Deep Transfer Learning-Based Approach for Glucose Transporter-1 (GLUT1) Expression Assessment.

Glucose transporter-1 (GLUT-1) expression level is a biomarker of tumour hypoxia condition in immunohistochemistry (IHC)-stained images. Thus, the GLUT-1 scoring is a routine procedure currently employed for predicting tumour hypoxia markers in clinical practice. However, visual assessment of GLUT-1 scores is subjective and consequently prone to inter-pathologist variability. Therefore, this study proposes an automated method for assessing GLUT-1 scores in IHC colorectal carcinoma images. For this purpose, we leverage deep transfer learning methodologies for evaluating the performance of six different pre-trained convolutional neural network (CNN) architectures: AlexNet, VGG16, GoogleNet, ResNet50, DenseNet-201 and ShuffleNet. The target CNNs are fine-tuned as classifiers or adapted as feature extractors with support vector machine (SVM) to classify GLUT-1 scores in IHC images. Our experimental results show that the winning model is the trained SVM classifier on the extracted deep features fusion Feat-Concat from DenseNet201, ResNet50 and GoogLeNet extractors. It yields the highest prediction accuracy of 98.86%, thus outperforming the other classifiers on our dataset. We also conclude, from comparing the methodologies, that the off-the-shelf feature extraction is better than the fine-tuning model in terms of time and resources required for training.

Insight into the liposomal encapsulation of mono and bis-naphthalimides.

Mitonafide-loaded liposomes are a promising strategy to overcome the neurotoxicity observed in clinical trials for this drug. This study investigates the influence of loaded mitonafide or a dimer analogue on different liposomal formulations and their therapeutic efficacy in vitro. Physicochemical properties of the liposomes were manipulated using different loading methods (namely bilayer or core loading) and varying the rigidity of the bilayer using distinct phospholipid compositions. Our results demonstrated that the mitonafide dimer analogue had a comparable encapsulation efficiency (EE%) into the liposomes when loaded into rigid or flexible bilayers in contrast to the low mitonafide monomer EE%. A pH gradient core loading method resulted in a more efficient mechanism to load the monomer into the liposomes. DOSY NMR and spectrofluorometric studies revealed key differences in the structure of the vesicles and the arrangement of the monomer or the dimer in the bilayer or the core of the liposomes. The in vitro assessment of the formulations using MDA-MB-231 and RT-112 cells revealed that a flexible lipid bilayer allows a faster drug release, which correlated well with the spectroscopy studies. This study investigated for the first time that the characteristics of the lipid bilayer and the loading method influence the encapsulation efficacy, colloidal properties, photoactivity and stability of mono and bis-naphthalimides loaded in a liposomal carrier, essential factors that will impact the performance of the formulation in a biological scenario.