Exploratory Training for Universal Lesion Detection: Enhancing Lesion Mining Quality Through Temporal Verification.

Universal lesion detection (ULD) has great value in clinical practice as it can detect various lesions across multiple organs. Deep learning-based detectors have great potential but require high-quality annotated training data. In practice, due to cost, expertise requirements, and the diverse nature of lesions, incomplete annotations are often encountered. Directly training ULD detectors under this condition can yield suboptimal results. Leading pseudo-label methods rely on a dynamic lesion-mining mechanism operating at the mini-batch level to address the issue of incomplete annotations. However, the quality of mined lesions in this approach is inconsistent across different iterations, potentially limiting performance enhancement. Inspired by the observation that deep models learn concepts with increasing complexity, we propose an innovative exploratory-training-based ULD (ET-ULD) method to assess the reliability of mined lesions over time. Specifically, we employ a teacher-student detection model, the teacher model is used to mine suspicious lesions, which are combined with incomplete annotations to train the student model. On top of that, we design a bounding-box bank to record the mining timestamps. Each image is trained in several rounds, allowing us to get a sequence of timestamps for the mined lesions. If a mined lesion consistently appears in the timestamp sequence, it is likely to be a true lesion, otherwise, it may just be a noise. This serves as a crucial criterion for selecting reliable mined lesions for subsequent retraining. Our experimental results confirm the effectiveness of ET-ULD, showcasing its ability to surpass existing state-of-the-art methods on two distinct lesion image datasets. Notably, on the DeepLesion dataset, ET-ULD achieved a significant enhancement, outperforming the previous leading method by 5.4% in Average Precision (AP), thus demonstrating its superior performance.

A digital nanoplasmonic microarray immunosensor for multiplexed cytokine monitoring during CAR T-cell therapy from a leukemia tumor microenvironment model.

The release of cytokines by chimeric antigen receptor (CAR) T-cells and tumor resident immune cells defines a significant part of CAR T-cell functional activity and patient immune responses during CAR T-cell therapy. However, few studies have so far precisely characterized the cytokine secretion dynamics in the tumor niche during CAR T-cell therapy, which requires multiplexed, and timely biosensing platforms and integration with biomimetic tumor microenvironment. Herein, we implemented a digital nanoplasmonic microarray immunosensor with a microfluidic biomimetic Leukemia-on-a-Chip model to monitor cytokine secretion dynamics during CD19 CAR T-cell therapy against precursor B-cell acute lymphocytic leukemia (B-ALL). The integrated nanoplasmonic biosensors achieved precise multiplexed cytokine measurements with low operating sample volume, short assay time, heightened sensitivity, and negligible sensor crosstalk. Using the digital nanoplasmonic biosensing approach, we measured the concentrations of six cytokines (TNF-α, IFN-γ, MCP-1, GM-CSF, IL-1ß, and IL-6) during first 5 days of CAR T-cell treatment in the microfluidic Leukemia-on-a-Chip model. Our results revealed a heterogeneous secretion profile of various cytokines during CAR T-cell therapy and confirmed a correlation between the cytokine secretion profile and the CAR T-cell cytotoxic activity. The capability to monitor immune cell cytokine secretion dynamics in a biomimetic tumor microenvironment could further help in study of cytokine release syndrome during CAR T-cell therapy and in development of more efficient and safer immunotherapies.

Autophagy and senescence of rat retinal precursor cells under high glucose.

Backgrounds: Diabetic retinopathy (DR) is a common diabetic ocular disease characterized by retinal ganglion cell (RGC) changes. An abnormal environment, hyperglycemia, may progressively alter the structure and function of RGCs, which is a primary pathological feature of retinal neurodegeneration in DR. Accumulated studies confirmed autophagy and senescence play a vital role in DR; however, the underlying mechanisms need to be clarified. Methods: This study included the microarray expression profiling dataset GSE60436 from Gene Expression Omnibus (GEO) to conduct the bioinformatics analysis. The R software was used to identify autophagy-related genes (ARGs) that were differentially expressed in fibrovascular membranes (FVMs) and normal retinas. Co-expression and tissue-specific expression were elicited for the filtered genes. The genes were then analyzed by ontology (GO) enrichment analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis and Gene Set Enrichment Analysis (GSEA). R28 cells were cultured with high glucose, detected by reverse transcription-quantitative (RT-qPCR) and stained by apoptosis kit. Results: In the retina, 31 differentially expressed ARGs (24 up-regulated genes) were discovered and enriched. The enrichment results revealed that differentially expressed ARGs were significantly enriched in autophagy, apoptosis, aging, and neural function. Four hub genes (i.e., TP53, CASP1, CCL2, and CASP1) were significantly up-regulated. Upregulation of cellular autophagy and apoptosis level was detected in the hyperglycemia model in vitro. Conclusions: Our results provide evidence for the autophagy and cellular senescence mechanisms involved in retinal hyperglycemia injury, and the protective function of autophagy is limited. Further study may favour understanding the disease progression and neuroprotection of DR.