Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei

The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved.

IMAGE SEGMENTATION BASED ON EDGE DETECTION AND REGION GROWING FOR THINPREP-CERVICAL SMEAR

This study has developed an object detection and segmentation technique for processing cytoplasm and cell nucleus on ThinPrep-cervical smear images at various magnifications. Both edge detection techniques and region growing for adaptive threshold were applied to a segment cell nucleus, a cytoplasm, and backgrounds using a cervical cell image. To validate the accuracy and feasibility of the proposed method, we took a variety of cervical cell images to perform a series of experiments. The images were of superficial cells, intermediate cells, and abnormal cells, with each taken from ThinPrep smears at various magnifications. The results indicate that the proposed method can automatically segment cell nucleus and cytoplasm regions while accurately extracting object contours. These results can serve as a reference for examiners of cell pathologies.

Basolateral membrane Na(+)-independent Cl-/HCO3- exchange in the inner stripe of the rabbit outer medullary collecting tubule.

The inner stripe of the outer medullary collecting tubule is a major distal nephron segment in urinary acidification. To examine the mechanism of basolateral membrane H+/OH-/HCO3- transport in this segment, cell pH was measured microfluorometrically in the inner stripe of the rabbit outer medullary collecting tubule perfused in vitro using the pH-sensitive fluorescent dye, (2',7')-bis(carboxyethyl)-(5,6)-carboxyfluorescein. Decreasing peritubular pH from 7.4 to 6.8 (changing [HCO3-] from 25 to 5 mM) caused a cell acidification of 0.25 +/- 0.02 pH units, while a similar luminal change resulted in a smaller cell acidification of only 0.04 +/- 0.01 pH units. Total replacement of peritubular Cl- with gluconate caused cell pH to increase by 0.18 +/- 0.04 pH units, an effect inhibited by 100 microM peritubular DIDS and independent of Na+. Direct coupling between Cl- and base was suggested by the continued presence of peritubular Cl- removal-induced cell alkalinization under the condition of a cell voltage clamp (K(+)-valinomycin). In addition, 90% of basolateral membrane H+/OH-/HCO3- permeability was inhibited by complete removal of luminal and peritubular Cl-. Peritubular Cl(-)-induced cell pH changes were inhibited two-thirds by removal of exogenous CO2/HCO3- from the system. The apparent Km for peritubular Cl- determined in the presence of 25 mM luminal and peritubular [HCO3-] was 113.5 +/- 14.8 mM. These results demonstrate that the basolateral membrane of the inner stripe of the outer medullary collecting tubule possesses a stilbene-sensitive Cl-/HCO3- exchanger which mediates 90% of basolateral membrane H+/OH-/HCO3- permeability and may be regulated by physiologic Cl- concentrations.