Weakly Supervised Exaggeration Transfer for Caricature Generation With Cross-Modal Knowledge Distillation.

Caricature generation aims to translate portrait photos into caricatures with exaggerated and hand-drawn artistic styles. Previous methods faced challenges in creating diverse and meaningful exaggeration effects, yielding unsatisfactory and uncontrollable results. To overcome this, we proposed ETCari, a novel weakly supervised exaggeration transfer network. ETCari enables the learning of diverse exaggeration caricature styles from various artists, better meeting individual customization requirements and achieving diversified exaggeration while retaining identity features. Specifically, we use the thin-plate spline control point deformation field as the ground truth, serving as the loss for weakly supervised learning to address the challenge of no labels. We convert input to an intermediate modality for domain adaptation, training a teacher model. Subsequently, we perform cross-modal knowledge distillation to train the student model, simplifying preprocessing during inference and avoiding the impact of face parser errors. Experiments on the WebCaricature dataset demonstrate that ETCari effectively performs exaggeration transfer, generating appealing caricatures.

[Clinical Value of Genetic Susceptibility Genes for Myeloid Neoplasm in Myeloproliferative Neoplasm].

OBJECTIVE: To investigate the influence of genetic susceptibility genes for myeloid tumors on the clinical characteristics of patients with myeloproliferative neoplasm (MPN). METHODS: Two hundred and thirty-two patients with MPN diagnosed at the Second Hospital of Tianjin Medical University from September 2017 to December 2021 were collected, myeloid neoplasm-related genes were detected by targeted next-generation sequencing, and germline mutations were verified. The clinical characteristics and prognosis of MPN patients with germlines mutations in the genetic susceptibility gene for myeloid neoplasm were analyzed. RESULTS: The germline mutation carrier rate of myeloid neoplasm genetic susceptibility gene in MPN patients was 21.6% (50/232), and the PV, ET and PMF patients carrying germline mutations of genetic susceptibility gene for myeloid neoplasm were 25/114 (21.9%), 8/69 (11.6%) and 17/49 (34.7%), respectively, among which PMF patients had the highest carrier rate (P=0.01) and were older (P=0.02). The incidence of chromosomal abnormalities in MPN patients carrying the genetic susceptibitity genes for myeloid neoplasm was higher than that in the non-carrier group (26.5% vs 11.8%, P=0.05). Germline mutations in the genetic susceptibility gene of myeloid neoplasm in MPN patients were mainly concentrated in the RAS pathway, and patients with germline mutations in the genetic susceptibility gene of myeloid neoplasm associated with the RAS pathway had shorter survival without AML progression (P<0.0001). The overall survival time in MPN patients with CBL and TP53 germline mutations was shorter than that of non-carrier group (P=0.001; P=0.043). CONCLUSION: In MPN, PMF patients are more likely to carry germline mutations in the genetic susceptibility gene for myeloid neoplasm. MPN patients with germline mutations carring the genetic susceptibility gene for myeloid neoplasm are prone to chromosomal abnormalities; Patients with MPN who have germline mutations in the genetic susceptibility gene for myeloid neoplasm in the RAS pathway are more likely to develop AML; CBL and TP53 germline mutations affect the overall survival of MPN patients.

Incidence and risk factors for second malignancies among patients with myeloproliferative neoplasms.

OBJECTIVE: The clinical characteristics and survival of patients with myeloproliferative neoplasms (MPNs) with secondary cancer were analyzed to explore the possible risk factors for secondary cancer in MPN patients. METHODS: The clinical characteristics of 1060 Chinese patients with MPN were retrospectively analyzed. The Kaplan-Meier method was used to analyze the survival. The Cox multivariate regression model was used to analyze the risk factors for developing secondary cancer in patients with MPNs. RESULTS: The 1060 patients with MPN had a median follow-up of 10 years (range 1-50) and a median age of 55 years (range 21-86), and 497 (45.2%) were male. The proportion of PV, ET, and PMF was 52.2%, 33.5%, and 14.3%, respectively. About 28.1% (298/1060) of 1060 MPN patients died. The median survival times of the PV, ET, and PMF groups were 20, 24, and 12 years, respectively (p < 0.0001). In age- and sex-matched healthy Chinese patients, the standardized incidence ratio (SIR) value of developing secondary cancer in MPN patients was 6.41 (95% CI: 4.90-9.48). The median survival time was 14 years in the MPN with secondary cancer group. The Cox multivariate analysis showed that age ≥ 65 years (p < 0.0001, HR = 5.027, 95% CI [2.823, 8.952]), MF-1 (p = 0.001, HR = 2.887, 95% CI [1.503, 5.545]) were risk factors for developing secondary cancer. CONCLUSIONS: The survival of MPN patients with secondary cancer was significantly worse than that of patients without secondary cancer. Compared with normal subjects, MPN patients had a 6.41-fold increased risk of developing secondary cancer, and age ≥ 65 years and MF-1 were risk factors for developing secondary cancer in MPN patients.

Process knowledge graph modeling techniques and application methods for ship heterogeneous models.

In the process design and reuse of marine component products, there are a lot of heterogeneous models, causing the problem that the process knowledge and process design experience contained in them are difficult to express and reuse. Therefore, a process knowledge representation model for ship heterogeneous model is proposed in this paper. Firstly, the multi-element process knowledge graph is constructed, and the heterogeneous ship model is described in a unified way. Then, the multi-strategy ontology mapping method is applied, and the semantic expression between the process knowledge graph and the entity model is realized. Finally, by obtaining implicit semantics based on case-based reasoning and checking the similarity of the matching results, the case knowledge reuse is achieved, to achieve rapid design of the process. This method provides reliable technical support for the design of ship component assembly and welding process, greatly shortens the design cycle, and improves the working efficiency. In addition, taking the double-deck bottom segment of a ship as an example, the process knowledge map of the heterogeneous model is constructed to realize the rapid design of ship process, which shows that the method can effectively acquire the process knowledge in the design case and improve the efficiency and intelligence of knowledge reuse in the process design of the heterogeneous model of a ship.

Bioinformatics analysis of the prognostic biomarkers and predictive accuracy of differentially expressed genes in high-risk multiple myeloma based on Gene Expression Omnibus database mining.

Background: Multiple myeloma (MM) is still an intractable disease for modern clinical system, and more researches are necessary for development of more effective therapeutic strategies. This study attempted to screen and validates the biomarkers in the progression of MM via excavating Gene Expression Omnibus (GEO) database. Identification of a biomarker may help not only facilitate early diagnosis and management but also identify individuals at risk for poor prognosis and development of MM. Methods: The mRNA expression profile of the GSE87900 dataset was analyzed by GEO2R. Using the SangerBox online program, differentially expressed genes (DEGs) in high-risk MM samples were screened with the filter criteria of P<0.05 and |logFC| >1. The SangerBox online analysis tool was used to analyze the volcano plot. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis was performed for DEGs. Twenty patients with high-risk MM and 20 patients with standard-risk MM from Taian City Central Hospital were included. Real-time quantitative polymerase chain reaction (RT-qPCR) was used to verify the selected key genes in MM tissues. Results: A total of 611 DEGs were obtained. GO functional enrichment analysis showed that the DEGs were mainly enriched in the DNA replication process at the biological level, and the top DEGs were CACYBP, PCNA, MCM6, SMC1A, DTL, GINS4, MCM2, CDT1, RRM2, BRCA1, RFC5, MCM4, GINS3, GINS1, MCM10, CDC7, CDAN1, BRIP1, GINS2, CDK1, NFIB, and BARD1. The expression of CDC7 and PCNA was significantly different in high-risk MM and standard-risk MM as determined by RT-qPCR. Receiver operating characteristic (ROC) analysis showed that the areas under the curve predicted by CDC7 and PCNA were 0.900 and 0.8863, respectively, which allowed the identification of CDC7 and PCNA could be a potential biomarker of MM. Kaplan-Meier survival analysis showed that MM patients with high CDC7 and PCNA expression had shorter 2-year overall survival (OS) (P<0.05). Conclusions: CDC7 and PCNA can be used as biomarkers for the prognosis of high-risk MM and evaluate the prognosis of MM patients, which is helpful for guiding the clinical treatment of MM patients.

Thrombosis among 1537 patients with JAK2V617F -mutated myeloproliferative neoplasms: Risk factors and development of a predictive model.

To explore the risk factors of thrombosis in patients with JAK2V617F -mutated myeloproliferative neoplasms (MPNs), a cohort of 1537 Chinese patients with JAK2V617F -mutated MPN was retrospectively analyzed. The Kaplan-Meier method and multivariate Cox analysis were used to study the risk factors of thrombosis in patients with JAK2V617F -mutated MPN. Among the 1537 MPN patients, 931, 468, and 138 had polycythemia vera (PV), essential thrombocythemia (ET), and primary myelofibrosis (PMF), respectively. The median follow-up time was 7 years (range 1-47), and 12.8% of patients (197/1537) died during this period. A total of 16.8% (259/1399) of PV and ET patients had secondary myelofibrosis, and 2.5% (38/1537) of patients developed acute myeloid leukemia (AML). Thrombotic events occurred in 43.9% (675/1537) of patients, among which 91.4% (617/675) were arterial thrombosis and 16.6% (112/675) were venous thrombosis. The number of thrombotic events in PV, ET, and PMF patients was 439 (47.2%), 197 (42.1%) and 39 (28.2%), respectively. The multivariate analysis indicated that age ≥60 years old, HCT ≥48%, at least one cardiovascular risk factor, a history of thrombosis, and JAK2V617F allele burden (V617F%) ≥50% are risk factors for thrombosis in JAK2V617F -mutated MPN. According to the results of the multivariate analysis, a risk model of thrombosis was established and comprised low-risk (0 points), intermediate-risk (1 points) and high-risk (≥2 points) groups, among which the incidence of thrombosis was 9.1%, 33.7% and 72.9%. For elderly patients with JAK2V617F -mutated MPN and a history of thrombosis, reducing the V617F%, controlling HCT and preventing cardiovascular risk factors are necessary measures to prevent thrombosis.