Application of convolutional neural network for differentiating ovarian thecoma-fibroma and solid ovarian cancer based on MRI.

BACKGROUND: Ovarian thecoma-fibroma and solid ovarian cancer have similar clinical and imaging features, and it is difficult for radiologists to differentiate them. Since the treatment and prognosis of them are different, accurate characterization is crucial. PURPOSE: To non-invasively differentiate ovarian thecoma-fibroma and solid ovarian cancer by convolutional neural network based on magnetic resonance imaging (MRI), and to provide the interpretability of the model. MATERIAL AND METHODS: A total of 156 tumors, including 86 ovarian thecoma-fibroma and 70 solid ovarian cancer, were split into the training set, the validation set, and the test set according to the ratio of 8:1:1 by stratified random sampling. In this study, we used four different networks, two different weight modes, two different optimizers, and four different sizes of regions of interest (ROI) to test the model performance. This process was repeated 10 times to calculate the average performance of the test set. The gradient weighted class activation mapping (Grad-CAM) was used to explain how the model makes classification decisions by visual location map. RESULTS: ResNet18, which had pre-trained weight, using Adam and one multiple ROI circumscribed rectangle, achieved best performance. The average accuracy, precision, recall, and AUC were 0.852, 0.828, 0.848, and 0.919 (P < 0.01), respectively. Grad-CAM showed areas associated with classification appeared on the edge or interior of ovarian thecoma-fibroma and the interior of solid ovarian cancer. CONCLUSION: This study shows that convolution neural network based on MRI can be helpful for radiologists in differentiating ovarian thecoma-fibroma and solid ovarian cancer.

Diagnosing schizophrenia using deep learning: Novel interpretation approaches and multi-site validation.

Schizophrenia is a profound and enduring mental disorder that imposes significant negative impacts on individuals, their families, and society at large. The development of more accurate and objective diagnostic tools for schizophrenia can be expedited through the employment of deep learning (DL), that excels at deciphering complex hierarchical non-linear patterns. However, the limited interpretability of deep learning has eroded confidence in the model and restricted its clinical utility. At the same time, if the data source is only derived from a single center, the model's generalizability is difficult to test. To enhance the model's reliability and applicability, leave-one-center-out validation with a large and diverse sample from multiple centers is crucial. In this study, we utilized Nine different global centers to train and test the 3D Resnet model's generalizability, resulting in an 82% classification performance (area under the curve) on all datasets sourced from different countries, employing a leave-one-center-out-validation approach. Per our approximation of the feature significance of each region on the atlas, we identified marked differences in the thalamus, pallidum, and inferior frontal gyrus between individuals with schizophrenia and healthy controls, lending credence to prior research findings. At the same time, in order to translate the model's output into clinically applicable insights, the SHapley Additive exPlanations (SHAP) permutation explainer method with an anatomical atlas have been refined, thereby offering precise neuroanatomical and functional interpretations of different brain regions.

Discriminating Between Benign and Malignant Solid Ovarian Tumors Based on Clinical and Radiomic Features of MRI.

RATIONALE AND OBJECTIVES: To develop and validate a combined model integrating clinical and radiomic features to non-invasive discriminate between the benign and malignant solid ovarian tumors. MATERIALS AND METHODS: A total of 148 patients with 156 solid ovarian tumors (86 benign and 70 malignant tumors) were included in this study. The dataset was split into the training and the test set with a ratio of 8:2 using stratified random sampling. 12 clinical features and 1612 radiomic features were extracted from each tumor. These features were selected by least absolute shrinkage and selection operator (Lasso). Three classification models were built using extreme gradient boosting (XGB) algorithm: clinical model, radiomic model, combined model. The area under the receiver operating characteristic curve (AUC), accuracy, precision and sensitivity were analyzed to evaluate the performance of these models. RESULTS: All of the three models obtained good performances in differentiating benign with malignant solid ovarian tumors in both training and test sets. The AUC, accuracy, precision, sensitivity of clinical model and radiomic model in test set were 0.847 (95% confidence interval (CI), 0.707-0.986, p <0.01), 0.774, 0.769, 0.714, and 0.807 (95%CI, 0.652-0.961, p <0.05), 0.677, 0.643, 0.643, respectively. Combined model had the best prediction results, the AUC, accuracy, precision and sensitivity were 0.954 (95%CI, 0.862-1.0, p <0.01), 0.839, 0.909 and 0.714 in test set. CONCLUSION: Radiomics based on machine learning can be helpful for radiologists in differentiating the benign and malignant solid ovarian tumors.

[Effects of carboidiimide with different bonding techniques on the property of dentin bonding].

PURPOSE: To explore the effects of carbodiimide combined with different bonding techniques on the property of dentin bonding. METHODS: 64 third molars in vitro were randomly divided into 8 groups(n=8), including EWB and EWBa (no pretreatment+ethanol-wet bonding), E-EWB and E-EWBa (0.5 mol/L EDC+ethanol-wet bonding), E-WB and E-WBa (0.5 mol/L EDC+water-wet bonding), E-DB and E-Dba (0.5 mol/L EDC+dry bonding). Group EWB, E-EWB, E-WB and E-DB were immediate groups, while group EWBa, E-EWBa, E-WBa and E-DBa were aging groups. Six specimens in each group were randomly chosen to test shear bonding strength and then observe failure patterns. The remaining specimens were used to observe bonding interface under SEM. SPSS 20.0 software package was used for statistical analysis of the data. RESULTS: There was no significant difference in shear bonding strength between group EWB and E-EWB, group E-EWB and E-WB(P＞0.05), while shear bounding strength in group E-EWB and E-WB were significantly greater than group E-DB(P＜0.05). The shear bonding strength of group E-EWBa was significantly greater than group EWBa (P＜0.05). The shear bonding strength of group E-EWBa, E-WBa and E-DBa was gradually decreased, and their differences were significant (P＜0.05). The factors of EDC, bonding techniques and aging played a significant role in shear bonding strength (P＜0.05). Interactions between EDC and aging was significant (P＜0.05), and that between bonding techniques and aging was also significant (P＜0.05). The main failure modes of the water-wet bonding and the ethanol-wet bonding were resin failure, adhesive interface failure and mixed failure. The main failure of dry bonding was adhesive interface failure. The thickest and densest hybrid layer were found in group E-EWB. Some tiny cracks were presented between the hybrid layer and adhesives layer in group EWBa and E-EWBa. Partially uneven cracks existed in the hybrid layer in group E-WBa, and that was more obvious in group E-DBa. CONCLUSIONS: EDC pretreatment combined with ethanol-wet adhesive technique acquires the optimal shear bonding strength and the durability of dentin bonding.

[The influence of carbodiimide in different solvents on bonding performance of acetone-based etch-and-rinsing adhesive system].

PURPOSE: To investigate the influence of carbodiimide (EDC) in water, ethanol and acetone on bonding performance of acetone-based etch-and-rinsing adhesive system. METHODS: Sixty-four third molars in vitro were randomly divided into 8 groups according to the types of pretreatment agents, with or without aging(n=8), group S0 and S0a: deionized water; group S and Sa: EDC in water; group E and Ea: EDC in ethanol; group B and Ba: EDC in acetone. After pretreatment, the adhesive specimens were prepared by Prime Bond NT. S0, S, E and B were immediate groups, and S0a, Sa, Ea and Ba groups were subjected to aging test for 5 000 times. Six specimens were randomly selected from each group to test the shear bond strength and observe the fracture mode. The remaining 2 specimens were used to observe the microstructure of bonding interface by scanning electron microscopy. The shear bond strength was statistically analyzed with SPSS 20.0 software package. RESULTS: It was found that the shear bond strength of group S was significantly higher than that of group S0, and the shear bond strength of group Sa was significantly higher than that of group S0a(P<0.05). There was no significant difference between groups S, E and B(P>0.05). The shear bond strength of Sa, Ea and Ba increased successively, and the difference was statistically significant(P<0.05). Three factor analysis of variance found that the main effect of EDC, aging and solvent alone was significantly different(P<0.05), and there was an interaction effect between EDC and aging(P<0.05). The fracture modes of immediate groups were mainly mixed failure, while the interface fracture was the most common in the aging groups. SEM observation showed that all the hybrid layers were uniform and complete in the immediate groups, and the largest crack in S0a group and a few cracks in Ba group. CONCLUSIONS: EDC pretreatment in water, ethanol, and acetone solvents can improve both the immediate and aging bonding strength of acetone-based etch-and-rinsing adhesive system. Acetone acts as the solvents of EDC maximizes the shear bond strength among the aging groups.

Naringenin Prevents Propofol Induced Neurodegeneration in Neonatal Mice Brain and Long-Term Neurocognitive Impacts on Adults.

BACKGROUND: Natural products have shown neuroprotective effects in neurodegenerative conditions. Naringenin is a natural flavonoid with various pharmacological activities especially antioxidant, anti-inflammatory and neuroprotective properties. We investigated the effects of naringenin on anesthetic propofol-induced impacts on neonatal mouse brain development and consequent long-term neurocognitive impacts during adulthood. MATERIALS AND METHODS: Female C57Bl/6 and male CD-1 mice and postnatal day 7 (P7) pups were exposed to propofol (2.5 mg/kg) and propofol with naringenin (50 mg/kg). Mice pups were allowed to grow until week 10 (adulthood), and memory and learning were assessed. RESULTS: Propofol caused neurodegeneration by inducing apoptosis in the neonatal mouse brains while naringenin administration prevented neuronal cell loss by preventing neuronal apoptosis in neonatal mouse brains. Propofol caused degenerative alterations in metabolic factors pH, PO2, glucose and lactate, which were subsequently restored by naringenin treatment. Propofol-exposed mice, when developed into adults, showed long-term neuronal deficits, impaired neurocognitive functions, and memory and learning restrictions. CONCLUSION: Administration of naringenin to propofol-exposed mice resulted in significant neuroprotective effects by restoring long-term neurocognitive functions. The molecular mechanism behind the effects of naringenin was mediated by suppressing apoptosis and preventing cellular inflammation. These findings suggest that propofol administration requires careful consideration and that naringenin may prevent neurodegeneration and neurocognitive functions.

Barotrauma after liquid nitrogen ingestion: a case report and literature review.

A 25-year-old man developed a gastric perforation after ingesting a homemade drink containing liquid nitrogen. Surgical repair had to be postponed to seek consultations with experts because the available practitioners in this case, including emergency physicians, surgeons, and anesthesiologists, had little experience and knowledge about the source of the patient's pneumothorax and subcutaneous emphysema. The patient ultimately underwent exploratory laparotomy with general anesthesia, considering that delaying the operation would lead to a longer duration of bacterial peritonitis and delay the standard treatment of postoperative systemic infectious complications. Our literature review revealed that barotrauma is the unique injury mechanism underlying liquid nitrogen ingestion. Injuries to the airway and esophagus are rare.