Accurate diagnosis of lung cancer brain metastasis is often hindered by incomplete magnetic resonance imaging (MRI) modalities, resulting in suboptimal utilization of complementary radiological information. To address the challenge of ineffective feature integration in missing-modality scenarios, a Transformer-based multi-modal feature fusion framework, referred to as Missing Modality Transformer (MMT), was introduced. In this study, multi-modal MRI data from 279 individuals diagnosed with lung cancer brain metastasis, including both small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC), were acquired and processed through a standardized radiomics pipeline encompassing feature extraction, feature selection, and controlled data augmentation. The proposed MMT framework was trained and evaluated under various single-modality and combined-modality configurations to assess its robustness to modality absence. A maximum diagnostic accuracy of 0.905 was achieved under single-modality missing conditions, exceeding the performance of the full-modality baseline by 0.017. Interpretability was further strengthened through systematic analysis of loss-function hyperparameters and quantitative assessments of modality-specific importance. The experimental findings collectively indicate that the MMT framework provides a reliable and clinically meaningful solution for diagnostic environments in which imaging acquisition is limited by patient conditions, equipment availability, or time constraints. These results highlight the potential of Transformer-based radiomics fusion to advance computational neuro-oncology by improving diagnostic performance, enhancing robustness to real-world imaging variability, and offering transparent interpretability that aligns with clinical decision-support requirements.
Rapid expansion of biodiesel production has generated large streams of low-value crude glycerol, whose role in industrial systems is partially explored. Since this stream is a by-product of policy-driven renewable energy and simultaneously a burden of waste management, its use as a metalworking fluids (MWFs) base stock provides a direct test of whether the transition of energy could be translated into cleaner manufacturing rather than impact shifting. This paper examined whether deploying glycerol-based MWFs in machining could reconfigure waste flows and occupational exposures, to be in line with circular economy and industrial-ecology principles, and under what conditions this could support sustainability transitions. Using a critical narrative review of technical, environmental, and policy literature, we synthesized evidence on the performance of glycerol as a base fluid and the system-level constraints that governed its adoption. The synthesis suggested that, in suitable machining regimes and under enforceable governance conditions, prospective gains included the reclassification of metallic residues from hazardous to non-hazardous streams and improved occupational safety by reducing reliance on biocides and volatile organic compounds. These prospective gains were conditional: adoption was constrained by thermal instability, possible acrolein formation at elevated temperatures, and inconsistent feedstock quality. The paper therefore offered a transdisciplinary synthesis connecting technical performance, waste-classification regimes, and governance instruments. The derived policy needs covered the minimum impurity specifications for industrial glycerol, clearer waste-coding guidance for swarf and spent fluids, and incentives for monitoring and process adaptation to secure net sustainability benefits. In this connection, Hephaestus serves as a metaphor for glycerol-based MWFs: a marginal by-product that could rework glycerol and metallic residues into useful resources, when technical optimization and institutional coordination (including standards and partnerships aligned with SDG 17) are in place.
For Authors
For Reviewers
For Editors
Open Access
