Deep Learning-Based TEM Image Analysis for Fully Automated Detection of Gold Nanoparticles Internalized Within Tumor Cell

Deep learning-based classification of the capillary ultrastructure in human skeletal muscles

Background

Capillary ultrastructure in human skeletal muscles is dynamic and prone to alterations in response to many stimuli, e.g., systemic pathologies such as diabetes mellitus and arterial hypertension. Using transmission electron microscopy (TEM) images, several studies have been conducted to quantify the capillary ultrastructure by means of morphometry. Deep learning techniques like convolutional neural networks (CNNs) are utilized to extract data-driven characteristics and to recognize patterns. Hence, the aim of this study was to train a CNN to identify morphometric patterns that differ between capillaries in muscle biopsies of healthy participants and patients with systemic pathologies for the purpose of hypothesis generation.

Methods

In this retrospective study we used 1810 electron micrographs from human skeletal muscle capillaries derived from 70 study participants which were classified as "healthy" controls or "patients" in dependence of the absence or presence of a documented history of diabetes mellitus, arterial hypertension or peripheral arterial disease. Using these micrographs, a pre-trained open-access CNN (ResNet101) was trained to discriminate between micrographs of capillaries of the two groups. The CNN with the highest diagnostic accuracies during training were subsequently compared with manual quantitative analysis of the capillary ultrastructure to distinguish between "healthy" controls and patients.

Results

Using classification into controls or patients as allocation reference, receiver-operating-characteristics (ROC)-analysis of manually obtained BM thickness showed the best diagnostic accuracy of all morphometric indicators (area under the ROC-curve (AUC): 0.657 ± 0.050). The best performing CNN demonstrated a diagnostic accuracy of 79% (sensitivity 93%, specificity 92%). DeLong-Test of the ROC-curves showed a significant difference (p < 0.001) between the AUC of the best performing CNN and the BM thickness. The underlying morphology responsible for the network prediction focuses mainly on debridement of pericytes.

Conclusion

The hypothesis-generating approach using pretrained CNN distinguishes between capillaries depicted on electron micrographs of "healthy" controls and participants with a systemic pathology more accurately than by commonly used morphometric analysis.

Peptide-Hydrogel Nanocomposites for Anti-Cancer Drug Delivery

Cancer is the second leading cause of death globally, but conventional anticancer drugs have side effects, mainly due to their non-specific distribution in the body in both cancerous and healthy cells. To address this relevant issue and improve the efficiency of anticancer drugs, increasing attention is being devoted to hydrogel drug-delivery systems for different kinds of cancer treatment due to their high biocompatibility and stability, low side effects, and ease of modifications. To improve the therapeutic efficiency and provide multi-functionality, different types of nanoparticles (NPs) can be incorporated within the hydrogels to form smart hydrogel nanocomposites, benefiting the advantages of both counterparts and suitable for advanced anticancer applications. Despite many papers on non-peptide hydrogel nanocomposites, there is limited knowledge about peptide-based nanocomposites, specifically in anti-cancer drug delivery. The aim of this short but comprehensive review is, therefore, to focus attention on the synergies resulting from the combination of NPs with peptide-based hydrogels. This review, which includes a survey of recent advances in this kind of material, does not aim to be an exhaustive review of hydrogel technology, but it instead highlights recent noteworthy publications and discusses novel perspectives to provide valuable insights into the promising synergic combination of peptide hydrogels and NPs for the design of novel anticancer drug delivery systems.