Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.
- MeSH
- umělá inteligence * MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.
- MeSH
- algoritmy * MeSH
- počítačové zpracování obrazu * MeSH
- sémantika MeSH
- strojové učení MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
Direct infusion of lipid extracts into the ion source of a mass spectrometer is a well-established method for lipid analysis. In most cases, nanofluidic devices are used for sample introduction. However, flow injection analysis (FIA) based on sample infusion from a chromatographic pump can offer a simple alternative to shotgun-based approaches. Here, we describe important modification of a method based on FIA and tandem mass spectrometry (MS/MS). We focus on minimizing contamination of the FIA/MS both to render the lipidomic platform more robust and to increase its capacity and applicability for long-sequence measurements required in clinical applications. Robust validation of the developed method confirms its suitability for lipid quantitation in human plasma analysis. Measurements of standard human plasma reference material (NIST SRM 1950) and a set of plasma samples collected from kidney cancer patients and from healthy volunteers yielded highly similar results between FIA-MS/MS and ultra-high-performance supercritical fluid chromatography (UHPSFC)/MS, thereby demonstrating that all modifications have practically no effect on the statistical output. Newly modified FIA-MS/MS allows for the quantitation of 141 lipid species in plasma (11 major lipid classes) within 5.7 min. Finally, we tested the method in a clinical laboratory of the General University Hospital in Prague. In the clinical setting, the method capacity reached 257 samples/day. We also show similar performance of the classification models trained based on the results obtained in clinical settings and the analytical laboratory at the University of Pardubice. Together, these findings demonstrate the high potential of the modified FIA-MS/MS for application in clinical laboratories to measure plasma and serum lipid profiles.
- MeSH
- krevní plazma chemie MeSH
- lidé MeSH
- lipidomika * metody MeSH
- lipidy analýza MeSH
- průtoková injekční analýza MeSH
- tandemová hmotnostní spektrometrie * metody MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
The applicability of ultrahigh-performance supercritical fluid chromatography coupled with mass spectrometry (UHPSFC/MS) for the qualitative analysis of metabolites with a wide polarity range (log P: -3.89-18.95) was evaluated using a representative set of 78 standards belonging to nucleosides, biogenic amines, carbohydrates, amino acids, and lipids. The effects of the gradient shape and the percentage of water (1, 2, and 5%) were investigated on the Viridis BEH column. The screening of eight stationary phases was performed for columns with different interaction sites, such as hydrogen bonding, hydrophobic, π-π, or anionic exchange type interactions. The highest number of compounds (67) of the set studied was detected on the Torus Diol column, which provided a resolution parameter of 39. The DEA column had the second best performance with 58 detected standards and the resolution parameter of 54. The overall performance of other parameters, such as selectivity, peak height, peak area, retention time stability, asymmetry factor, and mass accuracy, led to the selection of the Diol column for the final method. The comparison of additives showed that ammonium acetate gave a superior sensitivity over ammonium formate. Moreover, the influence of the ion source on the ionization efficiency was studied by employing atmospheric pressure chemical ionization (APCI) and electrospray ionization (ESI). The results proved the complementarity of both ionization techniques, but also the superior ionization capacity of the ESI source in the negative ion mode, for which 53% of the analytes were detected compared to only 7% for the APCI source. Finally, optimized analytical conditions were applied to the analysis of a pooled human plasma sample. 44 compounds from the preselected set were detected in human plasma using ESI-UHPSFC/MS in MSE mode considering both ionization modes.
- MeSH
- aminokyseliny MeSH
- atmosférický tlak MeSH
- chromatografie kapalinová MeSH
- hmotnostní spektrometrie MeSH
- lidé MeSH
- superkritická fluidní chromatografie * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
