Ultrasonic Diagnosis Research Articles

Features of Computer Static Perimetry in Primary Open-angle Glaucoma in Patients with Type 2 Diabetes Mellitus

Examined 110 eyes (55 patients) with POGC and type 2 diabetes mellitus; 40 eyes (20 patients) with POGC without diabetes mellitus and 60 eyes (30 patients) with diabetes without glaucoma. In addition to the generally accepted methods of research, the following were carried out: perimetry (static Octopus), ophthalmoscopy with Goldmann lens, binocular ophthalmoscope (Schepensa), and lens Volk-90,0D (USA), gonioscopy with lenses (Krasnova, Goldmana), tonometria by Maccov, NIidek (Japan) NT-2000 pneumometry, Tonography (Glau test-60). OCT disc optic nerve and yellow spot (Carl Zeiss Cirrus, HD OCT Model 4000/5000 Germany), OST retinal vessels with calibre meter (Cirrus HD-OCT Carl Zeiss), ultrasonic diagnosis (UZD) of central artery vessels and retinal vein (UZ-system of expert class Sono Scapesq), ultrasound of the eyes. Conducted studies of static perimetry in patients with POGC and type 2 diabetes suggest the influence of the severity of diabetic retinopathy on the course and progression of glaucoma.

Ultrasonic diagnosis of hepatic ectopic pregnancy: a case report

Hepatic ectopic pregnancy is an extremely rare ectopic pregnancy. Ectopic pregnancy is one of the reasons for acute abdominal pain. Ectopic pregnancy refers to the growth and development of zygotes outside the uterine cavity, and tubal pregnancy is the most common. Abdominal ectopic pregnancy is very rare, accounting for only 1.3% of all ectopic pregnancy including small intestine and large intestine, sigmoid colon, omentum, liver, diaphragm, pancreas, peritoneum and spleen [1], of which the incidence of hepatic ectopic pregnancy is about 1:15,000 per inner uterus pregnancy [2]. The present report describes the case of a 36-year-old woman who presented with continuous brown vaginal secretions after 57 days of amenorrhea. The patient was initially diagnosed with liver ectopic pregnancy by abdominal ultrasound and this was confirmed by laparoscopic exploration. The pathological examination revealed a pregnancy material in the liver tissue. The patient made good progress post-surgery, with serum levels returning to normal during a follow-up examination 1 month later. Overall, ultrasound and β-HCG levels are crucial in diagnosing ectopic pregnancy before patients show clinically consistent symptoms.

Ultrasound for breast cancer detection: A bibliometric analysis of global trends between 2004 and 2024.

With the advancement of computer technology and imaging equipment, ultrasound has emerged as a crucial tool in breast cancer diagnosis. To gain deeper insights into the research landscape of ultrasound in breast cancer diagnosis, this study employed bibliometric methods for a comprehensive analysis spanning from 2004 to 2024, analyzing 3523 articles from 2176 institutions in 82 countries/regions. Over this period, publications on ultrasound diagnosis of breast cancer showed a fluctuating growth trend from 2004 to 2024. Notably, China, Seoul National University and Kim EK emerged as leading contributors in ultrasound for breast cancer detection, with the most published and cited journals being Ultrasound Med Biol and Radiology. The research spots in this area included "breast lesion", "dense breast" and "breast-conserving surgery", while "machine learning", "ultrasonic imaging", "convolutional neural network", "case report", "pathological complete response", "deep learning", "artificial intelligence" and "classification" are anticipated to become future research frontiers. This groundbreaking bibliometric analysis and visualization of ultrasonic breast cancer diagnosis publications offer clinical medical professionals a reliable research focus and direction.

3D Printing and Biomedical Applications of Piezoelectric Composites: A Critical Review

AbstractPiezoelectric composites have received widespread attentions in the fields of biomedicine and in vitro wearable devices due to their ability to convert mechanical forces into charge signals. The preparation of piezoelectric composites with complex structures through 3D printing technology can not only effectively improve their piezoelectric output, but also enable their customized therapeutic applications. This paper first introduces the types of piezoelectric composites and reviews the 3D printing technology commonly used in their preparation, analyzing the advantages and disadvantages of each 3D printing technology. Then, the state‐of‐the‐art of the biomedical applications of piezoelectric composites, including drug sustained‐release, wound healing promotion, bone tissue cells growth promoting, neurorehabilitation stimulating, ultrasonic diagnosis, and in vivo biosensing and in vitro wearable sensing, are emphasized. Finally, the main factors affecting the applications of 3D printed piezoelectric composites are outlooked, and an in‐depth discussion on the challenges toward 3D printed piezoelectric composites are analyzed. This review is believed to provide some fundamental knowledge of 3D printed piezoelectric composites.

Giant enhancement of nonlinear harmonics of an optical-tweezer phonon laser

Phonon lasers, as mechanical analogues of optical lasers, are unique tools for not only fundamental studies of the emerging field of phononics but also diverse applications such as deep-ocean monitoring, force sensing, and biomedical ultrasonics. Recently, nonlinear phonon-lasing effects were observed in an opto-levitated micro-sphere, i.e., the spontaneous emerging of weak signals of high-order phonon harmonics in the phonon lasing regime. However, both the strengths and the quality factors of the emerging phonon harmonics are very poor, thus severely hindering their potential applications in making and utilizing nonlinear phonon-laser devices. Here we show that, by applying a single-colour electronic injection to this levitated system, giant enhancement can be achieved for all higher-order phonon harmonics, with more than 3 orders enhanced brightness and 5 orders narrowed linewidth. Such an electronically-enhanced phonon laser is also far more stable, with frequency stability extended from a dozen of minutes to over 1 h. More importantly, higher-order phonon correlations, as an essential lasing feature, are confirmed to be enhanced by the electronic injection as well, which as far as we know, has not been reported in previous works using this technique. This work, providing much stronger and better-quality signals of coherent phonon harmonics, is a key step towards controlling and utilizing nonlinear phonon lasers for applications such as phonon frequency combs, broadband phonon sensors, and ultrasonic bio-medical diagnosis.

Comparison of ultrasonic diagnosis of cesarean scar defects at different timepoints following cesarean section.

Cesarean scar defect (CSD) is a potential complication following cesarean section (CS), which has significant clinical implications, and is usually clinically diagnosed by ultrasound. However, the optimal timing for ultrasound diagnosis of CSD after CS has not been well established. This study aimed to evaluate the appropriate time for the diagnosis of CSD after CS by ultrasonography. The prospective study involved 120 women who delivered by elective CS with single birth and term birth from January 2021 to June 2022. Sample enrollment was consecutive in the study. Each woman underwent 3 ultrasound examinations for CSD diagnosis at 6 weeks, 6 months, and 12 months postpartum according to a modified Delphi method. The ultrasound indicators about the incision situation were recorded and statistically analyzed. Paired 4-fold table chi-square test was used to evaluate the consistency between the 3 diagnoses. The diagnostic sensitivity and specificity were calculated using a 4-cell table. According to whether the diagnosis was consistent to that at 6 or 12 months, the 120 cases at week 6 were separated into a consistent group and inconsistent group for statistical evaluation of the ultrasound indicators. Additionally, the menstrual duration of the included women was also recorded to analyze the correlation to ultrasound indicators of CSD at 6 months postpartum using the Person correlation coefficient. The included 120 women were divided into normal (3-7 days, n=52) and prolonged menstrual period (>7 days, n=68) groups. The 2 groups had no statistical differences in age, body mass index (BMI), gestational week of delivery, assisted reproduction rates, or postpartum complications. Among the 120 women, 100, 66, and 61 women were diagnosed as CSD at 6 weeks, 6 months, and 12 months postpartum, respectively. The results indicated that the diagnostic results of 6 weeks were inconsistent with those of 6 or 12 months postpartum, but the last 2 diagnostic results were consistent. The diagnostic sensitivity of 6 months was 100% and the specificity was 91.53% [95% confidence interval (CI): 85.84-95.26%]. Further, significant differences were found in depth of the defect, and the thickness (T) and ratio of residual muscle between the inconsistent group and the consistent group at 6 weeks. The patients could be considered self-recovered from CSD at 6 months when the defect depth was equal to or less than 4.04±0.82 mm at 6 weeks after CS. Additionally, in the CSD group at 6 months, the length (r=0.828, P<0.001), depth (r=0.784, P<0.001), width (r=0.787, P<0.001) of the defect, the T (r=0.831, P<0.001) and ratio of residual muscle (r=0.821, P<0.001) were strongly correlated with menstrual duration. CSD evaluation at week 6 after CS may cause misdiagnosis or overdiagnosis. The diagnosis of CSD was suggested to be made following 6 months or longer postpartum.

Prenatal ultrasonic diagnosis of esophageal atresia and tracheoesophageal fistula combined with interrupted inferior vena cava: a rare case report.

This is an extremely rare case of complicated fetal esophageal atresia (EA) with tracheoesophageal fistula (TEF) and interrupted inferior vena cava (IVC) diagnosed by prenatal ultrsonography and successfully treated with surgical repair. A 35-year-old pregnant woman was referred to our center for prenatal ultrasound, and the fetus was found to have a series of abnormalities, such as an interrupted IVC associated with a dilated azygos vein, an upper neck pouch sign of the thorax, and polyhydramnios. With suspicion of EA with TEF and interrupted IVC, the infant was born at 39weeks of gestation, and successfully underwent the surgical operation. The baby was doing well after 21months of follow-up. It is beneficial for the prenatal ultrasonic diagnosis of EA with TEF in optimizing labor care, postpartum treatment, and prompting neonatal management.

Photoactivated Gas-Generating Nanocontrast Agents for Long-Term Ultrasonic Imaging-Guided Combined Therapy of Tumors.

To date, long-term and continuous ultrasonic imaging for guiding the puncture biopsy remains a challenge. In order to address this issue, a multimodality imaging and therapeutic method was developed in the present study to facilitate long-term ultrasonic and fluorescence imaging-guided precision diagnosis and combined therapy of tumors. In this regard, certain types of photoactivated gas-generating nanocontrast agents (PGNAs), capable of exhibiting both ultrasonic and fluorescence imaging ability along with photothermal and sonodynamic function, were designed and fabricated. The advantages of these fabricated PGNAs were then utilized against tumors in vivo, and high therapeutic efficacy was achieved through long-term ultrasonic imaging-guided treatment. In particular, the as-prepared multifunctional PGNAs were applied successfully for the fluorescence-based determination of patient tumor samples collected through puncture biopsy in clinics, and superior performance was observed compared to the clinically used SonoVue contrast agents that are incapable of specifically distinguishing the tumor in ex vivo tissues.

Diagnostic Value of Ultrasound for Thyroid Nodules With a Spoke-Wheel Blood Flow Pattern

Objective To explore the diagnostic value of ultrasound for thyroid nodules with a spoke-wheel blood flow pattern.Methods The clinical data of the patients with thyroid nodules presenting a spoke-wheel blood flow pattern examined by ultrasound were collected,and the gray-scale ultrasound features of the nodules were recorded.The diagnostic performance of the Thyroid Imaging Reporting and Data System by American College of Radiology (ACR TI-RADS),Chinese Thyroid Imaging Reporting and Data System (C-TIRADS),and combined specific indicators for the thyroid nodules with a spoke-wheel blood flow pattern was evaluated by comparison with the pathological results,which was regarded as the gold standard.Results A total of 64 patients with thyroid nodules were finally included,including 47 patients with malignant nodules and 17 patients with benign nodules.In addition to the general ultrasound features,central scar mostly appeared in malignant nodules (χ2=5.968,P=0.015),while central coarse calcification was more common in benign nodules (χ2=10.899,P=0.001).After the combination of central scar and central gross calcification,the diagnostic performance of ACR TI-RADS and C-TIRADS was improved (both P<0.001).Conclusions When the thyroid nodule shows a spoke-wheel blood flow pattern,one should be cautious of the possibility of malignancy.Combining central scar and central coarse calcification can improve the accuracy of ultrasonic diagnosis.

Arterial Adventitial Vasa Vasorum Hyperplasia involved in Atherosclerotic Plaque Formation in a Rabbit Model

ObjectiveIt was previously believed that atherosclerotic (AS) plaque starts to develop from the intima and that intraplaque vasa vasorum (VV) hyperplasia promotes adventitial VV (AVV) hyperplasia. However, recent studies have shown that arterial AVV hyperplasia precedes early intimal thickening, suggesting its possible role as an initiating factor of AS. To provide further insight into this process, in this study, we examine the evolution of AAV and VV development in a preclinical model of early AS with longitudinal ultrasound imaging. MethodsModels of early AS were established. Duplex ultrasound scanning and contrast-enhanced ultrasound were performed for diagnosis. Pearson correlation tests were used to analyze the relationships between AVV hyperplasia and VV hyperplasia, or between AVV hyperplasia and intima-media thickness (IMT). ResultsDuring 0–12 wk of high-fat feeding, AVV gradually increased and intima-media thickened gradually in the observation area; in the 2nd wk of high-fat feeding, the observation area showed obvious AVV proliferation; at the 4th wk, the intima-media membrane became thicker; at the 12th wk, early plaque formation and intraplaque VV proliferation were observed. There was a strong positive correlation between AVV proliferation and IMT thickening and a strong negative correlation between AVV proliferation and the change rate of vessel diameter. ConclusionThis study demonstrated that AVV proliferation in the arteries occurred earlier than IMT thickening and was positively correlated with IMT. At present, the indicators of ultrasonic diagnosis of AS, such as IMT, Intraplaque VV, Echo property, all appear in the advanced stage of AS. The AVV may be an innovative diagnostic target for the early stage of AS plaque.

A “twelve-section ultrasonic screening and diagnosis method” and management system for screening and treating neonatal congenital heart disease at the grassroots level in Tang County, Hebei Province, China

BackgroundTo explore a method for screening and diagnosing neonatal congenital heart disease (CHD) applicable to grassroots level, evaluate the prevalence of CHD, and establish a hierarchical management system for CHD screening and treatment at the grassroots level.MethodsA total of 24,253 newborns born in Tang County between January 2016 and December 2020 were consecutively enrolled and screened by trained primary physicians via the “twelve-section ultrasonic screening and diagnosis method” (referred to as the “twelve-section method”). Specialized staff from the CHD Screening and Diagnosis Center of Hebei Children’s Hospital regularly visited the local area for definite diagnosis of CHD in newborns who screened positive. Newborns with CHD were managed according to the hierarchical management system.ResultsThe centre confirmed that, except for 2 newborns with patent ductus arteriosus missed in the diagnosis of ventricular septal defect combined with severe pulmonary hypertension, newborns with other isolated or concomitant simple CHDs were identified at the grassroots level. The sensitivity, specificity and diagnostic coincidence rate of the twelve-section method for screening complex CHD were 92%, 99.6% and 84%, respectively. A total of 301 children with CHD were identified. The overall CHD prevalence was 12.4‰. According to the hierarchical management system, 113 patients with simple CHD recovered spontaneously during local follow-up, 48 patients continued local follow-up, 106 patients were referred to the centre for surgery (including 17 patients with severe CHD and 89 patients with progressive CHD), 1 patient died without surgery, and 8 patients were lost to follow-up. Eighteen patients with complex CHD were directly referred to the centre for surgery, 3 patients died without surgery, and 4 patients were lost to follow-up. Most patients who received early intervention achieved satisfactory results. The mortality rate of CHD was approximately 28.86 per 100,000 children.ConclusionsThe “twelve-section method” is suitable for screening neonatal CHD at the grassroots level. The establishment of a hierarchical management system for CHD screening and treatment is conducive to the scientific management of CHD, which has important clinical and social significance for early detection, early intervention, reduction in mortality and improvement of the prognosis of complex and severe CHDs.

Clinical and Pathological Features of Pilomatrixoma in Children: A Retrospective Study

Plain Language SummaryPilomatrixoma is a benign skin neoplasm that is common in children and is often misdiagnosed. Fu et al. conducted a retrospective study at Shenzhen Baoan Women’s and Children’s Hospital. One hundred and seventy-one children with pilomatrixoma were included. There were 2 age peaks (≤1 year old, 5–11 years old) and 2 age valleys (2–4 years old, ≥12 years old). The mean disease course was 9.34 months, 69.0%, 86.5%, and 95.3% of the patients’ disease course in 6 months, 12 months, and 24 months, respectively. The mean tumor volume was 0.6 cm3, and 81.3% of patients’ tumor volume ≤1 cm3. Tumors were distributed sequentially in the head and neck (77.2%), upper limbs (12.9%), trunk (7.6%), and lower limbs (2.3%). The correct rates of clinical and ultrasonic diagnosis were 50.9% and 38.6%, respectively. The pathological features of pilomatrixoma were shadow cells (99.4%), basaloid cells (94.7%), calcification (39.8%), multinuclear giant cell aggregation (35.7%), inflammatory cell infiltration (33.9%), histiocytic hyperplasia (5.3%), and ossification (1.2%). There were no significant differences in age, disease course, or tumor volume between the male and female patients (p > 0.05). The age and tumor volume of the patients in different body parts were significantly different (P1 = 3.10E−05 and P2 = 5.60E−05, respectively). The correlation between the disease course and tumor volume was positively significant (p ≤ 0.05). There was a significant correlation between the disease course and tumor volume in patients with tumors at upper limbs (p = 0.03).

Generating lymphoma ultrasound image description with transformer model

Lymphoma, the most prevalent hematologic tumor originating from the lymphatic hematopoietic system, can be accurately diagnosed using high-resolution ultrasound. Microscopic ultrasound performance enables clinicians to identify suspected tumors and subsequently obtain a definitive pathological diagnosis through puncture biopsy. However, the complex and diverse ultrasonographic manifestations of lymphoma pose challenges for accurate characterization by sonographers. To address these issues, this study proposes a Transformer-based model for generating descriptive ultrasound images of lymphoma, aiming to provide auxiliary guidance for ultrasound doctors during screening procedures. Specifically, deep stable learning is integrated into the model to eliminate feature dependencies by training sample weights. Additionally, a memory module is incorporated into the model decoder to enhance semantic information modeling in descriptions and utilize learned semantic tree branch structures for more detailed image depiction. Experimental results on an ultrasonic diagnosis dataset from Shanghai Ruijin Hospital demonstrate that our proposed model outperforms relevant methods in terms of prediction performance.

Association of autoimmune thyroid disease with type 1 diabetes mellitus and its ultrasonic diagnosis and management.

As a common hyperglycemic disease, type 1 diabetes mellitus (T1DM) is a complicated disorder that requires a lifelong insulin supply due to the immune-mediated destruction of pancreatic β cells. Although it is an organ-specific autoimmune disorder, T1DM is often associated with multiple other autoimmune disorders. The most prevalent concomitant autoimmune disorder occurring in T1DM is autoimmune thyroid disease (AITD), which mainly exhibits two extremes of phenotypes: hyperthyroidism [Graves' disease (GD)] and hypo-thyroidism [Hashimoto's thyroiditis, (HT)]. However, the presence of comorbid AITD may negatively affect metabolic management in T1DM patients and thereby may increase the risk for potential diabetes-related complications. Thus, routine screening of thyroid function has been recommended when T1DM is diagnosed. Here, first, we summarize current knowledge regarding the etiology and pathogenesis mechanisms of both diseases. Subsequently, an updated review of the association between T1DM and AITD is offered. Finally, we provide a relatively detailed review focusing on the application of thyroid ultrasonography in diagnosing and managing HT and GD, suggesting its critical role in the timely and accurate diagnosis of AITD in T1DM.

Ultrasonic vascular visual-exercise early diagnosis of arterial hypertension

High level of prevalence of the arterial hypertension (AH) demands use of new technologies of early disease verification. Purpose. Develop a visual-exercise method of diagnostics of AH: bicycle-stressful doppler sonography of a renal-vascular blood-groove with assessment of the vascular motion status and definition of diagnostic criteria of disease. Materials and methods. The cohort (n=48) of healthy subjects and patients with AH I-II degree is surveyed. Bicycle-stressful research of renal-vascular reactivity included initial measurement and exercise monitoring of peak speed of a blood-groove (Vps) and the resistant index (RI) in renal artery (RA). Calculation the index of the pressor and high-speed relation (IPHSR) on a formula was carried out: IPHSR = Systolic BP/ Vps RA. Results. At peak bicycle-stressful test the VpsRA at patients with AH increased only 8% (2.8–11.0%) while at healthy volunteers – 27% (21.4–37.0%). Significantly differed IPHSR: at patients with AH it was measured 2.38–3.23 units (2.8 [2.650–2.892] units), and healthy volunteers 1.72–2.37 units (2.03 [1.91–2.16] units) (p=0,0001). The sensitivity of IPHSR was 91%, specificity – 88%, accuracy – 93%. The decrease of cortically kidney perfusion (increase in RI RA) in group of control was less expressed, than group of patients with AH: 8,6% (4.3–11.0) and 14.7% (9.7–23.2] respectively (r=0,0004). Conclusion. In the course of bicycle-exercise at patients with AH load the small growth of peak speed (25%), the IPHSR is highly sensitive (91%) and highly specific (88%) criterion of AH with differential border of 2,5 units.

Deep learning-assisted ultrasonic diagnosis of cervical lymph node metastasis of thyroid cancer: a retrospective study of 3059 patients.

This study aimed to develop a deep learning system to identify and differentiate the metastatic cervical lymph nodes (CLNs) of thyroid cancer. From January 2014 to December 2020, 3059 consecutive patients with suspected with metastatic CLNs of thyroid cancer were retrospectively enrolled in this study. All CLNs were confirmed by fine needle aspiration. The patients were randomly divided into the training (1228 benign and 1284 metastatic CLNs) and test (307 benign and 240 metastatic CLNs) groups. Grayscale ultrasonic images were used to develop and test the performance of the Y-Net deep learning model. We used the Y-Net network model to segment and differentiate the lymph nodes. The Dice coefficient was used to evaluate the segmentation efficiency. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the classification efficiency. In the test set, the median Dice coefficient was 0.832. The sensitivity, specificity, accuracy, PPV, and NPV were 57.25%, 87.08%, 72.03%, 81.87%, and 66.67%, respectively. We also used the Y-Net classified branch to evaluate the classification efficiency of the LNs ultrasonic images. The classification branch model had sensitivity, specificity, accuracy, PPV, and NPV of 84.78%, 80.23%, 82.45%, 79.35%, and 85.61%, respectively. For the original ultrasonic reports, the sensitivity, specificity, accuracy, PPV, and NPV were 95.14%, 34.3%, 64.66%, 59.02%, 87.71%, respectively. The Y-Net model yielded better accuracy than the original ultrasonic reports. The Y-Net model can be useful in assisting sonographers to improve the accuracy of the classification of ultrasound images of metastatic CLNs.

Ultrasonic Nondestructive Diagnosis of Cylindrical Batteries Under Various Charging Rates

Lithium-ion batteries have been used increasingly as electrochemical energy storage systems for electronic devices and vehicles. It is important to accurately estimate the state of charge (SoC) of a battery management system to control the battery operation to optimize performance, lifetime, and safety. The current work experimentally leverages ultrasonic diagnostic technology to investigate the SoC of lithium-ion batteries during the charge/discharge processes. A cylindrical-type nickel-cobalt-aluminum (NCA)–based 2500mAh 20A (INR18650-25R) battery was used for ultrasonic measurements with various charge/discharge rates of C/10.4, C/5.2, and C/1.3 at constant currents. The ultrasonic signals were analyzed for extracting wave velocity and wave attenuation. For all the testing rates, wave velocity increased in the charge process and decreased in the discharge process. Velocity profiles corresponding to lower rates of C/10.4 and C/5.2 exhibited primary peaks at the maximum SoCs, whereas the absolute wave velocity of C/1.3 rate showed primary peaks that occurred slightly after the SoC peak, indicating a delayed maximum Young's modulus. The wave attenuation computed for the C/10.4 rate had local maxima in the charge and discharge processes and depicted negative correlations with SoC, ranging from 0% to 18%, and positive correlations with SoC from 18% to 85%. On the other hand, the wave attenuation curves of the C/1.3 rate showed no local peaks and had negative correlations with SoC, ranging from 0% to 28%, and positive correlations with SoC ranging from 28% to 53%.

Ultrasonic diagnosis of esophageal perforation and deep neck infection caused by denture swallowing: a case description.

Ultrasonic diagnosis of esophageal perforation and deep neck infection caused by denture swallowing: a case description.

Is the diagnostic model based on convolutional neural network superior to pediatric radiologists in the ultrasonic diagnosis of biliary atresia?

Many screening and diagnostic methods are currently available for biliary atresia (BA), but the early and accurate diagnosis of BA remains a challenge with existing methods. This study aimed to use deep learning algorithms to intelligently analyze the ultrasound image data, build a BA ultrasound intelligent diagnostic model based on the convolutional neural network, and realize an intelligent diagnosis of BA. A total of 4,887 gallbladder ultrasound images of infants with BA, non-BA hyperbilirubinemia, and healthy infants were collected. Two mask region convolutional neural network (Mask R-CNN) models based on different backbone feature extraction networks were constructed. The diagnostic performance between the two models was compared through good-quality images at the image level and the patient level. The diagnostic performance between the two models was compared through poor-quality images. The diagnostic performance of BA between the model and four pediatric radiologists was compared at the image level and the patient level. The classification performance of BA in model 2 was slightly higher than that in model 1 in the test set, both at the image level and at the patient level, with a significant difference of p = 0.0365 and p = 0.0459, respectively. The classification accuracy of model 2 was slightly higher than that of model 1 in poor-quality images (88.3% vs. 86.4%), and the difference was not statistically significant (p = 0.560). The diagnostic performance of model 2 was similar to that of the two radiology experts at the image level, and the differences were not statistically significant. The diagnostic performance of model 2 in the test set was higher than that of the two radiology experts at the patient level (all p < 0.05). The performance of model 2 based on Mask R-CNN in the diagnosis of BA reached or even exceeded the level of pediatric radiology experts.

A clinical case of maxillofacial dirofilariasis in a child

The article presents a clinical case of surgical treatment of dirofilariasis in the maxillofacial region in a child. Diagnosis is difficult due to the complex mechanism of transmission, long incubation period and polymorphism of symptoms. The method of ultrasonic diagnosis allows the most accurate and clear verification of the diagnosis (the presence of a dense capsule, in the lumen of which linear hyperechogenic moving structures are determined). Treatment of dirofilariasis is only surgical - excision of the capsule with the helminth within healthy tissues with subsequent pathomorphologic examination and clarifying of the etiology of the parasite.