A Preliminary Study of Quantitative Ultrasound for Cancer-Risk Assessment of Thyroid Nodules

Improved cancer risk stratification of isoechoic thyroid nodules to reduce unnecessary biopsies using quantitative ultrasound

Objective

Gray-scale ultrasound (US) is the standard-of-care for evaluating thyroid nodules (TNs). However, the performance is better for the identification of hypoechoic malignant TNs (such as classic papillary thyroid cancer) than isoechoic malignant TNs. Quantitative ultrasound (QUS) utilizes information from raw ultrasonic radiofrequency (RF) echo signal to assess properties of tissue microarchitecture. The purpose of this study is to determine if QUS can improve the cancer risk stratification of isoechoic TNs.

Methods

Patients scheduled for TN fine needle biopsy (FNB) were recruited from the Thyroid Health Clinic at Boston Medical Center. B-mode US and RF data (to generate QUS parameters) were collected in 274 TNs (163 isoechoic, 111 hypoechoic). A linear combination of QUS parameters (CQP) was trained and tested for isoechoic [CQP(i)] and hypoechoic [CQP(h)] TNs separately and compared with the performance of conventional B-mode US risk stratification systems.

Results

CQP(i) produced an ROC AUC value of 0.937+/- 0.043 compared to a value of 0.717 +/- 0.145 (p >0.05) for the American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS) and 0.589 +/- 0.173 (p >0.05) for the American Thyroid Association (ATA) risk stratification system. In this study, CQP(i) avoids unnecessary FNBs in 73% of TNs compared to 55.8% and 11.8% when using ACR TI-RADS and ATA classification system.

Conclusion

This data supports that a unique QUS-based classifier may be superior to conventional US stratification systems to evaluate isoechoic TNs for cancer and should be explored further in larger studies.

Predicting head and neck cancer treatment outcomes with pre-treatment quantitative ultrasound texture features and optimising machine learning classifiers with texture-of-texture features

Aim

Cancer treatments with radiation present a challenging physical toll for patients, which can be justified by the potential reduction in cancerous tissue with treatment. However, there remain patients for whom treatments do not yield desired outcomes. Radiomics involves using biomedical images to determine imaging features which, when used in tandem with retrospective treatment outcomes, can train machine learning (ML) classifiers to create predictive models. In this study we investigated whether pre-treatment imaging features from index lymph node (LN) quantitative ultrasound (QUS) scans parametric maps of head & neck (H&N) cancer patients can provide predictive information about treatment outcomes.

Methods

72 H&N cancer patients with bulky metastatic LN involvement were recruited for study. Involved bulky neck nodes were scanned with ultrasound prior to the start of treatment for each patient. QUS parametric maps and related radiomics texture-based features were determined and used to train two ML classifiers (support vector machines (SVM) and k-nearest neighbour (k-NN)) for predictive modeling using retrospectively labelled binary treatment outcomes, as determined clinically 3-months after completion of treatment. Additionally, novel higher-order texture-of-texture (TOT) features were incorporated and evaluated in regards to improved predictive model performance.

Results

It was found that a 7-feature multivariable model of QUS texture features using a support vector machine (SVM) classifier demonstrated 81% sensitivity, 76% specificity, 79% accuracy, 86% precision and an area under the curve (AUC) of 0.82 in separating responding from non-responding patients. All performance metrics improved after implementation of TOT features to 85% sensitivity, 80% specificity, 83% accuracy, 89% precision and AUC of 0.85. Similar trends were found with k-NN classifier.

Conclusion

Binary H&N cancer treatment outcomes can be predicted with QUS texture features acquired from index LNs. Prediction efficacy improved by implementing TOT features following methodology outlined in this work.

Development of a Clinical-Radiomics Nomogram That Used Contrast-Enhanced Ultrasound Images to Anticipate the Occurrence of Preoperative Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Patients

Background and Objectives

Papillary thyroid carcinoma (PTC) is a prevalent histological type of thyroid cancer; however, noninvasive assessment of cervical lymph node metastasis (LNM) poses a challenge. This study aims to develop a novel clinical-radiomics nomogram that utilizes ultrasound (US) images to predict the presence of cervical LNM metastasis in patients with PTC.

Methods

A total of 423 patients with PTC were recruited to participate in this study between January 2020 and December 2022, of which 282 were classified into the training group and 141 patients were classified into the validation set. Contrast-enhanced ultrasound (CEUS) and B-mode ultrasound (BMUS) images were subjected to radiomic analysis, leading to the extraction of 912 radiomic features. Thereafter, a radiomics score (Radscore) was developed to effectively integrate the information derived from BMUS and CEUS modalities. Univariate and multivariate backward stepwise logistic regression analysis techniques were used to construct the clinical and clinical-radiomics models, respectively.

Results

The findings revealed that the clinical-radiomics nomogram incorporated age, sex, CEUS Radscore, and US-reported LNM as risk factors. The nomogram demonstrated good performance using data from the training (AUC = 0.891) and validation (AUC = 0.870) sets. The decision curve analysis implied that this nomogram exhibited good clinical utility, which was further supported by the results of the calibration curves and Hosmer-Lemeshow test.

Conclusion

The CEUS Radscore-based clinical radiomics nomogram could serve as a valuable tool for predicting cervical LNM metastasis in patients with PTC, thereby tailoring individualized treatment strategies for them.

High-Resolution Ultrasound Characterization of Local Scattering in Cancer Tissue

Ultrasound (US) has afforded an approach to tissue characterization for more than a decade. The challenge is to reveal hidden patterns in the US data that describe tissue function and pathology that cannot be seen in conventional US images. Our group has developed a high-resolution analysis technique for tissue characterization termed H-scan US, an imaging method used to interpret the relative size of acoustic scatterers. In the present study, the objective was to compare local H-scan US image intensity with registered histologic measurements made directly at the cellular level. Human breast cancer cells (MDA-MB 231, American Type Culture Collection, Manassas, VA, USA) were orthotopically implanted into female mice (N = 5). Tumors were allowed to grow for approximately 4 wk before the study started. In vivo imaging of tumor tissue was performed using a US system (Vantage 256, Verasonics Inc., Kirkland, WA, USA) equipped with a broadband capacitive micromachined ultrasonic linear array transducer (Kolo Medical, San Jose, CA, USA). A 15-MHz center frequency was used for plane wave imaging with five angles for spatial compounding. H-scan US image reconstruction involved use of parallel convolution filters to measure the relative strength of backscattered US signals. Color codes were applied to filter outputs to form the final H-scan US image display. For histologic processing, US imaging cross-sections were carefully marked on the tumor surface, and tumors were excised and sliced along the same plane. By use of optical microscopy, whole tumor tissue sections were scanned and digitized after nuclear staining. US images were interpolated to have the same number of pixels as the histology images and then spatially aligned. Each nucleus from the histologic sections was automatically segmented using custom MATLAB software (The MathWorks Inc., Natick, MA, USA). Nuclear size and spacing from the histology images were then compared with local H-scan US image features. Overall, local H-scan US image intensity exhibited a significant correlation with both cancer cell nuclear size (R2 > 0.27, p < 0.001) and the inverse relationship with nuclear spacing (R2 > 0.17, p < 0.001).

Classification of Metastatic Lymph Nodes In Vivo Using Quantitative Ultrasound at Clinical Frequencies

Quantitative ultrasound (QUS) methods characterizing the backscattered echo signal have been of use in assessing tissue microstructure. High-frequency (30 MHz) QUS methods have been successful in detecting metastases in surgically excised lymph nodes (LNs), but limited evidence exists regarding the efficacy of QUS for evaluating LNs in vivo at clinical frequencies (2-10 MHz). In this study, a clinical scanner and 10-MHz linear probe were used to collect radiofrequency (RF) echo data of LNs in vivo from 19 cancer patients. QUS methods were applied to estimate parameters derived from the backscatter coefficient (BSC) and statistics of the envelope-detected RF signal. QUS parameters were used to train classifiers based on linear discriminant analysis (LDA) and support vector machines (SVMs). Two BSC-based parameters, scatterer diameter and acoustic concentration, were the most effective for accurately detecting metastatic LNs, with both LDA and SVMs achieving areas under the receiver operating characteristic (AUROC) curve ≥0.94. A strategy of classifying LNs based on the echo frame with the highest cancer probability improved performance to 88% specificity at 100% sensitivity (AUROC = 0.99). These results provide encouraging evidence that QUS applied at clinical frequencies may be effective at accurately identifying metastatic LNs in vivo, helping in diagnosis while reducing unnecessary biopsies and surgical treatments.

Quantitative Ultrasound: An Emerging Technology for Detecting, Diagnosing, Imaging, Evaluating, and Monitoring Disease

Ultrasound has been a popular clinical imaging modality for decades. It is a well-established means of displaying the macroscopic anatomy of soft-tissue structures. While conventional ultrasound methods, i.e., B-mode and Doppler methods, are well proven and continue to advance technically in many ways, e.g., by extending into higher frequencies and taking advantage of harmonic phenomena in tissues, fundamentally new so-called quantitative ultrasound (QUS) technologies also are emerging and offer exciting promise for making significant improvements in clinical imaging and characterization of disease. These emerging quantitative methods include spectrum analysis, image statistics, elasticity imaging, contrast-agent methods, and flow-detection and -measurement techniques. Each provides independent information. When used alone, each can provide clinically valuable imaging capabilities; when combined with each other, their capabilities may be more powerful in many applications. Furthermore, all can be used fused with other imaging modalities, such as computed tomography (CT), magnetic-resonance (MR), positron-emission-tomography (PET), or single-photon emission computerized tomography (SPECT) imaging, to offer possibly even greater improvements in detecting, diagnosing, imaging, evaluating, and monitoring disease. This chapter focuses on QUS methods that are based on spectrum analysis and image statistics.

Implementation of Non-Invasive Quantitative Ultrasound in Clinical Cancer Imaging

Quantitative ultrasound (QUS) is a non-invasive novel technique that allows treatment response monitoring. Studies have shown that QUS backscatter variables strongly correlate with changes observed microscopically. Increases in cell death result in significant alterations in ultrasound backscatter parameters. In particular, the parameters related to scatterer size and scatterer concentration tend to increase in relation to cell death. The use of QUS in monitoring tumor response has been discussed in several preclinical and clinical studies. Most of the preclinical studies have utilized QUS for evaluating cell death response by differentiating between viable cells and dead cells. In addition, clinical studies have incorporated QUS mostly for tissue characterization, including classifying benign versus malignant breast lesions, as well as responder versus non-responder patients. In this review, we highlight some of the important findings of previous preclinical and clinical studies and expand the applicability and therapeutic benefits of QUS in clinical settings. We summarized some recent clinical research advances in ultrasound-based radiomics analysis for monitoring and predicting treatment response and characterizing benign and malignant breast lesions. We also discuss current challenges, limitations, and future prospects of QUS-radiomics.

Self-supervised multi-modal fusion network for multi-modal thyroid ultrasound image diagnosis

Ultrasound is a typical non-invasive diagnostic method often used to detect thyroid cancer lesions. However, due to the limitations of the information provided by ultrasound images, shear wave elastography (SWE) and color doppler ultrasound (CDUS) are also used clinically to assist in diagnosis, which makes the diagnosis time-consuming, labor-intensive, and highly subjective process. Therefore, automatic diagnosis of benign and malignant thyroid nodules is beneficial for the clinical diagnosis of the thyroid. To this end, based on three modalities of gray-scale ultrasound images(US), SWE, and CDUS, we propose a deep learning-based multi-modal feature fusion network for the automatic diagnosis of thyroid disease based on the ultrasound images. First, three ResNet18s initialized by self-supervised learning are used as branches to extract the image information of each modality, respectively. Then, a multi-modal multi-head attention branch is used to remove the common information of three modalities, and the knowledge of each modal is combined for thyroid diagnosis. At the same time, to better integrate the features between modalities, a multi-modal feature guidance module is also proposed to guide the feature extraction of each branch and reduce the difference between each-modal feature. We verify the multi-modal thyroid ultrasound image diagnosis method on the self-collected dataset, and the results prove that this method could provide fast and accurate assistance for sonographers in diagnosing thyroid nodules.