New Chitosan-Based Co-Delivery Nanosystem for Diabetes Mellitus Therapy.

Type 2 diabetes mellitus (T2DM) is one of the most common metabolic disorders, with a major involvement of oxidative stress in its onset and progression. Pioglitazone (Pio) is an antidiabetic drug that mainly works by reducing insulin resistance, while curcumin (Cur) is a powerful antioxidant with an important hypoglycemic effect. Both drugs are associated with several drawbacks, such as reduced bioavailability and a short half-life time (Pio), as well as instability and poor water solubility (Cur), which limit their therapeutic use. In order to overcome these disadvantages, new co-delivery (Pio and Cur) chitosan-based nanoparticles (CS-Pio-Cur NPs) were developed and compared with simple NPs (CS-Pio/CS-Cur NPs). The NPs were characterized using dynamic light scattering (DLS), transmission electron microscopy (TEM), X-ray diffraction (XRD), and Fourier-transform infrared spectroscopy (FTIR). In addition, the entrapment efficiency (EE) and loading capacity (LC), as well as the release profile, of the APIs (Pio and Cur) from the CS-APIs NPs in simulated fluids (SGF, SIF, and SCF) were also assessed. All the CS-APIs NPs presented a small particle size (PS) (211.6-337.4 nm), a proper polydispersity index (PI) (0.104 and 0.289), and a positive zeta potential (ZP) (21.83 mV-32.64 mV). Based on the TEM results, an amorphous state could be attributed to the CA-APIs NPs, and the TEM analysis showed a spherical shape with a nanometric size for the CS-Pio-Cur NPs. The FT-IR spectroscopy supported the successful loading of the APIs into the CS matrix and proved some interactions between the APIs and CS. The CS-Pio-Cur NPs presented increased or similar EE (85.76% ± 4.89 for Cur; 92.16% ± 3.79 for Pio) and LC% (23.40% ± 1.62 for Cur; 10.14% ± 0.98 for Pio) values in comparison with simple NPs, CS-Cur NPs (EE = 82.46% ± 1.74; LC = 22.31% ± 0.94), and CS-Pio NPs (EE = 93.67% ± 0.89; LC = 11.24% ± 0.17), respectively. Finally, based on the release profile results, it can be appreciated that the developed co-delivery nanosystem, CS-Pio-Cur NPs, assures a controlled and prolonged release of Pio and Cur from the polymer matrix along the GI tract.

Complexes of Ibuprofen Thiazolidin-4-One Derivatives with ß-Cyclodextrin: Characterization and In Vivo Release Profile and Biological Evaluation.

Generally, NSAIDs are weakly soluble in water and contain both hydrophilic and hydrophobic groups. One of the most widely used NSAIDs is ibuprofen, which has a poor solubility and high permeability profile. By creating dynamic, non-covalent, water-soluble inclusion complexes, cyclodextrins (CDs) can increase the dissolution rate of low aqueous solubility drugs, operating as a drug delivery vehicle, additionally contributing significantly to the chemical stability of pharmaceuticals and to reducing drug-related irritability. In order to improve the pharmacological and pharmacokinetics profile of ibuprofen, new thiazolidin-4-one derivatives of ibuprofen (4b, 4g, 4k, 4m) were complexed with ß-CD, using co-precipitation and freeze-drying. The new ß-CD complexes (ß-CD-4b, ß-CD-4g, ß-CD-4k, ß-CD-4m) were characterized using scanning electronic microscopy (SEM), differential scanning calorimetry (DSC), X-ray diffraction and a phase solubility test. Using the AutoDock-VINA algorithm included in YASARA-structure software, we investigated the binding conformation of ibuprofen derivatives to ß-CD and measured the binding energies. We also performed an in vivo biological evaluation of the ibuprofen derivatives and corresponding ß-CD complexes, using analgesic/anti-inflammatory assays, as well as a release profile. The results support the theory that ß-CD complexes (ß-CD-4b, ß-CD-4g, ß-CD-4k, ß-CD-4m) have a similar effect to ibuprofen derivatives (4b, 4g, 4k, 4m). Moreover, the ß-CD complexes demonstrated a delayed release profile, which provides valuable insights into the drug-delivery area, focused on ibuprofen derivatives.

Modern Approaches in Wounds Management.

Wound management represents a well-known continuous challenge and concern of the global healthcare systems worldwide. The challenge is on the one hand related to the accurate diagnosis, and on the other hand to establishing an effective treatment plan and choosing appropriate wound care products in order to maximize the healing outcome and minimize the financial cost. The market of wound dressings is a dynamic field which grows and evolves continuously as a result of extensive research on developing versatile formulations with innovative properties. Hydrogels are one of the most attractive wound care products which, in many aspects, are considered ideal for wound treatment and are widely exploited for extension of their advantages in healing process. Smart hydrogels (SHs) offer the opportunities of the modulation physico-chemical properties of hydrogels in response to external stimuli (light, pressure, pH variations, magnetic/electric field, etc.) in order to achieve innovative behavior of their three-dimensional matrix (gel-sol transitions, self-healing and self-adapting abilities, controlled release of drugs). The SHs response to different triggers depends on their composition, cross-linking method, and manufacturing process approach. Both native or functionalized natural and synthetic polymers may be used to develop stimuli-responsive matrices, while the mandatory characteristics of hydrogels (biocompatibility, water permeability, bioadhesion) are preserved. In this review, we briefly present the physiopathology and healing mechanisms of chronic wounds, as well as current therapeutic approaches. The rational of using traditional hydrogels and SHs in wound healing, as well as the current research directions for developing SHs with innovative features, are addressed and discussed along with their limitations and perspectives in industrial-scale manufacturing.

New Smart Bioactive and Biomimetic Chitosan-Based Hydrogels for Wounds Care Management.

Wound management represents a continuous challenge for health systems worldwide, considering the growing incidence of wound-related comorbidities, such as diabetes, high blood pressure, obesity, and autoimmune diseases. In this context, hydrogels are considered viable options since they mimic the skin structure and promote autolysis and growth factor synthesis. Unfortunately, hydrogels are associated with several drawbacks, such as low mechanical strength and the potential toxicity of byproducts released after crosslinking reactions. To overcome these aspects, in this study new smart chitosan (CS)-based hydrogels were developed, using oxidized chitosan (oxCS) and hyaluronic acid (oxHA) as nontoxic crosslinkers. Three active product ingredients (APIs) (fusidic acid, allantoin, and coenzyme Q10), with proven biological effects, were considered for inclusion in the 3D polymer matrix. Therefore, six API-CS-oxCS/oxHA hydrogels were obtained. The presence of dynamic imino bonds in the hydrogels' structure, which supports their self-healing and self-adapting properties, was confirmed by spectral methods. The hydrogels were characterized by SEM, swelling degree, pH, and the internal organization of the 3D matrix was studied by rheological behavior. Moreover, the cytotoxicity degree and the antimicrobial effects were also investigated. In conclusion, the developed API-CS-oxCS/oxHA hydrogels have real potential as smart materials in wound management, based on their self-healing and self-adapting properties, as well as on the benefits of APIs.

Feasibility of a lung airway navigation system using fiber-Bragg shape sensing and artificial intelligence for early diagnosis of lung cancer.

Currently early diagnosis of malignant lesions at the periphery of lung parenchyma requires guidance of the biopsy needle catheter from the bronchoscope into the smaller peripheral airways via harmful X-ray radiation. Previously, we developed an image-guided system, iMTECH which uses electromagnetic tracking and although it increases the precision of biopsy collection and minimizes the use of harmful X-ray radiation during the interventional procedures, it only traces the tip of the biopsy catheter leaving the remaining catheter untraceable in real time and therefore increasing image registration error. To address this issue, we developed a shape sensing guidance system containing a fiber-Bragg grating (FBG) catheter and an artificial intelligence (AI) software, AIrShape to track and guide the entire biopsy instrument inside the lung airways, without radiation or electromagnetic navigation. We used a FBG fiber with one central and three peripheral cores positioned at 120° from each other, an array of 25 draw tower gratings with 1cm/3nm spacing, 2 mm grating length, Ormocer-T coating, and a total outer diameter of 0.2 mm. The FBG fiber was placed in the working channel of a custom made three-lumen catheter with a tip bending mechanism (FBG catheter). The AIrShape software determines the position of the FBG catheter by superimposing its position to the lung airway center lines using an AI algorithm. The feasibility of the FBG system was tested in an anatomically accurate lung airway model and validated visually and with the iMTECH platform. The results prove a viable shape-sensing hardware and software navigation solution for flexible medical instruments to reach the peripheral airways. During future studies, the feasibility of FBG catheter will be tested in pre-clinical animal models.

Chitosan Microparticles Loaded with New Non-Cytotoxic Isoniazid Derivatives for the Treatment of Tuberculosis: In Vitro and In Vivo Studies.

Lately, in the world of medicine, the use of polymers for the development of innovative therapies seems to be a major concern among researchers. In our case, as a continuation of the research that has been developed so far regarding obtaining new isoniazid (INH) derivatives for tuberculosis treatment, this work aimed to test the ability of the encapsulation method to reduce the toxicity of the drug, isoniazid and its new derivatives. To achieve this goal, the following methods were applied: a structural confirmation of isoniazid derivatives using LC-HRMS/MS; the obtaining of microparticles based on polymeric support; the determination of their loading and biodegradation capacities; in vitro biocompatibility using MTT cell viability assays; and, last but not least, in vivo toxicological screening for the determination of chronic toxicity in laboratory mice, including the performance of a histopathological study and testing for liver enzymes. The results showed a significant reduction in tissue alterations, the disappearance of cell necrosis and microvesicular steatosis areas and lower values of the liver enzymes TGO, TGP and alkaline phosphatase when using encapsulated forms of drugs. In conclusion, the encapsulation of INH and INH derivatives with chitosan had beneficial effects, suggesting a reduction in hepatotoxicity and, therefore, the achievement of the aim of this paper.

Assessment of Deep Learning Methods for Differentiating Autoimmune Disorders in Ultrasound Images.

At present, deep learning becomes an important tool in medical image analysis, with good performance in diagnosing, pattern detection, and segmentation. Ultrasound imaging offers an easy and rapid method to detect and diagnose thyroid disorders. With the help of a computer-aided diagnosis (CAD) system based on deep learning, we have the possibility of real-time and non-invasive diagnosing of thyroidal US images. This paper proposed a study based on deep learning with transfer learning for differentiating the thyroidal ultrasound images using image pixels and diagnosis labels as inputs. We trained, assessed, and compared two pre-trained models (VGG-19 and Inception v3) using a dataset of ultrasound images consisting of 2 types of thyroid ultrasound images: autoimmune and normal. The training dataset consisted of 615 thyroid ultrasound images, from which 415 images were diagnosed as autoimmune, and 200 images as normal. The models were assessed using a dataset of 120 images, from which 80 images were diagnosed as autoimmune, and 40 images diagnosed as normal. The two deep learning models obtained very good results, as follows: the pre-trained VGG-19 model obtained 98.60% for the overall test accuracy with an overall specificity of 98.94% and overall sensitivity of 97.97%, while the Inception v3 model obtained 96.4% for the overall test accuracy with an overall specificity of 95.58% and overall sensitivity of 95.58.

Design, preparation and in vitro characterization of biomimetic and bioactive chitosan/polyethylene oxide based nanofibers as wound dressings.

Chitosan-based nanofibers (CS-NFs) are excellent artificial extracellular matrices (ECMs) due to the resemblance of CS with the glycosaminoglycans of the natural ECMs. Despite this excellent feature, the poor electrospinnability and mechanical properties of CS are responsible for important limitations in respect to its biomedical applications. To improve the CS's physico-chemical properties, new bioactive and biomimetic CS-NFs were formulated with polyethylene oxide (PEO), having incorporated different active components (ACs) with important beneficial effects for healing. Manuka honey (trophic and antimicrobial effects), propolis (antimicrobial effects), Calendula officinalis infusion (antioxidant effect, reepithelialization stimulating agent), insulin (trophic effect), and L-arginine (angiogenic effect) were selected as ACs. SEM morphology analysis revealed well-alignment, unidirectional arrays, with small diameters, no beads, and smooth surfaces for developed CS_PEO-ACs NFs. The developed NFs showed good biodegradability (NFs mats lost up to 60% of their initial weight in PBS), increased hemocompatibility (hemolytic index less than 4%), and a reduced cytotoxicity degree (cell viability degree more than 90%). In addition, significant antioxidant and antimicrobial effects were noted for the developed NFs which make them suitable for chronic wounds, due to the role of oxidative stress and infection risk in delaying normal wound healing. The most suitable for wound healing applications seems to be CS_PEO@P_C which showed an improved hemolysis index (2.92 ± 0.16%), is non-toxic (cell viability degree more than 97%), and has also significant radical scavenging effect (DPPH inhibition more than 65%). In addition, CS_PEO@P_C presents increased antimicrobial effects, more noticeably for Staphylococcus aureus strain, which is a key feature in preventing wound infection and delaying the healing process. It can be concluded that the developed CS/PEO-ACs NFs are very promising biomaterials for wound care, especially CS_PEO@P_C.

Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.

Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.

New Hyaluronic Acid/Polyethylene Oxide-Based Electrospun Nanofibers: Design, Characterization and In Vitro Biological Evaluation.

Natural compounds have been used as wound-healing promoters and are also present in today's clinical proceedings. In this research, different natural active components such as propolis, Manuka honey, insulin, L-arginine, and Calendula officinalis infusion were included into hyaluronic acid/poly(ethylene)oxide-based electrospun nanofiber membranes to design innovative wound-dressing biomaterials. Morphology and average fiber diameter were analyzed by scanning electron microscopy. Chemical composition was proved by Fourier transform infrared spectroscopy, which indicated successful incorporation of the active components. The nanofiber membranes with propolis and Calendula officinalis showed best antioxidant activity, cytocompatibility, and antimicrobial properties against pathogen strains Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa and had an average diameter of 217 ± 19 nm with smooth surface aspect. Water vapor transmission rate was in agreement with the range suitable for preventing infections or wound dehydration (~5000 g/m2 24 h). Therefore, the developed hyaluronic acid/poly(ethylene)oxide nanofibers with additional natural components showed favorable features for clinical use as wound dressings.

Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods.

Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.

Recent Biomedical Approaches for Chitosan Based Materials as Drug Delivery Nanocarriers.

In recent decades, drug delivery systems (DDSs) based on nanotechnology have been attracting substantial interest in the pharmaceutical field, especially those developed based on natural polymers such as chitosan, cellulose, starch, collagen, gelatin, alginate and elastin. Nanomaterials based on chitosan (CS) or chitosan derivatives are broadly investigated as promising nanocarriers due to their biodegradability, good biocompatibility, non-toxicity, low immunogenicity, great versatility and beneficial biological effects. CS, either alone or as composites, are suitable substrates in the fabrication of different types of products like hydrogels, membranes, beads, porous foams, nanoparticles, in-situ gel, microparticles, sponges and nanofibers/scaffolds. Currently, the CS based nanocarriers are intensely studied as controlled and targeted drug release systems for different drugs (anti-inflammatory, antibiotic, anticancer etc.) as well as for proteins/peptides, growth factors, vaccines, small DNA (DNAs) and short interfering RNA (siRNA). This review targets the latest biomedical approaches for CS based nanocarriers such as nanoparticles (NPs) nanofibers (NFs), nanogels (NGs) and chitosan coated liposomes (LPs) and their potential applications for medical and pharmaceutical fields. The advantages and challenges of reviewed CS based nanocarriers for different routes of administration (oral, transmucosal, pulmonary and transdermal) with reference to classical formulations are also emphasized.

Deep Learning Algorithm for the Confirmation of Mucosal Healing in Crohn's Disease, Based on Confocal Laser Endomicroscopy Images.

BACKGROUND AND AIMS: Mucosal healing (MH) is associated with a stable course of Crohn's disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator's errors and automate assessment of CLE images, we used a deep learning (DL) model for image analysis. We hypothesized that DL combined with convolutional neural networks (CNNs) and long short-term memory (LSTM) can distinguish between normal and inflamed colonic mucosa from CLE images. METHODS: The study included 54 patients, 32 with known active CD, and 22 control patients (18 CD patients with MH and four normal mucosa patients with no history of inflammatory bowel diseases). We designed and trained a deep convolutional neural network to detect active CD using 6,205 endomicroscopy images classified as active CD inflammation (3,672 images) and control mucosal healing or no inflammation (2,533 images). CLE imaging was performed on four colorectal areas and the terminal ileum. Gold standard was represented by the histopathological evaluation. The dataset was randomly split in two distinct training and testing datasets: 80% data from each patient were used for training and the remaining 20% for testing. The training dataset consists of 2,892 images with inflammation and 2,189 control images. The testing dataset consists of 780 images with inflammation and 344 control images of the colon. We used a CNN-LSTM model with four convolution layers and one LSTM layer for automatic detection of MH and CD diagnosis from CLE images. RESULTS: CLE investigation reveals normal colonic mucosa with round crypts and inflamed mucosa with irregular crypts and tortuous and dilated blood vessels. Our method obtained a 95.3% test accuracy with a specificity of 92.78% and a sensitivity of 94.6%, with an area under each receiver operating characteristic curves of 0.98. CONCLUSIONS: Using machine learning algorithms on CLE images can successfully differentiate between inflammation and normal ileocolonic mucosa and can be used as a computer aided diagnosis for CD. Future clinical studies with a larger patient spectrum will validate our results and improve the CNN-SSTM model.

Transfer learning with pre-trained deep convolutional neural networks for the automatic assessment of liver steatosis in ultrasound images.

AIM: In this paper we proposed different architectures of convolutional neural network (CNN) to classify fatty liver disease in images using only pixels and diagnosis labels as input. We trained and validated our models using a dataset of 629 images consisting of 2 types of liver images, normal and liver steatosis. MATERIAL AND METHODS: We assessed two pre-trained models of convolutional neural networks, Inception-v3 and VGG-16 using fine-tuning. Both models were pre-trained on ImageNet dataset to extract features from B-mode ultrasound liver images. The results obtained through these methods were compared for selecting the predictive model with the best performance metrics. We trained the two models using a dataset of 262 images of liver steatosis and 234 images of normal liver. We assessed the models using a dataset of 70 liver steatosis im-ages and 63 normal liver images. RESULTS: The proposed model that used Inception v3 obtained a 93.23% test accuracy with a sensitivity of 89.9%% and a precision of 96.6%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.93. The other proposed model that used VGG-16, obtained a 90.77% test accuracy with a sensitivity of 88.9% and a precision of 92.85%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.91. CONCLUSION: The deep learning algorithms that we proposed to detect steatosis and classify the images in normal and fatty liver images, yields an excellent test performance of over 90%. However, future larger studies are required in order to establish how these algorithms can be implemented in a clinical setting.

Finite Element Analysis of a Novel Aortic Valve Stent.

Worldwide, one of the leading causes of death for patients with cardiovascular disease is aortic valve failure or insufficiency as a result of calcification and cardiovascular disease. The surgical treatment consists of repair or total replacement of the aortic valve. Artificial aortic valve implantation via a percutaneous or endovascular procedure is the minimally invasive alternative to open chest surgery, and the only option for high-risk or older patients. Due to the complex anatomical location between the left ventricle and the aorta, there are still engineering design optimization challenges which influence the long-term durability of the valve. In this study we developed a computer model and performed a numerical analysis of an original self-expanding stent for transcatheter aortic valve in order to optimize its design and materials. The study demonstrates the current valve design could be a good alternative to the existing commercially available valve devices.

An Overview of Biopolymeric Electrospun Nanofibers Based on Polysaccharides for Wound Healing Management.

Currently, despite the thoroughgoing scientific research carried out in the area of wound healing management, the treatment of skin injuries, regardless of etiology remains a big provocation for health care professionals. An optimal wound dressing should be nontoxic, non-adherent, non-allergenic, should also maintain a humid medium at the wound interfacing, and be easily removed without trauma. For the development of functional and bioactive dressings, they must meet different conditions such as: The ability to remove excess exudates, to allow gaseous interchange, to behave as a barrier to microbes and to external physical or chemical aggressions, and at the same time to have the capacity of promoting the process of healing by stimulating other intricate processes such as differentiation, cell adhesion, and proliferation. Over the past several years, various types of wound dressings including hydrogels, hydrocolloids, films, foams, sponges, and micro/nanofibers have been formulated, and among them, the electrospun nanofibrous mats received an increased interest from researchers due to the numerous advantages and their intrinsic properties. The drug-embedded nanofibers are the potential candidates for wound dressing application by virtue of: Superior surface area-to volume ratio, enormous porosity (can allow oxy-permeability) or reticular nano-porosity (can inhibit the microorganisms'adhesion), structural similitude to the skin extracellular matrix, and progressive electrospinning methodology, which promotes a prolonged drug release. The reason that we chose to review the formulation of electrospun nanofibers based on polysaccharides as dressings useful in wound healing was based on the ever-growing research in this field, research that highlighted many advantages of the nanofibrillary network, but also a marked versatility in terms of numerous active substances that can be incorporated for rapid and infection-free tissue regeneration. In this review, we have extensively discussed the recent advancements performed on electrospun nanofibers (eNFs) formulation methodology as wound dressings, and we focused as well on the entrapment of different active biomolecules that have been incorporated on polysaccharides-based nanofibers, highlighting those bioagents capable of improving the healing process. In addition, in vivo tests performed to support their increased efficacy were also listed, and the advantages of the polysaccharide nanofiber-based wound dressings compared to the traditional ones were emphasized.

Skin Diseases Classification Using Deep Leaning Methods.

Due to the high incidence of skin tumors, the development of computer aided-diagnosis methods will become a very powerful diagnosis tool for dermatologists. The skin diseases are initially diagnosed visually, through clinical screening and followed in some cases by dermoscopic analysis, biopsy and histopathological examination. Automatic classification of dermatoscopic images is a challenge due to fine-grained variations in lesions. The convolutional neural network (CNN), one of the most powerful deep learning techniques proved to be superior to traditional algorithms. These networks provide the flexibility of extracting discriminatory features from images that preserve the spatial structure and could be developed for region recognition and medical image classification. In this paper we proposed an architecture of CNN to classify skin lesions using only image pixels and diagnosis labels as inputs. We trained and validated the CNN model using a public dataset of 10015 images consisting of 7 types of skin lesions: actinic keratoses and intraepithelial carcinoma/Bowen disease (akiec), basal cell carcinoma (bcc), benign lesions of the keratosis type (solar lentigine/seborrheic keratoses and lichen-planus like keratosis, bkl), dermatofibroma (df), melanoma (mel), melanocytic nevi (nv) and vascular lesions (angiomas, angiokeratomas, pyogenic granulomas and hemorrhages, vasc).

Preoperative Computer-Assisted Laparoscopy Planning for the Minimally Invasive Surgical Repair of Hiatal Hernia.

Minimal invasive surgical procedures such as laparoscopy are preferred over open surgery due to faster postoperative recovery, less trauma and inflammatory response, and less scarring. Laparoscopic repairs of hiatal hernias require pre-procedure planning to ensure appropriate exposure and positioning of the surgical ports for triangulation, ergonomics, instrument length and operational angles to avoid the fulcrum effect of the long and rigid instruments. We developed a novel surgical planning and navigation software, iMTECH to determine the optimal location of the skin incision and surgical instrument placement depth and angles during laparoscopic surgery. We tested the software on five cases of human hiatal hernia to assess the feasibility of the stereotactic reconstruction of anatomy and surgical planning. A whole-body CT investigation was performed for each patient, and abdominal 3D virtual models were reconstructed from the CT scans. The optical trocar access point was placed on the xipho-umbilical line. The distance on the skin between the insertion point of the optical trocar and the xiphoid process was 159.6, 155.7, 143.1, 158.3, and 149.1 mm, respectively, at a 40° elevation angle. Following the pre-procedure planning, all patients underwent successful surgical laparoscopic procedures. The user feedback was that planning software significantly improved the ergonomics, was easy to use, and particularly useful in obese patients with large hiatal defects where the insertion points could not be placed in the traditional positions. Future studies will assess the benefits of the planning system over the conventional, empirical trocar positioning method in more patients with other surgical challenges.

Preparation, Characterization and Wound Healing Effects of New Membranes Based on Chitosan, Hyaluronic Acid and Arginine Derivatives.

New membranes based on chitosan and chitosan-hyaluronic acid containing new arginine derivatives with thiazolidine-4-one scaffold have been prepared using the ionic cross-linking method. The presence of the arginine derivatives with thiazolidine-4-one scaffold into the polymer matrix was proved by Fourier-transform infrared spectroscopy (FT-IR). The scanning electron microscopy (SEM) revealed a micro-porous structure that is an important characteristic for the treatment of burns, favoring the exudate absorption, the rate of colonization, the cell structure, and the angiogenesis process. The developed polymeric membranes also showed good swelling degree, improved hydrophilicity, and biocompatibility in terms of surface free energy components, which supports their application for tissue regeneration. Moreover, the chitosan-arginine derivatives (CS-6h, CS-6i) and chitosan-hyaluronic acid-arginine derivative (CS-HA-6h) membranes showed good healing effects on the burn wound model induced to rats. For these membranes a complete reepithelialization was observed after 15 days of the experiment, which supports a faster healing process.