Autism spectrum disorder(ASD) is a group of multi-factor brain development disorders. At present,ASD treatment is still based on behavioral intervention,for there are no specific drugs. ASD comorbidities are extremely common in children with ASD,and the presence of comorbidities has an important impact on the treatment and prognosis of ASD. In recent years,the etiology and behavioral intervention of ASD has become a research hotspot at home and abroad,but there are few studies on comorbidity and drug intervention. Therefore,we summarize relevant literatures at home and abroad, hoping to be helpful for clinical research on ASD comorbidity and drug treatment.

OBJECTIVETo design ABC damage variable and positioning system for acetabular fracture and explore the feasibility and clinical practical value of the system through the multi-center analysis of 1122 acetabular fractures.

METHODSAccording to acetabular three-column conception, and pelvic ring lesions damage direction caused by acetabular fracture domino effect and injury degree of proximal femur joint, it defined class A as any column acetabular fracture; class B as any two-column acetabular fracture; class C as front, dome and posterior mixture acetabular fracture. Lower case English letters a, m, p represented front, dome, posterior fracture, respectively. Acetabular damage variables: 1 was simple displaced fractures; 2 was comminuted fractures; 3 was compression fractures. Pelvic ring lesions damage variables: alpha was sacroiliac joints or sacroiliac fracture horizontal separation deflection; beta was sacroiliac joints or sacroiliac fracture vertical separation deflection; gamma was pubic symphysis separation/superior and inferior ramus of pubis fracture deflection; alpha beta gamma delta was compound floating damage. Proximal humerus joint damage variables: I was femoral head fracture; II was femoral neck fracture; II was intertrochanteric fractures of femur; IV was I to III compound fracture. The ABC damage variable positioning system for acetabular fracture was made up by the above-mentioned variables. The statistics from March 1997 to February 2010 showed 1122 cases acetabular fractures with 18 cases of double side acetabular fracture and 1140 cases of acetabular fractures. The pelvics anterior-posterior view, ilium and obturator oblique view, and 2/3D-CT materials were analyzed and researched.

RESULTSEach damage variables distribution situation in 1140 cases of acetabular fracture involved A in 237 cases (20.8%), B in 605 cases (53.1%), C in 298 cases (26.1%);front column fracture in 808 cases(70.9%), dome fracture in 507 cases (44.5%), posterior fracture in 1026 cases (90%). Acetabular variables: variabe 1 in 203 cases of simple displaced fracture (17.8%); variabe 2 in 516 cases of comminuted fracture(45.3%); variabe 3 in 421 cases of compression fracture (36.9%); 249 cases of pelvic ring lesions damage (21.8%), 75 cases femoral head fracture (6.6%); 18 cases of double side acetabular fracture and relative pelvic ring and proximal humerus joint variables (1.58%). Key part and curative effect elements of 1140 cases acetabular fracture: 507 cases of dome or posterior acetabular fracture (44.5%); 421 cases of compression fracture (36.9%); 249 cases of pelvic ring variables (21.8%); 75 cases of proximal humerus joint variables (6.6%); 486 cases of simple Aa/pl/2,Bapl/2 acetabular fracture (42.6% ).

CONCLUSIONCompression fracture, especially defected compression fracture, takes important part in acetabular damage variables, and also presents that acetabular fracture with pelvic ring and proximal femoral damage variables are not rare at all. The relationship of the acetabular fracture damage variables, and its percentage shows the key points and elements in clinical treatment: weight-bearing to dome accounts for 44.5%; compression to defects account for 36.9%, pelvic ring to float accounts for 21.8%; dome fracture to double side fracture account for 6.6%. The system has significant guiding effects on clinic in terms of evaluation of injury severity, anatomic localization, difficulty index, alternative strategy, operative approach, effect of treatment,and prognosis. And the most important thing is that the system creates the comparison of damage variables in same type of fracture and the communication of homo-language and explores a new method.

Acetabulum ; injuries ; Adolescent ; Adult ; Aged ; Child ; Female ; Fractures, Bone ; classification ; diagnostic imaging ; Humans ; Male ; Medical Informatics ; methods ; Middle Aged ; Tomography, X-Ray Computed ; Young Adult

BACKGROUND: The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions. In China, breast masses are divided into four categories according to the treatment method: inflammatory masses, adenosis, benign tumors, and malignant tumors. These categorizations are important for guiding clinical treatment. In this study, we aimed to develop a convolutional neural network (CNN) for classification of these four breast mass types using ultrasound (US) images. METHODS: Taking breast biopsy or pathological examinations as the reference standard, CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers. The patients were randomly divided into training and test groups (n = 1810 vs. n = 1813). Separate models were created for two-dimensional (2D) images only, 2D and color Doppler flow imaging (2D-CDFI), and 2D-CDFI and pulsed wave Doppler (2D-CDFI-PW) images. The performance of these three models was compared using sensitivity, specificity, area under receiver operating characteristic curve (AUC), positive (PPV) and negative predictive values (NPV), positive (LR+) and negative likelihood ratios (LR-), and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators, between images from different hospitals with AUC, and with the performance of 37 radiologists. RESULTS: The accuracies of the 2D, 2D-CDFI, and 2D-CDFI-PW models on the test set were 87.9%, 89.2%, and 88.7%, respectively. The AUCs for classification of benign tumors, malignant tumors, inflammatory masses, and adenosis were 0.90, 0.91, 0.90, and 0.89, respectively (95% confidence intervals [CIs], 0.87-0.91, 0.89-0.92, 0.87-0.91, and 0.86-0.90). The 2D-CDFI model showed better accuracy (89.2%) on the test set than the 2D (87.9%) and 2D-CDFI-PW (88.7%) models. The 2D model showed accuracy of 81.7% on breast masses ≤1 cm and 82.3% on breast masses >1 cm; there was a significant difference between the two groups (P < 0.001). The accuracy of the CNN classifications for the test set (89.2%) was significantly higher than that of all the radiologists (30%). CONCLUSIONS: The CNN may have high accuracy for classification of US images of breast masses and perform significantly better than human radiologists. TRIAL REGISTRATION Chictr.org, ChiCTR1900021375; http://www.chictr.org.cn/showproj.aspx?proj=33139.
Area Under Curve ; Breast/diagnostic imaging* ; Breast Neoplasms/diagnostic imaging* ; China ; Deep Learning ; Humans ; ROC Curve ; Sensitivity and Specificity