Benchmarking Supervised and Self-Supervised Learning Methods in A Large Ultrasound Muti-task Images Dataset.

Deep learning in ultrasound(US) imaging aims to construct foundational models that accurately reflect the modality's unique characteristics. Nevertheless, the limited datasets and narrow task types have restricted this field in recent years. To address these challenges, we introduce US-MTD120K, a multi-task ultrasound dataset with 120,354 real-world two-dimensional images. This dataset covers three standard plane recognition and two diagnostic tasks in ultrasound imaging, providing a rich basis for model training and evaluation. We detail the data collection, distribution, and labelling processes, ensuring a thorough understanding of the dataset's structure. Furthermore, we conduct extensive benchmark tests on 27 state-of-the-art methods from both supervised and self-supervised learning(SSL) perspectives. In the realm of supervised learning, we analyze the sensitivity of two main feature computation methods to ultrasound images at the representational level, highlighting that models which judiciously constrain global feature computation could potentially serve as a viable analytical approach for US image analysis. In the context of self-supervised learning, we delved into the modelling process of self-supervised learning models for medical images and proposed an improvement strategy, named MoCo-US, a solution that addresses the excessive reliance on pretext task design from the input side. It achieves competitive performance with minimal pretext task design and enhances other SSL methods simply. The dataset and the code will be available at https://github.com/JsongZhang/CDOA-for-UMTD.

TUSPM-NET: A multi-task model for thyroid ultrasound standard plane recognition and detection of key anatomical structures of the thyroid.

The thyroid gland is a vital gland located in the anterior part of the neck. Ultrasound imaging of the thyroid gland is a non-invasive and widely used technique for diagnosing nodular growth, inflammation, and enlargement of the thyroid gland. In ultrasonography, the acquisition of ultrasound standard planes is crucial for disease diagnosis. However, the acquisition of standard planes in ultrasound examinations can be subjective, laborious and heavily reliant on the sonographer's clinical experience. To overcome these challenges, we design a multi-task model TUSP Multi-task Network (TUSPM-NET) that can recognize Thyroid Ultrasound Standard Plane (TUSP) and detect key anatomical structures in TUSPs in real-time. To improve TUSPM-NET's accuracy and learn prior knowledge in medical images, we proposed the plane target classes loss function and the plane targets position filter. Additionally, we collected 9778 TUSP images of 8 standard planes to train and validate the model. Experiments have shown that TUSPM-NET can accurately detect anatomical structures in TUSPs and recognize TUSP images. Compared to current models with better performance, TUSPM-NET's object detection map@0.5:0.95 improves by 9.3%; the precision and recall of plane recognition improve by 3.49% and 4.39%, respectively. Furthermore, TUSPM-NET recognizes and detects a TUSP image in just 19.9 ms, which means that the method is well suited to the needs of real-time clinical scanning.

Automatic detection and diagnosis of thyroid ultrasound images based on attention mechanism.

Incidents of thyroid cancer have dramatically increased in recent years; however, early ultrasound diagnosis can reduce morbidity and mortality. The work in clinical situations relies heavily on the subjective experience of the sonographer. Numerous computer-aided diagnostic techniques exist, but most consider how good the results are, ignoring the pre-image collecting and its usefulness in post-clinical practise. To address these issues, this study proposes a computer-aided diagnosis method based on an attentional mechanism. Due to its lightweight properties, the model can rapidly identify nodules and distinguish between benign and malignant ones without using much hardware. The model uses a bounding box to locate the thyroid nodule and determines whether it is benign or cancerous, and outputs the diagnostic result of the thyroid nodule ultrasound images. The latest attention mechanisms are used to get better results at a fraction of the cost. Additionally, ultrasound images with different features of benign and malignant thyroid nodules were collected following the Thyroid Imaging Reporting and Data System standards. The experimental results showed that the approach identifies and classifies thyroid nodules rapidly and effectively; the mAP value of the results reached 0.89, and the mAP value of malignant nodules reached 0.94, with detection rate of single image reached 7 ms. Young physicians and small hospitals with limited resources can benefit from using this method to assist with thyroid ultrasound examination diagnosis.

Recognition of Thyroid Ultrasound Standard Plane Images Based on Residual Network.

Ultrasound is one of the critical methods for diagnosis and treatment in thyroid examination. In clinical application, many reasons, such as large outpatient traffic, time-consuming training of sonographers, and uneven professional level of physicians, often cause irregularities during the ultrasonic examination, leading to misdiagnosis or missed diagnosis. In order to standardize the thyroid ultrasound examination process, this paper proposes using a deep learning method based on residual network to recognize the Thyroid Ultrasound Standard Plane (TUSP). At first, referring to multiple relevant guidelines, eight TUSP were determined with the advice of clinical ultrasound experts. A total of 5,500 TUSP images of 8 categories were collected with the approval and review of the Ethics Committee and the patient's informed consent. Then, after desensitizing and filling the images, the 18-layer residual network model (ResNet-18) was trained for TUSP image recognition, and five-fold cross-validation was performed. Finally, through indicators like accuracy rate, we compared the recognition effect of other mainstream deep convolutional neural network models. Experimental results showed that ResNet-18 has the best recognition effect on TUSP images with an average accuracy rate of 91.07%. The average macro precision, average macro recall, and average macro F1-score are 91.39%, 91.34%, and 91.30%, respectively. It proves that the deep learning method based on residual network can effectively recognize TUSP images, which is expected to standardize clinical thyroid ultrasound examination and reduce misdiagnosis and missed diagnosis.

Reference range of fetal thorax using two-dimensional and three-dimensional ultrasound VOCAL technique and application in fetal thoracic malformations.

BACKGROUND: To establish the normal reference range of fetal thorax by two-dimensional (2D) and three-dimensional (3D) ultrasound VOCAL technique and evaluate the application in diagnosing fetal thoracic malformations. METHODS: A prospective cross-sectional study was undertaken involving 1077 women who have a normal singleton pregnancy at 13-40 weeks gestational age (GA). 2D ultrasound and 3D ultrasound VOCAL technique were utilized to assess fetal thoracic transverse diameter, thoracic anteroposterior diameter, thoracic circumference, thoracic area, lung volume, thoracic volume and lung-to-thoracic volume ratio. The nomograms of 2D and 3D fetal thoracic measurements were created to GA. 50 cases were randomly selected to calculate intra- and inter-observer reliability and agreement. In addition, the case groups including congenital skeletal dysplasia (SD) (15), congenital diaphragmatic hernia (CDH) (30), pulmonary sequestration (PS) (25) and congenital cystic adenomatoid malformation (CCAM) (36) were assessed by the nomograms and followed up subsequently. RESULTS: Both 2D and 3D fetal thoracic parameters increased with GA using a quadratic regression equation. The intra- and inter-observer reliability and agreement of each thoracic parameter were excellent. 2D fetal thoracic parameters could initially evaluate the fetal thoracic development and diagnose the skeletal thoracic deformity, and lung volume, thoracic volume and lung-to-thorax volume ratio were practical to diagnose and differentiate CDH, PS and CCAM. CONCLUSION: We have established the normal fetal thoracic reference range at 13-40 weeks, which has a high value in diagnosing congenital thoracic malformations.

Prenatal Ultrasound Evaluation of the Position of Conus Medullaris for the Diagnosis of Tethered Cord Syndrome.

To determine the conus distance between the end of the conus medullaris and the distal end of the last vertebral body in healthy fetuses with various gestational ages using ultrasonography for its diagnostic value in tethered cord syndrome (TCS). This retrospective study included 540 healthy and 8 autopsy-confirmed TCS fetuses. Ultrasonographic measurement of the conus distance was performed when the fetus was in a prone position within the spine in the near field at 14 to 41 weeks of gestational age. Linear correlation analysis was performed to analyze the relationship between the conus distance and the gestational age, biparietal diameter, femur length, head circumference, and abdominal circumference. The normal results were compared with 8 cases of postnatally confirmed TCS. In 526 (95.9%) of 548 fetuses, the conus distance was successfully measured. The 95% limits of agreement in measurement of conus distance were -2.2 to 2.6 mm for the intraobserver variability and -3.7 to 3.1 mm for the interobserver variability. Significant correlations between the conus distance and the gestational age, biparietal diameter, femur length, head circumference, and abdominal circumference were observed. The most marked association was found to be between conus distance and femur length. The conus distance was significantly less in TCS fetuses than in healthy fetuses. Ultrasonographic measurement of conus distance is an easy and reliable method to evaluate the position of the conus medullaris and, therefore, can be helpful in the prenatal diagnosis of TCS.