A novel approach for yoga pose estimation based on in-depth analysis of human body joint detection accuracy.

Virtual motion and pose from images and video can be estimated by detecting body joints and their interconnection. The human body has diverse and complicated poses in yoga, making its classification challenging. This study estimates yoga poses from the images using a neural network. Five different yoga poses, viz. downdog, tree, plank, warrior2, and goddess in the form of RGB images are used as the target inputs. The BlazePose model was used to localize the body joints of the yoga poses. It detected a maximum of 33 body joints, referred to as keypoints, covering almost all the body parts. Keypoints achieved from the model are considered as predicted joint locations. True keypoints, as the ground truth body joint for individual yoga poses, are identified manually using the open source image annotation tool named Makesense AI. A detailed analysis of the body joint detection accuracy is proposed in the form of percentage of corrected keypoints (PCK) and percentage of detected joints (PDJ) for individual body parts and individual body joints, respectively. An algorithm is designed to measure PCK and PDJ in which the distance between the predicted joint location and true joint location is calculated. The experiment evaluation suggests that the adopted model obtained 93.9% PCK for the goddess pose. The maximum PCK achieved for the goddess pose, i.e., 93.9%, PDJ evaluation was carried out in the staggering mode where maximum PDJ is obtained as 90% to 100% for almost all the body joints.

Windowed Joint Detection and Decoding with IR-HARQ for Asynchronous SCMA Systems.

To improve the decoding performance of asynchronous sparse code multiple access (SCMA) systems over additive white Gaussian noise (AWGN) channels, this paper proposes a novel windowed joint detection and decoding algorithm for a rate-compatible (RC), LDPC code-based, incremental redundancy (IR) hybrid automatic repeat quest (HARQ) scheme. Since incremental decoding can exchange information iteratively with the detections made at previous consecutive time units, we propose a windowed joint detection and decoding algorithm. The extrinsic information exchanging process is performed between the decoders and the previous w detectors at different consecutive time units. Simulation results show that the sliding-window IR-HARQ scheme for the SCMA system outperforms the original IR-HARQ scheme with a joint detection and decoding algorithm. The throughput of the SCMA system with the proposed IR-HARQ scheme is also improved.

A robust method for approximate visual robot localization in feature-sparse sewer pipes.

Buried sewer pipe networks present many challenges for robot localization systems, which require non-standard solutions due to the unique nature of these environments: they cannot receive signals from global positioning systems (GPS) and can also lack visual features necessary for standard visual odometry algorithms. In this paper, we exploit the fact that pipe joints are equally spaced and develop a robot localization method based on pipe joint detection that operates in one degree-of-freedom along the pipe length. Pipe joints are detected in visual images from an on-board forward facing (electro-optical) camera using a bag-of-keypoints visual categorization algorithm, which is trained offline by unsupervised learning from images of sewer pipe joints. We augment the pipe joint detection algorithm with drift correction using vision-based manhole recognition. We evaluated the approach using real-world data recorded from three sewer pipes (of lengths 30, 50 and 90 m) and benchmarked against a standard method for visual odometry (ORB-SLAM3), which demonstrated that our proposed method operates more robustly and accurately in these feature-sparse pipes: ORB-SLAM3 completely failed on one tested pipe due to a lack of visual features and gave a mean absolute error in localization of approximately 12%-20% on the other pipes (and regularly lost track of features, having to re-initialize multiple times), whilst our method worked successfully on all tested pipes and gave a mean absolute error in localization of approximately 2%-4%. In summary, our results highlight an important trade-off between modern visual odometry algorithms that have potentially high precision and estimate full six degree-of-freedom pose but are potentially fragile in feature sparse pipes, versus simpler, approximate localization methods that operate in one degree-of-freedom along the pipe length that are more robust and can lead to substantial improvements in accuracy.

SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking.

Joint detection and embedding (JDE) methods usually fuse the target motion information and appearance information as the data association matrix, which could fail when the target is briefly lost or blocked in multi-object tracking (MOT). In this paper, we aim to solve this problem by proposing a novel association matrix, the Embedding and GioU (EG) matrix, which combines the embedding cosine distance and GioU distance of objects. To improve the performance of data association, we develop a simple, effective, bottom-up fusion tracker for re-identity features, named SimpleTrack, and propose a new tracking strategy which can mitigate the loss of detection targets. To show the effectiveness of the proposed method, experiments are carried out using five different state-of-the-art JDE-based methods. The results show that by simply replacing the original association matrix with our EG matrix, we can achieve significant improvements in IDF1, HOTA and IDsw metrics, and increase the tracking speed of these methods by around 20%. In addition, our SimpleTrack has the best data association capability among the JDE-based methods, e.g., 61.6 HOTA and 76.3 IDF1, on the test set of MOT17 with 23 FPS running speed on a single GTX2080Ti GPU.

Deep Learning-Based Computer-Aided Diagnosis of Rheumatoid Arthritis with Hand X-ray Images Conforming to Modified Total Sharp/van der Heijde Score.

INTRODUCTION: Rheumatoid arthritis (RA) is a systemic autoimmune disease; early diagnosis and treatment are crucial for its management. Currently, the modified total Sharp score (mTSS) is widely used as a scoring system for RA. The standard screening process for assessing mTSS is tedious and time-consuming. Therefore, developing an efficient mTSS automatic localization and classification system is of urgent need for RA diagnosis. Current research mostly focuses on the classification of finger joints. Due to the insufficient detection ability of the carpal part, these methods cannot cover all the diagnostic needs of mTSS. METHOD: We propose not only an automatic label system leveraging the You Only Look Once (YOLO) model to detect the regions of joints of the two hands in hand X-ray images for preprocessing of joint space narrowing in mTSS, but also a joint classification model depending on the severity of the mTSS-based disease. In the image processing of the data, the window level is used to simulate the processing method of the clinician, the training data of the different carpal and finger bones of human vision are separated and integrated, and the resolution is increased or decreased to observe the changes in the accuracy of the model. RESULTS: Integrated data proved to be beneficial. The mean average precision of the proposed model in joint detection of joint space narrowing reached 0.92, and the precision, recall, and F1 score all reached 0.94 to 0.95. For the joint classification, the average accuracy was 0.88, and the accuracy of severe, mild, and healthy reached 0.91, 0.79, and 0.9, respectively. CONCLUSIONS: The proposed model is feasible and efficient. It could be helpful for subsequent research on computer-aided diagnosis in RA. We suggest that applying the one-hand X-ray imaging protocol can improve the accuracy of mTSS classification model in determining mild disease if it is used in clinical practice.

Lightweight Deep Neural Network for Articulated Joint Detection of Surgical Instrument in Minimally Invasive Surgical Robot.

Vision-based detection and tracking of surgical instrument are attractive because it relies purely on surgical instrument already in the operating scenario. The vision knowledge of the surgical instruments is a crucial piece of topic for surgical task understanding, autonomous robot control and human-robot collaborative surgeries to enhance surgical outcomes. In this work, a novel method has been demonstrated by developing a multitask lightweight deep neural network framework to explore surgical instrument articulated joint detection. The model has an end-to-end architecture with two branches, which share the same high-level visual features provided by a lightweight backbone while holding respective layers targeting for specific tasks. We have designed a novel subnetwork with joint detection branch and an instrument classification branch to sufficiently take advantage of the relatedness of surgical instrument presence detection and surgical instrument articulated joint detection tasks. The lightweight joint detection branch has been employed to efficiently locate the articulated joint position with simultaneously holding low computational cost. Moreover, the surgical instrument classification branch is introduced to boost the performance of joint detection. The two branches are merged to output the articulated joint location with respective instrument type. Extensive validation has been conducted to evaluate the proposed method. The results demonstrate promising performance of our proposed method. The work represents the feasibility to perform real-time surgical instrument articulated joint detection by taking advantage of the components of surgical robot system, contributing to the reference for further surgical intelligence.

Multi-Target Joint Detection; Tracking and Classification Based on Marginal GLMB Filter and Belief Function Theory.

This paper proposes a new solution to multi-target joint detection, tracking and classification based on labeled random finite set (RFS) and belief function theory. A class dependent multi-model marginal generalized labeled multi-Bernoulli (MGLMB) filter is developed to analytically calculate the multi-target number, state estimates and model probabilities. In addition, a two-level classifier based on continuous transferable belief model (cTBM) is designed for target classification. To make full use of the kinematic characteristics for classification, both the dynamic modes and states are considered in the classifier, the model dependent class beliefs are computed on the continuous state feature subspace corresponding to different dynamic modes and then fused. As a result that the uncertainty about the classes is well described for decision, the classification results are more reasonable and robust. Moreover, as the estimation and classification problems are jointly solved, the tracking and classification performance are both improved. In the simulation, a scenario contains multi-target with miss detection and dense clutter is used. The performance of multi-target detection, tracking and classification is better than traditional methods based on Bayesian classifier or single model. Simulation results are illustrated to demonstrate the effectiveness and superiority of the proposed algorithm.

Significance of MUC2 gene methylation detection in pancreatic cancer diagnosis.

PURPOSE: This study was conducted to explore the diagnostic value of MUC2 gene methylation in pancreatic cancer. METHODS: Methylation restriction enzyme digestion (Msp I/Hap II) and polymerase chain reaction (PCR) were performed to detect methylation of the MUC2 gene in fecal and blood specimens from seven study subjects with pancreatic cancer (PC), chronic pancreatitis (CP), or normal controls (CON). Simultaneously, blood CA 19-9 levels were detected as a positive indicator of PC. RESULTS: MUC2 methylation was detected in 50% of PC cell lines. In fecal samples, the MUC2 methylation rate in PC (n = 30) was 43.3%, which was significantly higher than those in CP (n = 8, 0%, P < 0.05) and CON (n = 20, 5.0%, P < 0.05). In blood samples, the MUC2 methylation rate in PC (n = 40) was 52.5%, which was significantly higher than those in CP (n = 15, 0%, P < 0.01) and CON (n = 25, 4.0%, P < 0.01). For PC diagnosis, MUC2 gene methylation in blood samples showed higher specificity and positive predictive value than CA 19-9. The combined detection in the feces and blood showed a 60% MUC2 methylation rate in PC (n = 10), which was higher than those in the CP (n = 5, 0%, P < 0.01) and CON (n = 12, 0%, P < 0.01). CONCLUSIONS: The study can clearly indicate that combined detection of MUC2 gene methylation in the peripheral blood and feces could be used as a new screening and early diagnosis method for pancreatic cancer.

LDPC Coded Massive MIMO Systems.

We design a coded massive multiple-input multiple-output (MIMO) system using low-density parity-check (LDPC) codes and iterative joint detection and decoding (JDD) algorithm employing a low complexity detection. We introduce the factor graph representation of the LDPC coded massive MIMO system, based on which the message updating rule in the JDD is defined. We devise a tool for analyzing extrinsic information transfer (EXIT) characteristics of messages flowing in the JDD and the three-dimensional (3-D) EXIT chart provides a visualization of the JDD behavior. Based on the proposed 3-D EXIT analysis, we design jointly the degree distribution of irregular LDPC codes and the JDD strategy for the coded massive MIMO system. The JDD strategy was determined to achieve a higher error correction capability with a given amount of computational complexity. It was observed that the coded massive MIMO system equipped with the proposed LDPC codes and the proposed JDD strategy has lower bit error rate than conventional LDPC coded massive MIMO systems.

Detection and Tracking of Moving Targets for Thermal Infrared Video Sequences.

The joint detection and tracking of multiple targets from raw thermal infrared (TIR) image observations plays a significant role in the video surveillance field, and it has extensive applied foreground and practical value. In this paper, a novel multiple-target track-before-detect (TBD) method, which is based on background subtraction within the framework of labeled random finite sets (RFS) is presented. First, a background subtraction method based on a random selection strategy is exploited to obtain the foreground probability map from a TIR sequence. Second, in the foreground probability map, the probability of each pixel belonging to a target is calculated by non-overlapping multi-target likelihood. Finally, a δ generalized labeled multi-Bernoulli ( δ -GLMB) filter is employed to produce the states of multi-target along with their labels. Unlike other RFS-based filters, the proposed approach describes the target state by a pixel set instead of a single point. To meet the requirement of factual application, some extra procedures, including pixel sampling and update, target merging and splitting, and new birth target initialization, are incorporated into the algorithm. The experimental results show that the proposed method performs better in multi-target detection than six compared methods. Also, the method is effective for the continuous tracking of multi-targets.

Identification of six serum antigens and autoantibodies for the detection of early stage epithelial ovarian carcinoma by bioinformatics analysis and liquid chip analysis.

The early detection of ovarian cancer is critical for improving the prognosis of patients, but there are currently insufficient tumor biomarkers for early detection owing to their low diagnostic sensitivity and specificity. The aim of the present study was to investigate the use of the serum antigens C-C motif chemokine ligand 18 and C-X-C motif chemokine ligand 1, and autoantibodies C1D, transmembrane 4 L six family member 1, zinc finger protein 675 and fragile X mental retardation 1 autosomal homolog 1, for the early screening of epithelial ovarian cancer (EOC). The expression of these sex genes/proteins in ovarian cancer and normal ovarian tissue was examined, and the potential functions of the six genes/proteins in ovarian cancer were analyzed by bioinformatics. Finally, these data were verified in clinical samples, and the multi-analyte suspension array method was compared with the ELISA method. Taken together, these data indicated that these six genes/proteins may serve as potential biomarkers for the early detection of EOC.

Aspect-Aware Target Detection and Localization by Wireless Sensor Networks.

This paper considers the active detection of a stealth target with aspect dependent reflection (e.g., submarine, aircraft, etc.) using wireless sensor networks (WSNs). When the target is detected, its localization is also of interest. Due to stringent bandwidth and energy constraints, sensor observations are quantized into few-bit data individually and then transmitted to a fusion center (FC), where a generalized likelihood ratio test (GLRT) detector is employed to achieve target detection and maximum likelihood estimation of the target location simultaneously. In this context, we first develop a GLRT detector using one-bit quantized data which is shown to outperform the typical counting rule and the detection scheme based on the scan statistic. We further propose a GLRT detector based on adaptive multi-bit quantization, where the sensor observations are more precisely quantized, and the quantized data can be efficiently transmitted to the FC. The Cramer-Rao lower bound (CRLB) of the estimate of target location is also derived for the GLRT detector. The simulation results show that the proposed GLRT detector with adaptive 2-bit quantization achieves much better performance than the GLRT based on one-bit quantization, at the cost of only a minor increase in communication overhead.

The value of joint detection of sTREM-1 and PCT in the early diagnosis of children with sepsis / 中国医学装备

Objective: To investigate the value of joint detection of soluble triggering receptor expresses on myeloid cells-1(sTREM-1) and procalcitonin (PCT) in the early diagnosis of children with sepsis. Methods: 78 children with sepsis were selected into the sepsis group, 23 children with common infection were selected into the normal infection group. In addition, 25 healthy children selected into the health control group. The levels of sTREM-1, PCT, and C reactive protein (CRP) among the three groups were compared, respectively. And then, the sepsis group were further divided into general sepsis subgroup (32 cases), severe sepsis subgroup (26 cases) and septic shock subgroup (20 cases) according to the degree of sepsis. The levels of sTREM-1, PCT and CRP among the three sepsis subgroups were compared. And the receiver operating characteristic (ROC) curve was adopted to analyze the value that diagnosed children with sepsis by using the three indicators. Results: The levels of sTREM-1, PCT and CRP of sepsis group were significantly higher than those of common infection group and health control group (t=22.071, t=21.508, t=17.870, t=55.167, t=52.070, t=30.359, P<0.05). The differences of sTREM-1 and PCT among various sepsis subgroups were significant (H=22.082, H=39.449, P<0.05), but the difference of CRP level between septic shock subgroup and severe sepsis subgroup was no significant. As the compared result of AUC of ROC of diagnosing sepsis, the AUC of sTREM-1 was maximum (0.88), and its 95% confidence interval (CI) was 0.78-0.98. At the optimum cutoff value of sTREM-1, the sensitivity and specificity were 83.33% and 68%, respectively, and they were higher than those of PCT and CRP, respectively. Besides, the cutoff values of sTREM-1 and PCT were used as standard to carry out joint diagnosis for children with sepsis, and the sensitivity and specificity were 91.03% and 64%, respectively, at this joint diagnosis. Conclusion: The joint detection of sTREM-1 and PCT has higher sensitivity in the early diagnosis of children with sepsis and it has a certain clinical application value.

Mutation Analysis of EGFR,ALK and ROS1 in Tumor Tissues of Patients with Non-Small Cell Lung Cancer in South of China / 现代检验医学杂志

Objective To investigate the characteristics of EGFR,ALK and ROS1 mutations in patients with non-small cell lung cancer (NSCLC) in South of China and its relationship with clinical features.Methods The tumor tissues and corresponding clinical data of 76 NSCLC patients in South of China from November 2016 to June 2017 were collected.The mutations of EGFR,ALK and ROS1 were detected by ARMS assay with Joint detection kit.Meanwhile,the correlation between gene mutation rate and clinical features was analyzed.Results The mutation rate of EGFR was 67.3％ (42/76) in 76 patients with NSCLC in South of China,19 del and L858R mutations were the main mutation types.There was a co-mutation including 19 del and L858R.The positive rate of ALK gene fusion was 17.1％ (13/76),and 4 cases of ALK gene fusion combined with EGFR mutation were detected.The positive rate of ROS1 gene fusion was 1.3％ (1/76),and there was no co-mutation with other genes.Compared with ROS1,EGFR and ALK mutation rate was higher,the difference was statistically significant (x2 =54.515,P =0.000;x2 =11.329,P =0.001).The mutation rate of EGFR in non-smoking NSCLC patients was significantly higher than that in smokers (x2 =4.578,P=0.032),while the mutation rate of ALK and ROS1 was not statistically significant (x2=0.000,P＞0.05).There was no statistically significant difference in EGFR,ALK and ROS1 gene mutation rates among NSCLC patients of different age,sex and histology (x2 =0.000 ～ 2.219,P＞ 0.05).Conclusion EGFR,ALK and ROS1 gene mutations can be seen in patients with NSCLC in South China,in which EGFR and ALK gene mutation rate is higher.

Plasma HSP90 Alpha Testing Clinical Application Value in the Diagnosis of Lung Cancer Researc / 现代检验医学杂志

Objective To study the plasma heat shock protein 90 alpha (HSP90 α) in the diagnosis of lung cancer.Methods Chose 166 cases of patients with lung cancer,lung cancer group,the same physical examination of 20 cases of normal (control group),application of plasma concentration of HSP90 α enzyme-linked immunoassay detection,chemiluminescence detection of CEA,NSE,SCC and CYFRA21-1,of the two groups of data by t test statistical analysis,compared two groups of plasma HSP90 α level.With plasma HSP90 alpha was greater than 86 ng/ml for the critical value,calculation of HSP90 α testing sensitivity.Patients with lung cancer by histopathologic classification,compare different tumor classification in patients with plasma HSP90 α level.Used Pearman's correlation method to analyse the relationship of HSP90 α,CEA and NSE in patients with lung cancer,between SCC and CYFRA21-1 and used ROC curve to evaluate HSP90 α efficiency to the diagnosis of lung cancer.Results ① In lung cancer group and control group in the indicators HSP90 α,CEA,NSE,SCC and respectively CYFRA21-1 190.33±105.86 vs 41.02±19.73 ng/ml,8.68±5.02 vs 4.02±1.36 ng/ml,36.32±13.16 vs 8.32 ±3.96 ng/ml,6.21±1.62 vs 1.23±0.64 ng/ml,10.63±4.33 vs 3.02±1.66 ng/ml.Compared with control group (t=10.48,8.66,12.36,9.52,15.36,P＜0.01),the difference was statistically significant.② For biological reference range (HSP90 α:0～86 ng/ml,CEA 1.0～5 ng/ml,NSE:1.0～17.5 ng/ml,SCC:0.2～1.6 ng/ml,CYFRA21-1:1.0～2.6 ng/ ml) as the standard in lung cancer group,HSP90 α increased 73.49 ％,CEA increased 19.27 ％,NSE increased 19.27 ％,CYFRA21-1 (21.68％) and SCC increased 29.51％.③ Patients with lung cancer by histopathologic classification,different concentration of tumor classification HSP90 α was no difference (P＞0.05).④Spearman rank correlation analysis showed that HSP90 α levels were positively correlated with CYFRA21-1 (r,=0.44,P＜0.01).The difference was statistically significant (F=14.98,P =0.00).HSP90 α and CEA,NSE,SCC had no relevance.⑤ HSP90 α and CEA,NSE,SCC,CYFRA21-1 the area under the ROC curve (AUC) in the diagnosis of lung cancer were:0.961,0.562,0.731,0.465 and 0.632 best cutoff value were 89.3 ng/ml,6.32 ng/ml,18.63 ng/ml,1.93 ng/ml and 2.36 ng/ml.Sensitivity of 73.49％,52.3％,73.49％,59.6％ and 62.1％,specific degrees respectively.Accuracy of 98.6％,46.3％,66.3％,98.6％ and 46.3％,respectively,88.4％,80.3％,86.9％,87.2％ and 89.2％ of the five joint,the sensitivity of diagnosis of lung cancer and specific degrees respectively 100％ and 75％.Conclusion Using ROC curve analysis showed that HSP90 α plays an auxiliary role in diagnosis of lung cancer,CEA,NSE,CYFRA21-1 and SCC can significantly increase the detection rate of lung cancer.

Clinical Value of Serum GPDA Associated Tumor Markers for Early Diagnosis of Gastric Cancer / 现代检验医学杂志

Objective To investigate the clinical value of serum glycyl-proline dipeptidyl aminopeptidase(GPDA)combined with carcino-embryonic antigen (CEA),carbohydrate antigen724 (CA724),carbohydrate antigen242 (CA242) in the early diagnosis of gastric cancer.Methods Collected in Changan hospital in patients with gastric cancer and atrophic gastritis patients and healthy subjects 60 cases,by TBA-120FR biochemical analyzer glycyl-proline dipeptidyl aminopeptidase (GPDA),chemiluminescence analyzer to detect the levels of serum CEA,CA724 and CA242,analysis of single detection and joint detection and the differences between the positive rate and sensitivity.Results The detection of GPDA in gastric cancer group was significantly lower than that in atrophic gastritis group and healthy control group,the difference was statistically significant (F=69.532,P=0.000).The results of CEA,CA724 and CA242 in gastric cancer group were higher than those in atrophic gastritis group and healthy control group,the difference was statistically significant (CEA:F=59.926,P=0.001;CA724:F=51.056,P =0.001;CA242:F =72.613,P =0.000).Serum GPDA,CEA,CA724 and CA242 single detection positive rate were 70 ％,45 ％,61.7 ％ and 50 ％.Tumor markers CEA,CA724,CA242 positive rate of three joint detection was 75％.Serum GPDA and tumor markers of CEA,the positive rate of CA724 and CA242 combined detection of four was 86.7％.The positive rate of three and higher than that of single detection,the difference was statistically significant (F=49.635,P=0.003).Serum GPDA,CEA,CA724 and CA242 single detection sensitivity was 70.2 ％,50.2 ％,67.3 ％ and 53.2％.Tumor markers CEA,CA724,CA242 three joint detection sensitivity was 85.6％.Serum GPDA and tumor markers CEA,CA724 and CA242 four joint detection sensitivity was 90.3％.The sensitivity was higher than the three items and the individual tests,and the difference was statistically significant (F=52.016,P =0.001).Conclusion GPDA joint CEA,CA724 and CA242 tumor markers detection can improve the positive rate and sensitivity in early diagnosis of gastric cancer,but it will not reduce the diagnostic specificity,the clinical diagnosis of early gastric cancer has important significance and value.

Clinical value of joint detection of six tumor markers in patients with colorectal cancer / 中国综合临床

Objective To investigate the clinical value of joint detection of six tumor markers in patients with colorectal cancer. Methods Eighty?six patients with colorectal cancer were included in the study group,86 healthy subjects were selected as the control group at the same period. The difference of tumor markers in different groups,tumor stages and prognosis were compared. Results The levels of carcinoembryonic antigen (CEA),carbohydrate antigen 19?9 (CA19?9),carbohydrate antigen 242 (CA242),carbohydrate antigen 72?4 ( CA72?4) , carbohydrate antigen 125 ( CA125 ) and carbohydrate antigen 50 ( CA50 ) in study group were significantly higher than those in the control group (CEA: (22. 5±6. 2)μg/L vs. (2. 2±1. 0)μg/L;CA19?9:(95. 7±27. 3) U/ml vs. (17. 1±9. 5) U/ml;CA242:(29. 5±8. 3) U/ml vs. (6. 0±2. 7) U/ml;CA72?4:(21. 6 ±5. 1) U/ml vs. (3. 6±1. 2) U/ml;CA125:(95. 4±32. 8) U/ml vs. (18. 9±8. 4) U/ml;CA50:(51. 8±20. 6)μg/L vs. (8. 3±3. 7)μg/L,t=29. 98,25. 22,24. 97,31. 86,20. 95,19. 27,P<0. 05). Among the single index detections,the sensitivity and negative predictive value of CA72?4 were the highest ( 61. 6%, 68. 3%) , the specificity of CA19?9 was the highest( 91. 9%) ,the positive predictive value of CEA was the highest ( 80. 4%) . The sensitivity,positive predictive value and negative predictive value of the joint detection were all higher than those in each single index detection (80. 3%,87. 3%,74. 1%). The levels of CEA,CA19?9,CA242,CA72?4, CA125 and CA50 in patients with stage III and IV were significantly higher than those in patients with stageⅠandⅡ(CEA:(32. 7±7. 1)μg/L vs. (15. 9±4. 4)μg/L;CA19?9:(127. 8±33. 7) U/ml vs. (52. 5±13. 8) U/ml;CA242:(40. 3±12. 7) U/ml vs. (23. 5±8. 6) U/ml;CA72?4:(37. 6±10. 2) U/ml vs. (13. 6±4. 1) U/ml;CA125:(128. 9±38. 4) U/ml vs. (59. 7±12. 8) U/ml;CA50:(88. 3±23. 7)μg/L vs. (41. 8±15. 6)μg/L,t=13. 04,13. 32,7. 11,14. 06,10. 99,10. 64,P<0. 05) . The levels of CEA,CA19?9,CA242,CA72?4,CA125 and CA50 in the recurrent metastasis group were significantly higher than those in the non?recurrent metastasis group ( CEA:( 37. 7 ± 8. 6 ) μg/L vs. ( 3. 8 ± 1. 7 ) μg/L;CA19?9:( 110. 5 ± 29. 4 ) U/ml vs. ( 25. 5 ± 13. 8 ) U/ml;CA242:( 33. 6 ± 10. 3 ) U/ml vs. ( 15. 5 ± 6. 6 ) U/ml;CA72?4:( 33. 1 ± 15. 3 ) U/ml vs. ( 9. 3 ± 3. 0 ) U/ml;CA125:(113. 4±31. 7) U/ml vs. (28. 7±7. 8) U/ml;CA50:(55. 4±14. 6)μg/L vs. (16. 8±9. 6)μg/L,t=29. 04,18. 31,9. 86,11. 47,19. 28,14. 65,P<0. 05) . Conclusion The joint detection of six markers can further improve the sensitivity, positive predictive value and negative predictive value of diagnosis, and can provide a more reliable basis for the auxiliary diagnosis of colorectal cancer.

Multi-Target Joint Detection and Estimation Error Bound for the Sensor with Clutter and Missed Detection.

The error bound is a typical measure of the limiting performance of all filters for the given sensor measurement setting. This is of practical importance in guiding the design and management of sensors to improve target tracking performance. Within the random finite set (RFS) framework, an error bound for joint detection and estimation (JDE) of multiple targets using a single sensor with clutter and missed detection is developed by using multi-Bernoulli or Poisson approximation to multi-target Bayes recursion. Here, JDE refers to jointly estimating the number and states of targets from a sequence of sensor measurements. In order to obtain the results of this paper, all detectors and estimators are restricted to maximum a posteriori (MAP) detectors and unbiased estimators, and the second-order optimal sub-pattern assignment (OSPA) distance is used to measure the error metric between the true and estimated state sets. The simulation results show that clutter density and detection probability have significant impact on the error bound, and the effectiveness of the proposed bound is verified by indicating the performance limitations of the single-sensor probability hypothesis density (PHD) and cardinalized PHD (CPHD) filters for various clutter densities and detection probabilities.

CLINICAL VALUE OF CA125, CA153, HE4 JOINT DETECTION IN DIAGNOSIS OF GYNE-COLOGICAL MALIGNANCIES / 现代医院

Objective To investigate the clinical value of CA125, CA153, HE4 joint detection in diagnosis of gynecological malignancies.Methods 70 cases of gynecological malignancies were selected from our hospital in 2013, 72 cases of benign gynecological diseases selected in the same period, and 70 healthy controls were selected. The expression levels of CA125, CA153 and HE4 were detected and statistically analyzed.Results The positive rate of serum CA125 in the gynecological malignancies group was higher than that in the benign gynecological disease group (p <0.05).The positive rate of serum HE4 in the gynecological malignancies group was higher than that in the benign gynecological disease group (p <0.01).The positive rate of CA125, CA153, HE4 joint detection in the gy-necological malignancies group (up to 72.9%) was also significantly higher than that in the benign gynecological dis-ease group (p <0.01).Conclusion is a single tumor marker with the highest sensitivity and specificity for diagno-sis of gynecological malignancies.CA125, CA153, HE4 joint detection can improve the positive rate of diagnosis of gynecological malignancies.