to 0.885 and 0.938, respectively. For the remaining investigated morphologic features, the AUC values were less than 0.685, and the differences in means between the patients and control participants were not statistically significant (P > .10). The wrist configuration had no impact on differences in average parameter values (P > .09).Conclusions-Patients with CTS can be differentiated from healthy individuals on the basis of the median nerve CSA and echogenicity. Carpal tunnel syndrome is not manifested in a change of the median nerve shape that could be related to circularity or contour variability.

show abstract

Quantitative Ultrasound and B-Mode Image Texture Features Correlate with Collagen and Myelin Content in Human Ulnar Nerve Fascicles

Cited by 18 publications

References 49 publications

Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma

Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma

Median and ulnar nerve fascicle imaging using MR microscopy and high‐resolution ultrasound

Assessing the Performance of Morphologic and Echogenic Features in Median Nerve Ultrasound for Carpal Tunnel Syndrome Diagnosis

Contact Info

Product

Resources

About