Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion.

To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition.

A preliminary investigation of re-evaluating the irradiation dose in hepatocellular carcinoma radiotherapy applying 4D CT and deformable registration.

PURPOSE: To investigate the effect of breathing motion on dose distribution for hepatocellular carcinoma (HCC) patients using four-dimensional (4D) CT and deformable registration. METHODS: Fifty HCC patients who were going to receive radiotherapy were enrolled in this study. All patients had been treated with transarterial chemoembolization beforehand. Three-dimensional (3D) and 4D CT scans in free breathing were acquired sequentially. Volumetric modulated arc therapy (VMAT) was planned on the 3D CT images and maximum intensity projection (MIP) images. Thus, the 3D dose (Dose-3D ) and MIP dose (Dose-MIP ) were obtained, respectively. Then, the Dose-3D and Dose-MIP were recalculated on 10 phases of 4D CT images, respectively, in which the end-inhale and end-exhale phase doses were defined as Dose-3D-EI , Dose-3D-EE , Dose-MIP-EI , and Dose-MIP-EE . The 4D dose (Dose-4D-3D and Dose-4D-MIP ) were obtained by deforming 10 phase doses to the end-exhale CT to accumulate. The dosimetric difference in Dose-3D , Dose-EI3D , Dose-EE3D , Dose-4D-3D , Dose-MIP , Dose-EIMIP , Dose-EEMIP , and Dose-4D-MIP were compared to evaluate the motion effect on dose delivery to the planning target volume (PTV) and normal liver. RESULTS: Compared with Dose-3D , PTV D99 in Dose-EI3D , Dose-EE3D and Dose-4D-3D decreased by an average of 6.02%, 1.32%, 2.43%, respectively (P < 0.05); while PTV D95 decreased by an average of 3.34%, 1.51%, 1.93%, respectively (P < 0.05). However, CI and HI of the PTV in Dose-3D was superior to the other three distributions (P < 0.05). There was no significant differences for the PTV between Dose-EI and Dose-EE , and between the two extreme phase doses and Dose-4D (P> 0.05). Negligible difference was observed for normal liver in all dose distributions (P> 0.05). CONCLUSIONS: Four-dimensional dose calculations potentially ensure target volume coverage when breathing motion may affect the dose distribution. Dose escalation can be considered to improve the local control of HCC on the basis of accurately predicting the probability of radiation-induced liver disease.

[Comparison of the whole breast target volume delineated according to surface marks, palpation and glandular tissue on CT images after breast-conserving surgery].

OBJECTIVE: To compare the methods of delineating the whole breast target volume based on surface marks, palpation and glandular tissue on CT images, and to explore the contouring criteria after breast-conserving surgery. METHODS: In 15 patients with breast cancer after breast-conserving surgery, the whole breast target was delineated in 3D CT simulation images each by three different methods. The target volume delineated according to anatomical marks were named CTVan, according to breast palpation named CTVpa, and according to glandular mammary tissue showing by CT images named CTVgl. The volumes of CTVan, CTVpa and CTVgl, and the degree of inclusion (DI) and conformal index (CI) between the targets were measured. RESULTS: The mean volumes of CTVan, CTVpa and CTVgl were (792.23 ± 282.25) cm(3), (618.33 ± 295.90) cm(3) and (196.83 ± 117.62) cm(3), respectively. The differences among the three methods were statistically significant (P < 0.001). The difference between CTVan and CTVpa had no statistical significance (P = 0.08), and both the differences between CTVan and CTVgl, and between CTVpa and CTVgl had statistical significance (both P < 0.001). The CI between CTVan and CTVpa (0.644 ± 0.122) was significantly larger than the CI between CTVan and CTVgl (0.264 ± 0.108), and the CI between CTVpa and CTVgl (0.328 ± 0.115)(P < 0.001). The DI of CTVan to CTVpa was 0.709 ± 0.144,DI of CTVgl to CTVan was 0.994 ± 0.005 and DI of CTVgl to CTVpa was 0.989 ± 0.008. The differences of inner, outer, upper and lower boundaries of CTVpa and CTVan were (3.35 ± 7.23) mm, (5.57 ± 13.37) mm, (1.75 ± 11.62) mm, and (11.25 ± 4.07)mm, respectively. The cranial and medial boundaries had a negative correlation with CTVpa (P < 0.05 for all). CONCLUSIONS: The differences among the three methods in the delineation of whole breast target volume are statistically significant. The target volume delineated according to the glandular mammary tissue displayed by CT scan is significantly smaller than that by the other two methods. Combination of breast palpation and anatomical marks may be helpful in delineating the whole breast target volume is relatively reasonable at present.

Preparation and application of biocontrol formulation of nematode-trapping fungus-Duddingtonia flagrans.

The use of nematophagous fungi as a biological control strategy for parasitic gastrointestinal nematodes (GINs) in livestock holds promise as an innovative alternative approach. This study aimed to evaluate the clinical efficacy of a lyophilized Duddingtonia flagrans preparation, utilized in association with the anthelmintics ivermectin or albendazole, to control GINs in Tibetan sheep on a farm based in Qinghai Province. The experimental design included five groups: D. flagrans lyophilized preparation group; D. flagrans+ ivermectin combination tablets treatment group (0.6 tablets for each 10 kg b.w. containing 106 chlamydospores of D. flagrans); D. flagrans+ albendazole combination capsules treatment group (5 capsules for each 10 kg b.w. containing 106 chlamydospores of D. flagrans); ivermectin group (0.2 mg/kg); albendazole group (15 mg/kg), and a control group; The effect of these strategies was evaluated through the analysis of feces collected directly from the animals in each group at 24 h, 48 h, 72 h,96 h and 120 h after administration, by estimating the counts of fecal egg count reduction percentage (FECR) and larval development reduction percentage (LDR). The combination of D. flagrans lyophilized preparation with either ivermectin or albendazole yielded fecal egg and larval reduction rates of up to 100% within 72 h after oral administration, outperforming the groups treated with a single anthelmintic. Moreover, the application of the lyophilized preparation of D. flagrans chlamydospores in isolation demonstrated an 89.8% larval reduction rate. The formulation containing D. flagrans showed high predatory capacity after passage through the gastrointestinal tract of sheep and was effective for controlling gastrointestinal nematodes, which greatly reduced the pollution of the grassland, and avoid reinfection.

Comparative analysis of dose calculation algorithms for CyberKnife-based stereotactic radiotherapy in lung cancer.

Purpose: The accuracy of dose calculation is the prerequisite for CyberKnife (CK) to implement precise stereotactic body radiotherapy (SBRT). In this study, CK-MLC treatment planning for early-stage non-small cell lung cancer (NSCLC) were compared using finite-size pencil beam (FSPB) algorithm, FSPB with lateral scaling option (FSPB_LS) and Monte Carlo (MC) algorithms, respectively. We concentrated on the enhancement of accuracy with the FSPB_LS algorithm over the conventional FSPB algorithm and the dose consistency with the MC algorithm. Methods: In this study, 54 cases of NSCLC were subdivided into central lung cancer (CLC, n=26) and ultra-central lung cancer (UCLC, n=28). For each patient, we used the FSPB algorithm to generate a treatment plan. Then the dose was recalculated using FSPB_LS and MC dose algorithms based on the plans computed using the FSPB algorithm. The resultant plans were assessed by calculating the mean value of pertinent comparative parameters, including PTV prescription isodose, conformity index (CI), homogeneity index (HI), and dose-volume statistics of organs at risk (OARs). Results: In this study, most dose parameters of PTV and OARs demonstrated a trend of MC > FSPB_LS > FSPB. The FSPB_LS algorithm aligns better with the dose parameters of the target compared to the MC algorithm, which is particularly evident in UCLC. However, the FSPB algorithm significantly underestimated the does of the target. Regarding the OARs in CLC, differences in dose parameters were observed between FSPB and FSPB_LS for V10 of the contralateral lung, as well as between FSPB and MC for mean dose (Dmean) of the contralateral lung and maximum dose (Dmax) of the aorta, exhibiting statistical differences. There were no statistically significant differences observed between FSPB_LS and MC for the OARs. However, the average dose deviation between FSPB_LS and MC algorithms for OARs ranged from 2.79% to 11.93%. No significant dose differences were observed among the three algorithms in UCLC. Conclusion: For CLC, the FSPB_LS algorithm exhibited good consistency with the MC algorithm in PTV and demonstrated a significant improvement in accuracy when compared to the traditional FSPB algorithm. However, the FSPB_LS algorithm and the MC algorithm showed a significant dose deviation in OARs of CLC. In the case of UCLC, FSPB_LS showed better consistency with the MC algorithm than observed in CLC. Notwithstanding, UCLC's OARs were highly sensitive to radiation dose and could result in potentially serious adverse reactions. Consequently, it is advisable to use the MC algorithm for dose calculation in both CLC and UCLC, while the application of FSPB_LS algorithm should be carefully considered.

Deciphering the functional landscape of phosphosites with deep neural network.

Current biochemical approaches have only identified the most well-characterized kinases for a tiny fraction of the phosphoproteome, and the functional assignments of phosphosites are almost negligible. Herein, we analyze the substrate preference catalyzed by a specific kinase and present a novel integrated deep neural network model named FuncPhos-SEQ for functional assignment of human proteome-level phosphosites. FuncPhos-SEQ incorporates phosphosite motif information from a protein sequence using multiple convolutional neural network (CNN) channels and network features from protein-protein interactions (PPIs) using network embedding and deep neural network (DNN) channels. These concatenated features are jointly fed into a heterogeneous feature network to prioritize functional phosphosites. Combined with a series of in vitro and cellular biochemical assays, we confirm that NADK-S48/50 phosphorylation could activate its enzymatic activity. In addition, ERK1/2 are discovered as the primary kinases responsible for NADK-S48/50 phosphorylation. Moreover, FuncPhos-SEQ is developed as an online server.

Analysis of the advantage of individual PTVs defined on axial 3D CT and 4D CT images for liver cancer.

The purpose of this study was to compare positional and volumetric differences of planning target volumes (PTVs) defined on axial three dimensional CT (3D CT) and four dimensional CT (4D CT) for liver cancer. Fourteen patients with liver cancer underwent 3D CT and 4D CT simulation scans during free breathing. The tumor motion was measured by 4D CT. Three internal target volumes (ITVs) were produced based on the clinical target volume from 3DCT (CTV3D): i) A conventional ITV (ITVconv) was produced by adding 10 mm in CC direction and 5 mm in LR and and AP directions to CTV3D; ii) A specific ITV (ITVspec) was created using a specific margin in transaxial direction; iii) ITVvector was produced by adding an isotropic margin derived from the individual tumor motion vector. ITV4D was defined on the fusion of CTVs on all phases of 4D CT. PTVs were generated by adding a 5 mm setup margin to ITVs. The average centroid shifts between PTVs derived from 3DCT and PTV4D in left-right (LR), anterior-posterior (AP), and cranial-caudal (CC) directions were close to zero. Comparing PTV4D to PTVconv, PTVspec, and PTVvector resulted in a decrease in volume size by 33.18% ± 12.39%, 24.95% ± 13.01%, 48.08% ± 15.32%, respectively. The mean degree of inclusions (DI) of PTV4D in PTVconv, and PTV4D in PTVspec, and PTV4D in PTVvector was 0.98, 0.97, and 0.99, which showed no significant correlation to tumor motion vector (r = -0.470, 0.259, and 0.244; p = 0.090, 0.371, and 0.401). The mean DIs of PTVconv in PTV4D, PTVspec in PTV4D, and PTVvector in PTV4D was 0.66, 0.73, and 0.52. The size of individual PTV from 4D CT is significantly less than that of PTVs from 3DCT. The position of targets derived from axial 3DCT images scatters around the center of 4D targets randomly. Compared to conventional PTV, the use of 3D CT-based PTVs with individual margins cannot significantly reduce normal tissues being unnecessarily irradiated, but may contribute to reducing the risk of missing targets for tumors with large motion.

[Evaluation of dosimetric variance in forward intensity modulated radiotherapy of the breast based on 4D CT and 3D CT during free breathing].

OBJECTIVE: To explore the dosimetric variance in forward intensity modulated radiotherapy (IMRT) based on 4D CT and 3D CT after breast conserving surgery. METHODS: Seventeen patients after breast conserving surgery underwent 3D CT simulation scans followed by respiration-synchronized 4D CT simulation scans at free breathing state. The treatment plan constructed using the end inspiration (EI) scan was then copied and applied to the end expiration (EE), and 3D scans and dose distribution were calculated separately. Dose-volume histograms (DVHs) parameters for the CTV, PTV, ipsilateral lung and heart were evaluated and compared. RESULTS: The CTV volume difference was biggest between T0 and 3D CT, and the volume difference was 4.10 cm(3). Mean dose of PTV at EE was lower than that at EI (P = 0.019), but there were no statistically significant difference between 3D and EI, EE (all P > 0.05). The homogeneity index (HI) at EI, EE, 3D plans were 0.149, 0.159 and 0.164, respectively, and a significant difference was only between EI and EE (P = 0.039). The highest conformal index (CI) was at EI phase (P < 0.05), and there was no significant difference between EE and 3D (P = 0.758). The V(40) and V(50) of ipsilateral lung at EE phase were lower than that at EI (P < 0.05). There were no significant differences in all the indexes for heart (P > 0.05). CONCLUSIONS: The breast deformation during respiration may be disregarded in whole breast IMRT. PTV dose distribution is significantly changed between EI and EE phases, and the differentiation of the lung high dose area between EI and EE phases may be induced by thorax expansion. 3D treatment planning is sufficient for whole breast forward IMRT, but 4D CT scans assisted by respiratory gating ensures more precise delivery of radiation dose.

[Measurement of intrafraction displacement of the mediastinal metastatic lymph nodes of non-small cell lung cancer based on four-dimensional computed tomography (4D-CT)].

OBJECTIVE: To measure the intrafraction displacement of the mediastinal metastatic lymph nodes of non-small cell lung cancer (NSCLC) based on four-dimensional computed tomography (4D-CT), and to provide the basis for the internal margin of metastatic mediastinal lymph nodes. METHODS: Twenty-four NSCLC patients with mediastinal metastatic lymph nodes confirmed by contrast enhanced CT (short axis diameter ≥ 1 cm) were included in this study. 4D-CT simulation was carried out during free breathing and 10 image sets were acquired. The mediastinal metastatic lymph nodes and the dome of ipsilateral diaphragma were separately delineated on the CT images of 10 phases of breath cycle, and the lymph nodes were grouped as the upper, middle and lower mediastinal groups depending on the mediastinal station. Then the displacements of the lymph nodes in the left-right, anterior-posterior, superior-inferior directions and the 3-dimensional vector were measured. The differences of displacement in three directions for the same group of metastatic lymph nodes and in the same direction for different groups of metastatic lymph nodes were compared. The correlation between the displacement of ipsilateral diaphragma and mediastinal lymph nodes was analyzed in superior-inferior direction. RESULTS: The displacements in left-right, anterior-posterior and superior-inferior directions were (2.24 ± 1.55) mm, (1.87 ± 0.92) mm and (3.28 ± 2.59) mm for the total (53) mediastinal lymph nodes, respectively. The vectors were (4.70 ± 2.66) mm, (3.87 ± 2.45) mm, (4.97 ± 2.75) mm and (5.23 ± 2.67) mm for the total, upper, middle and lower mediastinal lymph nodes, respectively. For the upper mediastinal lymph nodes, the displacements in left-right, anterior-posterior and superior-inferior directions showed no significant difference between each other (P > 0.05). For the middle mediastinal lymph nodes, the displacements merely in anterior-posterior and superior-inferior directions showed significant difference (P = 0.005), while the displacements were not significantly different in the left-right and anterior-posterior, left-right and superior-inferior directions (P > 0.05). The displacements of the total and the lower mediastinal lymph nodes in left-right and superior-inferior, or anterior-posterior and superior-inferior directions were significantly different (P < 0.05), but was not significantly different in left-right and anterior-posterior directions (P > 0.05). The displacements of different group of mediastinal lymph nodes in a single direction or vector showed no significant difference (P > 0.05). In the superior-inferior direction, the correlation between the displacements of ipsilateral diaphragma and mediastinal lymph nodes were not statistically significant (P > 0.05). CONCLUSIONS: During free breathing, the differences between the intrafractional displacement of mediastinal metastatic lymph nodes in the same direction and its station were not statistically significant. The displacements of the total mediastinal metastatic lymph nodes in the superior-inferior direction were greater than that in the left-right and anterior-posterior directions, especially for the middle and lower mediastinal metastatic lymph nodes. There was no significant correlation between the displacements of ipsilateral diaphragma and the mediastinal metastatic lymph nodes in the superior-inferior direction, so it was unreasonable to estimate and predict the displacement of mediastinal metastatic lymph nodes by the displacement of ipsilateral diaphragma.

Using Pruning-Based YOLOv3 Deep Learning Algorithm for Accurate Detection of Sheep Face.

Accurate identification of sheep is important for achieving precise animal management and welfare farming in large farms. In this study, a sheep face detection method based on YOLOv3 model pruning is proposed, abbreviated as YOLOv3-P in the text. The method is used to identify sheep in pastures, reduce stress and achieve welfare farming. Specifically, in this study, we chose to collect Sunit sheep face images from a certain pasture in Xilin Gol League Sunit Right Banner, Inner Mongolia, and used YOLOv3, YOLOv4, Faster R-CNN, SSD and other classical target recognition algorithms to train and compare the recognition results, respectively. Ultimately, the choice was made to optimize YOLOv3. The mAP was increased from 95.3% to 96.4% by clustering the anchor frames in YOLOv3 using the sheep face dataset. The mAP of the compressed model was also increased from 96.4% to 97.2%. The model size was also reduced to 1/4 times the size of the original model. In addition, we restructured the original dataset and performed a 10-fold cross-validation experiment with a value of 96.84% for mAP. The results show that clustering the anchor boxes and compressing the model using this dataset is an effective method for identifying sheep. The method is characterized by low memory requirement, high-recognition accuracy and fast recognition speed, which can accurately identify sheep and has important applications in precision animal management and welfare farming.

A fast Tikhonov regularization method based on homotopic mapping for electrical resistance tomography.

Electrical resistance tomography (ERT) is considered a novel sensing technique for monitoring conductivity distribution. Image reconstruction of ERT is an ill-posed inverse problem. In this paper, an improved regularization reconstruction method is presented to solve this issue. We adopted homotopic mapping to choose the regularization parameter of the iterative Tikhonov algorithm. The standard normal distribution function was used to continuously adjust the regularization parameter. Subsequently, the resultant image vector was deployed as the initial value of the iterative Tikhonov algorithm to improve the image quality. Finally, the improved method was combined with a projection algorithm based on the Krylov subspace, which was also effective in reducing the computational time. Both simulation and experimental results indicated that the new algorithm could improve the real-time performance and imaging quality.

(-)-Epigallocatechin Gallate is a Noncompetitive Inhibitor of NAD Kinase.

Nicotinamide adenine dinucleotide kinase (NADK) controls the intracellular NADPH content and provides reducing power for the synthesis of macromolecules and anti-ROS. Moreover, NADK is considered to be a synthetic lethal gene for KRAS mutations. To discover NADK-targeted probes, a high-throughput screening assay was established and optimized with a Z factor of 0.71. The natural product (-)-epigallocatechin gallate (EGCG) was found to be a noncompetitive inhibitor of NADK with K i = 3.28 ± 0.32 µΜ. The direct binding of EGCG to NADK was determined by several biophysical methods, including NMR spectroscopy, surface plasmon resonance (SPR) assay, and hydrogen-deuterium exchange mass spectrometry (HDX-MS). The SPR assay showed a K d of 1.78 ± 1.15 µΜ. The HDX-MS experiment showed that EGCG was bound at the non-substrate-binding sites of NADK. Besides, binding mode prediction and derivative activity analysis revealed a potential structure-activity relationship between EGCG and NADK. Furthermore, EGCG can specifically inhibit the proliferation of KRAS-mutated lung cancer cell lines without affecting KRAS wild-type lung cancer cell lines.

A potent PGK1 antagonist reveals PGK1 regulates the production of IL-1ß and IL-6.

Glycolytic metabolism enzymes have been implicated in the immunometabolism field through changes in metabolic status. PGK1 is a catalytic enzyme in the glycolytic pathway. Here, we set up a high-throughput screen platform to identify PGK1 inhibitors. DC-PGKI is an ATP-competitive inhibitor of PGK1 with an affinity of K d = 99.08 nmol/L. DC-PGKI stabilizes PGK1 in vitro and in vivo, and suppresses both glycolytic activity and the kinase function of PGK1. In addition, DC-PGKI unveils that PGK1 regulates production of IL-1ß and IL-6 in LPS-stimulated macrophages. Mechanistically, inhibition of PGK1 with DC-PGKI results in NRF2 (nuclear factor-erythroid factor 2-related factor 2, NFE2L2) accumulation, then NRF2 translocates to the nucleus and binds to the proximity region of Il-1ß and Il-6 genes, and inhibits LPS-induced expression of these genes. DC-PGKI ameliorates colitis in the dextran sulfate sodium (DSS)-induced colitis mouse model. These data support PGK1 as a regulator of macrophages and suggest potential utility of PGK1 inhibitors in the treatment of inflammatory bowel disease.

Applications of IMAT in cervical esophageal cancer radiotherapy: a comparison with fixed-field IMRT in dosimetry and implementation.

This study aimed to compare fixed-field, intensity-modulated radiotherapy (f-IMRT) with intensity-modulated arc therapy (IMAT) treatment plans in dosimetry and practical application for cervical esophageal carcinoma. For ten cervical esophageal carcinoma cases, f-IMRT plan (seven fixed-fields) and two IMAT plans, namely RA (coplanar 360° arcs) and RAx (coplanar 360° arcs without sectors from 80° to 110°, and 250° to 280°), were generated. DVHs were adopted for the statistics of above parameters, as well as conformal index (CI), homogeneity index (HI), dose-volumetric parameters of normal tissues, total accelerator output MUs and total treatment time. There were differences between RAx and f-IMRT, as well as RA in PTV parameters such as HI, V(95%) and V(110%), but not in CI. RAx reduced lung V5 from (50.9% ± 9.8% in f-IMRT and (51.4% ± 10.8% in RA to (49.3% ± 10.4% in RAx (p < 0.05). However, lung V30, V40, V50 and MLD increased in RAx. There was no difference in the mean heart dose in three plans. Total MU was reduced from 1174.8 ± 144.6 in f-IMRT to 803.8 ± 122.2 in RA and 736.2 ± 186.9 in RAx (p < 0.05). Compared with f-IMRT, IMAT reduced low dose volumes of lung and total MU on the basis of meeting clinical requirements.

Evaluation of integrated respiratory gating systems on a Novalis Tx system.

The purpose of this study was to investigate the accuracy of motion tracking and radiation delivery control of integrated gating systems on a Novalis Tx system. The study was performed on a Novalis Tx system, which is equipped with Varian Real-time Position Management (RPM) system, and BrainLAB ExacTrac gating systems. In this study, the two systems were assessed on accuracy of both motion tracking and radiation delivery control. To evaluate motion tracking, two artificial motion profiles and five patients' respiratory profiles were used. The motion trajectories acquired by the two gating systems were compared against the references. To assess radiation delivery control, time delays were measured using a single-exposure method. More specifically, radiation is delivered with a 4 mm diameter cone within the phase range of 10%-45% for the BrainLAB ExacTrac system, and within the phase range of 0%-25% for the Varian RPM system during expiration, each for three times. Radiochromic films were used to record the radiation exposures and to calculate the time delays. In the work, the discrepancies were quantified using the parameters of mean and standard deviation (SD). Pearson's product-moment correlational analysis was used to test correlation of the data, which is quantified using a parameter of r. The trajectory profiles acquired by the gating systems show good agreement with those reference profiles. A quantitative analysis shows that the average mean discrepancies between BrainLAB ExacTrac system and known references are 1.5 mm and 1.9 mm for artificial and patient profiles, with the maximum motion amplitude of 28.0 mm. As for the Varian RPM system, the corresponding average mean discrepancies are 1.1 mm and 1.7 mm for artificial and patient profiles. With the proposed single-exposure method, the time delays are found to be 0.20 ± 0.03 seconds and 0.09 ± 0.01 seconds for BrainLAB ExacTrac and Varian RPM systems, respectively. The results indicate the systems can track motion and control radiation delivery with reasonable accuracy. The proposed single-exposure method has been demonstrated to be feasible in measuring time delay efficiently.

[A non-local means approach for PET image denoising].

Denoising is an important issue for medical image processing. Based on the analysis of the Non-local means algorithm recently reported by Buades A, et al. in international journals we herein propose adapting it for PET image denoising. Experimental de-noising results for real clinical PET images show that Non-local means method is superior to median filtering and wiener filtering methods and it can suppress noise in PET images effectively and preserve important details of structure for diagnosis.

Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: impact of tumor segmentation variability.

BACKGROUND: The reproducibility and non-redundancy of radiomic features are challenges in accelerating the clinical translation of radiomics. In this study, we focused on the robustness and non-redundancy of radiomic features extracted from computed tomography (CT) scans in hepatocellular carcinoma (HCC) patients with respect to different tumor segmentation methods. METHODS: Arterial enhanced CT images were retrospectively randomly obtained from 106 patients. As a training data set, 26 HCC patients were used to calculate the features' reproducibility and redundancy. Another data set (55 HCC patients and 25 healthy volunteers) was used for classification. The GrowCut and GraphCut semiautomatic segmentation methods were implemented in 3D Slicer software by two independent observers, and manual delineation was performed by five abdominal radiation oncologists to acquire the gross tumor volume (GTV). Seventy-one radiomic features were extracted from GTVs using Imaging Biomarker Explorer (IBEX) software, including 17 tumor intensity statistical features, 16 shape features and 38 textural features. For each radiomic feature, intraclass correlation coefficient (ICC) and hierarchical clustering were used to quantify its reproducibility and redundancy. Features with ICC values greater than 0.75 were considered reproducible. To generate the number of non-redundancy feature subgroups, the R2 statistic method was used. Then, a classification model was built using a support vector machine (SVM) algorithm with 10-fold cross validation, and area under ROC curve (AUC) was used to evaluate the utility of non-redundant feature extraction by hierarchical clustering. RESULTS: The percentages of excellent reproducible features in the manual delineation group, GraphCut and GrowCut segmentation group were 69% [49], 73% [52] and 79% [56], respectively. Sixty-five percent [46] of the features showed strong robustness for all segmentation methods. The optimal number of cluster subgroup were 9, 13 and 11 for manual delineation, GraphCut and GrowCut segmentation, respectively. The optimal cluster subgroup number was 6 for all groups when the collectively high reproducibility features were selected for clustering. The receiver operating characteristic (ROC) analysis of radiomics classification model with and without feature reduction for healthy liver and HCC had an AUC value of 0.857 and 0.721 respectively. CONCLUSIONS: Our study demonstrates that variations exist in the reproducibility of quantitative imaging features extracted from tumor regions segmented using different methods. The reproducibility and non-redundancy of the radiomic features rely greatly on the tumor segmentation in HCC CT images. We recommend that the most reliable and uniform radiomic features should be selected in the clinical use of radiomics. Classification experiments with feature reduction showed that radiomic features were effective in identifying healthy liver and HCC.

Quantification of heart, pericardium, and left ventricular myocardium movements during the cardiac cycle for thoracic tumor radiotherapy.

PURPOSE: The purpose of this study was to quantify variations in the heart, pericardium, and left ventricular myocardium (LVM) caused by cardiac movement using the breath-hold technique. PATIENTS AND METHODS: In this study, the electrocardiography-gated four-dimensional computed tomography (CT) images of 22 patients were analyzed, which were sorted into 20 phases (0-95%) according to the cardiac cycle. The heart, pericardium, and LVM were contoured on each phase of the CT images. The positions, volume, dice similarity coefficient (DSC) in reference to 0% phase, and morphological parameters (max 3D diameter, roundness, spherical disproportion, sphericity, and surface area) in different phases of the heart, pericardium, and LVM were analyzed, which were presented as mean ± standard deviation. RESULTS: The mean values of displacements along the X, Y, and Z axes respectively were as follows: 1.2 mm, 0.6 mm, and 0.6 mm for the heart; 0.5 mm, 0.4 mm, and 0.8 mm for the pericardium; and 1.0 mm, 4.1 mm, and 1.9 mm for the LVM. The maximum variations in volume and DSC respectively were 16.49%±3.85% and 10.08%±2.14% for the heart, 12.62%±3.94% and 5.20%±1.54% for the pericardium, and 24.23%±11.35% and 184.33%±128.61% for the LVM. The differences in the morphological parameters between the maximum and minimum DSC phases for the heart and pericardium were not significantly different (p>0.05) but were significantly different for the LVM (p<0.05). CONCLUSION: The volumetric and morphological variations of the heart were similar to those of pericardium, and all were significantly smaller than those of the LVM. This inconsistency in the volumetric and morphological variations between the LVM and the heart and pericardium indicates that special protection of the LVM should be considered.

Quantification of variation in dose-volume parameters for the heart, pericardium and left ventricular myocardium during thoracic tumor radiotherapy.

Cardiac activity can induce dose-volume evaluation errors for cardiac structures. The purpose of this study was to quantify the variation in dose-volume parameters for the heart, pericardium and left ventricular myocardium (LVM) throughout the cardiac circle. The heart, pericardium and LVM of 22 patients were contoured on 20 phases of electrocardiography-gated 4D computed tomography (4DCT) images acquired during breath-hold. Radiotherapy plans were designed on 0% phase of the 4DCT images, and the dose distributions of the plans were imported into MIM Maestro and deformed to each phase to generate distributions for all phases. Variations in dose-volume parameters for the heart, pericardium and LVM were compared among different phases. The rates of variation in Dmean for the heart and pericardium were 3.33 ± 1.04% and 2.66 ± 1.15%, respectively. The mean values of the maximum difference in V5, V10, V20, V30 and V40 were all <2% for the heart and pericardium and were not statistically significant (P > 0.05). The rate of variation in Dmean for the LVM reached 87.05 ± 38.34%, and the maximum differences in V5, V10, V20, V30 and V40 were 13.76 ± 4.46%, 13.64 ± 4.33%, 12.84 ± 4.55%, 11.62 ± 4.85% and 3.63 ± 2.56%, respectively; all differences were statistically significant (P < 0.05). Variations in dose-volume parameters were more significant in the LVM than in the heart and pericardium (P < 0.05). The dose-volume parameters for the LVM were significantly influenced by cardiac activity, whereas those for the heart and pericardium were not; therefore, individual dosimetric evaluation and limitation must be performed for the LVM.