Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics.

Bone age assessment (BAA) is a crucial task in clinical, forensic, and athletic fields. Since traditional age estimation methods are suffered from potential radiation damage, this study aimed to develop and evaluate a deep learning radiomics method based on multiparametric knee MRI for noninvasive and automatic BAA. This retrospective study enrolled 598 patients (age range,10.00-29.99 years) who underwent MR examinations of the knee joint (T1/T2*/PD-weighted imaging). Three-dimensional convolutional neural networks (3D CNNs) were trained to extract and fuse multimodal and multiscale MRI radiomic features for age estimation and compared to traditional machine learning models based on hand-crafted features. The age estimation error was greater in individuals aged 25-30 years; thus, this method may not be suitable for individuals over 25 years old. In the test set aged 10-25 years (n = 95), the 3D CNN (a fusion of T1WI, T2*WI, and PDWI) demonstrated the lowest mean absolute error of 1.32 ± 1.01 years, which is higher than that of other MRI modalities and the hand-crafted models. In the classification for 12-, 14-, 16-, and 18- year thresholds, accuracies and the areas under the ROC curves were all over 0.91 and 0.96, which is similar to the manual methods. Visualization of important features showed that 3D CNN estimated age by focusing on the epiphyseal plates. The deep learning radiomics method enables non-invasive and automated BAA from multimodal knee MR images. The use of 3D CNN and MRI-based radiomics has the potential to assist radiologists or medicolegists in age estimation.

A Homozygous Mutation in 5' Untranslated Region of TNFRSF11A Leading to Molecular Diagnosis of Osteopetrosis Coinheritance With Wiskott-Aldrich Syndrome.

Wiskott-Aldrich syndrome (WAS) and osteopetrosis are 2 different, rare hereditary diseases. Here we report clinical and molecular genetics investigations on an infant patient with persistent thrombocytopenia and prolonged fever. He was clinical diagnosed as osteopetrosis according to clinical presentation, radiologic skeletal features, and bone biopsy results. Gene sequencing demonstrated a de novo homozygous mutation in 5'-untranslated region of TNFRSF11A, c.-45A>G, which is relating to osteopetrosis. Meanwhile, a hemizygous transition mutation in WAS gene, c.400G>A diagnosed the infant with WAS. This is the first clinical report for the diagnosis of osteopetrosis coinheritance with WAS in a single patient.

Diffusion tensor imaging analysis of the corpus callosum in children with high-risk autism spectrum disorder.

BACKGROUND: Autism spectrum disorder (ASD) is a severe neurodevelopmental disorder that begins in early infancy and childhood and is characterized by impaired social communication and repetitive stereotyped behaviors. OBJECTIVE: The purpose of this study was to examine the development of the corpus callosum and its relationship to neurobehavior in young children with high-risk (HR) ASD using magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI). METHODS: Twenty-one children with HR-ASD who visited Anhui Children's Hospital between January 2020 and December 2021 were selected as the study group, while 19 matched children with normal development during the same time were adopted as the control group. Cranial MRI+DTI were performed for all of the enrolled children and fractional anisotropy (FA) measurements were taken in each region of the corpus callosum. RESULTS: The FA values in all regions of the corpus callosum were higher in the study group than in the control group (0.417 ± 0.016 vs. 0.412 ± 0.02 in the corpus callosum knee, 0.439 ± 0.018 vs. 0.431 ± 0.023 in the corpus callosum body, and 0.446 ± 0.017 vs. 0.434 ± 0.019 in the splenium of corpus callosum [SCC]), where the difference in the FA in the SCC was statistically significant between the two groups (P< 0.05). There was a positive correlation between the FA in the corpus callosum knee and speech scores in the neuropsychological development of the study group (P< 0.05). CONCLUSION: There was a premature development tendency for corpus callosum myelination in young children with HR-ASD, and the developmental tendency was visible in the SCC. There was also a positive relationship between corpus callosum knee development and language function.

Efficacy of transcatheter arterial chemoembolization combined with sirolimus for treating Kasabach-Merritt phenomenon in infants, a retrospective study.

OBJECTIVE: This retrospective study aimed to observe the efficacy of transcatheter arterial chemoembolization (TACE) combined with sirolimus in the treatment of haemangioma combined with the Kasabach-Merritt phenomenon (KMP). METHODS: A total of 11 infants with KMP who were treated at our hospital from January 2016 to September 2021 were selected and treated with arteriosclerosis embolotherapy using a microsphere emulsion formed by bleomycin + ultra-fluid lipiodol + dexamethasone + contrast agent or bleomycin mixed microspheres as the embolising agent. The patients were administered sirolimus orally after TACE. The clinical efficacy and examination indicators before and after treatment were observed and compared. RESULTS: The 11 infants underwent TACE treatment by arteriosclerosis embolotherapy a total of 21 times; of these cases, 10 were cured, and 1 showed a moderate response. There were no cases of non-response or death. The platelet count rose from 10.0 (7.0, 18.0) x 109/L before TACE to 236.0 (188.0, 275.0) x 109/L six months after the first TACE, and the tumour size decreased from 49.0 (43.0, 111.7) cm3 before TACE to 7.0 (3.5, 17.0) cm3 six months after the first TACE. The differences were statistically significant (the Z values were -2.943 and -2.934, respectively, p < 0.05). CONCLUSION: The combination of TACE and sirolimus has significant efficacy on critical children with KMP.

Long non-coding RNA (lncRNA) five prime to Xist (FTX) promotes retinoblastoma progression by regulating the microRNA-320a/with-no-lysine kinases 1 (WNK1) axis.

Long non-coding RNA (lncRNA) five prime to Xist (FTX) exerts important functions in human cancer, while its role in retinoblastoma (RB) remains unclear. This study aimed to investigate the role of FTX in RB. The expression levels of FTX were assessed by quantitative real-time polymerase chain reaction (qRT-PCR). Cell proliferation was evaluated by cell counting kit-8 (CCK-8), 5-ethynyl-2'-deoxyuridine (EdU) staining and colony formation assays. Cell migration and invasion were detected by Transwell assay. The relationship among FTX, microRNA-320a (miR-320a) and with-no-lysine kinase 1 (WNK1) was also investigated. In the present study, we found that the expression levels of FTX were notably elevated in RB tissues and cancer cell lines. Overexpression of FTX exacerbated the aggressive phenotypes (cell proliferation, migration and invasion) of RB cells. Downregulation of miR-320a obviously attenuated the inhibitory effects of knockdown of FTX in RB malignant phenotypes, and knockdown of WNK1 also reversed the impacts of miR-320a inhibitor on malignant phenotypes. In vivo experiments further confirmed that knockdown of FTX efficiently prevents tumor growth in vivo. Our results revealed that FTX promoted RB progression by targeting the miR-320a/WNK1 axis (graphical abstract), suggesting that FTX might be a novel therapeutic target for RB.

Computed Tomography Image Characteristics before and after Interventional Treatment of Children's Lymphangioma under Artificial Intelligence Algorithm.

The artificial intelligence algorithm was used to analyze the characteristics of computed tomography (CT) images before and after interventional treatment of children's lymphangioma. Retrospective analysis was performed, and 30 children with lymphangioma from the hospital were recruited as the study subjects. The ultrasound-guided bleomycin interventional therapy was adopted and applied to CT scanning through convolutional neural network (CNN). The CT imaging-related indicators before and after interventional therapy were detected, and feature analysis was performed. In addition, the CNN algorithm was adopted to segment the image of the tumor was clearer and more accurate. At the same time, the Dice similarity coefficient (DSC) of the CNN algorithm was 0.9, which had a higher degree of agreement. In terms of clinical symptoms, the cured children's lesions disappeared, the skin surface returned to normal color, and the treatment was smooth. In the two cases with effective treatment, the cystic mass at the lesion site was significantly smaller, and the nodules disappeared. CT images before interventional therapy showed that lymphangiomas in children were more common in the neck. The cystic masses at all lesion sites varied in diameter and size, and most of them were similar to round and irregular, with uniform density distribution. The boundary was clear, the cyst was solid, and there were different degrees of compression and spread to the surrounding structure. Most of them were polycystic, and a few of them were single cystic. After interventional treatment, CT images showed that 27 cases of cured children's lymphangioma completely disappeared. Lymphangioma was significantly reduced in two children with effective treatment. Edema around the tumor also decreased significantly. Patients who did not respond to the treatment received interventional treatment again, and the tumors disappeared completely on CT imaging. No recurrence or new occurrence was found in three-month follow-up. The total effective rate of interventional therapy for lymphangioma in children was 96.67%. The CNN algorithm can effectively compare the CT image features before and after interventional treatment for children's lymphangioma. It was suggested that the artificial intelligence algorithm-aided CT imaging examination was helpful to guide physicians in the accurate treatment of children's lymphangioma.

The magnetic resonance enterography imaging features of symptomatic Meckel's diverticulum in pediatric patients: a retrospective observational study of 31 cases.

BACKGROUND: The aim of this study was to explore the magnetic resonance enterography (MRE) imaging manifestations of a symptomatic Meckel's diverticulum (MD) in pediatric patients in order to provide a reference for the diagnosis of the condition. METHODS: The medical records of 31 pediatric patients with MD from May 2014 to October 2020 were retrospectively analyzed. The inclusion criteria were patients with MD accompanied by unexplained gastrointestinal bleeding, anemia (except hematological diseases), chronic persistent abdominal pain, repeated intussusception, or intussusception in older pediatric patients during surgery. The clinical variables (age, sex, and hemoglobin) and imaging, surgical, and pathological findings were recorded. RESULTS: MD was definitively identified in 28 patients, with the following characteristics: a blind-ending fluid-filled and/or gas-filled structure (n=23), an elongated shape (n=1), a dumbbell shape (n=1), and a solid mass (n=3). The diverticula were located in the right lower quadrant (n=16), the right abdomen at the level of the umbilicus (n=3), the right upper quadrant (n=2), the left upper quadrant (n=2), and the midline lower abdomen (n=5). Supply arteries were visualized in nine cases. In all cases, mural enhancement was comparable to that of the adjacent small-bowel (SB). Extravasation of the intravascular contrast medium was seen in two cases. Peripheral structural abnormalities included mesenteric fat stranding (n=7), hemorrhage in the adjacent lumen (n=3), free intraperitoneal gas (n=1), abnormal fluid retention (n=2), intestinal obstruction (n=1), and lymph node enlargement (n=7). A normal appendix was identified in 18 cases. CONCLUSIONS: MRE is an appropriate method of diagnosing symptomatic MD in pediatric patients and is particularly useful in the assessment of complications.

The value of cardiovascular magnetic resonance in the diagnosis of fetal aortic arch anomalies.

BACKGROUND: Here we report our preliminary experience of using fetal cardiovascular magnetic resonance (CMR) imaging, particularly with transverse views at the level of the aortic arch, in the diagnosis of aortic arch anomalies. MATERIALS AND METHODS: Between January 2013 and December 2015, routine prenatal obstetric ultrasound (US), echocardiography (Echo), and 1.5 T CMR were performed on approximately 600 pregnant women. CMR included balanced fast field echo and single-shot fast spin echo sequences. The images were analyzed using an anatomic segmental approach by two radiologists. The prenatal imaging findings were compared with postnatal diagnoses, from imaging or autopsy. RESULTS: A total of 22 cases with suspected aortic arch anomalies were found by prenatal Echo. These included the following: right aortic arch, 18 cases; double aortic arch, 2 cases; atrial isomerism, 3 cases including 2 with right aortic arch; and pulmonary atresia, aortic overriding and ventricular septal defect, 1 case. Fetal CMR diagnoses were: right aortic arch with aberrant left subclavian artery, 9 cases; right aortic arch with mirror-image branching, 8 cases; double aortic arch, 4 cases; left aortic arch with right aberrant subclavian artery, 1 case. 16 cases were born alive and subsequently underwent evaluation by Echo or MRI and 6 cases had autopsies. There were 23 aortic arch anomalies. Prenatal Echo misdiagnosed 5 of these (5/23), and missed the diagnosis in 4 cases (4/23). Consequently, the accuracy of prenatal Echo was 60.8% (14/23). Both prenatal Echo and CMR misdiagnosed the same single case as a double aortic arch. The correct diagnosis was found to be right aortic arch with aberrant subclavian artery. Consequently, the accuracy of fetal CMR was 95.6% (22/23). CONCLUSION: Unlike prenatal Echo, fetal CMR is unaffected by fetal position. Fetal CMR with transverse views at the level of the aortic arch is a useful adjunct for the diagnosis of fetal aortic arch anomalies.