TY - JOUR
T1 - SATINN
T2 - an automated neural network-based classification of testicular sections allows for high-throughput histopathology of mouse mutants
AU - Yang, Ran
AU - Stendahl, Alexandra M.
AU - Vigh-Conrad, Katinka A.
AU - Held, Madison
AU - Lima, Ana C.
AU - Conrad, Donald F.
N1 - Publisher Copyright:
© The Author(s) 2022. Published by Oxford University Press.
PY - 2022/11/30
Y1 - 2022/11/30
N2 - MOTIVATION: The mammalian testis is a complex organ with a cellular composition that changes smoothly and cyclically in normal adults. While testis histology is already an invaluable tool for identifying and describing developmental differences in evolution and disease, methods for standardized, digital image analysis of testis are needed to expand the utility of this approach. RESULTS: We developed SATINN (Software for Analysis of Testis Images with Neural Networks), a multi-level framework for automated analysis of multiplexed immunofluorescence images from mouse testis. This approach uses residual learning to train convolutional neural networks (CNNs) to classify nuclei from seminiferous tubules into seven distinct cell types with an accuracy of 81.7%. These cell classifications are then used in a second-level tubule CNN, which places seminiferous tubules into one of 12 distinct tubule stages with 57.3% direct accuracy and 94.9% within ±1 stage. We further describe numerous cell- and tubule-level statistics that can be derived from wild-type testis. Finally, we demonstrate how the classifiers and derived statistics can be used to rapidly and precisely describe pathology by applying our methods to image data from two mutant mouse lines. Our results demonstrate the feasibility and potential of using computer-assisted analysis for testis histology, an area poised to evolve rapidly on the back of emerging, spatially resolved genomic and proteomic technologies. AVAILABILITY AND IMPLEMENTATION: The source code to reproduce the results described here and a SATINN standalone application with graphic-user interface are available from http://github.com/conradlab/SATINN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
AB - MOTIVATION: The mammalian testis is a complex organ with a cellular composition that changes smoothly and cyclically in normal adults. While testis histology is already an invaluable tool for identifying and describing developmental differences in evolution and disease, methods for standardized, digital image analysis of testis are needed to expand the utility of this approach. RESULTS: We developed SATINN (Software for Analysis of Testis Images with Neural Networks), a multi-level framework for automated analysis of multiplexed immunofluorescence images from mouse testis. This approach uses residual learning to train convolutional neural networks (CNNs) to classify nuclei from seminiferous tubules into seven distinct cell types with an accuracy of 81.7%. These cell classifications are then used in a second-level tubule CNN, which places seminiferous tubules into one of 12 distinct tubule stages with 57.3% direct accuracy and 94.9% within ±1 stage. We further describe numerous cell- and tubule-level statistics that can be derived from wild-type testis. Finally, we demonstrate how the classifiers and derived statistics can be used to rapidly and precisely describe pathology by applying our methods to image data from two mutant mouse lines. Our results demonstrate the feasibility and potential of using computer-assisted analysis for testis histology, an area poised to evolve rapidly on the back of emerging, spatially resolved genomic and proteomic technologies. AVAILABILITY AND IMPLEMENTATION: The source code to reproduce the results described here and a SATINN standalone application with graphic-user interface are available from http://github.com/conradlab/SATINN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
UR - http://www.scopus.com/inward/record.url?scp=85143180684&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143180684&partnerID=8YFLogxK
U2 - 10.1093/bioinformatics/btac673
DO - 10.1093/bioinformatics/btac673
M3 - Article
C2 - 36214638
AN - SCOPUS:85143180684
SN - 1367-4803
VL - 38
SP - 5288
EP - 5298
JO - Bioinformatics (Oxford, England)
JF - Bioinformatics (Oxford, England)
IS - 23
ER -