Counting using deep learning regression gives value to ecological surveys

Automated age-at-death estimation by cementochronology: Essential application or additional complication?

It has been repeatedly acknowledged that age-at-death estimation based on dental cementum represents a partial and time-consuming method that hinders adoption of this histological approach. User-friendly micrograph analysis represents a growing request of cementochronology. This article evaluates the feasibility of using a module to accurately quantify cementum deposits and compares the module's performance to that of a human expert. On a dental collection (n = 200) of known-age individuals, precision and accuracy of estimates performed by a developed program (101 count/tooth; n = 20,200 counts) were compared to counts performed manually (5 counts/tooth; n = 975 counts). Reliability of the software and agreement between the two approaches were assessed by intraclass correlation coefficient and Bland Altman analysis. The automated module produced reliable and reproducible counts with a higher global precision than the human expert. Although the software is slightly more precise, it shows higher sensitivity to taphonomic damages and does not avoid the trajectory effect described for age-at-death estimation in adults. Likewise, for human counts, global accuracy is acceptable, but underestimations increase with age. The quantification of the agreement between the two approaches shows a minor bias, and 94% of individuals fall within the intervals of agreement. Automation gives an impression of objectivity even though the region of interest, profile position and parameters are defined manually. The automated system may represent a time-saving module that can allow an increase in sample size, which is particularly stimulating for population-based studies.

Self-normalized density map (SNDM) for counting microbiological objects

The statistical properties of the density map (DM) approach to counting microbiological objects on images are studied in detail. The DM is given by U\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^2$$\end{document}2-Net. Two statistical methods for deep neural networks are utilized: the bootstrap and the Monte Carlo (MC) dropout. The detailed analysis of the uncertainties for the DM predictions leads to a deeper understanding of the DM model’s deficiencies. Based on our investigation, we propose a self-normalization module in the network. The improved network model, called Self-Normalized Density Map (SNDM), can correct its output density map by itself to accurately predict the total number of objects in the image. The SNDM architecture outperforms the original model. Moreover, both statistical frameworks—bootstrap and MC dropout—have consistent statistical results for SNDM, which were not observed in the original model. The SNDM efficiency is comparable with the detector-base models, such as Faster and Cascade R-CNN detectors.

Comparing Machine Learning and Binary Thresholding Methods for Quantification of Callose Deposits in the Citrus Phloem

Callose is a polysaccharide that can be fluorescently stained to study many developmental and immune functions in plants. High-throughput methods to accurately gather quantitative measurements of callose from confocal images are useful for many applications in plant biology. Previous callose quantification methods relied upon binary local thresholding, which had the disadvantage of not being able to differentiate callose in conditions with low contrast from background material. Here, a measurement approach that utilizes the Ilastik supervised machine learning imagery data collection software is described. The Ilastik software method provided superior efficiency for acquiring counts of callose deposits. We also determined the accuracy of these methods as compared to manual counts. We demonstrate that the automated software methods are both good predictors of manual counts, but that the Ilastik counts are significantly closer. Researchers can use this information to guide their choice of method to quantify callose in their work.