ABSTRACT
OBJECTIVES: This in vitro study was formulated to clarify how mandibular partial edentulous distal extension involving three missing teeth affects the virtual occlusal record (VOR) accuracy, in terms of both trueness and precision, when using two different intraoral scanners (IOSs) - the Primescan (PS) and Trios 4 (TR) scanners. METHODS: A typodont model missing the left mandibular second premolar, first molar, and second molar as well as the right mandibular first molar was mounted on a semi-adjustable articulator. Four implants were placed at the sites of the missing mandibular teeth. Six pairs of stainless steel markers (diameter: 0.5 mm) were affixed to the maxillary and mandibular casts in the buccal gingiva adjacent to the implants and on the facial surfaces of teeth as reference positions for measurements. The model was digitized with an inEox X5 laboratory scanner to create a reference dataset. Intraoral scans were performed with the PS and TR scanners, with each scan duplicated 10 times to generate 20 paired IOS files. Automatic VOR generation followed the bilateral buccal scan protocol, divided into PS and TR groups (n=10). Six subgroups of linear distances between interarch markers were assessed with Geomagic Control software, comparing deviations from the reference scan. Data normality was confirmed with the Shapiro-Wilk test. Trueness was evaluated with two-way ANOVAs and pairwise comparisons performed with Tukey's test, whereas precision was assessed with the Levene test (α=0.05). RESULTS: The mean linear deviation (Δd) and standard deviation (SD) of VOR were both significantly affected by marker position (P < 0.001), and a significant positionâ¯×â¯scanner interaction was detected (P < 0.001). Negative mean deviations were observed for the distally extended edentulous areas in both groups. PS scans exhibited trueness that was significantly better than that for TR scans in the D16-46, D13-43, D23-33, and D27-37 subgroups (P < 0.05), whereas there were no significant differences in the D25-35 or D26-36 subgroups. PS scanning was associated with significantly better precision than TR scanning (P<0.001), and worse precision was observed at D27-37 for both tested IOSs. CONCLUSIONS: Mandibular partial edentulous distal extension can significantly affect VOR accuracy. The type of IOS could also affect VOR accuracy depending on the area being scanned, with better overall performance observed for the Primescan device as compared to the Trios 4 scanner. Both of these IOSs tended to underestimate VOR occlusal dimensions in mandibular distally extended edentulous areas. CLINICAL SIGNIFICANCE: Mandibular distal edentulous areas can contribute to occlusal dimensions that are underestimated in digital workflows, which may result in infraocclusal discrepancies that arise when performing restorations. IOSs and VOR scanning protocols should thus be carefully considered in order to minimize these risks.
ABSTRACT
Environmental pollution management and renewable energy development are humanity's biggest issues in the 21st century. The rise in atmospheric CO2, which has surpassed 400â parts per million, has stimulated research on CO2 reduction and conversion methods. Presently, photocatalytic conversion of CO2 to valuable hydrocarbons enables the transformation of solar energy into chemical energy and offers a novel avenue for energy conversion while regulating the greenhouse effect. This is an ideal strategy for simultaneously addressing environmental issues and the energy crisis. Photocatalysts are essential to photocatalytic processes. Photocatalyst is the core of photocatalytic technology, and graphite carbon nitride (g-C3N4) has attracted much attention because of its nonmetallic characteristics, and it has the characteristics of low cost, tunable electronic structure, easy manufacture and strong reducibility. However, its activity is not only affected by external reaction conditions, but also by the band gap structure, physical and chemical stability, surface morphology and specific surface area of the photocatalyst it. In this paper, the application progress of g-C3N4-based photocatalytic materials in CO2 reduction is reviewed, and the modification strategies of g-C3N4-based catalysts to obtain better catalytic efficiency and selectivity in CO2 photocatalytic reduction are summarized, and the future development of this material is prospected.
ABSTRACT
Pre-harvest spraying of benzothiadiazole (BTH) can improve the winemaking properties of grapes, especially their aroma compounds and phenolics. Limited research has explored the molecular mechanisms by which BTH influences the accumulation of grape aroma precursors during early grape development. This study investigated the effects and putative molecular mechanisms of applying 0.37 mM BTH through whole-plant spraying on the accumulation of aroma metabolism precursors and gene expression in Cabernet Gernischt grapes during ripening. The results showed that BTH treatment increased the levels of fructose, alanine, aspartate, threonine, myristic acid, myristoleic acid, palmitic acid, ß-cryptoxanthin, norisoprenoids and methoxypyrazines. Contrarily, it decreased the levels of glucose, sucrose, phenylalanine, tyrosine, leucine, valine, glycine, arginine, histidine, total unsaturated fatty acids (particularly linoleic acid), zeaxanthin, lutein, and organic acids. Additionally, BTH upregulated the expression of genes associated with the production and degradation of amino acids, fatty acids, and carotenoids while decreasing the expression of genes involved in the synthesis and degradation of soluble sugars and organic acids. Ten different metabolites, including fumaric acid, were identified as potential biological markers for distinguishing BTH-treated grapes from control grapes. The study demonstrates that BTH treatment had a substantial impact on the concentration and developmental patterns of aroma metabolism precursors. Furthermore, it altered the winemaking characteristics of Cabernet Gernischt grapes by modulating genes associated with the production and breakdown of metabolites.
Subject(s)
Thiadiazoles , Vitis , Wine , Vitis/metabolism , Wine/analysis , Odorants/analysis , Quality Improvement , Fruit/metabolismABSTRACT
Event cameras or dynamic vision sensors (DVS) record asynchronous response to brightness changes instead of conventional intensity frames, and feature ultra-high sensitivity at low bandwidth. The new mechanism demonstrates great advantages in challenging scenarios with fast motion and large dynamic range. However, the recorded events might be highly sparse due to either limited hardware bandwidth or extreme photon starvation in harsh environments. To unlock the full potential of event cameras, we propose an inventive event sequence completion approach conforming to the unique characteristics of event data in both the processing stage and the output form. Specifically, we treat event streams as 3D event clouds in the spatiotemporal domain, develop a diffusion-based generative model to generate dense clouds in a coarse-to-fine manner, and recover exact timestamps to maintain the temporal resolution of raw data successfully. To validate the effectiveness of our method comprehensively, we perform extensive experiments on three widely used public datasets with different spatial resolutions, and additionally collect a novel event dataset covering diverse scenarios with highly dynamic motions and under harsh illumination. Besides generating high-quality dense events, our method can benefit downstream applications such as object classification and intensity frame reconstruction.
ABSTRACT
Light field disparity estimation is an essential task in computer vision. Currently, supervised learning-based methods have achieved better performance than both unsupervised and optimization-based methods. However, the generalization capacity of supervised methods on real-world data, where no ground truth is available for training, remains limited. In this paper, we argue that unsupervised methods can achieve not only much stronger generalization capacity on real-world data but also more accurate disparity estimation results on synthetic datasets. To fulfill this goal, we present the Occlusion Pattern Aware Loss, named OPAL, which successfully extracts and encodes general occlusion patterns inherent in the light field for calculating the disparity loss. OPAL enables: i) accurate and robust disparity estimation by teaching the network how to handle occlusions effectively and ii) significantly reduced network parameters required for accurate and efficient estimation. We further propose an EPI transformer and a gradient-based refinement module for achieving more accurate and pixel-aligned disparity estimation results. Extensive experiments demonstrate our method not only significantly improves the accuracy compared with SOTA unsupervised methods, but also possesses stronger generalization capacity on real-world data compared with SOTA supervised methods. Last but not least, the network training and inference efficiency are much higher than existing learning-based methods. Our code will be made publicly available.
ABSTRACT
Pre-harvest application of elicitors improves grape quality, specifically the phenolic compounds and color characteristics. Limited research has been conducted on the impact of elicitors on the C6 compounds found in grapes. This is due to lack of comprehensive studies examining the combined effects of bound aroma compounds, enzyme activity, and substrate availability. This study aimed to assess the impact of benzothiadiazole (BTH) on the physicochemical properties and C6 compounds of Cabernet Gernischt grapes during ripening. Compared with the control group (CK), BTH treatment significantly increased the 100-berry weight, skin/berry ratio, pH, total phenolic content, and total flavonoid content in ripe grapes. Additionally, BTH treatment led to significant reductions in reducing sugar, total soluble solids, titratable acidity, linoleic acid, linolenic acid, and free C6 aldehydes. Furthermore, BTH treatment significantly decreased the contents of free C6 alcohols and increased the levels of free and bound C6 esters. BTH treatment also increased the activities of lipoxygenase, alcohol dehydrogenase, and alcohol acetyltransferase enzymes, while it decreased the activity of hydroperoxide lyase enzyme. The application of BTH resulted in changes to the physicochemical properties and levels of C6 compounds in Cabernet Gernischt grapes by up-regulating enzyme activity and down-regulating precursors.
ABSTRACT
Multiple potentially toxic elements (PTEs) often coexist in practical wastewater environment, which poses serious risks to the ecological environment and human health. However, few of the reported adsorbents are capable of simultaneously and effectively removing multiple PTEs from wastewater due to the unique properties of each element. In this work, a multifunctional adsorbent FMHs was developed by optimizing Fe2+/Fe3+/Mn2+/HA ratio, and applied to remove Cd(II), Pb(II), Cu(II), Zn(II), As(III), Sb(III), As(V) and Sb(V) from aqueous solution. Results revealed that the adsorption data obeyed the Elovich, Sips and Redlich-Peterson models in the mono-component system, and the maximum adsorption capacity of FMHs was superior to most adsorbents reported in the literatures. In addition, FMHs retained considerable removal capacity after four cycles, and maintained excellent adsorption performance under the interference of different environmental factors (including pH, ionic strength, co-existing ions and humic acid). In the multi-component system, FMHs also presented high adsorption capacity for all the selected PTEs, especially for Sb(III/V) and Pb(II). Characterization results conï¬rmed that various removal mechanisms, such as precipitation, surface complexation, ion exchange, electrostatic attraction and redox, were responsible for the capture of PTEs by FMHs.
Subject(s)
Cadmium , Lead , Humans , Wastewater , Adsorption , ZincABSTRACT
Individuals of virtually all vertebrate species are exposed to annual fluctuations in the deterioration and renewal of their environments. As such, organisms have evolved to restrict energetically expensive processes and activities to a specific time of the year. Thus, the precise timing of physiology and behavior is critical for individual reproductive success and subsequent fitness. Although the majority of research on seasonality has focused on seasonal reproduction, pronounced fluctuations in other non-reproductive social behaviors, including agonistic behaviors (e.g., aggression), also occur. To date, most studies that have investigated the neuroendocrine mechanisms underlying seasonal aggression have focused on the role of photoperiod (i.e., day length); prior findings have demonstrated that some seasonally breeding species housed in short "winter-like" photoperiods display increased aggression compared with those housed in long "summer-like" photoperiods, despite inhibited reproduction and low gonadal steroid levels. While fewer studies have examined how the hormonal correlates of environmental cues regulate seasonal aggression, our previous work suggests that the pineal hormone melatonin acts to increase non-breeding aggression in Siberian hamsters (Phodopus sungorus) by altering steroid hormone secretion. This review addresses the physiological and cellular mechanisms underlying seasonal plasticity in aggressive and non-aggressive social behaviors, including a key role for melatonin in facilitating a "neuroendocrine switch" to alternative physiological mechanisms of aggression across the annual cycle. Collectively, these studies highlight novel and important mechanisms by which melatonin regulates aggressive behavior in vertebrates and provide a more comprehensive understanding of the neuroendocrine bases of seasonal social behaviors broadly.
Subject(s)
Melatonin , Cricetinae , Animals , Seasons , Phodopus , Aggression/physiology , PhotoperiodABSTRACT
This work aimed to develop a noninvasive and reliable computed tomography (CT)-based imaging biomarker to predict early recurrence (ER) of intrahepatic cholangiocarcinoma (ICC) via radiomics analysis. In this retrospective study, a total of 177 ICC patients were enrolled from three independent hospitals. Radiomic features were extracted on CT images, then 11 feature selection algorithms and 4 classifiers were to conduct a multi-strategy radiomics modeling. Six established radiomics models were selected as stable ones by robustness-based rule. Among those models, Max-Relevance Min-Redundancy (MRMR) combined with Gradient Boosting Machine (GBM) yielded the highest areas under the receiver operating characteristics curve (AUCs) of 0.802 (95% confidence interval [CI]: 0.727-0.876) and 0.781 (95% CI: 0.655-0.907) in the training and test cohorts, respectively. To evaluate the generalization of the developed radiomics model, stratification analysis was performed regarding different centers. The MRMR-GBM-based model manifested good generalization with comparable AUCs in each hospital (p > 0.05 for paired comparison). Thus, the MRMR-GBM-based model could offer a potential imaging biomarker to assist the prediction of ER in ICC in a noninvasive manner.Clinical Relevance-The proposed radiomics model achieved satisfactory accuracy and good generalization ability in predicting ER in ICC, which might assist personalized surveillance and clinical treatment strategy making.
Subject(s)
Bile Duct Neoplasms , Cholangiocarcinoma , Bile Duct Neoplasms/diagnostic imaging , Bile Duct Neoplasms/surgery , Bile Ducts, Intrahepatic/diagnostic imaging , Bile Ducts, Intrahepatic/surgery , Cholangiocarcinoma/diagnostic imaging , Cholangiocarcinoma/surgery , Humans , Retrospective Studies , Tomography, X-Ray ComputedABSTRACT
BACKGROUND: Differentiation between cerebral glioblastoma multiforme (GBM) and solitary brain metastasis (MET) is important. The existing radiomic differentiation method ignores the clinical and routine magnetic resonance imaging (MRI) features. PURPOSE: To differentiate between GBM and MET and between METs from the lungs (MET-lung) and other sites (MET-other) through clinical and routine MRI, and radiomics analyses. METHODS AND MATERIALS: A total of 350 patients were collected from two institutions, including 182 patients with GBM and 168 patients with MET, which were all proven by pathology. The ROI of the tumor was obtained on axial postcontrast MRI which was performed before operation. Seven radiomic feature selection methods and four classification algorithms constituted 28 classifiers in two classification strategies, with the best classifier serving as the final radiomics model. The clinical and combination models were constructed using the nomograms developed. The performance of the nomograms was evaluated in terms of calibration, discrimination, and clinical usefulness. Student's t-test or the chi-square test was used to assess the differences in the clinical and radiological characteristics between the training and internal validation cohorts. Receiver operating characteristic curve analysis was performed to assess the performance of developed models with the area under the curve (AUC). RESULTS: The classifier fisher_decision tree (fisher_DT) showed the best performance (AUC: 0.696, 95% CI:0.608-0.783) for distinguishing between GBM and MET in internal validation cohorts; the classifier reliefF_random forest (reliefF_RF) showed the best performance (AUC: 0.759, 95% CI: 0.613-0.904) for distinguishing between MET-lung and MET-other in internal validation cohorts. The combination models incorporating the radiomics signature and clinical-radiological characteristics were superior to the clinical-radiological models in the two classification strategies (AUC: 0.764 for differentiation between GBM in internal validation cohorts and MET and 0.759 or differentiation between MET-lung and MET-other in internal validation cohorts). The nomograms showed satisfactory performance and calibration and were considered clinically useful, as revealed in the decision curve analysis. DATA CONCLUSION: The combination of radiomic and non-radiomic features is helpful for the differentiation among GBM, MET-lung, and MET-other.
ABSTRACT
OBJECTIVE: To investigate the capability of a radiomics model, which was designed to identify histopathologic growth pattern (HGP) of colorectal liver metastases (CRLMs) based on contrast-enhanced multidetector computed tomography (ceMDCT), to predict early response and 1-year progression free survival (PFS) in patients treated with bevacizumab-containing chemotherapy. METHODS: Patients with unresectable CRLMs who were treated with bevacizumab-containing chemotherapy were included in this multicenter retrospective study. For each target lesion, the radiomics-diagnosed HGP (RAD_HGP) of desmoplastic (D) pattern or replacement (R) pattern was determined. Logistic regression and receiver operating characteristic (ROC) curves were used to assess lesion- and patient-based responses according to morphologic response criteria. One-year PFS was calculated using Kaplan-Meier curves. Hazard ratios for 1-year PFS were obtained through Cox proportional hazard regression analysis. RESULTS: Among 119 study patients, 206 D pattern and 140 R pattern lesions were identified. In patients with multiple lesions, 52 had D pattern, 31 had R pattern, and 36 had mixed (D + R) pattern. The area under the curve value for RAD_HGP in predicting early response was 0.707 for lesion-based analysis and 0.720 for patient-based analysis. Patients with D pattern had a significantly longer PFS than patients with R pattern or mixed pattern (P < 0.001). RAD_HGP was the only independent predictor of 1-year PFS. CONCLUSIONS: HGP diagnosed using a radiomics model could be used as an effective predictor of PFS for patients with CRLMs treated with bevacizumab-containing chemotherapy.
Subject(s)
Colorectal Neoplasms , Liver Neoplasms , Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Bevacizumab/therapeutic use , Colorectal Neoplasms/diagnostic imaging , Colorectal Neoplasms/drug therapy , Humans , Liver Neoplasms/diagnostic imaging , Liver Neoplasms/drug therapy , Progression-Free Survival , Retrospective StudiesABSTRACT
OBJECTIVE: Several studies have explored the predictive value of impulse oscillometry (IOS) for asthma exacerbations in childhood, but its specific parameters are still unclear. Therefore, we designed this meta-analysis to determine the related indicators of acute asthma attacks. METHODS: A comprehensive literature search was performed on July 9, 2020 based on PubMed, Embase, and Web of Science database. Weighted mean differences (WMDs) were calculated using fixed- or random-effects models. RESULTS: A total of 615 patients from six trials were included in this analysis. IOS may be a useful tool to predict asthma exacerbations. And the results showed that R5 (WMD = -1.21, 95% CI: -1.55 to -0.87, p < .001), Fres (WMD = -1.34, 95% CI: -2.03 to -0.65, p = .018), and AX (WMD = -7.35, 95% CI: -9.94 to -4.76, p < .001) had significant correlation with asthma exacerbations. In addition, X5 may also predict the acute attack of asthma (WMD = 0.81, 95% CI: 0.56 to 1.01, p < .001). CONCLUSIONS: R5, AX, Fres, and X5 may be able to identify the risk of an acute attack of asthma. Besides, our research further demonstrated that peripheral airway injury may play an important role in the acute attack of asthma.
Subject(s)
Asthma , Oscillometry , Asthma/diagnosis , Databases, Factual , Humans , Respiratory Function Tests , Retrospective Studies , SpirometryABSTRACT
Purpose: Developing an MRI-based radiomics model to effectively and accurately predict the predominant histopathologic growth patterns (HGPs) of colorectal liver metastases (CRLMs). Materials and Methods: In this study, 182 resected and histopathological proven CRLMs of chemotherapy-naive patients from two institutions, including 123 replacement CRLMs and 59 desmoplastic CRLMs, were retrospectively analyzed. Radiomics analysis was performed on two regions of interest (ROI), the tumor zone and the tumor-liver interface (TLI) zone. Decision tree (DT) algorithm was used for radiomics modeling on each MR sequence, and fused radiomics model was constructed by combining the radiomics signature of each sequence. The clinical and combination models were developed through multivariate logistic regression method. The performance of the developed models was assessed by receiver operating characteristic (ROC) curves with indicators of area under curve (AUC), accuracy, sensitivity, and specificity. A nomogram was constructed to evaluate the discrimination, calibration, and usefulness. Results: The fused radiomicstumor and radiomicsTLI models showed better performance than any single sequence and clinical model. In addition, the radiomicsTLI model exhibited better performance than radiomicstumor model (AUC of 0.912 vs. 0.879) in internal validation cohort. The combination model showed good discrimination, and the AUC of nomogram was 0.971, 0.909, and 0.905 in the training, internal validation, and external validation cohorts, respectively. Conclusion: MRI-based radiomics method has high potential in predicting the predominant HGPs of CRLM. Preoperative non-invasive identification of predominant HGPs could further explore the ability of HGPs as a potential biomarker for clinical treatment strategy, reflecting different biological pathways.
ABSTRACT
Background: Intracranial hemangiopericytoma (IHPC) and meningioma are both meningeal neoplasms, but they have extremely different malignancy and outcomes. Because of their similar radiological characteristics, they are difficult to distinguish prior to surgery, leading to a high rate of misdiagnosis. Methods: We enrolled 292 patients (IHPC, 155; meningiomas, 137) with complete clinic-radiological and histopathological data, from a 10-year database established at Tiantan hospital. Radiomics analysis of tumor and peritumoral edema was performed on multisequence magnetic resonance images, and a fusion radiomics signature was generated using a machine-learning strategy. By combining clinic-radiological data with the fusion radiomics signature, we developed an integrated diagnostic approach that we named the IHPC and Meningioma Diagnostic Tool (HMDT). Results: The HMDT displayed remarkable diagnostic ability, with areas under the curve (AUCs) of 0.985 and 0.917 in the training and validation cohorts, respectively. The calibration curve showed excellent agreement between the diagnosis predicted by HMDT and the histological outcome, with p-values of 0.801 and 0.622 for the training and the validation cohorts, respectively. Cross-validation showed no statistical difference across three divisions of the cohort, with average AUCs of 0.980 and 0.941 for the training and validation cohorts, respectively. Stratification analysis showed consistent performance of the HMDT in distinguishing IHPC from highly misdiagnosed subgroups of grade I meningioma and angiomatous meningioma (AM) with AUCs of 0.913 and 0.914 in the validation cohorts for the two subgroups. Conclusions: By integrating clinic-radiological information with radiomics signature, the proposed HMDT could assist in preoperative diagnosis to distinguish IHPC from meningioma, providing the basis for strategic decisions regarding surgery.
ABSTRACT
Liver diseases, a wide spectrum of pathologies from inflammation to neoplasm, have become an increasingly significant health problem worldwide. Noninvasive imaging plays a critical role in the clinical workflow of liver diseases, but conventional imaging assessment may provide limited information. Accurate detection, characterization and monitoring remain challenging. With progress in quantitative imaging analysis techniques, radiomics emerged as an efficient tool that shows promise to aid in personalized diagnosis and treatment decision-making. Radiomics could reflect the heterogeneity of liver lesions via extracting high-throughput and high-dimensional features from multi-modality imaging. Machine learning algorithms are then used to construct clinical target-oriented imaging biomarkers to assist disease management. Here, we review the methodological process in liver disease radiomics studies in a stepwise fashion from data acquisition and curation, region of interest segmentation, liver-specific feature extraction, to task-oriented modelling. Furthermore, the applications of radiomics in liver diseases are outlined in aspects of diagnosis and staging, evaluation of liver tumour biological behaviours, and prognosis according to different disease type. Finally, we discuss the current limitations of radiomics in liver disease studies and explore its future opportunities.
Subject(s)
Liver Neoplasms , Machine Learning , Algorithms , Diagnostic Imaging , Forecasting , Humans , Liver Neoplasms/diagnostic imagingABSTRACT
BACKGROUND: Biopsy Gleason score (GS) is crucial for prostate cancer (PCa) treatment decision-making. Upgrading in GS from biopsy to radical prostatectomy (RP) puts a proportion of patients at risk of undertreatment. PURPOSE: To develop and validate a radiomics model based on multiparametric magnetic resonance imaging (mp-MRI) to predict PCa upgrading. STUDY TYPE: Retrospective, radiomics. POPULATION: A total of 166 RP-confirmed PCa patients (training cohort, n = 116; validation cohort, n = 50) were included. FIELD STRENGTH/SEQUENCE: 3.0T/T2 -weighted (T2 W), apparent diffusion coefficient (ADC), and dynamic contrast enhancement (DCE) sequences. ASSESSMENT: PI-RADSv2 score for each tumor was recorded. Radiomic features were extracted from T2 W, ADC, and DCE sequences and Mutual Information Maximization criterion was used to identify the optimal features on each sequence. Multivariate logistic regression analysis was used to develop predictive models and a radiomics nomogram and their performance was evaluated. STATISTICAL TESTS: Student's t or chi-square were used to assess the differences in clinicopathologic data between the training and validation cohorts. Receiver operating characteristic (ROC) curve analysis was performed and the area under the curve (AUC) was calculated. RESULTS: In PI-RADSv2 assessment, 67 lesions scored 5, 70 lesions scored 4, and 29 lesions scored 3. For each sequence, 4404 features were extracted and the top 20 best features were selected. The radiomics model incorporating signatures from the three sequences achieved better performance than any single sequence (AUC: radiomics model 0.868, T2 W 0.700, ADC 0.759, DCE 0.726). The combined mode incorporating radiomics signature, clinical stage, and time from biopsy to RP outperformed the clinical model and radiomics model (AUC: combined model 0.910, clinical model 0.646, radiomics model 0.868). The nomogram showed good performance (AUC 0.910) and calibration (P-values: training cohort 0.624, validation cohort 0.294). DATA CONCLUSION: Radiomics based on mp-MRI has potential to predict upgrading of PCa from biopsy to RP. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 5 J. Magn. Reson. Imaging 2020;52:1239-1248.
Subject(s)
Prostatectomy , Prostatic Neoplasms , Biomarkers , Biopsy , Humans , Magnetic Resonance Imaging , Male , Prostatic Neoplasms/diagnostic imaging , Prostatic Neoplasms/surgery , Retrospective StudiesABSTRACT
In real-time applications, a fast and robust visual tracker should generally have the following important properties: 1) feature representation of an object that is not only efficient but also has a good discriminative capability and 2) appearance modeling which can quickly adapt to the variations of foreground and backgrounds. However, most of the existing tracking algorithms cannot achieve satisfactory performance in both of the two aspects. To address this issue, in this paper, we advocate a novel and efficient visual tracker by exploiting the excellent feature learning and classification capabilities of an emerging learning technique, that is, extreme learning machine (ELM). The contributions of the proposed work are as follows: 1) motivated by the simplicity and learning ability of the ELM autoencoder (ELM-AE), an ELM-AE-based feature extraction model is presented, and this model can provide a compact and discriminative representation of the inputs efficiently and 2) due to the fast learning speed of an ELM classifier, an ELM-based appearance model is developed for feature classification, and is able to rapidly distinguish the object of interest from its surroundings. In addition, in order to cope with the visual changes of the target and its backgrounds, the online sequential ELM is used to incrementally update the appearance model. Plenty of experiments on challenging image sequences demonstrate the effectiveness and robustness of the proposed tracker.
ABSTRACT
OBJECTIVES: To predict histopathologic growth patterns (HGPs) in colorectal liver metastases (CRLMs) with a noninvasive radiomics model. METHODS: Patients with chemotherapy-naive CRLMs who underwent abdominal contrast-enhanced multidetector CT (MDCT) followed by partial hepatectomy between January 2007 and January 2019 from two institutions were included in this retrospective study. Hematoxylin- and eosin-stained histopathologic sections of CRLMs were reviewed, with HGPs defined according to international consensus. Lesions were divided into training and validation datasets based on patients' sources. Radiomic features were extracted from pre- and post-contrast (arterial and portal venous) phase MDCT images, with review focusing on the segmented tumor-liver interface zones of CRLMs. Minimum redundancy maximum relevance and decision tree methods were used for radiomics modeling. Multivariable logistic regression analyses and ROC curves were used to assess the predictive performance of these models in predicting HGP types. RESULTS: A total of 126 CRLMs with histopathologic-demonstrated desmoplastic (n = 68) or replacement (n = 58) HGPs were assessed. The radiomics signature consisted of 20 features of each phase selected. The 3 phases fused radiomics signature demonstrated the best predictive performance in distinguishing between replacement and desmoplastic HGPs (AUCs of 0.926 and 0.939 in the training and external validation cohorts, respectively). The clinical-radiomics combined model showed good discrimination (C-indices of 0.941 and 0.833 in the training and external validation cohorts, respectively). CONCLUSIONS: A radiomics model derived from MDCT images may effectively predict the HGP of CRLMs, thus providing a basis for prognostic stratification and therapeutic decision-making.