Nuquantus: Machine learning software for the characterization and quantification of cell nuclei in complex immunofluorescent tissue images

Abstract

Determination of fundamental mechanisms of disease often hinges on histopathology visualization and quantitative image analysis. Currently, the analysis of multi-channel fluorescence tissue images is primarily achieved by manual measurements of tissue cellular content and sub-cellular compartments. Since the current manual methodology for image analysis is a tedious and subjective approach, there is clearly a need for an automated analytical technique to process large-scale image datasets. Here, we introduce Nuquantus (Nuclei quantification utility software) - a novel machine learning-based analytical method, which identifies, quantifies and classifies nuclei based on cells of interest in composite fluorescent tissue images, in which cell borders are not visible. Nuquantus is an adaptive framework that learns the morphological attributes of intact tissue in the presence of anatomical variability and pathological processes. Nuquantus allowed us to robustly perform quantitative image analysis on remodeling cardiac tissue after myocardial infarction. Nuquantus reliably classifies cardiomyocyte versus non-cardiomyocyte nuclei and detects cell proliferation, as well as cell death in different cell classes. Broadly, Nuquantus provides innovative computerized methodology to analyze complex tissue images that significantly facilitates image analysis and minimizes human bias.

Cortical Bone Stem Cell Therapy Preserves Cardiac Structure and Function After Myocardial Infarction

“…We imaged and quantified the number of EdU + cells at 72hrs post–MI ± CBSCs. Confocal images from the IZ, BDZ, RZ and sBDZ of all animals were examined (Figure 4A1–A4 [VEH] & B1–B4[CBSC]) and EdU + cells were identified and quantified using Naquantus 34 , a novel semi–automated quantification software. We calculated the total number of nuclei (DAPI + [all cells]), EdU +/ DAPI + cells (total EdU + cells), Actin + /DAPI + (total myocytes) and EdU + /Actin + /DAPI + cells (EdU + myocytes) (Figure 4 & Online Figure V A – D) in each tissue section.…”

CPNE1 predicts poor prognosis and promotes tumorigenesis and radioresistance via the AKT singling pathway in triple‐negative breast cancer

“…MDA‐MB‐231 cells stably transduced with lentivirus knockdown CPNE1 or control (shCPNE1 or shNC) were subcutaneously injected into the right armpit of 6‐week‐old male nude mice (n = 6 peer group). On the day 33 day after inoculation, the tumors were collected, photographed, weighed, and analyzed by Western blot and TUNEL staining as previous described 18 . All animal studies were approved by Luodian Hospital Ethics Committee.…”

“…On the day 33 day after inoculation, the tumors were collected, photographed, weighed, and analyzed by Western blot and TUNEL staining as previous described. 18 All animal studies were approved by Luodian Hospital Ethics Committee.…”

Classical and Non-Classical Progesterone Signaling in Breast Cancers

“…Immunostaining can be utilized to differentiate between nuclear and membrane staining of PR and PGRMC1 respectively and assigning intensity scores could better distinguish PR and PGRMC1 expression in breast cancer tumors [ 139 ]. Furthermore, artificial intelligence along with machine learning software such as Nuquantus, that can be trained for accurate and rapid classification of cell subtype nuclei after studying and identifying patterns of tissue architecture could be trained to specifically identify and distinguish between nuclear and membrane staining [ 140 ]. Immunohistochemistry, immunofluorescence along with machine learning and staining intensity software could be used to identify PGRMC1 in human breast cancer tissues.…”