CHÚC MỪNG NĂM MỚI

 

Model separates malignant from benign thyroid nodules on ultrasound

 

By Amerigo Allegretto, AuntMinnie.com staff writer

December 27, 2022 -- A deep-learning model developed by Chinese researchers can identify thyroid malignancies on ultrasound images, a study published December 21 in Computers in Biology and Medicine found.

Researchers led by Zhenggang Yu from Huaqiao University in Quanzhou found that by using an attention mechanism, their model can distinguish malignant from benign thyroid nodules with a high level of accuracy. They also highlighted the model's high speed.

"Young physicians and small hospitals with limited resources can benefit from using this method to assist with thyroid ultrasound examination diagnosis," Yu and co-authors wrote.

Early diagnosis of thyroid cancer with the aid of ultrasound imaging can lead to better treatment outcomes. However, this is dependent on the experience of the sonographer.

The researchers noted that while computer-aided diagnosis (CADx) techniques are available, their ability to differentiate between features seen in benign and malignant nodules is still limited.

Yu and fellow researchers wanted to propose another such method, but with an attentional mechanism with lightweight properties. They hypothesized that this could help identify nodules and distinguish malignant from benign findings by using a bounding box. They also highlighted that the model could do this without using much hardware while still being cost-effective.

The team tested the algorithm on data collected in 2020 and 2021 from a total of 1,921 thyroid ultrasound images from 1,357 patients. They looked at mean average precision (mAP) to evaluate performance and also assessed different intersection-over-union (IoU) thresholds, which measure the accuracy of an object detector on a particular dataset.

The researchers reported that the model showed good diagnostic results for benign and malignant thyroid nodules, especially for malignant nodules.

Performance of AI model for characterizing thyroid nodules on ultrasound
	All nodules	Benign	Malignant
Precision	0.885	0.829	0.941
Recall	0.851	0.838	0.863
mAP (0.5 IoU)	0.89	0.868	0.911
mAP (0.5 – 0.95 IoU)	0.501	0.478	0.523

The proposed model's mAP (with 0.5 IoU threshold) of 0.89 and an average speed of seven milliseconds, suggests high accuracy and rapid detection, according to the authors. They also highlighted that the model performs well with nodules of different sizes.

"In the clinical setting, it is possible to achieve a direct diagnosis of thyroid cancer once ultrasound images have been acquired, thus making the method practical," they added.

The study authors suggested that their model can aid inexperienced sonographers in this setting and can help them to free up their workloads. They added that it can also help avoid unnecessary invasive fine-needle aspiration.

However, the authors also called for better sample balance in testing the model. They wrote that their study was imbalanced between high- and low-risk nodules, which could result in poorer learning for the model.

Elastography helps detect autoimmune thyroid diseases in children

 

By Amerigo Allegretto, AuntMinnie.com staff writer

December 13, 2022

Although the study findings are promising for identifying autoimmune thyroid diseases in children, authors Dr. Eda Celebi Bitkin and Dr. Nursen Toprak from Van Yüzüncü Yıl University wrote, although they noted that elastography by itself is not enough to differentiate between the two diseases.

"If the clinical aspect is poor or thyroid-stimulating hormone receptor antibodies are missing, the combined use of conventional ultrasound and acoustic radiation force impulse may be helpful in distinguishing between the two diseases," the authors wrote.

Hashimoto's thyroiditis and Graves' disease are autoimmune diseases that affect the thyroid gland. Ultrasound findings and autoantibody elevation are typically used to diagnose either disease. In rare cases, ultrasound findings may be normal in both diseases, but previous research has suggested that shear-wave velocity values from elastography are higher in autoimmune thyroiditis than in healthy thyroid glands.

Bitkin and Toprak explored the use of elastography in 88 pediatric patients with Hashimoto's thyroiditis and Graves' disease. Out of these, 28 had Hashimoto's thyroiditis, 20 had Graves' disease, and the remaining 40 were healthy controls. All patients underwent thyroid elastography and ultrasound.

The duo found that shear-wave velocity values of patients with either disease showed higher thyroid tissue stiffness than healthy controls, but when such values were compared between both diseases, the team found no significant difference (p = 0.73). As for conventional ultrasound, patients with Hashimoto's thyroiditis had a hypoechoic echo pattern similar to those with Graves' disease (p < 0.05).

"These ultrasound imaging findings reflect longer-term inflammation and may not be found in the early stages of thyroiditis," Bitkin and Toprak wrote.

The researchers did not track disease stage in their study but suggested that the degree of tissue stiffness may change as the diseases progress. They called for future studies to consider disease staging, especially for patients with Hashimoto's thyroiditis.

FATTY LIVER DISEASE AREA

 Abstract

Liver steatosis is a chronic liver disease that is becoming one of the most important global health problems, due to its direct connection with metabolic syndrome, its significant impact on patients’ socioeconomic status and frailty, and the occurrence of advanced chronic liver disease. In recent years, there has been rapid technological progress in the ultrasound-based diagnostics field that can help us to quantitatively assess liver steatosis, including continuous attenuation parameters in A and B ultrasound modes, backscatter coefficients (e.g., speed of sound) and ultrasound envelope statistic parametric imaging. The methods used in this field are widely available, have favorable time and financial profiles, and are well accepted by patients. Less is known about their reliability in defining the presence and degree of liver steatosis. Numerous study reports have shown the methods’ favorable negative and positive predictive values in comparison with reference investigations (liver biopsy and MRI). Important research has also evaluated the role of these methods in diagnosing and monitoring non-alcoholic fatty liver disease (NAFLD). Since NAFLD is becoming the dominant global cause of liver cirrhosis, and due to the close but complex interplay of liver steatosis with the coexistence of liver fibrosis, knowledge regarding NAFLD’s influence on the progression of liver fibrosis is of crucial importance. Study findings, therefore, indicate the possibility of using these same diagnostic methods to evaluate the impact of NAFLD on the patient’s liver fibrosis progression risk, metabolic risk factors, cardiovascular complications, and the occurrence of hepatocellular carcinoma. The mentioned areas are particularly important in light of the fact that most of the known chronic liver disease etiologies are increasingly intertwined with the simultaneous presence of NAFLD.

Keywords: 

ultrasound; attenuation; predictive value; liver steatosis; non-alcoholic fatty liver disease; metabolic syndrome

JMU Vol 49-4 2022

Download from THU VIEN MEDIC 

https://drive.google.com/file/d/11i8Xbukp263jeNWc1fRrHdfifCTOaJnj/view?usp=sharing

Liver in Advance, US, CT, and MRI Moving toward the Future

ABSTRACT

Over the past two decades, the epidemiology of chronic liver disease has changed with an increase in the prevalence of nonalcoholic fatty liver disease in parallel to the advent of curative treatments for hepatitis C. Recent developments provided new tools for diagnosis and monitoring of liver diseases based on ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI), as applied for assessing steatosis, fibrosis, and focal lesions. This narrative review aims to discuss the emerging approaches for qualitative and quantitative liver imaging, focusing on those expected to become adopted in clinical practice in the next 5 to 10 years. While radiomics is an emerging tool for many of these applications, dedicated techniques have been investigated for US (controlled attenuation parameter, backscatter coefficient, elastography methods such as point shear wave elastography [pSWE] and transient elastography [TE], novel Doppler techniques, and three-dimensional contrast-enhanced ultrasound [3D-CEUS]), CT (dual-energy, spectral photon counting, extracellular volume fraction, perfusion, and surface nodularity), and MRI (proton density fat fraction [PDFF], elastography [MRE], contrast enhancement index, relative enhancement, T1 mapping on the hepatobiliary phase, perfusion). Concurrently, the advent of abbreviated MRI protocols will help fulfill an increasing number of examination requests in an era of healthcare resource constraints.

Key points

• Technical advances in liver imaging have been observed for ultrasound, computed tomography, and magnetic resonance imaging (MRI).

• Quantitative liver imaging biomarkers are promising to measure disease severity and reduce interoperator variability.

• Quantitative liver imaging biomarkers have the potential to be increasingly adopted in clinical practice.

• Abbreviated MRI protocols will help fulfill an increasing number of examination requests.

TI-RADS helps classify thyroid lesions on ultrasound

By Amerigo Allegretto, AuntMinnie.com staff writer

May 3, 2022

Researchers in three separate but related presentations discussed existing and new research that shows the effectiveness of TI-RADS in thyroid imaging with ultrasound.

"It provides descriptive features that are associated with increased rates of malignancy," said Dr. Michelle Melany from Cedars-Sinai Medical Center in Los Angeles in her keynote speech. "It helps categorize nodules and increases the number of reports with unambiguous management recommendations."

The American College of Radiology (ACR) in 2017 developed a standardized TI-RADS risk-stratification system to inform practitioners about which thyroid nodules require biopsy. This was in response to costly interventions for nodules that turned out to be benign on biopsy.

TI-RADS uses a scoring scale that goes from 0 to 5. A score of 0 indicates a benign lesion, while 5 represents a highly suspicious finding.

Benefits of TI-RADS include having higher sensitivity than risk stratification systems, ensuring all nodules can be classified, and reducing unnecessary biopsies, among others.

However, in her ARRS 2022 talk, Melany also listed some challenges the system faces. These include having a higher interobserver variability, varying appearances, and dependence on scanning parameters.

"In most of our practices, we're super busy. If only the ultrasound technician scans, then we're really dependent on what's captured and recorded on still images or cinematic clips," Melany said.

In an abstract presentation following Melany's keynote address, Dr. Logan Haug from the Mayo Clinic in Arizona showed research he co-led assessing whether adjusting TI-RADS could further reduce including benign nodules while keeping all malignant nodules. The current TI-RADS assign a score of two points for any lobulation found on ultrasound.

The team retrospectively looked at all ultrasound and pathology records to identify 516 thyroid nodules that underwent fine-needle aspiration (FNA) and had 58 lobulated margins in a two-year period. Images were divided into two groups showing "only macrolobulated" or "microlobulations present." Microlobulations were defined as being less than 2.5 mm in circumference.

Out of the lobulated margins, 14 were found to be malignant. A total of 37 lobulated margins were solely macrolobulated (two malignant), while 21 were microlobulated (12 malignant) (p < 0.0001).

Of nodules greater than or equal to 10 mm, 53 were lobulated, including 10 malignancies. The researchers found that under current TI-RADS standards, all 53 nodules met the criteria for FNA. However, under the team's microlobulation TI-RADS standards, 38 met the criteria for FNA.

In a second abstract presentation, Dr. Meredith Bara from the University of Alberta in Canada talked about research she co-led that looked at interreader agreement after teaching sessions for residents.

The study authors used 50 test nodules scored independently by three radiology residents with no formal TI-RADS training. Bara said the residents underwent a one-hour teaching session after initial scoring, which included reviewing sonographic features of nodules and 30 training cases.

The team found that the residents showed "significant" improvement in agreement after training, with a pooled specificity between 76.6% and 96.8%. They showed the strongest agreement on nodular shape and composition.

Melany in her keynote listed some potential future modifications to TI-RADS that could further improve its effects. These include using active surveillance, changing points for certain features, incorporating nodule location, using artificial intelligence, and using newer ultrasonic methods such as contrast-enhanced ultrasound and elastography.

HCC Screening Biomarkers and Ultrasound

 

New Guidelines for LUS

 

NAFLD Patient at Risk

 

KIDNEY FUNCTION PREDICTION via US