Since degraded underwater images are not always accompanied with distortion-free counterparts in real-world situations, existing underwater image enhancement (UIE) methods are mostly learned on a paired set consisting of raw underwater images and their corresponding pseudo-reference labels. Although the existing UIE datasets manually select the best model-generated results as pseudo-References, such pseudo-reference labels do not always exhibit perfect visual quality. Therefore, it would be interesting to investigate whether it is possible to break through the performance bottleneck of UIE networks trained with imperfect pseudo-references. Motivated by these facts, this paper focuses on innovating more advanced loss functions rather than designing more complex network architectures. Specifically, a plug-and-play hybrid Performance SurPassing Loss (PSPL), consisting of a Quality Score Comparison Loss (QSCL) and a scene Depth-aware Unpaired Contrastive Loss (DUCL), is formulated to guide the training of UIE network. Functionally, QSCL aims to guide the UIE network to generate enhanced results with better visual quality than pseudo-references by constructing image quality score comparison losses from both image-level and region-level. Nevertheless, only using QSCL cannot guarantee obtaining desired results for those severely degraded distant regions. Therefore, we also design a tailored DUCL to handle this challenging issue from the scene depth perspective, i.e., DUCL encourages the distant regions of the enhanced results to be closer to the high-quality nearby regions (pull) and far away from the low-quality distant regions (push) of the pseudo-references. Extensive experimental results demonstrate the advantage of using PSPL over the state-of-the-arts even with an extremely simple and lightweight UIE network. The source code will be released at https://github.com/lewis081/PSPL.

MOTIVATION: Molecular profiling of blood-based liquid biopsies is a promising disease detection method, which overcomes the limitations of invasive diagnostic strategies. Recently, gene expression profiling of platelets reportedly provides valuable resource for developing new biomarkers for the detection of diseases, including cancer. However, there is no database containing RNAs in platelets. RESULTS: In this study, we constructed PltDB (http://www.pltdb-hust.com), a blood platelets-based gene expression database featuring integration and visualization of RNA expression profiles based on RNA-seq and microarray data spanning both normal individuals and patients with different diseases. PltDB currently contains the expression landscape of mRNAs, lncRNAs, circRNAs and miRNAs in platelets from patients with different disease types and healthy controls. Moreover, PltDB provides users with the tools for visualizing results of comparison and correlation analysis and for downloading expression profiles and analysis results. A submission interface for the scientific community is also embraced for uploading novel RNA expression profiles derived from platelet samples. PltDB will offer a comprehensive review of the clinical use of platelets, overcome technical problems when analyzing data from diverse studies and serve as a powerful platform for developing new blood biomarkers. AVAILABILITY AND IMPLEMENTATION: PltDB is accessible at http://www.pltdb-hust.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.