Transfer learning radiomics based on multimodal ultrasound imaging for staging liver fibrosis.

OBJECTIVES: To propose a transfer learning (TL) radiomics model that efficiently combines the information from gray scale and elastogram ultrasound images for accurate liver fibrosis grading. METHODS: Totally 466 patients undergoing partial hepatectomy were enrolled, including 401 with chronic hepatitis B and 65 without fibrosis pathologically. All patients received elastography and got liver stiffness measurement (LSM) 2-3 days before surgery. We proposed a deep convolutional neural network by TL to analyze images of gray scale modality (GM) and elastogram modality (EM). The TL process was used for liver fibrosis classification by Inception-V3 network which pretrained on ImageNet. The diagnostic performance of TL and non-TL was compared. The value of single modalities, including GM and EM alone, and multimodalities, including GM + LSM and GM + EM, was evaluated and compared with that of LSM and serological indexes. Receiver operating characteristic curve analysis was performed to calculate the optimal area under the curve (AUC) for classifying fibrosis of S4, ≥ S3, and ≥ S2. RESULTS: TL in GM and EM demonstrated higher diagnostic accuracy than non-TL, with significantly higher AUCs (all p < .01). Single-modal GM and EM both performed better than LSM and serum indexes (all p < .001). Multimodal GM + EM was the most accurate prediction model (AUCs are 0.950, 0.932, and 0.930 for classifying S4, ≥ S3, and ≥ S2, respectively) compared with GM + LSM, GM and EM alone, LSM, and biomarkers (all p < .05). CONCLUSIONS: Liver fibrosis can be staged by a transfer learning modal based on the combination of gray scale and elastogram ultrasound images, with excellent performance. KEY POINTS: • Transfer learning consists in applying to a specific deep learning algorithm that pretrained on another relevant problem, expected to reduce the risk of overfitting due to insufficient medical images. • Liver fibrosis can be staged by transfer learning radiomics with excellent performance. • The most accurate prediction model of transfer learning by Inception-V3 network is the combination of gray scale and elastogram ultrasound images.

Preoperative diagnosis and prediction of hepatocellular carcinoma: Radiomics analysis based on multi-modal ultrasound images.

BACKGROUND: This study aims to establish a radiomics analysis system for the diagnosis and clinical behaviour prediction of hepatocellular carcinoma (HCC) based on multi-parametric ultrasound imaging. METHODS: A total of 177 patients with focal liver lesions (FLLs) were included in the study. Every patient underwent multi-modal ultrasound examination, including B-mode ultrasound (BMUS), shear wave elastography (SWE), and shear wave viscosity (SWV) imaging. The radiomics analysis system was built on sparse representation theory (SRT) and support vector machine (SVM) for asymmetric data. Through the sparse regulation from the SRT, the proposed radiomics system can effectively avoid over-fitting issues that occur in regular radiomics analysis. The purpose of the proposed system includes differential diagnosis between benign and malignant FLLs, pathologic diagnosis of HCC, and clinical prognostic prediction. Three biomarkers, including programmed cell death protein 1 (PD-1), antigen Ki-67 (Ki-67) and microvascular invasion (MVI), were included and analysed. We calculated the accuracy (ACC), sensitivity (SENS), specificity (SPEC) and area under the receiver operating characteristic curve (AUC) to evaluate the performance of the radiomics models. RESULTS: A total of 2560 features were extracted from the multi-modal ultrasound images for each patient. Five radiomics models were built, and leave-one-out cross-validation (LOOCV) was used to evaluate the models. In LOOCV, the AUC was 0.94 for benign and malignant classification (95% confidence interval [CI]: 0.88 to 0.98), 0.97 for malignant subtyping (95% CI: 0.93 to 0.99), 0.97 for PD-1 prediction (95% CI: 0.89 to 0.98), 0.94 for Ki-67 prediction (95% CI: 0.87 to 0.97), and 0.98 for MVI prediction (95% CI: 0.93 to 0.99). The performance of each model improved when the viscosity modality was included. CONCLUSIONS: Radiomics analysis based on multi-modal ultrasound images could aid in comprehensive liver tumor evaluations, including diagnosis, differential diagnosis, and clinical prognosis.

Development of a deep pathomics score for predicting hepatocellular carcinoma recurrence after liver transplantation.

BACKGROUND AND PURPOSE: Tumor recurrence after liver transplantation (LT) impedes the curative chance for hepatocellular carcinoma (HCC) patients. This study aimed to develop a deep pathomics score (DPS) for predicting tumor recurrence after liver transplantation using deep learning. PATIENTS AND METHODS: Two datasets of 380 HCC patients who underwent LT were enrolled. Residual convolutional neural networks were used to identify six histological structures of HCC. The individual risk score of each structure and DPS were derived by a modified DeepSurv network. Cox regression analysis and Concordance index were used to evaluate the prognostic significance. The cellular exploration of prognostic immune biomarkers was performed by quantitative and spatial proximity analysis according to three panels of 7-color immunofluorescence. RESULTS: The overall classification accuracy of HCC tissue was 97%. At the structural level, immune cells were the most significant tissue category for predicting post-LT recurrence (HR 1.907, 95% CI 1.490-2.440). The C-indices of DPS achieved 0.827 and 0.794 in the training and validation cohorts, respectively. Multivariate analysis for recurrence-free survival (RFS) showed that DPS (HR 4.795, 95% CI 3.017-7.619) was an independent risk factor. Patients in the high-risk subgroup had a shorter RFS, larger tumor diameter and a lower proportion of clear tumor borders. At the cellular level, a higher infiltration of intratumoral NK cells was negatively correlated with recurrence risk. CONCLUSIONS: This study established an effective DPS. Immune cells were the most significant histological structure related to HCC recurrence. DPS performed well in post-LT recurrence prediction and the identification of clinicopathological features.

[Effect of high-concentration fluoride on apoptosis of human periodontal ligament stem cells].

PURPOSE: To explore the effects of high-concentration fluoride(F) on apoptosis of human periodontal ligament stem cells (PDLSCs). METHODS: PDLSCs were isolated from periodontal ligament tissues of extracted third molars, and treated with different concentrations (0-40 ppm F) of NaF for indicated period of time. CCK-8 assay was performed to detect cell viability. After stained with Annexin V-PI and JC-1, cell apoptosis and mitochondrial membrane potential were analyzed by flow cytometry. Immunofluorescence staining and confocal microscopic assay were used to detect the protein expression level of cyt-c, cleaved-caspase-9 and -3. The mRNA level of caspase -9 and -3 were examined by RT-PCR. The protein expression level of total and phosphate-ERK, JNK and p38 were analyzed by Western blot. SPSS 13.0 software package was used for statistical analysis. RESULTS: Fluoride treatment inhibited cell viability (CCK-8 assay) and induced apoptosis of PDLSCs (Annexin V-PI staining) in a dose- and time-dependent manner. Immunofluorescence assay showed that fluoride with a dose ≥10 ppm significantly induced release of cyt-c from the mitochondria to cytosol, and up-regulation of expression of cleaved-caspase -9 and -3. RT-PCR confirmed that the mRNA level of caspase-9 and -3 increased with the dose of fluoride. Western blot assay confirmed that fluoride induced up-regulation of p-ERK, but not that of p-JNK and p-p38, and specifically blocking ERK pathway with U0126 could partially rescue the fluoride-induced cell apoptosis. CONCLUSIONS: High concentrations of fluoride induces apoptosis of PDLSCs via intrinsic mitochondrial pathway, and phosphation of MAPK/ERK is involved in the F-induce cell apoptosis.

Recognition of moyamoya disease and its hemorrhagic risk using deep learning algorithms: sourced from retrospective studies.

Although intracranial hemorrhage in moyamoya disease can occur repeatedly, predicting the disease is difficult. Deep learning algorithms developed in recent years provide a new angle for identifying hidden risk factors, evaluating the weight of different factors, and quantitatively evaluating the risk of intracranial hemorrhage in moyamoya disease. To investigate whether convolutional neural network algorithms can be used to recognize moyamoya disease and predict hemorrhagic episodes, we retrospectively selected 460 adult unilateral hemispheres with moyamoya vasculopathy as positive samples for diagnosis modeling, including 418 hemispheres with moyamoya disease and 42 hemispheres with moyamoya syndromes. Another 500 hemispheres with normal vessel appearance were selected as negative samples. We used deep residual neural network (ResNet-152) algorithms to extract features from raw data obtained from digital subtraction angiography of the internal carotid artery, then trained and validated the model. The accuracy, sensitivity, and specificity of the model in identifying unilateral moyamoya vasculopathy were 97.64 ± 0.87%, 96.55 ± 3.44%, and 98.29 ± 0.98%, respectively. The area under the receiver operating characteristic curve was 0.990. We used a combined multi-view conventional neural network algorithm to integrate age, sex, and hemorrhagic factors with features of the digital subtraction angiography. The accuracy of the model in predicting unilateral hemorrhagic risk was 90.69 ± 1.58% and the sensitivity and specificity were 94.12 ± 2.75% and 89.86 ± 3.64%, respectively. The deep learning algorithms we proposed were valuable and might assist in the automatic diagnosis of moyamoya disease and timely recognition of the risk for re-hemorrhage. This study was approved by the Institutional Review Board of Huashan Hospital, Fudan University, China (approved No. 2014-278) on January 12, 2015.

An Ultrasound Radiomics Nomogram for Preoperative Prediction of Central Neck Lymph Node Metastasis in Papillary Thyroid Carcinoma.

Purpose: This study aimed to establish and validate an ultrasound radiomics nomogram for the preoperative prediction of central lymph node (LN) metastasis in patients with papillary thyroid carcinoma (PTC). Patients and Methods: The prediction model was developed in 609 patients with clinicopathologically confirmed unifocal PTC who received ultrasonography between Jan 2018 and June 2018. Radiomic features were extracted after the ultrasonography of PTC. Lasso regression model was used for data dimensionality reduction, feature selection, and radiomics signature building. The predicting model was established based on the multivariable logistic regression analysis in which the radiomics signature, ultrasonography-reported LN status, and independent clinicopathologic risk factors were incorporated, and finally a radiomics nomogram was established. The performance of the nomogram was assessed with respect to the discrimination and consistence. An independent validation was performed in 326 consecutive patients from July 2018 to Sep 2018. Results: The radiomics signature consisted of 23 selected features and was significantly associated with LN status in both primary and validation cohorts. The independent predictors in the radiomics nomogram included the radiomics signature, age, TG level, TPOAB level, and ultrasonography-reported LN status. The model showed good discrimination and consistence in both cohorts: C-index of 0.816 (95% CI, 0.808-0.824) in the primary cohort and 0.858 (95% CI, 0.849-0.867) in the validation cohort. The area under receiver operating curve was 0.858. In the validation cohort, the accuracy, sensitivity, specificity and AUC of this model were 0.812, 0.816, 0.810, and 0.858 (95% CI, 0.785-0.930), respectively. Decision curve analysis indicated the radiomics nomogram was clinically useful. Conclusion: This study presents a convenient, clinically useful ultrasound radiomics nomogram that can be used for the pre-operative individualized prediction of central LN metastasis in patients with PTC.

Recognition of Cognitive Impairment in Adult Moyamoya Disease: A Classifier Based on High-Order Resting-State Functional Connectivity Network.

Objective: Vascular cognitive impairment (VCI) is a common complication in adult patients with moyamoya disease (MMD), and is reversible by surgical revascularization in its early stage of mild VCI. However, accurate diagnosis of mild VCI is difficult based on neuropsychological examination alone. This study proposed a method of dynamic resting-state functional connectivity (FC) network to recognize global cognitive impairment in MMD. Methods: For MMD, 36 patients with VCI and 43 patients with intact cognition (Non-VCI) were included, as well as 26 normal controls (NCs). Using resting-state fMRI, dynamic low-order FC networks were first constructed with multiple brain regions which were generated through a sliding window approach and correlated in temporal dimension. In order to obtain more information of network interactions along the time, high-order FC networks were established by calculating correlations among each pair of brain regions. Afterwards, a sparse representation-based classifier was constructed to recognize MMD (experiment 1) and its cognitive impairment (experiment 2) with features extracted from both low- and high-order FC networks. Finally, the ten-fold cross-validation strategy was proposed to train and validate the performance of the classifier. Results: The three groups did not differ significantly in demographic features (p > 0.05), while the VCI group exhibited the lowest MMSE scores (p = 0.001). The Non-VCI and NCs groups did not differ significantly in MMSE scores (p = 0.054). As for the classification between MMD and NCs, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 90.70, 88.57, 93.67, and 73.08%, respectively. While for the classification between VCI and Non-VCI, the AUC, accuracy, sensitivity, and specificity of the classifier reached 91.02, 84.81, 80.56, and 88.37%, respectively. Conclusion: This study not only develops a promising classifier to recognize VCI in adult MMD in its early stage, but also implies the significance of time-varying properties in dynamic FC networks.

Hsa-let-7c controls the committed differentiation of IGF-1-treated mesenchymal stem cells derived from dental pulps by targeting IGF-1R via the MAPK pathways.

The putative tumor suppressor microRNA let-7c is extensively associated with the biological properties of cancer cells. However, the potential involvement of let-7c in the differentiation of mesenchymal stem cells has not been fully explored. In this study, we investigated the influence of hsa-let-7c (let-7c) on the proliferation and differentiation of human dental pulp-derived mesenchymal stem cells (DPMSCs) treated with insulin-like growth factor 1 (IGF-1) via flow cytometry, CCK-8 assays, alizarin red staining, real-time RT-PCR, and western blotting. In general, the proliferative capabilities and cell viability of DPMSCs were not significantly affected by the overexpression or deletion of let-7c. However, overexpression of let-7c significantly inhibited the expression of IGF-1 receptor (IGF-1R) and downregulated the osteo/odontogenic differentiation of DPMSCs, as indicated by decreased levels of several osteo/odontogenic markers (osteocalcin, osterix, runt-related transcription factor 2, dentin sialophosphoprotein, dentin sialoprotein, alkaline phosphatase, type 1 collagen, and dentin matrix protein 1) in IGF-1-treated DPMSCs. Inversely, deletion of let-7c resulted in increased IGF-1R levels and enhanced osteo/odontogenic differentiation. Furthermore, the ERK, JNK, and P38 MAPK pathways were significantly inhibited following the overexpression of let-7c in DPMSCs. Deletion of let-7c promoted the activation of the JNK and P38 MAPK pathways. Our cumulative findings indicate that Let-7c can inhibit the osteo/odontogenic differentiation of IGF-1-treated DPMSCs by targeting IGF-1R via the JNK/P38 MAPK signaling pathways.

[Detecting MTHFR gene mutation with a new approach: molecular beacons].

OBJECTIVE: To detect the methylenetetrahydrofolate reductase(MTHFR) gene C677T mutation with molecular beacon technique and assess the revant applicability. METHODS: A total of 228 samples were analyzed using molecular beacons which are oligonucleotide probes to become fluorescent upon hybridization. Wild-type molecular beacon and mutant beacon were designed to detect the genotypes of MTHFR gene. RESULTS: Analysis of the 228 samples indicated that there were three genotypes including 41 homozygous mutants, 113 heterozygous individuals and 74 wild-type individuals. Every sample was identified clearly. CONCLUSION: The present method, a closed-tube PCR/hybridization assay, is a simple, high-throughput and fast procedure that is fully automated for detecting gene mutation.

Adult stem cell-based apexogenesis.

Generally, the dental pulp needs to be removed when it is infected, and root canal therapy (RCT) is usually required in which infected dental pulp is replaced with inorganic materials (paste and gutta percha). This treatment approach ultimately brings about a dead tooth. However, pulp vitality is extremely important to the tooth itself, since it provides nutrition and acts as a biosensor to detect the potential pathogenic stimuli. Despite the reported clinical success rate, RCT-treated teeth are destined to be devitalized, brittle and susceptible to postoperative fracture. Recently, the advances and achievements in the field of stem cell biology and regenerative medicine have inspired novel biological approaches to apexogenesis in young patients suffering from pulpitis or periapical periodontitis. This review mainly focuses on the benchtop and clinical regeneration of root apex mediated by adult stem cells. Moreover, current strategies for infected pulp therapy are also discussed here.

[Effect of KH2PO4 on the odonto- and osteogenic differentiation potential of human stem cells from apical papillae].

OBJECTIVE: To determine the effects of KH2PO4 on the odonto- and osteogenic differentiation potential of human stem cells from apical papillae (SCAP) in vitro. METHODS: SCAP were isolated and cultured respectively in alpha minimum essential medium (α-MEM) or α-MEM containing 1.8 mmol/L KH2PO4. Alkaline phosphatase (ALP) activity, alizarin red staining, real-time reverse transcription polymerase chain reaction (RT-PCR) and Western blotting were used to examine the odonto and osteogenic potential of SCAP in the two media. RESULTS: SCAP cultured in α-MEM containing 1.8 mmol/L KH2PO4 exhibited a higher ALP activity [(0.370 ± 0.013) Sigma unit×min(-1)×mg(-1)] at day 3 than control group [(0.285 ± 0.008) Sigma unit×min(-1)×mg(-1)] and KH2PO4-treated SCAP formed more calcified nodules at day 5 [(0.539 ± 0.007) µg/g] and day 7 [(1.617 ± 0.042) µg/g] than those in normal medium [(0.138 ± 0.037) µg/g, P < 0.01]. The expression of odonto- and osteogenic markers were significantly up-regulated after the stimulation of KH2PO4 at day 3 and 7 respectively, as compared with control group. CONCLUSIONS: 1.8 mmol/L KH2PO4 can promote the odonto and osteogenic differentiation potential of human SCAP.

Bilateral maxillary fused second and third molars: a rare occurrence.

This case report describes the diagnosis and endodontic therapy of maxillary fused second and third molars, using cone-beam computed tomography (CBCT). A 31-year-old Chinese male, with no contributory medical or family/social history, presented with throbbing pain in the maxillary right molar area following an unsuccessful attempted tooth extraction. Clinical examination revealed what appeared initially to be a damaged large extra cusp on the buccal aspect of the distobuccal cusp of the second molar. However, CBCT revealed that a third molar was fused to the second molar. Unexpectedly, the maxillary left third molar also was fused to the second molar, and the crown of an unerupted supernumerary fourth molar was possibly also fused to the apical root region of the second molar. Operative procedures should not be attempted without adequate radiographic investigation. CBCT allowed the precise location of the root canals of the right maxillary fused molar teeth to permit successful endodontic therapy, confirmed after 6 months.

Nonlinear finite element analysis of three implant- abutment interface designs.

The objective of this study was to investigate the mechanical characteristics of implant-abutment interface design in a dental , using nonlinear finite element analysis (FEA) method. This finite element simulation study was applied on three commonly used commercial dental implant systems: model I, the reduced-diameter 3i implant system (West Palm Beach, FL, USA) with a hex and a 12-point double internal hexagonal connection; model II, the Semados implant system (Bego, Bremen, Germany) with combination of a conical (450 taper) and internal hexagonal connection; and model III, the Brinemark implant system (Nobel Biocare, Gothenburg,Sweden) with external hexagonal connection. In simulation, a force of 170 N with 45" oblique to the longitudinal axis of the implant was loaded to the top surface of the abutment. It has been found from the strength and stiffness analysis that the 3i implant system has the lowest maximum von Mises stress, principal stress and displacement while the Br Bnemark implant system has the highest. It was concluded from our preliminary study using nonlinear FEA that the reduced-diameter 3i implant system with a hex and a 12-point double internal hexagonal connection had a better stress distribution, and produced a smaller displacement than the other two implant systems.

Cell pellets from dental papillae can reexhibit dental morphogenesis and dentinogenesis.

We isolated dental papilla mesenchymal cells (DPMCs) from different rat incisor germs at the late bell stage and incubated them as cell pellets in polypropylene tubes. In vitro pellet culture of DPMCs presented several crucial characteristics of odontoblasts, as indicated by accelerated mineralization, positive immunostaining for dentin sialophosphoprotein and dentin matrix protein 1, and expression of dentin sialophosphoprotein mRNA. The allotransplantation of these pellets into renal capsules was also performed. Despite the absence of dental epithelial components, dissociated DPMCs with a complete loss of positional information rapidly underwent dentinogenesis and morphogenesis, and formed a cusp-like dentin-pulp complex containing distinctive odontoblasts, predentin, dentin, and dentinal tubules. These results imply that DPMCs at the late bell stage can reexhibit the dental morphogenesis and dentinogenesis by themselves, and epithelial-mesenchymal interactions at this stage may not be indispensable. Furthermore, different DPMC populations from the similar stage may keep the same developmental pattern.

Temporal expression of estrogen receptor alpha in rat bone marrow mesenchymal stem cells.

Estrogen responsiveness of bone formation is mediated by the estrogen receptor alpha (ERalpha) in osteoblastic lineage. As osteoblasts arise from the multipotent bone marrow stromal (mesenchymal) cells, this study was undertaken to observe the ERalpha in primary female adult rat bone marrow mesenchymal stem cells (BMSCs). The ERalpha was localized using immunocytochemical analysis in identified primary BMSCs. Then, using real-time PCR analysis, we measured the expression of ERalpha messenger RNA (mRNA) in BMSCs. ERalpha transcripts showed different trends between untreated cultures (control group) and osteogenic-induced cultures (treated group). In the control group, ERalpha mRNA climbed at peak levels at a confluence stage and decreased until day 20, whereas, in the treated group, the ERalpha mRNA kept climbing from a low level until day 20. Thus, the observed developmental expression of ERalpha mRNA correlates with progressive BMSCs growth and osteogenic differentiation and BMSCs may be a primary target cell for estrogen in maintaining bone formation.

[The clinical evaluation of tinidazole-iodoform-phenocamphor paste as an intra-canal sterilization medication for acute periapical periodontitis].

OBJECTIVE: To compare the clinical effect of tinidazole-iodoform-phenocamphor paste on acute periapical periodontitis with of formocresol. METHODS: 80 permanent teeth of acute periapical periodontitis were selected and divided randomly into tinidazole-iodoform-phenocamphor paste group (T group) and formocresol group (C group). The periapical signs and symptoms were recorded. Radiographs were taken and periapical radiolucent areas were calculated. After root canal preparation,the tinidazole-iodoform-phenocamphor paste was used as an intra-canal dressing medication for 7 days in T group and the formocresol paper point was used in C group. During the course of root canal treatment,the standard paper-point sampling method was used to collect and quantify the periapical exudates and the clinical findings were assessed with clinical periapical index(CPI). All statistical analyses were finished with Sigmastat software. RESULTS: At the first visit, there was no significant difference between two groups of CPI indexes and exudates volumes (P>0.05). The stepwise regression results suggested that exudates volumes had a significant correlation to periapical percussion(P=0.0031). There was a close relationship between radiolucent areas and periapical percussion or swelling degree (P=0.1148, P<0.0001). After the root canal sterilization, there was a statistically significant decrease in exudates volumes and CPI indexes (P<0.01), but the difference of exudates volumes and CPI indexes between two groups was not statistically significant (P>0.05). CONCLUSION: It indicated that tinidazole-iodoform-phenocamphor paste had the same effect on controlling acute periapical periodontitis as that of formocresol.