Few-shot Tumor Bud Segmentation Using Generative Model in Colorectal Carcinoma.

Current deep learning methods in histopathology are limited by the small amount of available data and time consumption in labeling the data. Colorectal cancer (CRC) tumor budding quantification performed using H&E-stained slides is crucial for cancer staging and prognosis but is subject to labor-intensive annotation and human bias. Thus, acquiring a large-scale, fully annotated dataset for training a tumor budding (TB) segmentation/detection system is difficult. Here, we present a DatasetGAN-based approach that can generate essentially an unlimited number of images with TB masks from a moderate number of unlabeled images and a few annotated images. The images generated by our model closely resemble the real colon tissue on H&E-stained slides. We test the performance of this model by training a downstream segmentation model, UNet++, on the generated images and masks. Our results show that the trained UNet++ model can achieve reasonable TB segmentation performance, especially at the instance level. This study demonstrates the potential of developing an annotation-efficient segmentation model for automatic TB detection and quantification.

Recent Uses of Paper Microfluidics in Isothermal Nucleic Acid Amplification Tests.

Isothermal nucleic acid amplification tests have recently gained popularity over polymerase chain reaction (PCR), as they only require a constant temperature and significantly simplify nucleic acid amplification. Recently, numerous attempts have been made to incorporate paper microfluidics into these isothermal amplification tests. Paper microfluidics (including lateral flow strips) have been used to extract nucleic acids, amplify the target gene, and detect amplified products, all toward automating the process. We investigated the literature from 2020 to the present, i.e., since the onset of the COVID-19 pandemic, during which a significant surge in isothermal amplification tests has been observed. Paper microfluidic detection has been used extensively for recombinase polymerase amplification (RPA) and its related methods, along with loop-mediated isothermal amplification (LAMP) and rolling circle amplification (RCA). Detection was conducted primarily with colorimetric and fluorometric methods, although a few publications demonstrated flow distance- and surface-enhanced Raman spectroscopic (SERS)-based detection. A good number of publications could be found that demonstrated both amplification and detection on paper microfluidic platforms. A small number of publications could be found that showed extraction or all three procedures (i.e., fully integrated systems) on paper microfluidic platforms, necessitating the need for future work.