An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images.

Medical image registration is an essential technique to achieve spatial consistency geometric positions of different medical images obtained from single- or multi-sensor, such as computed tomography (CT), magnetic resonance (MR), and ultrasound (US) images. In this paper, an improved unsupervised learning-based framework is proposed for multi-organ registration on 3D abdominal CT images. First, the explored coarse-to-fine recursive cascaded network (RCN) modules are embedded into a basic U-net framework to achieve more accurate multi-organ registration results from 3D abdominal CT images. Then, a topology-preserving loss is added in the total loss function to avoid a distortion of the predicted transformation field. Four public databases are selected to validate the registration performances of the proposed method. The experimental results show that the proposed method is superior to some existing traditional and deep learning-based methods and is promising to meet the real-time and high-precision clinical registration requirements of 3D abdominal CT images.

Association of miR-502-binding site single nucleotide polymorphism in the 3'-untranslated region of SET8 and TP53 codon 72 polymorphism with non-small cell lung cancer in Chinese population.

The objective of this study was to identify whether the miR-502-binding site single nucleotide polymorphism (SNP) in the 3'-untranslated region (3'-UTR) of set domain-containing protein 8 (SET8) and the tumor protein p53 (TP53) codon 72 polymorphism were associated with the risk for non-small cell lung cancer (NSCLC), either independently or jointly, among Chinese people from southern Han. The genotypes of SET8 and TP53 codon 72 polymorphisms of peripheral blood DNA were detected using polymerase chain reaction-restriction fragment length polymorphism and direct DNA sequencing in a case-control study on 164 NSCLC cases and 199 controls. The SET8 TT (odds ratio, OR = 2.173, 95% confidence interval, CI = 1.0454.517) or TP53 GG (OR = 2.579, 95% CI = 1.366-4.870) genotype was associated with an increased risk of NSCLC by comparing with the SET8 CC or TP53 CC genotype, respectively. Similar results were obtained in SET8 recessive model (OR = 2.074, 95% CI = 1.019-4.221, P < 0.05), and the dominant and recessive model of TP53 codon 72 were performed, respectively (OR = 1.809, 95% CI = 1.159-2.825, P < 0.05; OR = 1.933, 95% CI = 1.096-3.409, P < 0.05). In addition, interaction between the SET8 and TP53 polymorphisms increased the risk of NSCLC in a multiply manner, with the OR being 3.032 (95%CI = 1.580-5.816) for subjects carrying both SET8 TT and TP53 GG genotypes. Therefore, the miR-502-binding site SNP in the 3'-UTR of SET8 and the TP53 codon 72 polymorphism may be markers of genetic susceptibility to NSCLC in Chinese population, and there is a possible gene-gene interaction in the incidence of NSCLC.

Association of p73 G4C14-A4T14 and p53 codon 72 polymorphism with cervical cancer in Chinese population.

Background: Cervical cancer is known to be the fourth most common cancer among women globally. In various factors, genetic factors have been considered as one major risk factor for cervical cancer. The research of genetic susceptibility to cervical cancer can be greatly helpful in studying the complex mechanism. This study was conducted to identify whether polymorphic variants of p73 G4C14-A4T14 and tumor protein p53 (p53) codon 72, either independently or jointly, might be associated with the risk of cervical cancer. Methods: The genotypes of p73 G4C14-A4T14 and p53 codon 72 polymorphisms of peripheral blood DNA from 190 cervical cancer patients and 210 controls were investigated using polymerase chain reaction with confronting two-pair primers and polymerase chain reaction-restriction fragment length polymorphism, respectively. Results: The frequency of p73 G4C14-A4T14 AT/AT (P = 0.013) or p53 codon 72 GG (P = 0.026) genotype was associated with an increased risk of cervical cancer by comparing with the p73 G4C14-A4T14 GC/GC or p53 codon 72 CC genotype, respectively. In addition, the interaction between the p73 G4C14-A4T14 and p53 codon 72 polymorphisms increased the risk of cervical cancer in a multiply manner, with the odds ratio being 3.692 (95% confidence interval =2.106-6.473) for subjects carrying both p73 G4C14-A4T14 GC/AT+AT/AT and p53 codon 72 GG genotypes. Conclusion: These results suggest that there is a statistical difference between p73 and p53 gene polymorphism and the risk of cervical cancer in Chinese women, and there is a potential gene-gene interaction in the incidence of cervical cancer.

An Abdominal Registration Technology for Integration of Nanomaterial Imaging-Aided Diagnosis and Treatment.

Image registration technology is a key technology used in the process of nanomaterial imaging-aided diagnosis and targeted therapy effect monitoring for abdominal diseases. Recently, the deep-learning based methods have been increasingly used for large-scale medical image registration, because their iteration is much less than those of traditional ones. In this paper, a coarse-to-fine unsupervised learning-based three-dimensional (3D) abdominal CT image registration method is presented. Firstly, an affine transformation was used as an initial step to deal with large deformation between two images. Secondly, an unsupervised total loss function containing similarity, smoothness, and topology preservation measures was proposed to achieve better registration performances during convolutional neural network (CNN) training and testing. The experimental results demonstrated that the proposed method severally obtains the average MSE, PSNR, and SSIM values of 0.0055, 22.7950, and 0.8241, which outperformed some existing traditional and unsupervised learning-based methods. Moreover, our method can register 3D abdominal CT images with shortest time and is expected to become a real-time method for clinical application.

Association between the p73 gene G4C14-to-A4T14 single nucleotide polymorphism and risk of cervical cancer by high resolution melting and PCR with confronting two-pair primers in a Chinese population.

As a member of the p53 gene family, the p73 gene can affect an individual's susceptibility to cancer through a p53-like manner. DNA sequence variation in the p73 gene has been reported to be associated with cancer risk. The present study aimed to identify whether the p73 gene G4C14-to-A4T14 single nucleotide polymorphism (SNP) is associated with risk of cervical cancer in a Chinese population. The p73 G4C14-to-A4T14 polymorphism was genotyped in 175 cervical cancer and 189 healthy control peripheral blood DNA samples using high resolution melting, polymerase chain reaction with confronting two-pair primers and direct DNA sequencing. The results demonstrated that carriers of the AT/AT genotype were associated with a significantly increased risk of cervical cancer (P=0.042; χ2=4.122; odds ratio = 2.241; 95% confidence interval = 1.013-4.956) compared with the GC/GC genotype carriers. In addition, there was a significant association between p73 genotypes and tumor size in patients with cervical cancer (P=0.014; χ2=8.607). However, no association was identified between p73 genotypes and tumor stage, histological type or lymph node metastasis in patients with cervical cancer. These results suggest that the p73 G4C14-to-A4T14 SNP may function as a marker of genetic susceptibility to cervical cancer in the Chinese population.

Association of a miR-502-binding site single nucleotide polymorphism in the 3'-untranslated region of SET8 and the TP53 codon 72 polymorphism with cervical cancer in the Chinese population.

OBJECTIVE: This study was conducted to identify whether polymorphic variants of set domain-containing protein 8 (SET8) and tumor protein p53 (TP53) codon 72, either independently or jointly, might be associated with increased risk for cervical cancer. METHODS: We genotyped SET8 and TP53 codon 72 polymorphisms of peripheral blood DNA from 114 cervical cancer patients and 200 controls using the polymerase chain reaction- restriction fragment length polymorphism (PCR-RFLP) and direct DNA sequencing. RESULTS: The frequency of SET8 CC (odds ratios (OR) = 2.717, 95% CI=1.436-5.141) or TP53 GG (OR=2.168, 95% CI=1.149-4.089) genotype was associated with an increased risk of cervical cancer on comparison with the SET8 TT or TP53 CC genotypes, respectively. In additional, interaction between the SET8 and TP53 polymorphisms increased the risk of cervical cancer in a synergistic manner, with the OR being 9.913 (95% CI=2.028-48.459) for subjects carrying both SET8 CC and TP53 GG genotypes. CONCLUSION: These data suggest that there are significant associations between the miR-502-binding site SNP in the 3'-UTR of SET8 and the TP53 codon 72 polymorphism with cervical cancer in Chinese, and there is a gene-gene interaction.