Search

Explainable Artificial Intelligence (XAI) is a branch of AI that mainly focuses on developing systems that provide understandable and clear explanations for their decisions. In the context of cancer diagnoses on medical imaging, an XAI technology uses advanced image analysis methods like deep learning (DL) to make a diagnosis and analyze medical images, as well as provide a clear explanation for how it arrived at its diagnoses. This includes highlighting specific areas of the image that the system recognized as indicative of cancer while also providing data on the fundamental AI algorithm and decision-making process used. The objective of XAI is to provide patients and doctors with a better understanding of the system’s decision-making process and to increase transparency and trust in the diagnosis method. Therefore, this study develops an Adaptive Aquila Optimizer with Explainable Artificial Intelligence Enabled Cancer Diagnosis (AAOXAI-CD) technique on Medical Imaging. The proposed AAOXAI-CD technique intends to accomplish the effectual colorectal and osteosarcoma cancer classification process. To achieve this, the AAOXAI-CD technique initially employs the Faster SqueezeNet model for feature vector generation. As well, the hyperparameter tuning of the Faster SqueezeNet model takes place with the use of the AAO algorithm. For cancer classification, the majority weighted voting ensemble model with three DL classifiers, namely recurrent neural network (RNN), gated recurrent unit (GRU), and bidirectional long short-term memory (BiLSTM). Furthermore, the AAOXAI-CD technique combines the XAI approach LIME for better understanding and explainability of the black-box method for accurate cancer detection. The simulation evaluation of the AAOXAI-CD methodology can be tested on medical cancer imaging databases, and the outcomes ensured the auspicious outcome of the AAOXAI-CD methodology than other current approaches.

Hydrophobic drug encapsulation inside targeted nanoparticles can enhance accumulation in inflamed sites, limit toxicity to healthy tissue, and improve pharmacokinetics compared to free drug dosing. This study reports a functionalized marine polysaccharide nanoparticle with a controlled release, targeting abilities, and in-situ imaging properties. Carbon dots functionalized Enteromorpha polysaccharide/Mannose/Methionine functionalized Chitosan (CDs.EP/Man/Meth.Cs) NPs could deliver apremilast to inflammatory macrophages and Caco-2 intestinal cells as an in vitro model for application in oral drug delivery to cure IBD. The nanoparticles were simply a polyelectrolyte complex between cationic functionalized chitosan and anionic polysaccharide of Enteromorpha prolifera. Functionalized polysaccharides and the prepared NPs were well characterized. The functionalized nanoparticles could overcome the limitation of poor drug bioavailability and showed a high loading capacity of (45 %) with a controlled release of about (74.5 %). Confocal laser scanning imaging showed higher cellular uptake of the modified nanoparticles than that of the unmodified nanoparticles in LPS-activated RAW 264.7 macrophages and Caco-2 cells. The effect of functionalization on the cellular uptake targetability was assessed using spectrofluorometric measurements after mannose competition. Anti-inflammatory activity of apremilast-loaded NPs is more elevated than the free drug. These results suggest the feasibility of using functionalized EP/Cs nanoparticles in IBD oral drug delivery.

The catastrophe of the coronavirus continues from one part of the world to another, and hardly a country is left without its devastations. Millions of people were infected and several hundred thousand died of the COVID-19 pandemic across the world. There is no clear targeted drug therapy available for the treatment of the patients. The discovery of vaccines is not enough to curtail its spread and disastrous implications. An instantly qualifying approach is needed to utilize the current drugs and isolated compounds. The purpose of this work is to determine potent inhibitors against the target proteins of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). For this purpose, molecular docking study of pathogenic spike glycoproteins (S), nucleocapsid phosphoprotein (N), an envelope protein (E), two drugs i.e., cefixime, etoposide, and a previously isolated compound nebrodenside A is performed. Promising results were obtained via complimentary analysis of molecular dynamics (MD) simulations performed for the complexes of three proteins with etoposide drug. Minimum values were recorded for the docking scores and binding energies of the complexes. These results were further supported by the RMSD, RMSF data for the stability of proteins and ligands. Additionally, ligand properties and ligand-protein contacts were also explained with histograms of every simulation trajectory. The computational studies confirmed that cefixime, etoposide, and nebrodenoside A can be used as potent inhibitors of COVID-19. Nevertheless, additional experimental investigations and validation of the selected candidates are mandatory to confirm their applicability for clinical trials., Graphical Abstract Image, graphical abstract