Ultrasound Scatterer Density Classification Using Convolutional Neural Networks and Patch Statistics

Tehrani, Ali K. Z.; Amiri, Mina; Rosado-Méndez, Iván M.; Hall, Timothy J.; Rivaz, Hassan

doi:10.1109/tuffc.2021.3075912

Cited by 16 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, in one line of domain adaptation techniques, BN layers were modified and adapted to learn domain invariant features. In ultrasound imaging, Tehrani et al demonstrated that freezing BN layers during training improves domain adaptation [29]. Therefore, as a third baseline method, the proposed calibration approach was compared to BN freezing.…”

Section: Bn Freezingmentioning

confidence: 99%

Machine-to-Machine Transfer Function in Deep Learning-Based Quantitative Ultrasound

Soylu,

Oelze

2024

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

A Transfer Function approach was recently demonstrated to mitigate data mismatches at the acquisition level for a single ultrasound scanner in deep learning (DL) based quantitative ultrasound (QUS). As a natural progression, we further investigate the transfer function approach and introduce a Machine-to-Machine (M2M) Transfer Function, which possesses the ability to mitigate data mismatches at a machine level. This ability opens the door to unprecedented opportunities for reducing DL model development costs, enabling the combination of data from multiple sources or scanners, or facilitating the transfer of DL models between machines. We tested the proposed method utilizing a SonixOne machine and a Verasonics machine with an L9-4 array and an L11-5 array. We conducted two types of acquisitions to obtain calibration data: stable and free-hand, using two different calibration phantoms. Without the proposed method, the mean classification accuracy when applying a model on data acquired from one system to data acquired from another system was 50%, and the mean AUC was 0.405. With the proposed method, mean accuracy increased to 99%, and the AUC rose to the 0.999. Additional observations include the choice of the calibration phantom led to statistically significant changes in the performance of the proposed method. Moreover, robust implementation inspired by Wiener filtering provided an effective method for transferring the domain from one machine to another machine, and it can succeed using just a single calibration view. Lastly, the proposed method proved effective when a different transducer was used in the test machine.

show abstract

Section: Bn Freezingmentioning

confidence: 99%

Machine-to-Machine Transfer Function in Deep Learning-Based Quantitative Ultrasound

Soylu,

Oelze

2024

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

show abstract

“…In the context of QUS, tissue microstructures can be characterized by extracting quantitative parameters connected with acoustic scatterers from ultrasound backscattered signals, as opposed to the commonly used B-mode ultrasound which is qualitative. The QUS parameters frequently used in ultrasound tissue characterization include backscatter coefficient [1] , [2] , [4] , [6] , acoustic attenuation [1] , [2] , [4] , speed of sound [4] , [5] , envelope statistics [1] , [2] , [3] , [4] , [6] , [7] , [8] , [9] , [10] , [11] , Lizzi–Feleppa spectral parameters [1] , [2] , [12] , [13] , [14] , mean scatterer spacing [15] , [16] , [17] , scatterer number densities [18] , [19] , and scatterer sizes [7] , [20] , [21] .…”

Section: Introductionmentioning

confidence: 99%

Multimodality quantitative ultrasound envelope statistics imaging based support vector machines for characterizing tissue scatterer distribution patterns: Methods and application in detecting microwave-induced thermal lesions

Li,

Tsui,

et al. 2024

Ultrasonics Sonochemistry

View full text Add to dashboard Cite

“…In the proposed method, a single frame from a single calibration source from the testing domain is sufficient. The problem of data mismatch has also become more prominent in recent literature on DL-based QUS [ 15 ], [ 16 ], [ 17 ], [ 18 ], [ 19 ]. Therani et al [ 16 ] utilized reference phantoms, which have known scatter number density to mitigate system dependency in the problem of classifying scatterer number density through adaptive batch normalization.…”

Section: Introductionmentioning

confidence: 99%

Calibrating Data Mismatches in Deep Learning-Based Quantitative Ultrasound Using Setting Transfer Functions

Soylu

Oelze

2023

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

Deep learning (DL) can fail when there are data mismatches between training and testing data distributions. Due to its operator-dependent nature, acquisitionrelated data mismatches, caused by different scanner settings, can occur in ultrasound imaging. As a result, it is crucial to mitigate the effects of these mismatches to enable wider clinical adoption of DL-powered ultrasound imaging and tissue characterization. To address this challenge, we propose an inexpensive and generalizable method that involves collecting a large training set at a single setting and a small calibration set at each scanner setting. Then, the calibration set will be used to calibrate data mismatches by using a signals and systems perspective. We tested the proposed solution to classify two phantoms using an L9-4 array connected to a SonixOne scanner. To investigate generalizability of the proposed solution, we calibrated three types of data mismatches: pulse frequency mismatch, focus mismatch and output power mismatch. Two well-known convolutional neural networks (CNN)s, i.e., ResNet-50 and DenseNet-201, were trained using the ultrasound radiofrequency (RF) data. To calibrate the setting mismatches, we calculated the setting transfer functions. The CNNs trained without calibration resulted in mean classification accuracies of around 52%, 84% and 85% for pulse frequency, focus and output power mismatches, respectively. By using the setting transfer functions, which allowed a matching of the training and testing domains, we obtained mean accuracies of 96%, 96% and 98%, respectively. Therefore, the incorporation of the setting transfer functions between scanner settings can provide an economical means of generalizing a DL model for specific classification tasks where scanner settings are not fixed by the operator.

show abstract

Ultrasound Scatterer Density Classification Using Convolutional Neural Networks and Patch Statistics

Cited by 16 publications

References 56 publications

Machine-to-Machine Transfer Function in Deep Learning-Based Quantitative Ultrasound

Machine-to-Machine Transfer Function in Deep Learning-Based Quantitative Ultrasound

Multimodality quantitative ultrasound envelope statistics imaging based support vector machines for characterizing tissue scatterer distribution patterns: Methods and application in detecting microwave-induced thermal lesions

Calibrating Data Mismatches in Deep Learning-Based Quantitative Ultrasound Using Setting Transfer Functions

Contact Info

Product

Resources

About