On the objectivity, reliability, and validity of deep learning enabled bioimage analyses
Segebarth, D.; Griebel, M.; Stein, N.; R. von Collenberg, C.; Martin, C.; Fiedler, D.; Comeras, L. B.; Sah, A.; Schoeffler, V.; Lueffe, T.; Duerr, A.; Gupta, R.; Sasi, M.; Lillesaar, C.; Lange, M. D.; Tasan, R. O.; Singewald, N.; Pape, H.-C.; Flath, C. M.; Blum, R.
Show abstract
Fluorescent labeling of biomolecules is widely used for bioimage analyses throughout the life sciences. Recent advances in deep learning (DL) have opened new possibilities to scale the image analysis processes through automation. However, the annotation of fluorescent features with a low signal-to-noise ratio is frequently based on subjective criteria. Training on subjective annotations may ultimately lead to biased DL models yielding irreproducible results. An end-to-end analysis process that integrates data annotation, ground truth estimation, and model training can mitigate this risk. To highlight the importance of this integrated process, we compare different DL-based analysis approaches. Based on data from different laboratories, we show that ground truth estimation from multiple human annotators is indispensable to establish objectivity in fluorescent feature annotations. We demonstrate that ensembles of multiple models trained on the estimated ground truth establish reliability and validity. Our research provides guidelines for reproducible and transparent bioimage analyses using DL methods.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Tracking cell lineages in 3D by incremental deep learning 94%
- An image segmentation method based on the spatial correlation coefficient of Local Moran's I - identification of A-type potassium channel clusters in the thalamus. 94%
- Bi-channel Image Registration and Deep-learning Segmentation (BIRDS) for efficient, versatile 3D mapping of mouse brain 94%
Similar papers in this journal
- BigNeuron: A resource to benchmark and predict best-performing algorithms for automated reconstruction of neuronal morphology 95%
- Deep Learning-Based Point-Scanning Super-Resolution Imaging 94%
- Cross-modality supervised image restoration enables nanoscale tracking of synaptic plasticity in living mice 93%
Similar papers in this journal
- Efficient cell-wide mapping of mitochondria in electron microscopic volumes using webKnossos 94%
- PatchWarp: Corrections of non-uniform image distortions in two-photon calcium imaging data by patchwork affine transformations 93%
- UniFORM: Towards Universal Immunofluorescence Normalization for Multiplex Tissue Imaging 93%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.