On the objectivity, reliability, and validity of deep learning enabled bioimage analyses
- University Hospital Würzburg, Germany
- University of Würzburg, Germany
- Westfälische Wilhlems-Universität, Germany
- University of Innsbruck, Austria
- University of Inssbruck, Austria
Abstract
Bioimage analysis of fluorescent labels is widely used in the life sciences. Recent advances in deep learning (DL) allow automating time-consuming manual image analysis processes based on annotated training data. However, manual annotation of fluorescent features with a low signal-to-noise ratio is somewhat subjective. Training DL models on subjective annotations may be instable or yield biased models. In turn, these models may be unable to reliably detect biological effects. An analysis pipeline integrating data annotation, ground truth estimation, and model training can mitigate this risk. To evaluate this integrated process, we compared different DL-based analysis approaches. With data from two model organisms (mice, zebrafish) and five laboratories, we show that ground truth estimation from multiple human annotators helps to establish objectivity in fluorescent feature annotations. Furthermore, ensembles of multiple models trained on the estimated ground truth establish reliability and validity. Our research provides guidelines for reproducible DL-based bioimage analyses.
Data availability
Official repository of our study "On the objectivity, reliability, and validity of deep learning enabled bioimage analyses" can be found at Dryad (https://doi.org/10.5061/dryad.4b8gtht9d). In addition, we also provide all code in our GitHub repository (https://github.com/matjesg/bioimage_analysis).
-
Data from: On the objectivity, reliability, and validity of deep learning enabled bioimage analysesDryad Digital Repository, 10.5061/dryad.4b8gtht9d.
Article and author information
Author details
Christina Lillesaar
Hans-Christian Pape
Funding
Deutsche Forschungsgemeinschaft (ID 44541416 - TRR58,A10)
- Robert Blum
Deutsche Forschungsgemeinschaft (ID 44541416 - TRR58,A03)
- Hans-Christian Pape
Deutsche Forschungsgemeinschaft (ID 44541416 - TRR58,B08)
- Maren D Lange
Graduate School of Life Sciences Wuerzburg (fellowship)
- Rohini Gupta
- Manju Sasi
Austrian Science Fund (P29952 & P25851)
- Ramon O Tasan
Austrian Science Fund (I2433-B26,DKW-1206,SFB F4410)
- Nicolas Singewald
Interdisziplinaeres Zentrum fuer Klinische Zusammenarbeit Wuerzburg (N-320)
- Christina Lillesaar
Deutsche Forschungsgemeinschaft (ID 424778381)
- Robert Blum
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Ethics
Animal experimentation: All effort was taken to minimize the number of animals used and their suffering.Lab-Wue1: All experiments with C57BL/6J wildtype mice were in accordance with the Guidelines set by the European Union and approved by our institutional Animal Care, the Utilization Committee and the Regierung von Unterfranken, Würzburg, Germany (License number: 55.2-2531.01-95/13). C57BL/6J wildtype mice were bred in the animal facility of the Institute of Clinical Neurobiology, University Hospital of Würzburg, Germany.Lab Mue: Male All animal experiments with male C57Bl/6J mice (Charles River, Sulzfeld, Germany) were carried out in accordance with European regulations on animal experimentation and protocols were approved by the local authorities (Landesamt für Natur, Umwelt und Verbraucherschutz Nordrhein-Westfalen).Lab-Inns1: Experiments were performed in adult, male C57Bl/6NCrl mice (Charles River, Sulzfeld, Germany). They were bred in the Department of Pharmacology at the Medical University Innsbruck, Austria. All procedures involving animals and animal care were conducted in accordance with international laws and policies (Directive 2010/63/EU of the European parliament and of the council of 22 September 2010 on the protection of animals used for scientific purposes; Guide for the Care and Use of Laboratory Animals, U.S. National Research Council, 2011) and were approved by the Austrian Ministry of Science.Lab-Inns2: Male 129S1/SvImJ (S1) mice (Charles River, Sulzfeld, Germany) were used for experimentation. The Austrian Animal Experimentation Ethics Board (Bundesministerium für Wissenschaft Forschung und Wirtschaft, Kommission für Tierversuchsangelegenheiten) approved all experimental procedures.
Copyright
© 2020, Segebarth et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 4,572
- views
-
- 501
- downloads
-
- 30
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
On the objectivity, reliability, and validity of deep learning enabled bioimage analyses
eLife 9:e59780.
https://doi.org/10.7554/eLife.59780
Further reading
-
- Computational and Systems Biology
- Neuroscience
Hypothalamic kisspeptin (Kiss1) neurons are vital for pubertal development and reproduction. Arcuate nucleus Kiss1 (Kiss1ARH) neurons are responsible for the pulsatile release of gonadotropin-releasing hormone (GnRH). In females, the behavior of Kiss1ARH neurons, expressing Kiss1, neurokinin B (NKB), and dynorphin (Dyn), varies throughout the ovarian cycle. Studies indicate that 17β-estradiol (E2) reduces peptide expression but increases Slc17a6 (Vglut2) mRNA and glutamate neurotransmission in these neurons, suggesting a shift from peptidergic to glutamatergic signaling. To investigate this shift, we combined transcriptomics, electrophysiology, and mathematical modeling. Our results demonstrate that E2 treatment upregulates the mRNA expression of voltage-activated calcium channels, elevating the whole-cell calcium current that contributes to high-frequency burst firing. Additionally, E2 treatment decreased the mRNA levels of canonical transient receptor potential (TPRC) 5 and G protein-coupled K+ (GIRK) channels. When Trpc5 channels in Kiss1ARH neurons were deleted using CRISPR/SaCas9, the slow excitatory postsynaptic potential was eliminated. Our data enabled us to formulate a biophysically realistic mathematical model of Kiss1ARH neurons, suggesting that E2 modifies ionic conductances in these neurons, enabling the transition from high-frequency synchronous firing through NKB-driven activation of TRPC5 channels to a short bursting mode facilitating glutamate release. In a low E2 milieu, synchronous firing of Kiss1ARH neurons drives pulsatile release of GnRH, while the transition to burst firing with high, preovulatory levels of E2 would facilitate the GnRH surge through its glutamatergic synaptic connection to preoptic Kiss1 neurons.
-
- Computational and Systems Biology
Degree distributions in protein-protein interaction (PPI) networks are believed to follow a power law (PL). However, technical and study bias affect the experimental procedures for detecting PPIs. For instance, cancer-associated proteins have received disproportional attention. Moreover, bait proteins in large-scale experiments tend to have many false-positive interaction partners. Studying the degree distributions of thousands of PPI networks of controlled provenance, we address the question if PL distributions in observed PPI networks could be explained by these biases alone. Our findings are supported by mathematical models and extensive simulations and indicate that study bias and technical bias suffice to produce the observed PL distribution. It is, hence, problematic to derive hypotheses about the topology of the true biological interactome from the PL distributions in observed PPI networks. Our study casts doubt on the use of the PL property of biological networks as a modeling assumption or quality criterion in network biology.
