Testicular histology based on testicular biopsy is an important factor for determining appropriate testicular sperm extraction surgery and predicting sperm retrieval outcomes in patients with azoospermia. Therefore, we developed a deep learning (DL) model to establish the associations between testicular grayscale ultrasound images and testicular histology. We retrospectively included two-dimensional testicular grayscale ultrasound from patients with azoospermia (353 men with 4357 images between July 2017 and December 2021 in The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China) to develop a DL model. We obtained testicular histology during conventional testicular sperm extraction. Our DL model was trained based on ultrasound images or fusion data (ultrasound images fused with the corresponding testicular volume) to distinguish spermatozoa presence in pathology (SPP) and spermatozoa absence in pathology (SAP) and to classify maturation arrest (MA) and Sertoli cell-only syndrome (SCOS) in patients with SAP. Areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were used to analyze model performance. DL based on images achieved an AUC of 0.922 (95% confidence interval [CI]: 0.908-0.935), a sensitivity of 80.9%, a specificity of 84.6%, and an accuracy of 83.5% in predicting SPP (including normal spermatogenesis and hypospermatogenesis) and SAP (including MA and SCOS). In the identification of SCOS and MA, DL on fusion data yielded better diagnostic performance with an AUC of 0.979 (95% CI: 0.969-0.989), a sensitivity of 89.7%, a specificity of 97.1%, and an accuracy of 92.1%. Our study provides a noninvasive method to predict testicular histology for patients with azoospermia, which would avoid unnecessary testicular biopsy.
Humans ; Male ; Azoospermia/diagnostic imaging* ; Deep Learning ; Testis/pathology* ; Retrospective Studies ; Adult ; Ultrasonography/methods* ; Sperm Retrieval ; Sertoli Cell-Only Syndrome/diagnostic imaging*

OBJECTIVES: According to the World Health Organization (WHO), infertility rates have been steadily rising worldwide. Identifying risk factors for contrast agent reflux into the myometrium during hysterosalpingo-contrast sonography (HyCoSy) is of clinical significance in reducing this complication and improving infertility treatment. However, there is currently no standardized pre-evaluation method for predicting intra-myometrial contrast reflux, with clinical assessment often relying on physician experience and patient symptoms. This study aims to identify imaging risk factors for contrast agent reflux into the myometrium using four-dimensional (4D) HyCoSy and to construct a nomogram-based predictive model to assist in clinical decision-making. METHODS: A retrospective analysis was conducted on 1 274 infertile women who underwent 4D HyCoSy at the Women and Children's Hospital of Hunan and the the Third Xiangya Hospital of Central South University from January 1, 2020, to December 15, 2022. Patients were divided into a reflux group (n=234) and a non-reflux group (n=1 040) based on the presence of intra-myometrial contrast reflux. Univariate and multivariable Logistic regression analyses were used to identify significant predictors, which were then used to construct a nomogram model. Internal validation was performed using 500 bootstrap resamples. RESULTS: The age of the reflux group was significantly higher than that of the non-reflux group [(31.82±5.27) years vs (30.66±4.83) years, P=0.001 1]. Primary infertility was more common in the non-reflux group (50.96%), while secondary infertility dominated in the reflux group (76.50%), with 72.65% having a history of gynecological surgery (P<0.001). Abnormal menstrual volume and discomfort during the procedure were more common in the reflux group, while the non-reflux group tolerated higher contrast agent doses (P<0.001). Imaging differences included endometrial thickness, tubal wall smoothness, and peritoneal contrast dispersion, with the non-reflux group showing thicker endometrium and smoother, more patent tubes. The nomogram model yielded an area under the curve (AUC) of 0.854, indicating good predictive performance. The AUC of the decision curve analysis (DCA) for internal validation of the model was 0.737. When the threshold probability for contrast agent reflux into the myometrium ranged from 0.05 to 0.95, the maximum net benefit reached 0.18. The net benefit of applying the nomogram predictive model exceeded that of either full intervention or no intervention, indicating that the model demonstrates good clinical predictive performance. CONCLUSIONS The nomogram model, based on infertility type, endometrial thickness, contrast agent dose, and discomfort symptoms, effectively predicts intra-myometrial contrast agent reflux after 4D HyCoSy. It provides a valuable tool for clinicians to implement early preventive measures and reduce the risk of contrast leakage and associated complications.
Humans ; Female ; Nomograms ; Contrast Media/adverse effects* ; Retrospective Studies ; Adult ; Ultrasonography/methods* ; Hysterosalpingography/methods* ; Infertility, Female/diagnostic imaging* ; Myometrium/diagnostic imaging* ; Risk Factors

OBJECTIVES: The diagnostic value of ultrasonographic quantitative indicators of umbilical cord coiling, such as the umbilical coiling index (UCI) and pitch value, in identifying hypercoiling and predicting adverse pregnancy outcomes remains controversial. This study aims to evaluate the predictive value of UCI, pitch value, and the cerebroplacental ratio in pregnancies complicated by umbilical cord hypercoiling. METHODS: Pregnant women with densely coiled umbilical cords identified by routine obstetric ultrasound at Changsha Maternal and Child Health Hospital between November 2022 and November 2024 were enrolled. Complete clinical data, including UCI, pitch value, and cerebroplacental ratio (CPR), were collected. Pregnancy outcome scores were calculated, and newborns were categorized into the normal outcome group (n=177) and adverse outcome group (n=85), with the latter further subdivided into mild (n=51), moderate (n=19), and severe (n=15) subgroups. Differences in baseline data, UCI, pitch value, and incidence of CRP<1 were compared between groups and among subgroups. Correlations between UCI, pitch value, and adverse pregnancy outcomes were analyzed. Receiver operating characteristic (ROC) curve were used to assess the predictive performance of UCI, pitch value, CPR<1, and their combinations. RESULTS: Compared with the normal outcome group, the adverse outcome group had higher age, parity, parity, incidence of CPR<1, and UCI, while gestational age at delivery and pitch values were lower (all P<0.05). The incidence of obesity, gestational diabetes mellitus, and hypertensive disorders of pregnancy did not differ significantly between the 2 groups (all P>0.05). The normal outcome group showed lower UCI and higher pitch values than all 3 adverse outcome subgroups (all P<0.05), while differences among the 3 adverse subgroups were not significant (all P>0.05). UCI was positively correlated with adverse pregnancy outcomes (r_s=0.350, P<0.05), whereas pitch value was negatively correlated (r_s=-0.286, P<0.05). ROC curve analysis showed that the area under the curve (AUC) values for predicting adverse outcomes were 0.837 for UCI, 0.886 for pitch value, and 0.610 for CPR<1, with sensitivities of 77.6%, 82.4%, and 27.1% and specificities of 78.5%, 83.6%, and 94.9%, respectively. The combined UCI+CPR<1 and pitch value+CPR<1 models yielded AUCs of 0.841 and 0.886, with sensitivities of 78.8% and 81.2% and specificities of 78.5% and 84.2%, respectively. No significant differences were found between the AUCs of UCI and pitch value (P>0.05), but both outperformed CPR<1 alone (both P<0.001). The combined models showed no significant improvement over UCI or pitch value alone (both P>0.05), though both were superior to CPR<1 alone (both P<0.001). CONCLUSIONS Most umbilical cord hypercoiling cases had favorable outcomes, with UCI, pitch value, CPR<1 and their combinations demonstrating significant predictive value for adverse pregnancy outcomes.
Humans ; Female ; Pregnancy ; Pregnancy Outcome ; Adult ; Ultrasonography, Prenatal/methods* ; Umbilical Cord/diagnostic imaging* ; Hemodynamics ; Predictive Value of Tests ; Infant, Newborn ; ROC Curve

Prostate cancer is the second most common cancer in men, accounting for 14.1% of new cancer cases in 2020. The aggressiveness of prostate cancer is highly variable, depending on its grade and stage at the time of diagnosis. Despite recent advances in prostate cancer treatment, some patients still experience recurrence or even progression after undergoing radical treatment. Accurate initial staging and monitoring for recurrence determine patient management, which in turn affect patient prognosis and survival. Classical imaging has limitations in the diagnosis and treatment of prostate cancer, but the use of novel molecular probes has improved the detection rate, specificity, and accuracy of prostate cancer detection. Molecular probe-based imaging modalities allow the visualization and quantitative measurement of biological processes at the molecular and cellular levels in living systems. An increased understanding of tumor biology of prostate cancer and the discovery of new tumor biomarkers have allowed the exploration of additional molecular probe targets. The development of novel ligands and advances in nano-based delivery technologies have accelerated the research and development of molecular probes. Here, we summarize the use of molecular probes in positron emission tomography (PET), single-photon emission computed tomography (SPECT), magnetic resonance imaging (MRI), optical imaging, and ultrasound imaging, and provide a brief overview of important target molecules in prostate cancer.
Humans ; Male ; Prostatic Neoplasms/diagnosis* ; Molecular Probes ; Molecular Imaging/methods* ; Magnetic Resonance Imaging ; Positron-Emission Tomography ; Tomography, Emission-Computed, Single-Photon ; Ultrasonography ; Optical Imaging ; Biomarkers, Tumor ; Precision Medicine/methods*

OBJECTIVES: To construct an intelligent analysis model for classifying fetal orientation during intrapartum ultrasound videos based on multi-feature fusion. METHODS: The proposed model consists of the Input, Backbone Network and Classification Head modules. The Input module carries out data augmentation to improve the sample quality and generalization ability of the model. The Backbone Network was responsible for feature extraction based on Yolov8 combined with CBAM, ECA, PSA attention mechanism and AIFI feature interaction module. The Classification Head consists of a convolutional layer and a softmax function to output the final probability value of each class. The images of the key structures (the eyes, face, head, thalamus, and spine) were annotated with frames by physicians for model training to improve the classification accuracy of the anterior occipital, posterior occipital, and transverse occipital orientations. RESULTS: The experimental results showed that the proposed model had excellent performance in the tire orientation classification task with the classification accuracy reaching 0.984, an area under the PR curve (average accuracy) of 0.993, and area under the ROC curve of 0.984, and a kappa consistency test score of 0.974. The prediction results by the deep learning model were highly consistent with the actual classification results. CONCLUSIONS The multi-feature fusion model proposed in this study can efficiently and accurately classify fetal orientation in intrapartum ultrasound videos.
Humans ; Female ; Ultrasonography, Prenatal/methods* ; Pregnancy ; Fetus/diagnostic imaging* ; Neural Networks, Computer ; Video Recording

OBJECTIVE: To explore the genetic etiology of fetal skeletal dysplasia using whole exome sequencing (WES) and copy number variation sequencing (CNV-seq) techniques, and the feasibility of using WES as the first-tier method for such fetuses. METHODS: Seventy four fetuses with skeletal dysplasia detected by prenatal ultrasound at the Genetic Testing Center of the Women and Children's Hospital Affiliated to Qingdao University from January 2020 to August 2024 were selected as the study subjects. Fetal muscle and peripheral blood samples of the pregnant women and their spouses were collected and subjected to WES analysis. CNV-seq was carried out on all fetal muscle tissue samples. And the results were compared with the CNVs indicated by WES. Genetic etiologies were analyzed across different subtypes of skeletal dysplasia. And the feasibility of using WES as the first-tier genetic test for similar fetuses was assessed, in addition with a systematic cost-effectiveness analysis. This study was approved by the Medical Ethics Committee of the Hospital (Ethics No.: QFELL-YJ-2024-201). RESULTS: A total of 50 fetuses were diagnosed, which yielded a diagnostic rate of 67.57%. These included 6 chromosomal aneuploidies, 4 chromosomal CNVs and 40 monogenic disorders. The monogenic diseases had involved 46 variant sites in 23 pathogenic genes, among which 12 were unreported previously, including MYH3: c.735T>C, ALPL: c.1324C>T, NEK9: c.1973G>A, MAGEL2: c.2024_2025del, LMBR1: c.423+4914A>C, NEB: c.21273_21276del, COL1A1: c.2651G>C and c.2758G>C, ASPM: c.2473delinsGA, TBX5: c.704G>A, DYNC2H1: c.10893del, and DYNC2I2: c.1270C>T. Substantial concordance was reached between WES-derived CNV calls and CNV-seq findings. No clinically significant CNV was exclusively detected by CNV-seq. Cost-effectiveness modeling demonstrated that implementing WES as the first-tier genetic testing method could reduce the total expenditure when WES unit cost remained below 6.4 folds that of the CNV-seq. CONCLUSION Genetic variants including single nucleotide variations (SNV) of monogenic disorders, chromosomal aneuploidies and genomic CNVs are important causes for fetal skeletal dysplasia. WES is an accurate and efficient method for analyzing the etiology of fetal skeletal dysplasia, particularly in those with a family history of similar phenotype or maternal history of adverse pregnancies.
Humans ; Exome Sequencing/methods* ; Female ; Pregnancy ; DNA Copy Number Variations/genetics* ; Genetic Testing/methods* ; Prenatal Diagnosis/methods* ; Adult ; Male ; Fetus ; Bone Diseases, Developmental/diagnosis* ; Ultrasonography, Prenatal

OBJECTIVE: To explore the detection rate of copy number variations (CNVs) in fetuses with isolated Congenital anomalies of the kidney and urinary tract (CAKUT) and pregnancy outcomes in order to provide a basis for genetic counseling. METHODS: One hundred and eighty eight fetuses who underwent chromosomal microarray analysis (CMA) due to isolated CAKUT detected by prenatal ultrasonography at Qingdao Women and Children's Hospital from January 2021 to December 2024 were selected as the study subjects. According to the ultrasound findings, the fetuses were divided into 8 groups, including renal parenchymal dysplasia group, renal cystic dysplasia group, simple renal parenchymal echo enhancement group, abnormal development of renal collecting system group, duplicated kidney group, ectopic kidney group, horseshoe kidney group, and bladder/posterior urethral abnormalities group. The detection of CNVs was retrospectively analyzed, and the pregnant women were followed up to summarize their pregnancy outcomes. 2 test (or Fisher's exact probability method) was used to compare the CNV detection rates between the groups. This study was approved by the Medical Ethics Committee of the Qingdao Women and Children's Hospital (Ethics No.: QFELL-YJ-2025-85). RESULTS: Among the 188 fetuses with isolated CAKUT, 23 CNVs (12.23%) were detected, of which 13 cases (6.91%) were pathogenic and 10 cases were rated as variants of unknown significance (VOUS). Among the 8 groups, the three groups with the highest proportion were renal cystic dysplasia group, renal metaplasia group, and renal parenchymal dysplasia group. The detection rates of pathogenic CNVs in the three groups were 1.79% (1/56), 6.78% (4/59), and 16.67% (5/30), respectively, with statistically significant differences (P < 0.05). Parental verification was conducted on 12 fetuses detected with the CNVs, confirming that 2 cases were de novo and 10 were inherited from parents with a normal phenotype. After genetic counseling, the parents of 9 fetuses opted to terminate the pregnancy, while 11 chose to continue with the pregnancy, and 3 were lost to follow-up. At the time of last follow-up, the youngest offspring was 5 months old and the oldest was 3 years and 11 months old. One child had renal aplasia, and two were born with hydronephrosis, which have been cured through surgery. The remainders had no obvious abnormality with their growth and development. CONCLUSION CMA testing has important value for prenatal diagnosis of isolated CAKUT. In this study, the detection rate of pathogenic CNVs has increased sequentially in fetuses with renal cystic developmental abnormalities, renal collecting system developmental abnormalities, and renal parenchymal dysplasia, while there was no significant difference in the detection rate of CNVs. For fetuses with isolated CAKUT detected by prenatal ultrasound, CMA testing should be considered, and reasonable pregnancy decisions should be made based on the results of prenatal ultrasound and parental verification.
Humans ; Female ; Pregnancy ; Prenatal Diagnosis/methods* ; DNA Copy Number Variations/genetics* ; Kidney/abnormalities* ; Adult ; Ultrasonography, Prenatal ; Urogenital Abnormalities/diagnosis* ; Microarray Analysis/methods* ; Retrospective Studies ; Urinary Tract/abnormalities* ; Fetus ; Pregnancy Outcome ; Vesico-Ureteral Reflux

Endoscopic ultrasonography (EUS) has progressed beyond diagnostic imaging to include EUS-guided tissue acquisition and EUS-directed therapies. This review provides an update on EUS-guided drainage and anastomotic procedures, and other therapeutic procedures. Today, EUS-guided drainage of symptomatic walled-off pancreatic fluid collections is the norm, with endoscopic necrosectomy as an adjunct. For high-risk surgical patients unsuitable for cholecystectomy, EUS-guided gallbladder drainage of acute cholecystitis is an option. Additionally, EUS-guided drainage of obstructed biliary and pancreatic ductal system can be performed as salvage procedures after unsuccessful endoscopic retrograde cholangiopancreatography (ERCP). Bariatric procedures such as Roux-en-Y gastric bypass alter the gastric anatomy, hindering access to the major papilla. This can be overcome by creating a conduit through the excluded stomach using EUS-directed transgastric ERCP. Gastric outlet obstruction and afferent loop syndrome can be treated using EUS-guided gastrojejunostomy. These therapeutic interventions are a major advancement in the field of interventional EUS, achieving significant clinical impact.
Humans ; Endosonography/methods* ; Drainage/methods* ; Cholangiopancreatography, Endoscopic Retrograde/methods* ; Ultrasonography, Interventional/methods* ; Anastomosis, Surgical/methods*

OBJECTIVE: To observe the effects of ultrasound-guided foraminal electroacupuncture on neuronal apoptosis and motor function in rats with spinal cord injury (SCI), and to explore the potential underlying mechanisms. METHODS: Thirty-six SPF-grade Sprague-Dawley rats were randomly assigned to a sham operation group, a model group, and an ultrasound-guilded electroacupuncture group (electroacupuncture group), with 12 rats in each group. In the sham operation group, the spinal cord was exposed and then the incision was sutured without contusion. In the other two groups, SCI models were established using a modified Allen's impact method. On days 1, 3, 7, and 14 after modeling, the electroacupuncture group received electroacupuncture intervention at the T₉/T₁₀ and T₁₀/T₁₁ intervertebral foramen under ultrasound guidance, avoiding spinal cord injury. Stimulation parameters were dense-disperse wave at 2 Hz/100 Hz and 1-2 mA for each session. Following interventions on days 1, 3, 7, and 14, the Basso-Beattie-Bresnahan (BBB) score was assessed; the inclined plane test was used to assess hindlimb grip strength in rats. After the intervention, HE staining was used to observe spinal cord morphology; TUNEL staining was used to detect neuronal apoptosis; ELISA was used to measure the serum levels of interleukin (IL)-6, IL-1β, and tumor necrosis factor-alpha (TNF-α); Western blot was used to analyze the protein expression of Wnt-4, β-catenin, c-Myc, Bax, Bcl-2, and NeuN in spinal tissue; quantitative real-time PCR was used to detect the mRNA expression of Wnt-4, β-catenin, c-Myc, Bax, Bcl-2, and NeuN. RESULTS: Compared with the sham operation group, the model group showed significantly reduced BBB scores (P<0.05), and reduced inclined plane angles (P<0.05) at all time points. Compared with the model group, the electroacupuncture group exhibited increased BBB scores on days 3, 7, and 14 (P<0.05), and higher inclined plane angles on days 1, 3, 7, and 14 (P<0.05). Compared with the sham operation group, the model group showed disorganized spinal cord structure with increased inflammatory cells and necrotic neurons, higher number of apoptotic neurons in spinal tissue (P<0.05), elevated serum IL-6, IL-1β, and TNF-α levels (P<0.05), increased protein and mRNA expression of Wnt-4, β-catenin, c-Myc, and Bax (P<0.05), and decreased protein and mRNA expression of Bcl-2 and NeuN in spinal tissue (P<0.05). Compared with the model group, the electroacupuncture group had fewer inflammatory cells and apoptotic neurons in spinal tissue (P<0.05), reduced serum IL-6, IL-1β, and TNF-α levels (P<0.05), increased protein and mRNA expression of Wnt-4, β-catenin, Bcl-2, and NeuN (P<0.05), and decreased protein and mRNA expression of c-Myc and Bax in spinal tissue (P<0.05). CONCLUSION Ultrasound-guided foraminal electroacupuncture could improve motor function in rats with SCI, potentially by regulating the expression of molecules related to the Wnt-4/β-catenin signaling pathway to inhibit neuronal apoptosis and inflammatory responses.
Animals ; Electroacupuncture/methods* ; Spinal Cord Injuries/physiopathology* ; Rats, Sprague-Dawley ; Rats ; Wnt Signaling Pathway ; Male ; Humans ; Female ; beta Catenin/metabolism* ; Apoptosis ; Ultrasonography ; Tumor Necrosis Factor-alpha/genetics* ; Spinal Cord/metabolism*

The accurate segmentation of breast ultrasound images is an important precondition for the lesion determination. The existing segmentation approaches embrace massive parameters, sluggish inference speed, and huge memory consumption. To tackle this problem, we propose T ²KD Attention U-Net (dual-Teacher Knowledge Distillation Attention U-Net), a lightweight semantic segmentation method combined double-path joint distillation in breast ultrasound images. Primarily, we designed two teacher models to learn the fine-grained features from each class of images according to different feature representation and semantic information of benign and malignant breast lesions. Then we leveraged the joint distillation to train a lightweight student model. Finally, we constructed a novel weight balance loss to focus on the semantic feature of small objection, solving the unbalance problem of tumor and background. Specifically, the extensive experiments conducted on Dataset BUSI and Dataset B demonstrated that the T ²KD Attention U-Net outperformed various knowledge distillation counterparts. Concretely, the accuracy, recall, precision, Dice, and mIoU of proposed method were 95.26%, 86.23%, 85.09%, 83.59%and 77.78% on Dataset BUSI, respectively. And these performance indexes were 97.95%, 92.80%, 88.33%, 88.40% and 82.42% on Dataset B, respectively. Compared with other models, the performance of this model was significantly improved. Meanwhile, compared with the teacher model, the number, size, and complexity of student model were significantly reduced (2.2×10 ⁶ vs. 106.1×10 ⁶, 8.4 MB vs. 414 MB, 16.59 GFLOPs vs. 205.98 GFLOPs, respectively). Indeedy, the proposed model guarantees the performances while greatly decreasing the amount of computation, which provides a new method for the deployment of clinical medical scenarios.
Humans ; Breast Neoplasms/diagnostic imaging* ; Female ; Ultrasonography, Mammary/methods* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Neural Networks, Computer ; Breast/diagnostic imaging*