A comprehensive survey on deep active learning in medical image analysis.

Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets. Yet, the high cost of annotating medical images severely hampers the development of deep learning in this field. To reduce annotation costs, active learning aims to select the most informative samples for annotation and train high-performance models with as few labeled samples as possible. In this survey, we review the core methods of active learning, including the evaluation of informativeness and sampling strategy. For the first time, we provide a detailed summary of the integration of active learning with other label-efficient techniques, such as semi-supervised, self-supervised learning, and so on. We also summarize active learning works that are specifically tailored to medical image analysis. Additionally, we conduct a thorough comparative analysis of the performance of different AL methods in medical image analysis with experiments. In the end, we offer our perspectives on the future trends and challenges of active learning and its applications in medical image analysis. An accompanying paper list and code for the comparative analysis is available in https://github.com/LightersWang/Awesome-Active-Learning-for-Medical-Image-Analysis.

Degradation of ofloxacin by potassium ferrate: kinetics and degradation pathways.

Drug residues, including various antibiotics, are being increasingly detected in aqueous environments. Ofloxacin (OFX) is one such antibiotic that is widely used in the treatment of several bacterial infections; however, chronic exposure to this antibiotic can have adverse impacts on human health. Hence, the identification of an effective OFX degradation method is essential. Thus, in this study, the degradation performance of OFX using potassium ferrate (Fe(VI)) under the influence of different initial concentrations, pH, temperature, and common ions in water was investigated. OFX degradation by Fe(VI) was directly proportional to the concentration of Fe(VI) and temperature and inversely proportional to the pH. Among the common ions in water, Fe3+ and NH4+ could significantly promote the degradation of OFX by Fe(IV), while humic acid (HA) significantly inhibited it. Under the conditions of [Fe(VI)]:[OFX] = 15:1, T = 25℃, and pH = 7.0, the removal efficiency of 8 µM OFX reached more than 90% in 4 min. Seven intermediates were identified by quadrupole time-of-flight tandem ultra-performance liquid chromatography mass spectrometry (Q-TOF LC/MS), and two possible pathways for the degradation of OFX by Fe(VI) were proposed. Overall, the results suggest that advanced oxidation technology using Fe(VI) is effective for treating wastewater containing OFX.

A histone methylation network regulates transgenerational epigenetic memory in C. elegans.

How epigenetic information is transmitted from generation to generation remains largely unknown. Deletion of the C. elegans histone H3 lysine 4 dimethyl (H3K4me2) demethylase spr-5 leads to inherited accumulation of the euchromatic H3K4me2 mark and progressive decline in fertility. Here, we identified multiple chromatin-modifying factors, including H3K4me1/me2 and H3K9me3 methyltransferases, an H3K9me3 demethylase, and an H3K9me reader, which either suppress or accelerate the progressive transgenerational phenotypes of spr-5 mutant worms. Our findings uncover a network of chromatin regulators that control the transgenerational flow of epigenetic information and suggest that the balance between euchromatic H3K4 and heterochromatic H3K9 methylation regulates transgenerational effects on fertility.