Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools
In vivo 1-photon (1p) calcium imaging is an increasingly prevalent method in behavioral neuroscience. Numerous analysis pipelines have been developed to improve the reliability and scalability of pre-processing and ROI extraction for these large calcium imaging datasets. Despite these advancements i...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-07-01
|
| Series: | Frontiers in Neural Circuits |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fncir.2020.00042/full |
| _version_ | 1818240611486007296 |
|---|---|
| author | Lina M. Tran Lina M. Tran Lina M. Tran Andrew J. Mocle Andrew J. Mocle Adam I. Ramsaran Adam I. Ramsaran Alexander D. Jacob Alexander D. Jacob Paul W. Frankland Paul W. Frankland Paul W. Frankland Paul W. Frankland Paul W. Frankland Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn |
| author_facet | Lina M. Tran Lina M. Tran Lina M. Tran Andrew J. Mocle Andrew J. Mocle Adam I. Ramsaran Adam I. Ramsaran Alexander D. Jacob Alexander D. Jacob Paul W. Frankland Paul W. Frankland Paul W. Frankland Paul W. Frankland Paul W. Frankland Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn |
| author_sort | Lina M. Tran |
| collection | DOAJ |
| description | In vivo 1-photon (1p) calcium imaging is an increasingly prevalent method in behavioral neuroscience. Numerous analysis pipelines have been developed to improve the reliability and scalability of pre-processing and ROI extraction for these large calcium imaging datasets. Despite these advancements in pre-processing methods, manual curation of the extracted spatial footprints and calcium traces of neurons remains important for quality control. Here, we propose an additional semi-automated curation step for sorting spatial footprints and calcium traces from putative neurons extracted using the popular constrained non-negative matrixfactorization for microendoscopic data (CNMF-E) algorithm. We used the automated machine learning (AutoML) tools TPOT and AutoSklearn to generate classifiers to curate the extracted ROIs trained on a subset of human-labeled data. AutoSklearn produced the best performing classifier, achieving an F1 score >92% on the ground truth test dataset. This automated approach is a useful strategy for filtering ROIs with relatively few labeled data points and can be easily added to pre-existing pipelines currently using CNMF-E for ROI extraction. |
| first_indexed | 2024-12-12T13:16:12Z |
| format | Article |
| id | doaj.art-e007498310e04931a0f0cf1a763b4490 |
| institution | Directory Open Access Journal |
| issn | 1662-5110 |
| language | English |
| last_indexed | 2024-12-12T13:16:12Z |
| publishDate | 2020-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neural Circuits |
| spelling | doaj.art-e007498310e04931a0f0cf1a763b44902022-12-22T00:23:24ZengFrontiers Media S.A.Frontiers in Neural Circuits1662-51102020-07-011410.3389/fncir.2020.00042542656Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML ToolsLina M. Tran0Lina M. Tran1Lina M. Tran2Andrew J. Mocle3Andrew J. Mocle4Adam I. Ramsaran5Adam I. Ramsaran6Alexander D. Jacob7Alexander D. Jacob8Paul W. Frankland9Paul W. Frankland10Paul W. Frankland11Paul W. Frankland12Paul W. Frankland13Sheena A. Josselyn14Sheena A. Josselyn15Sheena A. Josselyn16Sheena A. Josselyn17Sheena A. Josselyn18Hospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, CanadaDepartment of Physiology, University of Toronto, Toronto, ON, CanadaPostgraduate Affiliates Program, Vector Institute, Toronto, ON, CanadaHospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, CanadaDepartment of Physiology, University of Toronto, Toronto, ON, CanadaHospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, CanadaDepartment of Psychology, University of Toronto, Toronto, ON, CanadaHospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, CanadaDepartment of Psychology, University of Toronto, Toronto, ON, CanadaHospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, CanadaDepartment of Physiology, University of Toronto, Toronto, ON, CanadaDepartment of Psychology, University of Toronto, Toronto, ON, CanadaInstitute of Medical Sciences, University of Toronto, Toronto, ON, CanadaChild & Brain Development Program, Canadian Institute for Advanced Research (CIFAR), Toronto, ON, CanadaHospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, CanadaDepartment of Physiology, University of Toronto, Toronto, ON, CanadaDepartment of Psychology, University of Toronto, Toronto, ON, CanadaInstitute of Medical Sciences, University of Toronto, Toronto, ON, CanadaBrain, Mind & Consciousness Program, Canadian Institute for Advanced Research (CIFAR), Toronto, ON, CanadaIn vivo 1-photon (1p) calcium imaging is an increasingly prevalent method in behavioral neuroscience. Numerous analysis pipelines have been developed to improve the reliability and scalability of pre-processing and ROI extraction for these large calcium imaging datasets. Despite these advancements in pre-processing methods, manual curation of the extracted spatial footprints and calcium traces of neurons remains important for quality control. Here, we propose an additional semi-automated curation step for sorting spatial footprints and calcium traces from putative neurons extracted using the popular constrained non-negative matrixfactorization for microendoscopic data (CNMF-E) algorithm. We used the automated machine learning (AutoML) tools TPOT and AutoSklearn to generate classifiers to curate the extracted ROIs trained on a subset of human-labeled data. AutoSklearn produced the best performing classifier, achieving an F1 score >92% on the ground truth test dataset. This automated approach is a useful strategy for filtering ROIs with relatively few labeled data points and can be easily added to pre-existing pipelines currently using CNMF-E for ROI extraction.https://www.frontiersin.org/article/10.3389/fncir.2020.00042/fullcalcium imagingopen-sourcemachine learningmicroendoscopy1-photonCNMF-E |
| spellingShingle | Lina M. Tran Lina M. Tran Lina M. Tran Andrew J. Mocle Andrew J. Mocle Adam I. Ramsaran Adam I. Ramsaran Alexander D. Jacob Alexander D. Jacob Paul W. Frankland Paul W. Frankland Paul W. Frankland Paul W. Frankland Paul W. Frankland Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Sheena A. Josselyn Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools Frontiers in Neural Circuits calcium imaging open-source machine learning microendoscopy 1-photon CNMF-E |
| title | Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools |
| title_full | Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools |
| title_fullStr | Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools |
| title_full_unstemmed | Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools |
| title_short | Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools |
| title_sort | automated curation of cnmf e extracted roi spatial footprints and calcium traces using open source automl tools |
| topic | calcium imaging open-source machine learning microendoscopy 1-photon CNMF-E |
| url | https://www.frontiersin.org/article/10.3389/fncir.2020.00042/full |
| work_keys_str_mv | AT linamtran automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT linamtran automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT linamtran automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT andrewjmocle automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT andrewjmocle automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT adamiramsaran automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT adamiramsaran automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT alexanderdjacob automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT alexanderdjacob automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT paulwfrankland automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT paulwfrankland automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT paulwfrankland automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT paulwfrankland automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT paulwfrankland automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT sheenaajosselyn automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT sheenaajosselyn automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT sheenaajosselyn automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT sheenaajosselyn automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools AT sheenaajosselyn automatedcurationofcnmfeextractedroispatialfootprintsandcalciumtracesusingopensourceautomltools |