Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

A randomized phase II trial of a drug eluting bead in the treatment of hepatocellular carcinoma by transcatheter arterial chemoembolization

Background: Transcatheter arterial chemoembolization (TACE) has been shown to offer a survival benefit for patients with intermediate-stage hepatocellular carcinoma (HCC). A widely accepted TACE regimen includes the administration of a doxorubicin-in-oil emulsion followed by gelatine sponge particles. Recently, a drug-eluting bead (DEB) has been developed to enhance drug delivery to the tumor and reduce its systemic availability. Purpose of this randomized trial was to compare conventional TACE with DEB-TACE for the treatment of intermediate-stage HCC in patients with cirrhosis. Methods: Two hundred and twelve patients (185 males and 27 females; mean age, 67 years) with Child-Pugh A or B liver cirrhosis and large and/or multinodular, unresectable HCC were randomized to receive DEB-TACE (DC Bead; Biocompatibles, UK) uploaded with doxorubicin or conventional TACE with doxorubicin, lipiodol, and gelatin sponge particles. Randomization was stratified according to Child Pugh status (A or B), performance status (ECOG 0 or 1), bilobar disease (yes or no) and prior curative treatment (yes or no). Tumor response at 6 months was the primary study endpoint. An independent, blinded review of magnetic resonance imaging studies was conducted to assess tumor response according to amended RECIST criteria. Results: DEB-TACE with doxorubicin showed a higher rate of complete response, objective response and disease control compared with conventional TACE (27% vs 22%; 52% vs 44%; and 63% vs 52%, respectively; p>0.05). Patients with Child Pugh B, ECOG 1, bilobar disease and recurrence following curative treatment showed a significant increase in objective response (p=0.038) compared to the control. There was a marked reduction in serious liver toxicity in patients treated with DEB-TACE. The rate of doxorubicin related side effects was significantly lower (p=0.0001) in the DEB-TACE group compared with the conventional TACE group. Conclusions: DEB-TACE with doxorubicin is safe and effective in the treatment of intermediate-stage HCC and may offer benefit to patients with more advanced disease.

Long-term Outcome after Liver Resection for Hepatocellular Carcinoma Larger than 10 cm.

BACKGROUND: The purpose of the present study was to analyze long-term survival and disease-free survival after liver resection for giant hepatocellular carcinoma (HCC) ≥ 10 cm compared to HCC < 10 cm in diameter. The surgical approach in the treatment of giant HCC may achieve long-term survival and disease-free survival comparable to treatment of smaller lesions. METHODS: This retrospective analysis was a monocentric study conducted in a tertiary university center. It included 101 patients from 114 consecutive liver resections for HCC, separated into two groups: those with tumors less than 10 cm in diameter (small HCC; n = 79) and those with tumors larger than 10 cm (giant HCC; n = 22). The main outcome measures were overall five-year survival, five-year disease-free survival, recurrence rate, perioperative mortality at 30 days, surgical complication rate, and re-intervention rate. RESULTS: The two groups were homogeneously distributed, apart from cirrhosis, which was found more frequently in the group with small HCC (77 vs. 41 %; p = 0.0013). Both median survival (24 vs. 27 months; p = 0.0085) and overall 5-year survival (21 vs. 45; p = 0.04) were significantly poorer in the small HCC group compared to the giant HCC group. There were no differences en terms of recurrence rate, pattern, and timing. CONCLUSIONS: Liver resection for HCC larger than 10 cm is a valuable option in selected patients, one that provides overall survival and disease-free survival comparable to smaller lesions. Functional reserves of the liver, more than the size of the lesion, may be important in patient selection for surgical resection.

Metabolomic profiles of hepatocellular carcinoma in a European prospective cohort.

BACKGROUND Hepatocellular carcinoma (HCC), the most prevalent form of liver cancer, is difficult to diagnose and has limited treatment options with a low survival rate. Aside from a few key risk factors, such as hepatitis, high alcohol consumption, smoking, obesity, and diabetes, there is incomplete etiologic understanding of the disease and little progress in identification of early risk biomarkers. METHODS To address these aspects, an untargeted nuclear magnetic resonance metabolomic approach was applied to pre-diagnostic serum samples obtained from first incident, primary HCC cases (n = 114) and matched controls (n = 222) identified from amongst the participants of a large European prospective cohort. RESULTS A metabolic pattern associated with HCC risk comprised of perturbations in fatty acid oxidation and amino acid, lipid, and carbohydrate metabolism was observed. Sixteen metabolites of either endogenous or exogenous origin were found to be significantly associated with HCC risk. The influence of hepatitis infection and potential liver damage was assessed, and further analyses were made to distinguish patterns of early or later diagnosis. CONCLUSION Our results show clear metabolic alterations from early stages of HCC development with application for better etiologic understanding, prevention, and early detection of this increasingly common cancer.

Learning spatial filters for multispectral image segmentation

We present a novel filtering method for multispectral satellite image classification. The proposed method learns a set of spatial filters that maximize class separability of binary support vector machine (SVM) through a gradient descent approach. Regularization issues are discussed in detail and a Frobenius-norm regularization is proposed to efficiently exclude uninformative filters coefficients. Experiments carried out on multiclass one-against-all classification and target detection show the capabilities of the learned spatial filters.

Liver, Gastrointestinal, and Cardiac Toxicity in Intermediate Hepatocellular Carcinoma Treated With PRECISION TACE With Drug-Eluting Beads: Results From the PRECISION V Randomized Trial.

OBJECTIVE. The purpose of our study was to evaluate hepatic, gastrointestinal, and cardiac toxicity after PRECISION transarterial chemoembolization (TACE) with drug-eluting beads (DEB) versus conventional TACE with doxorubicin in the treatment of intermediate-stage hepatocellular carcinoma (HCC).SUBJECTS AND METHODS. Two hundred twelve patients (185 men and 27 women; mean age, 67 years) were randomized to TACE with DEB or conventional TACE. The majority of patients (67% in both groups) presented in a more advanced stage. Safety was measured by rate of adverse events (Southwest Oncology Group criteria) and changes in laboratory parameters. Cardiotoxicity was assessed with left ventricular ejection fraction (LVEF) mainly on MRI or echocardiography.RESULTS. The mean maximum postchemoembolization alanine transaminase increase in the DEB group was 50% less than in the conventional TACE group (p < 0.001) and 41% less in respect to aspartate transaminase (p < 0.001). End-of-study values returned to approximately baseline levels but with greater variability in conventional TACE patients. Treatment-emergent adverse events in the hepatobiliary system organ class occurred in 16.1% of DEB group patients compared with 25% of conventional TACE patients. There were fewer liver toxicity events in the DEB group. There was a small but statistically significant difference in mean change from baseline in LVEF between the two groups of 4 percentage points for the conventional TACE group (95% CI, 0.71-7.3; p = 0.018).CONCLUSION. PRECISION TACE with DEB loaded with doxorubicin offers a safe therapy option for intermediate-stage HCC, even in patients with more advanced liver disease.

Personalized modeling for drug concentration prediction using Support Vector Machine

Building a personalized model to describe the drug concentration inside the human body for each patient is highly important to the clinical practice and demanding to the modeling tools. Instead of using traditional explicit methods, in this paper we propose a machine learning approach to describe the relation between the drug concentration and patients' features. Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. We focus mainly on the prediction of the drug concentrations as well as the analysis of different features' influence. Models are built based on Support Vector Machine and the prediction results are compared with the traditional analytical models.

Time Series Input Selection using Multiple Kernel Learning

In this paper we study the relevance of multiple kernel learning (MKL) for the automatic selection of time series inputs. Recently, MKL has gained great attention in the machine learning community due to its flexibility in modelling complex patterns and performing feature selection. In general, MKL constructs the kernel as a weighted linear combination of basis kernels, exploiting different sources of information. An efficient algorithm wrapping a Support Vector Regression model for optimizing the MKL weights, named SimpleMKL, is used for the analysis. In this sense, MKL performs feature selection by discarding inputs/kernels with low or null weights. The approach proposed is tested with simulated linear and nonlinear time series (AutoRegressive, Henon and Lorenz series).

Methodological assessment of HCC literature.

Despite the fact that the hepatocellular carcinoma (HCC) represents a major health problem, very few interventions are available for this disease, and only sorafenib is approved for the treatment of advanced disease. Of note, only very few interventions have been thoroughly evaluated over time for HCC patients compared with several hundreds in other, equally highly lethal, tumours. Additionally, clinical trials in HCC have often been questioned for poor design and methodological issues. As a consequence, a gap between what is measured in clinical trials and what clinicians have to face in daily practice often occurs. As a result of this scenario, even the most recent guidelines for treatment of HCC patients use low strength evidence to make recommendations. In this review, we will discuss some of the potential methodological issues hindering a rational development of new treatments for HCC patients.

Genetic analyses reveal a role for vitamin D insufficiency in HCV-associated hepatocellular carcinoma development

BACKGROUND: Vitamin D insufficiency has been associated with the occurrence of various types of cancer, but causal relationships remain elusive. We therefore aimed to determine the relationship between genetic determinants of vitamin D serum levels and the risk of developing hepatitis C virus (HCV)-related hepatocellular carcinoma (HCC). METHODOLOGY/PRINCIPAL FINDINGS: Associations between CYP2R1, GC, and DHCR7 genotypes that are determinants of reduced 25-hydroxyvitamin D (25[OH]D3) serum levels and the risk of HCV-related HCC development were investigated for 1279 chronic hepatitis C patients with HCC and 4325 without HCC, respectively. The well-known associations between CYP2R1 (rs1993116, rs10741657), GC (rs2282679), and DHCR7 (rs7944926, rs12785878) genotypes and 25(OH)D3 serum levels were also apparent in patients with chronic hepatitis C. The same genotypes of these single nucleotide polymorphisms (SNPs) that are associated with reduced 25(OH)D3 serum levels were found to be associated with HCV-related HCC (P = 0.07 [OR = 1.13, 95% CI = 0.99-1.28] for CYP2R1, P = 0.007 [OR = 1.56, 95% CI = 1.12-2.15] for GC, P = 0.003 [OR = 1.42, 95% CI = 1.13-1.78] for DHCR7; ORs for risk genotypes). In contrast, no association between these genetic variations and liver fibrosis progression rate (P>0.2 for each SNP) or outcome of standard therapy with pegylated interferon-α and ribavirin (P>0.2 for each SNP) was observed, suggesting a specific influence of the genetic determinants of 25(OH)D3 serum levels on hepatocarcinogenesis. CONCLUSIONS/SIGNIFICANCE: Our data suggest a relatively weak but functionally relevant role for vitamin D in the prevention of HCV-related hepatocarcinogenesis.

Le carcinome hépatocellulaire: une approche multidisciplinaire [Hepatocellular carcinoma: a multidisciplinary approach]

The treatment of the hepatocellular carcinoma (HCC) is multidisciplinary. Hepatic transplantation offers the best chances of survival for patients with hepatic cirrhosis and HCC. However the indications for transplantation are limited. For patients that do not qualify for liver transplantation, surgical excision and percutaneous ablative treatment can also be curative. Five years survival then reaches 50%. The choice of treatment is based upon the patient's clinical state, the hepatic function and the cancer clinical stage. Follow-up is crucial as recurrences can be treated by following similar algorithms. The efficacy of oncological adjuvant and neoadjuvant treatment is not yet proved.

Example-based support vector machine for drug concentration analysis

Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (S VM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVM-based approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.

Multitask learning of environmental spatial data

The present research deals with an application of artificial neural networks for multitask learning from spatial environmental data. The real case study (sediments contamination of Geneva Lake) consists of 8 pollutants. There are different relationships between these variables, from linear correlations to strong nonlinear dependencies. The main idea is to construct a subsets of pollutants which can be efficiently modeled together within the multitask framework. The proposed two-step approach is based on: 1) the criterion of nonlinear predictability of each variable ?k? by analyzing all possible models composed from the rest of the variables by using a General Regression Neural Network (GRNN) as a model; 2) a multitask learning of the best model using multilayer perceptron and spatial predictions. The results of the study are analyzed using both machine learning and geostatistical tools.

Idarubicin-loaded beads for chemoembolisation of hepatocellular carcinoma: results of the IDASPHERE phase I trial.

BACKGROUND: A phase I dose-escalation trial of transarterial chemoembolisation (TACE) with idarubicin-loaded beads was performed in cirrhotic patients with hepatocellular carcinoma (HCC). AIM: To estimate the maximum-tolerated dose (MTD) and to assess safety, efficacy, pharmacokinetics and quality of life. METHODS: Patients received a single TACE session with injection of 2 mL drug-eluting beads (DEBs; DC Bead 300-500 μm) loaded with idarubicin. The idarubicin dose was escalated according to a modified continuous reassessment method. MTD was defined as the dose level closest to that causing dose-limiting toxicity (DLT) in 20% of patients. RESULTS: Twenty-one patients were enrolled, including nine patients at 5 mg, six patients at 10 mg, and six patients at 15 mg. One patient at each dose level experienced DLT (acute myocardial infarction, hyperbilirubinaemia and elevated aspartate aminotransferase (AST) at 5-, 10- and 15-mg, respectively). The calculated MTD of idarubicin was 10 mg. The most frequent grade ≥3 adverse events were pain, elevated AST, elevated γ-glutamyltranspeptidase and thrombocytopenia. At 2 months, the objective response rate was 52% (complete response, 28%, and partial response, 24%) by modified Response Evaluation Criteria in Solid Tumours. The median time to progression was 12.1 months (95% CI 7.4 months - not reached); the median overall survival was 24.5 months (95% CI 14.7 months - not reached). Pharmacokinetic analysis demonstrated the ability of DEBs to release idarubicin slowly. CONCLUSIONS: Using drug-eluting beads, the maximum-tolerated dose of idarubicin was 10 mg per TACE session. Encouraging responses and median time to progression were observed. Further clinical investigations are warranted (NCT01040559).

Influence of HIV-related immunodeficiency on the risk of hepatocellular carcinoma.

OBJECTIVE: To investigate HIV-related immunodeficiency as a risk factor for hepatocellular carcinoma (HCC) among persons infected with HIV, while controlling for the effect of frequent coinfection with hepatitis C and B viruses. DESIGN: A case-control study nested in the Swiss HIV Cohort Study. METHODS: Twenty-six HCC patients were identified in the Swiss HIV Cohort Study or through linkage with Swiss Cancer Registries, and were individually matched to 251 controls according to Swiss HIV Cohort Study centre, sex, HIV-transmission category, age and year at enrollment. Odds ratios and corresponding confidence intervals were estimated by conditional logistic regression. RESULTS: All HCC patients were positive for hepatitis B surface antigen or antibodies against hepatitis C virus. HCC patients included 14 injection drug users (three positive for hepatitis B surface antigen and 13 for antibodies against hepatitis C virus) and 12 men having sex with men/heterosexual/other (11 positive for hepatitis B surface antigen, three for antibodies against hepatitis C virus), revealing a strong relationship between HIV transmission route and hepatitis viral type. Latest CD4+ cell count [Odds ratio (OR) per 100 cells/mul decrease = 1.33, 95% confidence interval (CI) 1.06-1.68] and CD4+ cell count percentage (OR per 10% decrease = 1.65, 95% CI 1.01-2.71) were significantly associated with HCC. The effects of CD4+ cell count were concentrated among men having sex with men/heterosexual/other rather than injecting drug users. Highly active antiretroviral therapy use was not significantly associated with HCC risk (OR for ever versus never = 0.59, 95% confidence interval 0.18-1.91). CONCLUSION: Lower CD4+ cell counts increased the risk for HCC among persons infected with HIV, an effect that was particularly evident for hepatitis B virus-related HCC arising in non-injecting drug users.