From Sea to Science: Coral Aquaculture for Sustainable Anticancer Drug Development.

Marine natural products offer immense potential for drug development, but the limited supply of marine organisms poses a significant challenge. Establishing aquaculture presents a sustainable solution for this challenge by facilitating the mass production of active ingredients while reducing our reliance on wild populations and harm to local environments. To fully utilize aquaculture as a source of biologically active products, a cell-free system was established to target molecular components with protein-modulating activity, including topoisomerase II, HDAC, and tubulin polymerization, using extracts from aquaculture corals. Subsequent in vitro studies were performed, including MTT assays, flow cytometry, confocal microscopy, and Western blotting, along with in vivo xenograft models, to verify the efficacy of the active extracts and further elucidate their cytotoxic mechanisms. Regulatory proteins were clarified using NGS and gene modification techniques. Molecular docking and SwissADME assays were performed to evaluate the drug-likeness and pharmacokinetic and medicinal chemistry-related properties of the small molecules. The extract from Lobophytum crassum (LCE) demonstrated potent broad-spectrum activity, exhibiting significant inhibition of tubulin polymerization, and showed low IC50 values against prostate cancer cells. Flow cytometry and Western blotting assays revealed that LCE induced apoptosis, as evidenced by the increased expression of apoptotic protein-cleaved caspase-3 and the populations of early and late apoptotic cells. In the xenograft tumor experiments, LCE significantly suppressed tumor growth and reduced the tumor volume (PC3: 43.9%; Du145: 49.2%) and weight (PC3: 48.8%; Du145: 7.8%). Additionally, LCE inhibited prostate cancer cell migration, and invasion upregulated the epithelial marker E-cadherin and suppressed EMT-related proteins. Furthermore, LCE effectively attenuated TGF-ß-induced EMT in PC3 and Du145 cells. Bioactivity-guided fractionation and SwissADME validation confirmed that LCE's main component, 13-acetoxysarcocrassolide (13-AC), holds greater potential for the development of anticancer drugs.

Fair evaluation of federated learning algorithms for automated breast density classification: The results of the 2022 ACR-NCI-NVIDIA federated learning challenge.

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical Schools' Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location.

Expert-centered Evaluation of Deep Learning Algorithms for Brain Tumor Segmentation.

Purpose To present results from a literature survey on practices in deep learning segmentation algorithm evaluation and perform a study on expert quality perception of brain tumor segmentation. Materials and Methods A total of 180 articles reporting on brain tumor segmentation algorithms were surveyed for the reported quality evaluation. Additionally, ratings of segmentation quality on a four-point scale were collected from medical professionals for 60 brain tumor segmentation cases. Results Of the surveyed articles, Dice score, sensitivity, and Hausdorff distance were the most popular metrics to report segmentation performance. Notably, only 2.8% of the articles included clinical experts' evaluation of segmentation quality. The experimental results revealed a low interrater agreement (Krippendorff α, 0.34) in experts' segmentation quality perception. Furthermore, the correlations between the ratings and commonly used quantitative quality metrics were low (Kendall tau between Dice score and mean rating, 0.23; Kendall tau between Hausdorff distance and mean rating, 0.51), with large variability among the experts. Conclusion The results demonstrate that quality ratings are prone to variability due to the ambiguity of tumor boundaries and individual perceptual differences, and existing metrics do not capture the clinical perception of segmentation quality. Keywords: Brain Tumor Segmentation, Deep Learning Algorithms, Glioblastoma, Cancer, Machine Learning Clinical trial registration nos. NCT00756106 and NCT00662506 Supplemental material is available for this article. © RSNA, 2023.