Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.

Abstract: Sarcomas are rare malignant tumors arising from the mesenchymal tissues at all body sites. The inventors show that in a mouse model of p16/p19 deficiency prone to tumor development, the absence of the mouse pantetheinase Vnn1 enhances the frequency of aggressive fibrosarcomas. They also show that reintroduction of a catalytically active form of the Vnn1 pantetheinase limits tumor growth in vivo. Interestingly, VNN1 expression in human sarcomas is associated with reduced aggressiveness and lower risk of metastatic relapse in patients. In conclusion, Vnn1 represents a novel marker of sarcoma and may modulate tumor aggressiveness by sustaining myofibroblast cell differentiation, thereby limiting evolution towards undifferentiated tumors. The present invention relates to the use of Vnn1 as a biomarker and a therapeutic target in sarcomas.

Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.

Abstract: Sarcomas are rare malignant tumors arising from the mesenchymal tissues at all body sites. The inventors show that in a mouse model of p16/p19 deficiency prone to tumor development, the absence of the mouse pantetheinase Vnn1 enhances the frequency of aggressive fibrosarcomas. They also show that reintroduction of a catalytically active form of the Vnn1 pantetheinase limits tumor growth in vivo. Interestingly, VNN1 expression in human sarcomas is associated with reduced aggressiveness and lower risk of metastatic relapse in patients. In conclusion, Vnn1 represents a novel marker of sarcoma and may modulate tumor aggressiveness by sustaining myofibroblast cell differentiation, thereby limiting evolution towards undifferentiated tumors. The present invention relates to the use of Vnn1 as a biomarker and a therapeutic target in sarcomas.

Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.

Abstract: The method for predicting the anti-tumor response in a human or animal having a tumor to multiple kinase inhibitors, using any multiple kinase inhibitor, comprises selection of genes encoding for protein kinases targeted by the said tyrosine kinase inhibitor, for each one of these genes, providing at least one nucleic acid probe which hybridizes to said gene under stringent conditions, thus providing an array of nucleic acid probes, having a biological sample containing cancer cells from said human or animal, extracting DNA from the sample, fragmenting into DNA fragments, optionally labeling the DNA fragments, submitting the optionally labeled DNA fragments to hybridization with the array of nucleic acid probes, recovering and quantifying for all the genes the gains or losses in gene copy numbers, wherein gains and losses of gene copy numbers of each selected gene are used to determine whether the tumor is sensitive or not to said kinase inhibitor.

Abstract: The present invention relates to a method making it possible to identify the patients, from among those affected by a given solid cancer, that have increased risk of premature death. Said method is based on the ex vivo analysis of the lymphocytic diversity of the patients on the basis of a biological sample containing lymphocytes. In fact, low lymphocytic diversity is related to a poor prognosis. Specifically, it is possible to set a diversity threshold, depending on the analysis technology used and the cancer affecting the patient, beyond which the life expectancy of the patient is significantly less than that, in general, of the patients affected by the same disease.

Abstract: The subject of the present invention concerns proteins with IL-6 inhibiting activity and thier use, and the use of proteins containing at least the amino acid seqeunce SEQ ID NO. 4 as medicianl product, in paritcular as anti-cancerous agent.

Abstract: The subject of the present invention concerns proteins with IL-6 inhibiting activity and thier use, and the use of proteins containing at least the amino acid seqeunce SEQ ID NO. 4 as medicianl product, in paritcular as anti-cancerous agent.