Sea organisms as a source of collagen-derived polymers for skin tissue engineering applications

Advanced therapies combating acute and chronic skin wounds are likely to be brought about using our knowledge of regenerative medicine coupled with appropriately tissue engineered skin substitutes. At the present time, there are no models of an artificial skin that completely replicate normal uninjured skin and they are usually accompanied by fibrotic reactions that result in the production of a scar. Natural biopolymers such as collagen have been a lot investigated as potential source of biomaterial for skin replacement in Tissue Engineering. Collagens are the most abundant high molecular weight proteins in both invertebrate and vertebrate organisms, including mammals, and possess mainly a structural role in connective tissues. From this, they have been elected as one of the key biological materials in tissue regeneration approaches, as skin tissue engineering. In addition, industry is constantly searching for new natural sources of collagen and upgraded methodologies for their production. The most common sources are skin and bone from bovine and porcine origin. However, these last carry high risk of bovine spongiform encephalopathy or transmissible spongiform encephalopathy and immunogenic responses. On the other hand, the increase of jellyfish has led us to consider this marine organism as potential collagen source for tissue engineering applications. In the present study, novel form of acid and pepsin soluble collagen were extracted from dried Rhopilema hispidum jellyfish species in an effort to obtain an alternative and safer collagen. We studied different methods of collagen purification (tissues and experimental procedures). The best collagen yield was obtained using pepsin extraction method (34.16 mg collagen/g of tissue). The isolated collagen was characterized by SDS-polyacrylamide gel electrophoresis and circular dichroism spectroscopy.

Application of active and transfer learning to wound image segmentation

Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications on wound management for pets. The importance of a precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for the chronic wounds. The goal of the research was to propose an automated pipeline capable of segmenting natural light-reflected wound images of animals. Two datasets composed by light-reflected images were used in this work: Deepskin dataset, 1564 human wound images obtained during routine dermatological exams, with 145 manual annotated images; Petwound dataset, a set of 290 wound photos of dogs and cats with 0 annotated images. Two implementations of U-Net Convolutioal Neural Network model were proposed for the automated segmentation. Active Semi-Supervised Learning techniques were applied for human-wound images to perform segmentation from 10% of annotated images. Then the same models were trained, via Transfer Learning, adopting an Active Semi- upervised Learning to unlabelled animal-wound images. The combination of the two training strategies proved their effectiveness in generating large amounts of annotated samples (94% of Deepskin, 80% of PetWound) with the minimal human intervention. The correctness of automated segmentation were evaluated by clinical experts at each round of training thus we can assert that the results obtained in this thesis stands as a reliable solution to perform a correct wound image segmentation. The use of Transfer Learning and Active Semi-Supervied Learning allows to minimize labelling effort from clinicians, even requiring no starting manual annotation at all. Moreover the performances of the model with limited number of parameters suggest the implementation of smartphone-based application to this topic, helping the future standardization of light-reflected images as acknowledge medical images.