Craniomaxillofacial Bone Segmentation and Landmark Detection Using Semantic Segmentation Networks and an Unbiased Heatmap.

Craniomaxillofacial (CMF) surgery always relies on accurate preoperative planning to assist surgeons, and automatically generating bone structures and digitizing landmarks for CMF preoperative planning is crucial. Since the soft and hard tissues of the CMF regions possess complicated attachment, segmenting the CMF bones and detecting the CMF landmarks are challenging problems. In this study, we proposed a semantic segmentation network to segment the maxilla, mandible, zygoma, zygomatic arch, and frontal bones. Then, we obtained the minimum bounding box around the CMF bones. After cropping, we used the top-down heatmap landmark detection network, similar to the segmentation module, to identify 18 CMF landmarks from the cropping patch. In addition, an unbiased heatmap encoding method was proposed to generate actual landmark coordinates in the heatmap. To overcome quantization effects in the heatmap-based landmark detection networks, the distribution-prior coordinate representation of medical landmarks (DCRML) was proposed to utilize the prior distribution of the encoding heatmap, approximating the accurate landmark coordinates in heatmap decoding by Taylor's theorem. The encoding and decoding method can easily contribute to other existing landmark detection frameworks based on heatmaps; consequently, these approaches can readily benefit without changing model structure. We used prior segmentation knowledge to enhance the semantic information around the landmarks, increasing landmark detection accuracy. The proposed framework was evaluated by 100 healthy persons and 86 patients from multicenter cooperation. The mean Dice score of our proposed segmentation network achieved over 88 %; in particular, the mandible accuracy was approximately 95%. The mean error of landmarks was 1.84 ±1.32 mm.

Automatic implant shape design for minimally invasive repair of pectus excavatum using deep learning and shape registration.

Minimally invasive repair of pectus excavatum (MIRPE) is an effective method for correcting pectus excavatum (PE), a congenital chest wall deformity characterized by concave depression of the sternum. In MIRPE, a long, thin, curved stainless plate (implant) is placed across the thoracic cage to correct the deformity. However, the implant curvature is difficult to accurately determine during the procedure. This implant depends on the surgeon's expert knowledge and experience and lacks objective criteria. Moreover, tedious manual input by surgeons is required to estimate the implant shape. In this study, a novel three-step end-to-end automatic framework is proposed to determine the implant shape during preoperative planning: (1) The deepest depression point (DDP) in the sagittal plane of the patient's CT volume is automatically determined using Sparse R-CNN-R101, and the axial slice containing the point is extracted. (2) Cascade Mask R-CNN-X101 segments the anterior intercostal gristle of the pectus, sternum and rib in the axial slice, and the contour is extracted to generate the PE point set. (3) Robust shape registration is performed to match the PE shape with a healthy thoracic cage, which is then utilized to generate the implant shape. The framework was evaluated on a CT dataset of 90 PE patients and 30 healthy children. The experimental results show that the average error of the DDP extraction was 5.83 mm. The end-to-end output of our framework was compared with surgical outcomes of professional surgeons to clinically validate the effectiveness of our method. The results indicate that the root mean square error (RMSE) between the midline of the real implant and our framework output was less than 2 mm.

Promoter methylation-mediated repression of UNC5 receptors and the associated clinical significance in human colorectal cancer.

BACKGROUND: Deregulated methylation of tumor suppressor genes is a hallmark event in colorectal cancer (CRC) carcinogenesis. UNC5 receptors, down-regulated in various human malignancies due to epigenetic alterations, have been proposed as putative tumor suppressor genes. In this study, we focused on the methylation-mediated inhibition of UNC5 receptors and the associated clinical significance in CRC. METHODS: Methylation and expression analysis was performed in TCGA datasets. And the results were confirmed in vitro in CRC cell lines treated with 5-aza-deoxycytidine. Then, the expression and epigenetic alterations of UNC5 receptors were evaluated in clinical specimens. Moreover, the diagnostic and prognostic values of the methylation alterations were also analyzed. RESULTS: Methylation-mediated repression was observed in UNC5C and UNC5D, but not in UNC5A and UNC5B, which was confirmed in CRC cell lines. Except for UNC5B, significantly elevated methylation was observed in UNC5A, UNC5C, and UNC5D in CRC. The discrimination efficiency of the three receptors was comparable with that of SEPT9. Kaplan-Meier curve survival analysis showed that hypermethylation of UNC5A, UNC5C and UNC5D was associated with poor progression-free and overall survival. Moreover, methylation levels of UNC5C and UNC5D were independent predictors of CRC progression-free (P = 0.001, P = 0.003, respectively) and overall survival (P = 0.008, P = 0.004, respectively). CONCLUSIONS: Hypermethylation of UNC5C and UNC5D mediates the repression and has promising diagnostic and prognostic values in CRC.

Development and validation of a RNA binding protein-associated prognostic model for head and neck squamous cell carcinoma.

Evidence shows that defects in RNA-binding proteins (RBPs) are closely related to the occurrence and development of HNSCC. We obtained 502 tumors and 44 normal samples from the TCGA database, among which 190 differentially expressed RBPs were screened. Finally, a prognostic model containing nine RBPs (CELF2, CPEB1, DDX39B, EIF3L, EZH2, KHDRBS3, RNASE10, RNASE3 and SIDT1) was produced. Further analysis showed that the overall survival rate in the high-risk group was lower than that in the low-risk group. The area under the ROC curve (AUC) in the training and testing groups was significant (3-year AUC, 0.735 vs 0.796; 5-year AUC, 0.821 vs 0.804). In addition, a comprehensive analysis of nine identified RBPs showed that most of them were related to the OS of HNSCC patients, and three of them (CELF2, EZH2, and SIDT1) were differentially expressed in HNSCC and control tissues at the protein level. In addition, our data revealed that the identified RBPs are highly interconnected, with high frequency copy number changes in HNSCC samples. GSEA indicated that the abnormal biological processes related to RNA and the activation of some classical tumor signaling pathways were important driving forces for the development of HNSCC. Our results provide novel insights into the pathogenesis of HNSCC, among which nine RBP markers have potential application value in clinical decision-making and individualized treatment of HNSCC.

Multiprobe Assay for Clinical SEPT9 Methylation Based on the Carbon Dot-Modified Liquid-Exfoliated Graphene Field Effect Transistor with a Potential to Present a Methylation Panorama.

The hypermethylation in the promoter region of the SEPT9 gene is associated with the development of colorectal cancer (CRC). Although its clinical significance for early diagnosis and screening of CRC has been demonstrated, the tedious operations in the conventional DNA methylation (DNAm) detection hinder its wide application. Herein, an electronic method for determining SEPT9 methylation in CRC patients is proposed by using the carbon dot-modified liquid exfoliated graphene field effect transistor (CDs-LEG-FET) as the DNAm sensor, the specifically designed probes to capture the SEPT9 gene and the immunologic recognition to recognize 5-methylcytosine (5mC) positions on the anchored sequences. The identification and nanomorphology of the as-prepared materials and devices are executed first by the characterizations of UV-vis, Raman, atomic force microscopy, Fourier transform infrared spectroscopy, X-ray photoelectron spectroscopy, and electronic measurements. Then, the role of CDs in enhancing DNAm sensitivity of CD-LEG-FET is manifested by comparing it with that of CD-free LEG-FET. Third, the captured SEPT9 genes on CD-LEG-FETs by different probes are evaluated, and the optimized temperature for hybridizing the target ssDNA sequences is determined to be 48 °C. Furthermore, the detection sensitivity for the low-quantity of DNA samples is demonstrated to be as low as 2 ng. Finally, the methylation degree of the tumor and corresponding noncancerous tissue DNA samples were examined by the proposed electric method and methylight assay in parallel. The diagnostic value of the electrical assay is confirmed by using the receiver operating characteristic curves; meanwhile, the superiority of the CD-LEG-FET platform is found to present a methylation panorama of the target gene.

TGFß regulates NK1R-Tr to affect the proliferation and apoptosis of breast cancer cells.

OBJECTIVES: TGFß promotes cancer aggressiveness in advanced stages. NK1R-Tr expression in advanced breast cancer has a pro-carcinogenic effect. In this study, we aimed to investigate the effect of the association of TGFß with NK1R-Tr expression on the proliferation and apoptosis of breast cancer cells. METHODS: Immunohistochemical staining and Western blot analysis were used to detect TGFß and NK1R-Tr in breast cancer and paracancerous tissue samples. MDA-MB-231 and BT549 cells were stimulated with TGFß after NK1R knockdown or treated with the NK1R antagonist aprepitant, and the effects of TGFß and NK1R-Tr on proliferation and apoptosis were detected by CCK-8, colony formation and flow cytometry assays. In vivo xenograft models were used to further verify the effects of NK1R-Tr and TGFß. The regulatory effects of Smad4 on NK1R promoter activity were confirmed by ChIP and dual-luciferase reporter assays. RESULTS: The expression levels of TGFß and NK1R-Tr were higher in breast cancer tissues than in adjacent tissues and were positively correlated in human breast cancer tissues. NK1R knockdown or aprepitant treatment in MDA-MB-231 and BT549 cells attenuated the effects of TGFß on cell proliferation. The proportion of cells in G2/M phase significantly increased, the expression of cyclin B1 decreased, and the expression of P21 increased; these effects were weakened by TGFß treatment. Apoptosis in breast cancer cells was significantly increased. In vivo xenograft models were used to further verify that NK1R-Tr and TGFß promoted tumour growth. After TGFß treatment, the binding capacity of Smad4 to the NK1R promoter, as well as luciferase activity, was enhanced. CONCLUSIONS: The expression levels of TGFß and NK1R-Tr were higher in breast cancer tissues than in normal tissues, and both were correlated with a poor patient prognosis. TGFß and NK1R-Tr promoted cell proliferation and inhibited apoptosis, and TGFß regulated the expression of NK1R-Tr via Smad4.