Diagnosis of cervical lymph node metastasis with thyroid carcinoma by deep learning application to CT images.

Introduction: The incidence of thyroid diseases has increased in recent years, and cervical lymph node metastasis (LNM) is considered an important risk factor for locoregional recurrence. This study aims to develop a deep learning-based computer-aided diagnosis (CAD) method to diagnose cervical LNM with thyroid carcinoma on computed tomography (CT) images. Methods: A new deep learning framework guided by the analysis of CT data for automated detection and classification of LNs on CT images is proposed. The presented CAD system consists of two stages. First, an improved region-based detection network is designed to learn pyramidal features for detecting small nodes at different feature scales. The region proposals are constrained by the prior knowledge of the size and shape distributions of real nodes. Then, a residual network with an attention module is proposed to perform the classification of LNs. The attention module helps to classify LNs in the fine-grained domain, improving the whole classification network performance. Results: A total of 574 axial CT images (including 676 lymph nodes: 103 benign and 573 malignant lymph nodes) were retrieved from 196 patients who underwent CT for surgical planning. For detection, the data set was randomly subdivided into a training set (70%) and a testing set (30%), where each CT image was expanded to 20 images by rotation, mirror image, changing brightness, and Gaussian noise. The extended data set included 11,480 CT images. The proposed detection method outperformed three other detection architectures (average precision of 80.3%). For classification, ROI of lymph node metastasis labeled by radiologists were used to train the classification network. The 676 lymph nodes were randomly divided into 70% of the training set (73 benign and 401 malignant lymph nodes) and 30% of the test set (30 benign and 172 malignant lymph nodes). The classification method showed superior performance over other state-of-the-art methods with an accuracy of 96%, true positive and negative rates of 98.8 and 80%, respectively. It outperformed radiologists with an area under the curve of 0.894. Discussion: The extensive experiments verify the high efficiency of the proposed method. It is considered instrumental in a clinical setting to diagnose cervical LNM with thyroid carcinoma using preoperative CT images. The future research can consider adding radiologists' experience and domain knowledge into the deep-learning based CAD method to make it more clinically significant. Conclusion: The extensive experiments verify the high efficiency of the proposed method. It is considered instrumental in a clinical setting to diagnose cervical LNM with thyroid carcinoma using preoperative CT images.

Comparison of diffusion-weighted imaging mono-exponential mode with diffusion kurtosis imaging for predicting pathological grades of clear cell renal cell carcinoma.

PURPOSE: To evaluate the role of diffusion kurtosis imaging (DKI1) in the characterization of clear cell renal cell carcinoma (ccRCC2) compared with standard diffusion-weighted imaging (DWI3). METHODS: 89 patients with histologically proven ccRCC were evaluated by DKI and DWI on a 3-T scanner. All ccRCCs were classified as grade 1-4 according to the Fuhrman classification system. The apparent diffusion coefficient (ADC4), fractional anisotropy (FA5), mean diffusivity (MD6), mean kurtosis (MK7), axial kurtosis (Ka8) and radial kurtosis (Kr9) values were recorded. The differences in DWI and DKI parameters were evaluated by independent-sample t test and a receiver operating characteristic (ROC10) analysis was performed. The DeLong test was performed to compare the ROCs. RESULTS: Compared to normal renal parenchyma, ADC and MD values of ccRCC decreased and MK, Ka, and Kr values increased (p < 0.05). ADC and MD values of ccRCC decreased with the increase in pathological grade, while MK, Ka, and Kr values were increased (p < 0.05). ADC could discriminate G1 vs G3, G1 vs G4, G2 vs G3, G2 vs G4, and G3 vs G4 (p < 0.05) except for G1 vs G2 (p > 0.05). Ka and Kr could discriminate G1 vs G2, G1 vs G3, G1 vs G4, G2 vs G4, and G3 vs G4 (p < 0.05) except for G2 vs G3 (p > 0.05). MD and MK could discriminate G1 vs G2, G1 vs G3, G1 vs G4, G2 vs G3, G2 vs G4, and G3 vs G4 (p < 0.05). The AUC of MK was the highest. The DeLong test showed that there were significant differences regarding ROCs between ADC/MK, ADC/Ka, ADC/Kr in grading G1/G2, and ADC/MK, MK/Ka in grading G3/G4 (p < 0.05). CONCLUSION: DKI was superior compared to the mono-exponential mode of DWI in grading ccRCC.

Effect and mechanism of lentivirus-mediated silencing of TPX2 gene on proliferation and apoptosis of human hepatoma cells.

This study aimed to investigate the role and mechanism of action of targeting protein for Xklp2 (TPX2) in liver cancer, we compared TPX messenger RNA (mRNA) expression in liver cancer tissue samples and adjacent normal liver tissue samples as well as in human liver cancer cell lines and nonmalignant cell line by quantitative reverse transcription polymerase chain reaction (qRT-PCR). TPX2 gene was silenced in HepG2 cells by transfection with the lentiviral vector expressing TPX2-targeting short hairpin RNA (shRNA), and the knockdown efficiency was evaluated by RT-qPCR. Cell proliferation, apoptosis as well as protein level of c-Myc, cyclin D1, caspase-3, phosphorylated glycogen synthase kinase-3ß (p-GSK-3ß), and ß-catenin in HepG2 cells were evaluated before and after the TPX2 knockdown. Wnt/ß-catenin signaling pathway was inhibited by treatment with 20 µM of XAV-939 or activated by treatment with 20 mM of LiCl. We found that TPX2 mRNA level was significantly increased in liver cancer tissue samples and cell lines comparing to noncancerous counterparts (P < 0.05). TPX2 knockdown significantly reduces TPX2 expression (P < 0.01), cell proliferation (P < 0.05), protein level of c-Myc and cyclin D1 (P < 0.01), activation of Wnt/ß-catenin signaling in HepG2 cells (P < 0.01) while increasing cell apoptosis (P < 0.01). Treatment with XAV-939 significantly reduced HepG2 cell proliferation (P < 0.05) while increasing cell apoptosis (P < 0.01). Treatment with LiCl significantly attenuated the antiproliferative and apoptosis-promoting effect of TPX2 knockdown on HepG2 cells (P < 0.05). Lentivirus-mediated silencing of TPX2 gene could inhibit proliferation and induce apoptosis in hepatoma cells by inhibiting Wnt signaling pathway and regulating cyclin and apoptosis-related proteins.

Normal development of sacrococcygeal centrum ossification centers in the fetal spine: a postmortem magnetic resonance imaging study.

PURPOSE: To describe the temporal pattern of the appearance of the S1-Co1 centrum ossification centers (COCs) and provide reference data for the S1-S5 COCs and sacral length at various gestational ages (GAs). METHODS: Postmortem magnetic resonance imaging (MRI) was performed on 71 fetuses (GA, 17-42 weeks) using the 3D dual-echo steady-state with water excitation T2 sequence in the sagittal plane. To confirm the reliability of this sequence, the MRI data were compared with the CT and histologic data obtained from two fetuses (GAs, 21 and 30 weeks). The presence or absence of each sacrococcygeal COC was recorded. Sacral length and S1-S5 COC height, sagittal diameter, transverse diameter, cross-sectional area, and volume were measured. RESULTS: All fetuses showed S1-S3 COCs by 17 weeks, S4 COCs by 19 weeks, and S5 COCs by 28 weeks. The S4, S5, and Co-1 COCs were visualized in 70 (98.59%), 51 (71.83%), and 21 (29.58%) fetuses, respectively. Sacral length, height, sagittal, and transverse diameters increased linearly, while cross-sectional area and volume increased exponentially with advancing GA. Mean growth rates of the sagittal and transverse diameters, cross-sectional area, and volume, but not of height, significantly differed among the S1-S5 vertebrae. CONCLUSION: We have presented the timing of appearance of individual sacrococcygeal COCs and the age-specific, normative MRI reference values for sacral length and the morphometric parameters of the sacral COCs, which are of clinical importance in the diagnosis of congenital sacral abnormalities and skeletal dysplasia.

Sequential treatment of superior vena cava syndrome caused by of non-small cell carcinoma lung cancer (NSCLC) with vascular stenting and iodine-125 implantation.

Feasibility and efficacy of sequentially performed endovascular stenting and Iodine-125 brachytherapy for malignant superior vena cava syndrome (SVCS) were evaluated. Thirty-four patients with malignant SVCS caused by NSCLC underwent sequential treatment of endovascular stenting and Iodine-125 brachytherapy. SVCS was diagnosed in all patients by CT images or vena-cavography. Pathology diagnosis was acquired by image guided biopsy. Endovascular stent placement was performed as first-line treatment for symptom relief. CT-guided Iodine-125 seed implantation performed 24hr after stenting. Clinical end points were resolution of symptoms and local efficacy of primary malignancy regression. Symptom relief rate was >90% after 24hr and 97% after 3 months. No migration of seeds or restenosis occurred in any patient. The local efficacy (defined as either partial or complete response) was 53%, 79%, 88% and 74% after 1, 3, 6 and 12 months, respectively. Mean SVCS-free survival time was 305 days (range 120-960 days). Two patients were still alive at the time of this writing, Thirty-one died from progression and one died from acute heart disease. Sequentially performed endovascular stenting and Iodine-125 brachytherapy provides a safe and effective alternative for malignant SVCS caused by NSCLC.