Background: Tumor programmed death-ligand 1 (PD-L1) status is useful in determining which patients may benefit from programmed death-1 (PD-1)/PD-L1 inhibitors. However, little is known about the association between PD-L1 status and tumor histopathological patterns. Using deep learning, we predicted PD-L1 status from hematoxylin and eosin (H and E) whole-slide images (WSIs) of nonsmall cell lung cancer (NSCLC) tumor samples. Materials and Methods: One hundred and thirty NSCLC patients were randomly assigned to training ( n = 48) or test ( n = 82) cohorts. A pair of H and E and PD-L1-immunostained WSIs was obtained for each patient. A pathologist annotated PD-L1 positive and negative tumor regions on the training samples using immunostained WSIs for reference. From the H and E WSIs, over 145,000 training tiles were generated and used to train a multi-field-of-view deep learning model with a residual neural network backbone. Results: The trained model accurately predicted tumor PD-L1 status on the held-out test cohort of H and E WSIs, which was balanced for PD-L1 status (area under the receiver operating characteristic curve [AUC] =0.80, P << 0.01). The model remained effective over a range of PD-L1 cutoff thresholds (AUC = 0.67–0.81, P ≤ 0.01) and when different proportions of the labels were randomly shuffled to simulate interpathologist disagreement (AUC = 0.63–0.77, P ≤ 0.03). Conclusions: A robust deep learning model was developed to predict tumor PD-L1 status from H and E WSIs in NSCLC. These results suggest that PD-L1 expression is correlated with the morphological features of the tumor microenvironment.
Context:Color normalization techniques for histology have not been empirically tested for their utility for computational pathology pipelines.Aims:We compared two contemporary techniques for achieving a common intermediate goal – epithelial-stromal classification.Settings and Design:Expert-annotated regions of epithelium and stroma were treated as ground truth for comparing classifiers on original and color-normalized images.Materials and Methods:Epithelial and stromal regions were annotated on thirty diverse-appearing H and E stained prostate cancer tissue microarray cores. Corresponding sets of thirty images each were generated using the two color normalization techniques. Color metrics were compared for original and color-normalized images. Separate epithelial-stromal classifiers were trained and compared on test images. Main analyses were conducted using a multiresolution segmentation (MRS) approach; comparative analyses using two other classification approaches (convolutional neural network [CNN], Wndchrm) were also performed.Statistical Analysis:For the main MRS method, which relied on classification of super-pixels, the number of variables used was reduced using backward elimination without compromising accuracy, and test - area under the curves (AUCs) were compared for original and normalized images. For CNN and Wndchrm, pixel classification test-AUCs were compared.Results:Khan method reduced color saturation while Vahadane reduced hue variance. Super-pixel-level test-AUC for MRS was 0.010–0.025 (95% confidence interval limits ± 0.004) higher for the two normalized image sets compared to the original in the 10–80 variable range. Improvement in pixel classification accuracy was also observed for CNN and Wndchrm for color-normalized images.Conclusions:Color normalization can give a small incremental benefit when a super-pixel-based classification method is used with features that perform implicit color normalization while the gain is higher for patch-based classification methods for classifying epithelium versus stroma.
Neuron activity and insulin release were measured simultaneously from 33 preparations of intrapancreatic canine ganglia and pancreatic parenchyma adjacent to the ganglia. The electrical activity of single neurons of the ganglia was recorded with intracellular microelectrodes, and insulin release from the attached islets was determined with an enzyme-linked immunosorbent assay. Insulin release was 62 ± 18 fmol preparation/min in the presence of 10 mmol/l glucose and pulsatile (3.7 ± 0.4 min/pulse). Corresponding measurements of neuronal electrical activity showed a stable membrane potential of -53.5 ± 0.6 mV. Short, high-frequency (20 Hz) preganglionic nerve stimulation evoked action potentials and, in 46% of the preparations, a threefold rise in the insulin secretory rate associated with increased amplitude of the insulin pulses. The effects were blocked by 10 µmol/l tetrodotoxin (TTX). In other preparations, continuous low-frequency (0.05-0.5 Hz) preganglionic nerve stimulation evoked action potentials and, in 50% of the preparations, a gradual increase of insulin release associated with augmentation of insulin pulse amplitude without alteration of the duration. The effects were blocked by 50 µmol/l hexamethonium (HEX). In the remaining preparations, no change in insulin release was observed during nerve stimulation. In the absence of stimulation, neither TTX nor HEX affected the membrane potential or insulin secretion. These first simultaneous measurements of intrapancreatic ganglion activity and insulin secretion are consistent with amplitude modulation of pulsatile insulin secretion induced by changes in electrical activity in a population of intrapancreatic ganglion neurons. Diabetes 50:51-55, 2001
Biochemistry and molecular techniques are used for the development of the scientific practice of students. To improve both the teaching and learning quality and promote the students' motivation, this article outlines an interactive “Virtual Simulation and Actual Operation Combined” approach by using a tailored virtual practice‐learning platform and participated by students and lectures, as well as a curriculum secretary. The implementation of the Virtual Simulation Laboratory provides a series of learning resources, which the students can access in their own time; and the participation of the curriculum secretary also makes the class more interactive and efficient. This method incorporates an experimental platform and a virtual experiment class to utilize fully both the traditional and virtual teaching methods and thereby promote effective student learning. © 2018 International Union of Biochemistry and Molecular Biology, 46(6):585–591, 2018.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.