Classification of skin cancer from dermoscopic images using deep neural network architectures.

A powerful medical decision support system for classifying skin lesions from dermoscopic images is an important tool to prognosis of skin cancer. In the recent years, Deep Convolutional Neural Network (DCNN) have made a significant advancement in detecting skin cancer types from dermoscopic images, in-spite of its fine grained variability in its appearance. The main objective of this research work is to develop a DCNN based model to automatically classify skin cancer types into melanoma and non-melanoma with high accuracy. The datasets used in this work were obtained from the popular challenges ISIC-2019 and ISIC-2020, which have different image resolutions and class imbalance problems. To address these two problems and to achieve high performance in classification we have used EfficientNet architecture based on transfer learning techniques, which learns more complex and fine grained patterns from lesion images by automatically scaling depth, width and resolution of the network. We have augmented our dataset to overcome the class imbalance problem and also used metadata information to improve the classification results. Further to improve the efficiency of the EfficientNet we have used ranger optimizer which considerably reduces the hyper parameter tuning, which is required to achieve state-of-the-art results. We have conducted several experiments using different transferring models and our results proved that EfficientNet variants outperformed in the skin lesion classification tasks when compared with other architectures. The performance of the proposed system was evaluated using Area under the ROC curve (AUC - ROC) and obtained the score of 0.9681 by optimal fine tuning of EfficientNet-B6 with ranger optimizer.

Self-Assembly of Block Heterochiral Peptides into Helical Tapes.

Patterned substitution of d-amino acids into the primary sequences of self-assembling peptides influences molecular-level packing and supramolecular morphology. We report that block heterochiral analogs of the model amphipathic peptide KFE8 (Ac-FKFEFKFE-NH2), composed of two FKFE repeat motifs with opposite chirality, assemble into helical tapes with dimensions greatly exceeding those of their fibrillar homochiral counterparts. At sufficient concentrations, these tapes form hydrogels with reduced storage moduli but retain the shear-thinning behavior and consistent mechanical recovery of the homochiral analogs. Varying the identity of charged residues (FRFEFRFE and FRFDFRFD) produced similarly sized nonhelical tapes, while a peptide with nonenantiomeric l- and d-blocks (FKFEFRFD) formed helical tapes closely resembling those of the heterochiral KFE8 analogs. A proposed energy-minimized model suggests that a kink at the interface between l- and d-blocks leads to the assembly of flat monolayers with nonidentical surfaces that display alternating stacks of hydrophobic and charged groups.