Objective To construct the machine learning models based on the radiomic features of non-contrast and enhanced CT and to evaluate the predictive value in the risk stratification of gastrointestinal stromal tumor(GIST).Methods A total of 182 patients with pathologically confirmed GIST were randomly divided into a training set and a validation set at a ratio of 7∶3.The volume of interest(VOI)was outlined in the non-contrast phase,arterial phase and venous phase,and its radiomic features were extracted.The most valuable radiomic features were selected using the least absolute shrinkage and selection operator(LASSO)algorithm.The logistic regression(LR)classifier was used to construct the prediction models based on single-phase or multi-phase images.The predictive efficacy of the different models was compared by using receiver operating characteristic(ROC)curves.Results Four,three,and four radiomic features were selected in the non-contrast phase,arterial phase and venous phase,and 4 models were constructed in total.Among the single-phase models,the venous phase had better predictive efficacy,with the area under the curve(AUC)of 0.932[95％confidence interval(CI)0.873-0.969]and 0.924(95％CI 0.819-0.979)in the training and validation sets.The predictive efficacy of the combined model was improved,with the AUC of 0.946(95％CI 0.891-0.978)and 0.938(95％CI 0.838-0.986).Conclusion The venous phase model can predict the risk stratification of GIST accurately,and the prediction efficacy can be improved by combining the non-contrast and arterial phases.

Objective To explore artificial reconstruction vs artificial intelligence reconstruction in coronary artery volume rendering(VR).Methods A total of 110 coronary heart disease(CHD)patients were enrolled in the study,and underwent computed tomography arteriography.Artificial reconstruction(artificial group)and artificial intelligence reconstruction(intelligent group)were conducted in coronary artery VR.The image quality of VR and curved planar reconstruction(CPR),the diagnosis coincidence rate of arterial stenosis,and vascular reconstruction score were compared between two groups.Results The VR image quality of intelligent group was significantly higher than that of artificial group,with excellence rate of 90.91%vs 80.00%;and intelligent group scored higher than artificial group in CPR image quality(P<0.05).The differences in the diagnostic coincidence rates of arterial vessels(RCA,LAD,LCX)with no stenosis,slight stenosis,moderate stenosis,and vascular occlusion between two groups were trivial(P>0.05),while the two groups differed significantly in the diagnosis coincidence rates of mild stenosis and severe stenosis(P<0.05).The mean total score,the median value of the 3 main branches+posterior descending branch+intermediate branch+diagonal branch+blunt margin branch,and the median value of the other vascular branches were all significantly increased in intelligent group as compared with artificial group(P<0.05).Conclusion Artificial intelligence reconstruction has higher application value than artificial reconstruction in coronary artery VR.

Objective:To explore the value of machine learning models based on multiple structural MRI features for diagnosis of Parkinson disease (PD).Methods:The clinical and imaging data of 60 PD patients (PD group) diagnosed in the Neurology Department of the Second Affiliated Hospital of Soochow University from November 2017 to August 2019 and 56 normal elderly people (NC group) recruited from the community were retrospectively analyzed. All subjects underwent brain MR imaging. Multiple structural MRI features were extracted from cerebellum, deep nuclei and of brain cortex based on different partition templates. The Mann-Whitney U test, as well as least absolute shrinkage and selection operator regression were used to select the most discriminating features. Finally, logistic regression (LR) and linear discriminant analysis (LDA) classifier combined with the 5-fold cross-validation scheme were used to construct the models based on structural features of cerebellum, deep nuclei and cortex, and a combined model based on all features. The receiver operating characteristic curves were drawn, and the diagnostic performance and clinical net benefit of each model were evaluated by the area under curve (AUC) and the decision curve analysis (DCA). Results:In total, four cerebellum (asymmetry index of Lobule Ⅵ volume, asymmetry index of Lobule ⅦB cortical thickness, asymmetry index of total gray matter volume and absolute value of right Lobule Ⅵ gray matter volume), 3 deep nuclei (absolute value of right nucleus accumbens volume, absolute and relative value of total nucleus accumbens volume) and 3 cortex features (local gyration index of left PFm, local fractal dimension of right superior frontal gyrus and sulcal depth of left superior occipital gyrus) were selected as the most discriminating features, and the related models were constructed. In validation set, the AUC of cerebellum, deep nuclei, cortex and combined models for diagnosis of PD based on LR classifier were 0.692, 0.641, 0.747 and 0.816; the AUC of cerebellum, deep nuclei, cortex and combined models for diagnosis of PD based on LDA classifier were 0.726, 0.610, 0.752 and 0.818. The diagnostic efficiency of the combined models based on LR and LDA classifiers were significantly better than those of other models ( P<0.05). The DCA curve demonstrated that the combined models based on LR and LDA classifiers showed the highest clinical net benefit. Conclusion:The combined models with all structural features of cerebellum, deep nuclei and cortex included based on LR and LDA classifiers showed favorable performance and clinical net benefit for diagnosis of PD, which have the potential application value in clinical diagnosis.

Objective:To analysis the effect of two methods of transposition of pectoralis major in different degrees deep sternal wound infection(DSWI) after undergoing cardiac surgery.Methods:128 patients with DSWI after cardiac surgery were treated, 72 were mild, and 56 were severe. 66 cases of pectoralis major muscle flap docking method(medial muscle flap docking group) and 62 cases of lateral pectoralis major muscle flap turnover method(lateral muscle flap turnover group) were implemented respectively. Drainage tube indwelling time, reoperation rate, incidence of lung infection, long-term thoracic stability and other aspects were observed to compared the treatment effect.Results:In the mild patients, the medial muscle flap docking group and the lateral muscle flap turnover group were compared( P<0.05). The postoperative hospital stay [(14.2±4.7)days vs.(17.1±3.9)days], drainage tube retention time[(6.2±1.7)h vs.(9.1±2.9)h], and reoperation rate(2.4% vs. 6.7%), the incidence of lung infection(14.3% vs. 23.3%), long-term thoracic stability[73.8%(31/42)vs.43.3%(13/30)]. In the severe patients, the medial muscle flap docking group and the lateral muscle flap turnover group were compared. The postoperative hospital stay[(24.2±7.2)days vs.(20.1±3.5)days], drainage tube retention time[(20.2±6.6)h vs.(13.2±3.1)h], reoperation rate(20.8% vs.12.5%), incidence of pulmonary infection(41.7% vs. 31.3%), long-term thoracic stability[25.0%(6/24)vs.68.8%(22/32)]. The differences of the indicators in each group were significant , P<0.05. In the mild group, each index of the pectoralis major medial muscle flap docking method was superior to the lateral muscle flap turnover method, but the treatment results of the two methods in the severe group were opposite. Conclusion:Patients with mild deep DSWI treated with medial pectoralis major muscle flap docking and suture have less hospital stay, less reoperation rate, less complications and better treatment effect than reverse lateral pectoralis major muscle flap turnover. But the two treatments in the severe DSWI have the opposite effect.

Objective:To investigate the pre-pregnancy vitamin D level and pregnancy outcome in patients with unexplained recurrent spontaneous abortion (URSA).Methods:A prospective study was performed in 4 534 patients with URSA from May 2017 to April 2019 at Shanghai First Maternity and Infant Health Hospital Affiliated to Tongji University. The serum Vitamin D levels was obtained before pregnancy. Pregnancy complications and newborns outcomes were recorded after pregnancy.Results:The serum vitamin D level of patients with URSA before pregnancy was (42.22±16.27)nmol/L, and the proportions of vitamin D deficiency, insufficiency and sufficiency were 72.3%, 24.0 %, and 3.7%, respectively. The Vitamin D level was positively correlated with age ( P<0.05); The age of vitamin D<50 nmol/L group was lower than that of vitamin D≥50 nmol/L group ( P<0.05); patients with vitamin D<50 nmol/L had higher proportion of spontaneous abortions ≥3 times than those with the vitamin D≥50 nmol/L ( P<0.05); The level of vitamin D was negatively correlated with the ratio of CD3 + CD4 + T cells in peripheral blood ( P<0.05); In multivariate logistic regression analysis, the final model adjusted for age, abortion frequency and season. The risk of pregnancy failure was increased in vitamin D <50 nmol/L group [30.6%(76/248) vs 17.9%(12/67), χ 2=3.67, P=0.02], OR=2.02(95% CI: 1.02-3.9); In the group of vitamin D<50 nmol/L before pregnancy, the risk of newborns entering NICU was increased, OR=3.16(95% CI: 1.15-8.65). Conclusions:Vitamin D deficiency is prevalent in URSA patients before pregnancy, which correlates with the times of previous spontaneous abortions and recurrent pregnancy failure. Vitamin D deficiency before pregnancy is one of the high-risk factors for URSA.

The corona virus disease 2019 (COVID-19) caused by the new coronavirus (SARS-CoV-2) has spread rapidly around the world,posing a serious threat to the public"s health. As of September 30,2020,the number of infected people in the world has reached 33 million,causing more than 1 million deaths. Normalized nucleic acid detection methods based on lab have long turnaround time and high cost. Therefore,there is an urgent need to develop a convenient method to detect SARS-CoV-2,so as to achieve rapid testing and timely control of the epidemic when resources are limited.This review summarizes the point-of-care testing (POCT) methods developed for SARS-CoV-2 in terms of extraction,amplification and detection,and briefly introduces commercial POCT instruments that integrate these three steps,in order to provide references for emergency response and rapid deployment of COVID-19 and other emerging infectious diseases.

BACKGROUND:Tissue-engineered bone has been considered to be a promising candidate for the repair and reconstruction of load-bearing large segmental bone defects. Currently, the studies on the application of tissue-engineered bone mainly focus on cel-scaffold or cytokine-scaffold constructs, which haveshed light upon the repair of large segmental bone defects. OBJECTIVE:Toestablish simple and convenient tissue engineering of anatomicaly shaped tibial bone defect models using three-dimensional rapid prototyping technology to manufacture rabbit tibia biomimetic artificial bone scaffolds. METHODS:Three-dimensional electronic models were constructed using Mimic software. Hydroxyapatite/polycaprolactonescaffolds were manufactured by fused deposition modeling equipment. Fifty rabbits aged 6 months were randomly divided into three groups: blank control(n=3), control(n=6) and experimental groups(n=6), respectively. Tibial defects ranged 1.2 cmweremade in al groups. No treatment was given in blank control group. The bone defects in control and experimental groups were repaired with autogenous osteotomized bone and anatomicaltissue-engineered bone, respectively, and fixed with plates and screws. RESULTS AND CONCLUSION:(1) Rabbit tibial bone measurements:tibiallengthwas (93.77±0.59)mm, tibiofibular transverse diameter(8.36±0.13)mm, sagittal diameter(5.97±0.12)mm, average thickness of bone cortex(1.20±0.10)mm, average diameter of the medulary cavity(4.30±0.06)mm. Anglebetween the connection line of the midpoints of superior and inferior articular surfaces at the side of tibial bone models and the connection lineof the midpoints of superior and inferior intersecting surfaces at the side of osteotomized bone modelswasα=(5.97±0.13)°.(2) X-ray in bone defects: at postoperative 4 and 12 weeks, no obvious displacement and angulated deformity were found in bone grafts, suggesting the good bone defect repair.(3) Histological examination: at postoperative 4 weeks, bone scaffolds were filed with new bone in the experimental group. Furthermore, considerably increased new bone formation and mineralization were observed at postoperative 12 weeks.(4) General observation: no obvious displacement and angulated deformity occurredin bone defect grafts at postoperative 4 and 12 weeks. These findings suggest that rabbit anatomical models of large segmental tibial bone defects with good stability were constructed using three-dimensional prototyping technology, which may simulate the structure and function of bone tissue and be used for guiding the new bone regeneration.

Rosai-Dorfman disease in nasal cavity and nasal sinuses is known as an idiopathic proliferative disease of histiocytes with a distinct morphologic feature and is very rare. It is easy to relapse and be misdiagnosed. In on case, the infiltrating histiocytes had large round or oval nuclei. The cytoplasm was abundant, granular or vacuolated and foamy. Immunohistochemical studies showed that the histiocytes were strongly reactive with antibodies against S100 and CD68. The diagnosis of extranodal RDD in the paranasal sinuses could be differentiated with rhinoscleroma, eosinophilic granuloma, plasmacytoma, or fibrous histiocytoma. It showed that the identification of the distinctive histiocytes which are typically immunoreactive to S100 and CD68 can be quite helpful for correct diagnosis.
Adult ; Histiocytosis, Sinus ; pathology ; Humans ; Male ; Nasal Cavity ; pathology ; Paranasal Sinuses ; pathology

A female patient, now 6 years old, received cochlear implant in the right ear at the age of 2 (February, 2006). In August 16, 2010, a cervical spine MRI examination was required due to the cervical spine injury in order to confirm the diagnosis. Considering the cochlea coil may interfere with the MRI examination results, a local bandaging around the ear was given to isolate cochlear magnetic field. The results of cervical spine MRI examinations showed no obvious disturbance, which suggests that we could further explore this method clinically.
Cervical Vertebrae ; Child ; Cochlear Implantation ; Cochlear Implants ; Female ; Humans ; Magnetic Resonance Imaging ; Postoperative Period