A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods.

The comprehensive integration of machine learning healthcare models within clinical practice remains suboptimal, notwithstanding the proliferation of high-performing solutions reported in the literature. A predominant factor hindering widespread adoption pertains to an insufficiency of evidence affirming the reliability of the aforementioned models. Recently, uncertainty quantification methods have been proposed as a potential solution to quantify the reliability of machine learning models and thus increase the interpretability and acceptability of the results. In this review, we offer a comprehensive overview of the prevailing methods proposed to quantify the uncertainty inherent in machine learning models developed for various medical image tasks. Contrary to earlier reviews that exclusively focused on probabilistic methods, this review also explores non-probabilistic approaches, thereby furnishing a more holistic survey of research pertaining to uncertainty quantification for machine learning models. Analysis of medical images with the summary and discussion on medical applications and the corresponding uncertainty evaluation protocols are presented, which focus on the specific challenges of uncertainty in medical image analysis. We also highlight some potential future research work at the end. Generally, this review aims to allow researchers from both clinical and technical backgrounds to gain a quick and yet in-depth understanding of the research in uncertainty quantification for medical image analysis machine learning models.

Graphene oxide membrane chemically modified by electron-transfer diazonium chemistry for efficient dye separation.

By chemical modification of the graphene oxide (GO) surface via diazonium chemistry, we introduce nitrobenzene groups as new interlayer pillars to GO memebranes like the surface oxygen-containing functional groups. The larger pillar can finely enlarge the interlayer space of the GO membrane. The filtration performance of modified GO membranes with different mass ratios of nitrobenzene diazonium tetrafluoroborate (NDT) were tested for EB, DR81, and MB. Notably, when the GO : NDT ratio is 1 : 1, it is found that the water flux can be enhanced by more than twice and by nearly 1.4 times its value for EB and DR81, respectively, while maintaining a high rejection (92% for EB and 95% for DR81). In conclusion, the chemical modification of GO through the dediazonization reaction of NDT can indeed improve the separation efficiency of the dye.

One step synthesis of Co/Cr-codoped ZnO nanoparticle with superb adsorption properties for various anionic organic pollutants and its regeneration.

Adsorption is an effective means to remove organic pollutant. However, it is challenging to prepare the adsorbents with high adsorption capacities and their regeneration. Herein, Co/Cr-codoped ZnO nanoparticles (NPs) with superb adsorption for dyes and antibiotics have been successfully synthesized by a mild solvothermal method. At the optimal Co:Cr:Zn doping moral ratio of 4:6:100, the maximum adsorption capacities of methyl orange (MO) and tetracycline hydrochloride (TC-HCl) on Co/Cr-codoped ZnO NPs is 1057.90 mg g-1 and 874.46 mg g-1, respectively. The adsorption process of the sample over MO and TC-HCl both agreed well with the pseudo-second-order kinetic model and Langmuir isotherm model. Adsorption thermodynamics proved that the adsorption of MO and TC-HCl on Co/Cr-codoped ZnO NPs was a spontaneous and endothermic process. The mechanism shows that the surface of Co/Cr-codoped ZnO NPs have more positive charges, larger specific surface area and more crystal defects due to Co3+ and Cr3+ substitutes Zn2+ in ZnO lattice, improving their adsorption property. In addition, Co/Cr-codoped ZnO NPs have also excellent adsorption capacity for Direct Red, Congo Red, Evans Blue and Methyl Blue. More importantly, the regeneration of adsorbents was studied to achieve the reuse of materials, and avoid secondary pollution. Co/Cr-codoped ZnO NPs will be a promising choice for wastewater treatment owing to its excellent adsorption capacity and relatively low cost.