Alizad, Azra

Abstract Background Accurate assessment of axillary lymph nodes (ALNs) is a critical step for timely diagnosis of metastasis and proper subsequent intervention in breast cancer patients. Herein, we compare the diagnostic utility of quantitative high-definition microvasculature imaging (qHDMI), shear wave elastography (SWE) and their combination for differentiation of metastatic ALNs from reactive. Methods A total of 85 female patients with suspicious ALNs recommended for fine needle aspiration biopsy (FNAB) were included in the study, and the pathology results were used as the gold standard for labeling the status of each ALN. Three SWE metrics and ten qHDMI-derived biomarkers were used in our analyses. Additionally, age, as well as clinical ultrasound features such as nodal size and cortical thickness were included as clinical factors. The Wilcoxon rank-sum test was utilized to analyze distributional differences in biomarkers between metastatic and reactive ALNs. Multiple elastic-net logistic regression models were developed based on varying combinations of clinical, qHDMI, and SWE feature sets. A 70%/30% train/test split was adopted, and ROC curve analyses were performed to evaluate and compare classification performance. Moreover, distributional differences in qHDMI and SWE biomarkers between ALNs corresponding to breast cancer immunohistochemical subtypes luminal A and B were investigated. Results Of the total of 85 ALNs included in the analysis, 42 were metastatic. Statistically significant (p-value < 0.05) differences were observed in all but one of the qHDMI biomarkers, as well as all the SWE metrics. Test-set discrimination defined by area under ROC curve (AUC) was low for the model using only clinical features (0.62; 95% CI = [0.39,0.84]), with higher performance observed for models using SWE only (0.93; [0.82,1.00]), qHDMI only (0.97; [0.91,1.00]), qHDMI-SWE (0.97; [0.92,1.00]), and qHDMI-SWE plus clinical biomarkers (0.98; [0.94,1.00]). No statistically significant improvements were seen in the combined SWE-qHDMI and SWE-qHDMI-C classification models relative to the qHDMI-only model, although power for comparison was limited. Four qHDMI biomarkers and two SWE measures exhibited statistically significant distributions among breast cancer luminal A and B subtypes. Conclusions qHDMI classification model was able to separate metastatic from reactive ALNs with high accuracy. qHDMI, SWE, and the combined models had improved classification performance over the baseline Clinical model. qHDMI biomarkers can be valuable in determining the malignancy status of suspicious ALNs, providing helpful information regarding breast cancer prognosis.

Angiogenesis has an essential role in the de novo evolution of choroidal melanoma as well as choroidal nevus transformation into melanoma. Differentiating early-stage melanoma from nevus is of high clinical importance; thus, imaging techniques that provide objective information regarding tumor microvasculature structures could aid accurate early detection. Herein, we investigated the feasibility of quantitative high-definition microvessel imaging (qHDMI) for differentiation of choroidal tumors in humans. This new ultrasound-based technique encompasses a series of morphological filtering and vessel enhancement techniques, enabling the visualization of tumor microvessels as small as 150 microns and extracting vessel morphological features as new tumor biomarkers. Distributional differences between the malignant melanomas and benign nevi were tested on 37 patients with choroidal tumors using a non-parametric Wilcoxon rank-sum test, and statistical significance was declared for biomarkers with p-values < 0.05. The ocular oncology diagnosis was choroidal melanoma (malignant) in 21 and choroidal nevus (benign) in 15 patients. The mean thickness of benign and malignant masses was 1.70 ± 0.40 mm and 3.81 ± 2.63 mm, respectively. Six HDMI biomarkers, including number of vessel segments (p = 0.003), number of branch points (p = 0.003), vessel density (p = 0.03), maximum tortuosity (p = 0.001), microvessel fractal dimension (p = 0.002), and maximum diameter (p = 0.003) exhibited significant distributional differences between the two groups. Contrast-free HDMI provided noninvasive imaging and quantification of microvessels of choroidal tumors. The results of this pilot study indicate the potential use of qHDMI as a complementary tool for characterization of small ocular tumors and early detection of choroidal melanoma.

Functional ultrasound (fUS), an emerging hemodynamic-based functional neuroimaging technique, is especially suited to probe brain activity and primarily used in animal models. Increasing use of pharmacological models for essential tremor extends new research to the utilization of fUS imaging in such models. Harmaline-induced tremor is an easily provoked model for the development of new therapies for essential tremor (ET). Furthermore, harmaline-induced tremor can be suppressed by the same classic medications used for essential tremor, which leads to the utilization of this model for preclinical testing. However, changes in local cerebral activities under the effect of tremorgenic doses of harmaline have not been completely investigated. In this study, we explored the feasibility of fUS imaging for visualization of cerebral activation and deactivation associated with harmaline-induced tremor and tremor-suppressing effects of propranolol. The spatial resolution of fUS using a high frame rate imaging enabled us to visualize time-locked and site-specific changes in cerebral blood flow associated with harmaline-evoked tremor. Intraperitoneal administration of harmaline generated significant neural activity changes in the primary motor cortex and ventrolateral thalamus (VL Thal) regions during tremor and then gradually returned to baseline level as tremor subsided with time. To the best of our knowledge, this is the first functional ultrasound study to show the neurovascular activation of harmaline-induced tremor and the therapeutic suppression in a rat model. Thus, fUS can be considered a noninvasive imaging method for studying neuronal activities involved in the ET model and its treatment.

Breast cancer is the second-leading cause of mortality among women around the world. Ultrasound (US) is one of the noninvasive imaging modalities used to diagnose breast lesions and monitor the prognosis of cancer patients. It has the highest sensitivity for diagnosing breast masses, but it shows increased false negativity due to its high operator dependency. Underserved areas do not have sufficient US expertise to diagnose breast lesions, resulting in delayed management of breast lesions. Deep learning neural networks may have the potential to facilitate early decision-making by physicians by rapidly yet accurately diagnosing and monitoring their prognosis. This article reviews the recent research trends on neural networks for breast mass ultrasound, including and beyond diagnosis. We discussed original research recently conducted to analyze which modes of ultrasound and which models have been used for which purposes, and where they show the best performance. Our analysis reveals that lesion classification showed the highest performance compared to those used for other purposes. We also found that fewer studies were performed for prognosis than diagnosis. We also discussed the limitations and future directions of ongoing research on neural networks for breast ultrasound.

Background and motivation: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. Methodology: The system consists of a cascade of quality control, ResNet–UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL’s. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts—Croatia (80 COVID) and Italy (72 COVID and 30 controls)—leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. Results: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. Conclusion: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.

Axillary lymph nodes (ALNs) are generally among the first to be impacted by the metastatic spread of breast tumors. Consequently, evaluating their condition is of great importance as the removal of affected ALNs can potentially curtail the further spread of cancer cells to other parts of the body. Conventional ultrasound imaging suffers from low sensitivity and specificity and does not provide a comprehensive picture of the status of the node. In this work, we utilize an ultrasound microvessel imaging technique to visualize vascular structures within ALNs and, through several image processing steps, characterize the morphology of these structures. Several morphological metrics are used as biomarkers to differentiate between reactive and metastatic lymph nodes of patients with suspicious ALNs. A group of 68 patients is included in this study. Pathology examination results are used as the gold-standard reference for data labeling. A support vector machine (SVM) model is trained, and its performance is evaluated. Statistical analysis of the discriminative potential of individual biomarkers and receiver operating characteristic (ROC) curve analysis of the trained model are presented. Preliminary results suggest that a sensitivity of 0.88, specificity of 0.88, and area under the curve of 0.94 are achievable. Work supported by NIH-R01CA239548.

Observation of thyroid nodules in ultrasound examinations is a common occurrence. However, accurate diagnosis of the malignancy status of these nodules is a challenging task relying only on conventional ultrasound imaging. Therefore, increasing the sensitivity and specificity of non-invasive screening methods can be helpful in reducing the probability of missed diagnosis and decreasing the rate of unnecessary biopsies. In this feasibility study, a quantitative ultrasound microvasculature imaging technique is applied to ultrasound data collected from a cohort of 92 patients. This technique consists of first enabling the visualization of vascular networks inside the scanned nodules, followed by a morphometric analysis framework with a number of biomarkers to distinguish between benign and malignant thyroid nodules. Statistical tests are performed to find significant differences between the distribution of the values of the biomarkers. Subsequently, these biomarkers are utilized to train classification models that solely benefit from morphological biomarkers and those trained with additional clinical features. The receiver operating characteristic (ROC) curve analysis of these models, which helps us evaluate their predictive power, is presented. In our preliminary results, the model trained with combined morphological and clinical features achieves an AUC of 0.90, a sensitivity of 0.81, and a specificity of 0.79. [Work supported by R01CA239548.]

Abstract While being a relatively prevalent condition particularly among aging patients, peripheral arterial disease (PAD) of lower extremities commonly goes undetected or misdiagnosed due to its symptoms being nonspecific. Additionally, progression of PAD in the absence of timely intervention can lead to dire consequences. Therefore, development of non-invasive and affordable diagnostic approaches can be highly beneficial in detection and treatment planning for PAD patients. In this study, we present a contrast-free ultrasound-based quantitative blood flow imaging technique for PAD diagnosis. The method involves monitoring the variations of blood flow in the calf muscle in response to thigh-pressure-cuff-induced occlusion. Four quantitative metrics are introduced for analysis of these variations. We examine the feasibility of this method through an in vivo study consisting of 14 PAD patients with abnormal ankle-brachial index (ABI) and 8 healthy volunteers. Ultrasound data acquired from 13 legs in the patient group and 13 legs in the healthy group are analyzed. Out of the four utilized metrics, three exhibited significantly different distributions between the two groups (p-value < 0.05). The results of this feasibility study indicate the diagnostic potential of the proposed method for the detection of PAD.

Low specificity in current ultrasound modalities for thyroid cancer detection necessitates the development of new imaging modalities for optimal characterization of thyroid nodules. Herein, the quantitative biomarkers of a new high-definition microvessel imaging (HDMI) were evaluated for discrimination of benign from malignant thyroid nodules. Without the help of contrast agents, this new ultrasound-based quantitative technique utilizes processing methods including clutter filtering, denoising, vessel enhancement filtering, morphological filtering, and vessel segmentation to resolve tumor microvessels at size scales of a few hundred microns and enables the extraction of vessel morphological features as new tumor biomarkers. We evaluated quantitative HDMI on 92 patients with 92 thyroid nodules identified in ultrasound. A total of 12 biomarkers derived from vessel morphological parameters were associated with pathology results. Using the Wilcoxon rank-sum test, six of the twelve biomarkers were significantly different in distribution between the malignant and benign nodules (all p < 0.01). A support vector machine (SVM)-based classification model was trained on these six biomarkers, and the receiver operating characteristic curve (ROC) showed an area under the curve (AUC) of 0.9005 (95% CI: [0.8279,0.9732]) with sensitivity, specificity, and accuracy of 0.7778, 0.9474, and 0.8929, respectively. When additional clinical data, namely TI-RADS, age, and nodule size were added to the features, model performance reached an AUC of 0.9044 (95% CI: [0.8331,0.9757]) with sensitivity, specificity, and accuracy of 0.8750, 0.8235, and 0.8400, respectively. Our findings suggest that tumor vessel morphological features may improve the characterization of thyroid nodules.