A Review of the Role of Ultrasound Radiomics and Its Application and Limitations in the Investigation of Thyroid Disease.

The incidence of thyroid disease has gradually increased in recent years. Conventional ultrasound is one of the most critical thyroid imaging methods, but it still has certain limitations. The use of B-model ultrasound (BMUS) diagnosis of thyroid disease will be affected by a doctors' clinical experience. The ultrasound radiomics is based on ultrasound images to delineate the region of interest (ROI), and then extract features to quantify the disease information contained in the image, which helps to analyze the correlation between the image and the clinical pathology of the disease. By building a powerful model, it can be used to diagnose benign and malignant thyroid nodules, predict lymph node status in thyroid cancer, analyze molecular biological characteristics, and predict the survival of thyroid cancer patients. At present, the application of ultrasound radiomics in the thyroid is pervasive. These ultrasound radiomics studies have further promoted the progress of ultrasonic technology in the field of thyroid disease. Clinicians should be familiar with the workflow of ultrasound radiomics and understand the application of this technology to the thyroid. In this article, we first describe the workflow of ultrasound radiomics, followed by an overview of the application of ultrasound radiomics to the thyroid. Finally, some current limitations of the technology and areas for future improvement are discussed. This article aims to review the role of ultrasound radiomics and its application and limitations in the investigation of thyroid disease.

Preoperative Prediction of Microvascular Invasion in Patients With Hepatocellular Carcinoma Based on Radiomics Nomogram Using Contrast-Enhanced Ultrasound.

PURPOSE: This study aimed to develop a radiomics nomogram based on contrast-enhanced ultrasound (CEUS) for preoperatively assessing microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. METHODS: A retrospective dataset of 313 HCC patients who underwent CEUS between September 20, 2016 and March 20, 2020 was enrolled in our study. The study population was randomly grouped as a primary dataset of 192 patients and a validation dataset of 121 patients. Radiomics features were extracted from the B-mode (BM), artery phase (AP), portal venous phase (PVP), and delay phase (DP) images of preoperatively acquired CEUS of each patient. After feature selection, the BM, AP, PVP, and DP radiomics scores (Rad-score) were constructed from the primary dataset. The four radiomics scores and clinical factors were used for multivariate logistic regression analysis, and a radiomics nomogram was then developed. We also built a preoperative clinical prediction model for comparison. The performance of the radiomics nomogram was evaluated via calibration, discrimination, and clinical usefulness. RESULTS: Multivariate analysis indicated that the PVP and DP Rad-score, tumor size, and AFP (alpha-fetoprotein) level were independent risk predictors associated with MVI. The radiomics nomogram incorporating these four predictors revealed a superior discrimination to the clinical model (based on tumor size and AFP level) in the primary dataset (AUC: 0.849 vs. 0.690; p < 0.001) and validation dataset (AUC: 0.788 vs. 0.661; p = 0.008), with a good calibration. Decision curve analysis also confirmed that the radiomics nomogram was clinically useful. Furthermore, the significant improvement of net reclassification index (NRI) and integrated discriminatory improvement (IDI) implied that the PVP and DP radiomics signatures may be very useful biomarkers for MVI prediction in HCC. CONCLUSION: The CEUS-based radiomics nomogram showed a favorable predictive value for the preoperative identification of MVI in HCC patients and could guide a more appropriate surgical planning.

A Review of the Role of the S-Detect Computer-Aided Diagnostic Ultrasound System in the Evaluation of Benign and Malignant Breast and Thyroid Masses.

Computer-aided diagnosis (CAD) systems have attracted extensive attention owing to their performance in the field of image diagnosis and are rapidly becoming a promising auxiliary tool in medical imaging tasks. These systems can quantitatively evaluate complex medical imaging features and achieve efficient and high-diagnostic accuracy. Deep learning is a representation learning method. As a major branch of artificial intelligence technology, it can directly process original image data by simulating the structure of the human brain neural network, thus independently completing the task of image recognition. S-Detect is a novel and interactive CAD system based on a deep learning algorithm, which has been integrated into ultrasound equipment and can help radiologists identify benign and malignant nodules, reduce physician workload, and optimize the ultrasound clinical workflow. S-Detect is becoming one of the most commonly used CAD systems for ultrasound evaluation of breast and thyroid nodules. In this review, we describe the S-Detect workflow and outline its application in breast and thyroid nodule detection. Finally, we discuss the difficulties and challenges faced by S-Detect as a precision medical tool in clinical practice and its prospects.

Ultrasonographic characteristics of Killian-Jamieson diverticula.

PURPOSE: A Killian-Jamieson diverticulum (KJD) may be mistaken for a thyroid nodule on ultrasound (US). The purpose of this retrospective study was to search for specific US features that would help differentiate between KJD and thyroid nodules. METHODS: A total of 12 patients with KJD who had undergone an US examination of the neck were identified. The size, shape, boundary, echopattern, location, color flow signals on color Doppler US of KJD and the relationship between the lesion and esophageal wall were analyzed. The change of size, shape and internal echotexture were also observed when the lesion was compressed with the probe and when the patient was asked to drink water. RESULTS: All KJD were confirmed by barium esophagography. All KJD were posterior to the left thyroid lobe on US, and were associated with a semicircular hypoechoic anterior wall. The internal echotexture was heterogeneous. In eight cases, the connection to the esophageal wall was seen. When compressing with the US probe or when the patients swallowed water, the size, shape or internal echotexture of the lesion changed. CONCLUSION: The specific criteria for US diagnosis of KJD included the connection to the esophageal wall and the fact that the internal echotexture, shape and size of KJD changed in real-time when the patient swallowed water or when the lesion was compressed with the transducer.

An intraneural ganglion cyst of the ulnar nerve at the wrist: a case report and literature review.

BACKGROUND: Intraneural ganglion cysts of the ulnar nerve at the wrist are rare and poorly understood. We report a case of an intraneural ganglion cyst at the level of the wrist.Case presentation: A 48-year-old man presented with the complaints of weakness for 6 months and serious aggravation for 1 month in his right hand. After examinations, including ultrasound, the patient was diagnosed with an intraneural ganglion cyst. Intraoperatively, with exposure of the ulnar nerve, we found that the intraneural ganglion cyst was at the level of Guyon's canal and extended approximately 6 cm proximally. Postoperatively, sensation of the fingers was normal, but atrophy of his muscles and limited straightening of his ring and little fingers were similar to those preoperatively. CONCLUSIONS: Diagnosis of an intraneural cyst before surgery is mostly based on ultrasound and magnetic resonance imaging. Transection of the articular branch is an important measure to prevent recurrence of this cyst. If the ulnar nerve is compressed and causes symptoms, nerve decompression, including removal/aspiration of the cyst, and sometimes external neurolysis of the nerve, are necessary to relieve the symptoms and allow regeneration of the nerve. However, these should be performed without damaging the nerve fascicles.

Deep learning with convolutional neural network in the assessment of breast cancer molecular subtypes based on US images: a multicenter retrospective study.

OBJECTIVES: To evaluate the prediction performance of deep convolutional neural network (DCNN) based on ultrasound (US) images for the assessment of breast cancer molecular subtypes. METHODS: A dataset of 4828 US images from 1275 patients with primary breast cancer were used as the training samples. DCNN models were constructed primarily to predict the four St. Gallen molecular subtypes and secondarily to identify luminal disease from non-luminal disease based on the ground truth from immunohistochemical of whole tumor surgical specimen. US images from two other institutions were retained as independent test sets to validate the system. The models' performance was analyzed using per-class accuracy, positive predictive value (PPV), and Matthews correlation coefficient (MCC). RESULTS: The model achieved good performance in identifying the four breast cancer molecular subtypes in the two test sets, with accuracy ranging from 80.07% (95% CI, 76.49-83.23%) to 97.02% (95% CI, 95.22-98.16%) and 87.94% (95% CI, 85.08-90.31%) to 98.83% (95% CI, 97.60-99.43) for the two test cohorts for each sub-category, respectively. In terms of 4-class weighted average MCC, the model achieved 0.59 for test cohort A and 0.79 for test cohort B. Specifically, the DCNN also yielded good diagnostic performance in discriminating luminal disease from non-luminal disease, with a PPV of 93.29% (95% CI, 90.63-95.23%) and 88.21% (95% CI, 85.12-90.73%) for the two test cohorts, respectively. CONCLUSION: Using pretreatment US images of the breast cancer, deep learning model enables the assessment of molecular subtypes with high diagnostic accuracy. TRIAL REGISTRATION: Clinical trial number: ChiCTR1900027676 KEY POINTS: • Deep convolutional neural network (DCNN) helps clinicians assess tumor features with accuracy. • Multicenter retrospective study shows that DCNN derived from pretreatment ultrasound imagine improves the prediction of breast cancer molecular subtypes. • Management of patients becomes more precise based on the DCNN model.

The High-Frequency Ultrasound Detection of Rat Sciatic Nerve in a Crushed Injury Model.

OBJECTIVE: This study aimed to visualize sciatic nerve injury in rats using ultrasound imaging in a crushed injury model. METHODS: Adult male Sprague-Dawley rats were subjected to a left sciatic nerve crush operation. Then, high-frequency ultrasound was used to image both sciatic nerves at 2 days and at 1, 2, 3, 4, and 6 weeks after surgery. RESULTS: Normal uninjured nerves have uniform thickness, display a smooth epineurium and inner adventitia, and are oblong in transverse sections. After the crush operation, nerve thickness increased, the inner echo signal decreased, the image of the epineurium became obscured and coarse before becoming smooth again, and transverse sections of the nerve fibers changed from being semicircular to oval in shape before becoming elliptical again. These observations were consistent with pathological changes associated with nerve injury. CONCLUSIONS: High-frequency ultrasound is capable of capturing dynamic changes in rat sciatic nerves in a crushed injury model. This can be used as an auxiliary method of evaluation in traditional peripheral nerve injury experiments.

Histone deacetylase HDAC4 promotes the proliferation and invasion of glioma cells.

Glioma is the most lethal type of primary brain tumor characterized by aggressiveness and a poor prognosis. Histone deacetylase 4 (HDAC4) is frequently dysregulated in human malignancies. However, its biological functions in the development of glioma are not fully understood. The present study aimed to evaluate HDAC4 expression in human glioma and to elucidate the mechanistic role of HDAC4 in glioma. The results suggested that HDAC4 was significantly upregulated in glioma tissues and a number of glioma cell lines compared with adjacent non-tumor tissues and the non-cancerous human glial cell line SVG p12, respectively (P<0.05). The proliferation, adenosine triphosphate (ATP) levels and invasion ability were substantially enhanced in U251 cells with HDAC4 overexpression, and suppressed in U251 cells with a knockdown of HDAC4 compared with that in U251 cells transfected with the negative control. Knockdown of HDAC4 resulted in cell cycle arrest at the G0/G1 phase and induced the increase of reactive oxygen species level in U251 cells. Furthermore, HDAC4 overexpression was revealed to substantially inhibit the expression of cyclin-dependent kinase (CDK) inhibitors p21 and p27, and the expression of E-cadherin and ß­catenin in glioma U251 cells. Knockdown of HDAC4 substantially promoted the expression of CDK1 and CDK2 and vimentin in glioma U251 cells. Mechanistically, the results of the present study demonstrated that HDAC4 displayed a significant upregulation in glioma, and promoted glioma cell proliferation and invasion mediated through the repression of p21, p27, E-cadherin and ß­catenin, and the potentiation of CDK1, CDK2 and vimentin. Altogether, the present study revealed that HDAC4 overexpression was central for the tumorigenesis of glioma, which may serve as a useful prognostic biomarker and potential therapeutic target for glioma.

The Effect of Low-Intensity Ultrasound on Brain-Derived Neurotropic Factor Expression in a Rat Sciatic Nerve Crushed Injury Model.

Low-intensity ultrasound (LIU) can improve nerve regeneration and functional recovery after peripheral nerve crush injury, but the underlying mechanism is not clear. The objective of this study was to examine the effects of LIU on rat sciatic crush injury and to investigate a possible molecular mechanism. Adult male Sprague-Dawley rats underwent left sciatic nerve crush surgery and were then randomized into two groups: a treatment group that received LIU every other d, and a control group that received sham exposure. Compared with rats in the control group, rats in the treatment group had higher sciatic nerve function indexes, compound muscle action potentials, wet weight ratios of the target muscle and mRNA expression of brain-derived neurotropic factor (BDNF) in the crushed nerve and ipsilateral dorsal root ganglia. Our findings suggest that LIU might promote injured nerve regeneration by stimulating BDNF release.