No abstract

This study evaluated whether deep learning frameworks trained in large datasets can help non-dermatologist physicians improve their accuracy in categorizing the seven most common pigmented skin lesions. Open-source skin images were downloaded from the International Skin Imaging Collaboration (ISIC) archive. Different deep neural networks (DNNs) (n = 8) were trained based on a random dataset constituted of 8015 images. A test set of 2003 images was used to assess the classifiers’ performance at low (300 × 224 RGB) and high (600 × 450 RGB) image resolution and aggregated data (age, sex and lesion localization). We also organized two different contests to compare the DNN performance to that of general practitioners by means of unassisted image observation. Both at low and high image resolution, the DNN framework differentiated dermatological images with appreciable performance. In all cases, the accuracy was improved when adding clinical data to the framework. Finally, the least accurate DNN outperformed general practitioners. The physician’s accuracy was statistically improved when allowed to use the output of this algorithmic framework as guidance. DNNs are proven to be high performers as skin lesion classifiers and can improve general practitioner diagnosis accuracy in a routine clinical scenario.

Heterogeneity in the distribution of tumor blood supply affects the response to chemotherapy by influencing the intratumoral delivery of therapeutic agents. After the administration of effective doses of anticancer drugs to a tumor, cells in profusely perfused areas receive enough to destroy them while cells in the poorly perfused areas are exposed to lower drug concentrations and, therefore, survive. This phenomenon could explain in part the difficulty in the treatment of human solid tumors.

No abstract

Background: Trabectedin (ET-743, Yondelis) is a marine alkaloid isolated from the tunicate Ecteinascidia turbinata, cytotoxic against a variety of tumor cell lines in vitro and human tumor xenografts in vivo. It has been approved by EMEA for the 2nd line therapy of soft tissue sarcomas in 2007 and for the 2nd line therapy of ovarian cancer in 2009. Myxoid liposarcoma (MLS) is a specific histological subtype within the family of adults soft tissue sarcomas. Specifically >90% of usual myxoid/round cell liposarcomas (MLS/RCLS) are characterized by the chromosomal translocation t(12;16) (q13;p11), which produces the FUS-CHOP oncogene. Different variants of the fusion gene have been previously described but with no demonstrable prognostic effect although the type III MLS seem correlate with a more severe outcome than type II MLS. Materials and Methods: To elucidate the mechanisms behind the differential sensitivity to trabectedin, myxoid liposarcomas type II and type III were xenografted in nude mice. When tumor load achieves about 200–400 mg mice were divided into the experimental groups. Trabectedin was administered at 0.15 mg/kg, i.v. every 7 days for three times. Tumor growth was monitored by Vernier caliper. The binding of FUS-CHOP to some of its target promoters was monitored by Chromatin Immuno Precipitation (ChIP) to verify the drug ability to displace the binding. ChIP were performed with ProtG Sepharose and the anti-FUS and anti-CHOP antibody. The immunoprecipitated DNAs were analyzed by quantitative Real Time PCR. FN1, PTX3, CDK4, IL8 and CHOP were used as target genes. Results: We found that trabectedin was more effective on type II than type III MLS xenografts. The response to trabectedin in type II xenografts was associated with partial regression and pathological response. Type III MLS xenografts appeared much less sensitive to trabectedin and tumors did not regress. Molecular analysis revealed that trabectedin was able to remove FUS-CHOP type II and III from its own target genes 24 hours after treatment. 72 hours after treatment, FUS-CHOP Type III was attached to its targets whereas FUS-CHOP Type II remained unbound. These data explain why in order to achieve a significant regression of type III MLS xenografts a more prolonged treatment with trabectedin is required. Conclusions: These results suggest that the different sensitivity of type II and type III MLS to trabectedin are related to a different duration of the drug ability to display FUS-CHOP from the selected target genes. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference: Molecular Targets and Cancer Therapeutics; 2011 Nov 12-16; San Francisco, CA. Philadelphia (PA): AACR; Mol Cancer Ther 2011;10(11 Suppl):Abstract nr A17.