Embryo Staging with Weakly-Supervised Region Selection and Dynamically-Decoded Predictions Article Swipe
Tingfung Lau
,
Nathan Ng
,
Julian A. Gingold
,
Nina Desai
,
Julian McAuley
,
Zachary C. Lipton
·
YOU?
·
· 2019
· Open Access
·
YOU?
·
· 2019
· Open Access
·
To optimize clinical outcomes, fertility clinics must strategically select which embryos to transfer. Common selection heuristics are formulas expressed in terms of the durations required to reach various developmental milestones, quantities historically annotated manually by experienced embryologists based on time-lapse EmbryoScope videos. We propose a new method for automatic embryo staging that exploits several sources of structure in this time-lapse data. First, noting that in each image the embryo occupies a small subregion, we jointly train a region proposal network with the downstream classifier to isolate the embryo. Notably, because we lack ground-truth bounding boxes, our we weakly supervise the region proposal network optimizing its parameters via reinforcement learning to improve the downstream classifier's loss. Moreover, noting that embryos reaching the blastocyst stage progress monotonically through earlier stages, we develop a dynamic-programming-based decoder that post-processes our predictions to select the most likely monotonic sequence of developmental stages. Our methods outperform vanilla residual networks and rival the best numbers in contemporary papers, as measured by both per-frame accuracy and transition prediction error, despite operating on smaller data than many.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- http://arxiv.org/pdf/1904.04419.pdf
- OA Status
- green
- Cited By
- 1
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2990878470
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2990878470Canonical identifier for this work in OpenAlex
- Title
-
Embryo Staging with Weakly-Supervised Region Selection and Dynamically-Decoded PredictionsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2019Year of publication
- Publication date
-
2019-10-28Full publication date if available
- Authors
-
Tingfung Lau, Nathan Ng, Julian A. Gingold, Nina Desai, Julian McAuley, Zachary C. LiptonList of authors in order
- Landing page
-
https://arxiv.org/pdf/1904.04419.pdfPublisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/1904.04419.pdfDirect OA link when available
- Concepts
-
Bounding overwatch, Computer science, Artificial intelligence, Heuristics, Classifier (UML), Machine learning, Selection (genetic algorithm), Ground truth, Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1Per-year citation counts (last 5 years)
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2990878470 |
|---|---|
| doi | |
| ids.mag | 2990878470 |
| ids.openalex | https://openalex.org/W2990878470 |
| fwci | 0.27626919 |
| type | article |
| title | Embryo Staging with Weakly-Supervised Region Selection and Dynamically-Decoded Predictions |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 679 |
| biblio.first_page | 663 |
| topics[0].id | https://openalex.org/T10364 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9926999807357788 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2739 |
| topics[0].subfield.display_name | Public Health, Environmental and Occupational Health |
| topics[0].display_name | Reproductive Biology and Fertility |
| topics[1].id | https://openalex.org/T11732 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.9545000195503235 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2735 |
| topics[1].subfield.display_name | Pediatrics, Perinatology and Child Health |
| topics[1].display_name | Assisted Reproductive Technology and Twin Pregnancy |
| topics[2].id | https://openalex.org/T11156 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9501000046730042 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2743 |
| topics[2].subfield.display_name | Reproductive Medicine |
| topics[2].display_name | Reproductive Health and Technologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C63584917 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6713199019432068 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q333286 |
| concepts[0].display_name | Bounding overwatch |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6598145365715027 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6532660126686096 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C127705205 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5956462025642395 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q5748245 |
| concepts[3].display_name | Heuristics |
| concepts[4].id | https://openalex.org/C95623464 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5479100942611694 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[4].display_name | Classifier (UML) |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5385442972183228 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C81917197 |
| concepts[6].level | 2 |
| concepts[6].score | 0.43673932552337646 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q628760 |
| concepts[6].display_name | Selection (genetic algorithm) |
| concepts[7].id | https://openalex.org/C146849305 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4298757314682007 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q370766 |
| concepts[7].display_name | Ground truth |
| concepts[8].id | https://openalex.org/C111919701 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[8].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/bounding-overwatch |
| keywords[0].score | 0.6713199019432068 |
| keywords[0].display_name | Bounding overwatch |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6598145365715027 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6532660126686096 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/heuristics |
| keywords[3].score | 0.5956462025642395 |
| keywords[3].display_name | Heuristics |
| keywords[4].id | https://openalex.org/keywords/classifier |
| keywords[4].score | 0.5479100942611694 |
| keywords[4].display_name | Classifier (UML) |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.5385442972183228 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/selection |
| keywords[6].score | 0.43673932552337646 |
| keywords[6].display_name | Selection (genetic algorithm) |
| keywords[7].id | https://openalex.org/keywords/ground-truth |
| keywords[7].score | 0.4298757314682007 |
| keywords[7].display_name | Ground truth |
| language | en |
| locations[0].id | mag:2990878470 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | |
| locations[0].raw_source_name | arXiv (Cornell University) |
| locations[0].landing_page_url | http://arxiv.org/pdf/1904.04419.pdf |
| authorships[0].author.id | https://openalex.org/A5009069781 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3565-3701 |
| authorships[0].author.display_name | Tingfung Lau |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Tingfung Lau |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5086226474 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7063-6870 |
| authorships[1].author.display_name | Nathan Ng |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Nathan Ng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5045456666 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-0354-5933 |
| authorships[2].author.display_name | Julian A. Gingold |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Julian Gingold |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5048457996 |
| authorships[3].author.orcid | https://orcid.org/0009-0004-6502-2822 |
| authorships[3].author.display_name | Nina Desai |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Nina Desai |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5021827617 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0955-7588 |
| authorships[4].author.display_name | Julian McAuley |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Julian J. McAuley |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5029448258 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3824-4241 |
| authorships[5].author.display_name | Zachary C. Lipton |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Zachary C. Lipton |
| authorships[5].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | http://arxiv.org/pdf/1904.04419.pdf |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Embryo Staging with Weakly-Supervised Region Selection and Dynamically-Decoded Predictions |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-10-10T17:16:08.811792 |
| primary_topic.id | https://openalex.org/T10364 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9926999807357788 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2739 |
| primary_topic.subfield.display_name | Public Health, Environmental and Occupational Health |
| primary_topic.display_name | Reproductive Biology and Fertility |
| related_works | https://openalex.org/W2938557231, https://openalex.org/W3176047859, https://openalex.org/W3130750498, https://openalex.org/W2342546612, https://openalex.org/W2797178690, https://openalex.org/W2998873753, https://openalex.org/W2026770594, https://openalex.org/W2766453073, https://openalex.org/W1639984653, https://openalex.org/W3211930213, https://openalex.org/W135774226, https://openalex.org/W2887545942, https://openalex.org/W2980469003, https://openalex.org/W2532798634, https://openalex.org/W3209542436, https://openalex.org/W2798471433, https://openalex.org/W2968351798, https://openalex.org/W2949923404, https://openalex.org/W2804015809, https://openalex.org/W2077760583 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | mag:2990878470 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | arXiv (Cornell University) |
| best_oa_location.landing_page_url | http://arxiv.org/pdf/1904.04419.pdf |
| primary_location.id | mag:2990878470 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | arXiv (Cornell University) |
| primary_location.landing_page_url | http://arxiv.org/pdf/1904.04419.pdf |
| publication_date | 2019-10-28 |
| publication_year | 2019 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 44, 70, 76, 130 |
| abstract_inverted_index.To | 0 |
| abstract_inverted_index.We | 42 |
| abstract_inverted_index.as | 161 |
| abstract_inverted_index.by | 34, 163 |
| abstract_inverted_index.in | 19, 57, 64, 158 |
| abstract_inverted_index.of | 21, 55, 144 |
| abstract_inverted_index.on | 38, 173 |
| abstract_inverted_index.to | 11, 25, 84, 109, 137 |
| abstract_inverted_index.we | 73, 90, 96, 128 |
| abstract_inverted_index.Our | 147 |
| abstract_inverted_index.and | 153, 167 |
| abstract_inverted_index.are | 16 |
| abstract_inverted_index.for | 47 |
| abstract_inverted_index.its | 104 |
| abstract_inverted_index.new | 45 |
| abstract_inverted_index.our | 95, 135 |
| abstract_inverted_index.the | 22, 67, 81, 86, 99, 111, 120, 139, 155 |
| abstract_inverted_index.via | 106 |
| abstract_inverted_index.best | 156 |
| abstract_inverted_index.both | 164 |
| abstract_inverted_index.data | 175 |
| abstract_inverted_index.each | 65 |
| abstract_inverted_index.lack | 91 |
| abstract_inverted_index.most | 140 |
| abstract_inverted_index.must | 6 |
| abstract_inverted_index.than | 176 |
| abstract_inverted_index.that | 51, 63, 117, 133 |
| abstract_inverted_index.this | 58 |
| abstract_inverted_index.with | 80 |
| abstract_inverted_index.based | 37 |
| abstract_inverted_index.data. | 60 |
| abstract_inverted_index.image | 66 |
| abstract_inverted_index.loss. | 114 |
| abstract_inverted_index.many. | 177 |
| abstract_inverted_index.reach | 26 |
| abstract_inverted_index.rival | 154 |
| abstract_inverted_index.small | 71 |
| abstract_inverted_index.stage | 122 |
| abstract_inverted_index.terms | 20 |
| abstract_inverted_index.train | 75 |
| abstract_inverted_index.which | 9 |
| abstract_inverted_index.Common | 13 |
| abstract_inverted_index.First, | 61 |
| abstract_inverted_index.boxes, | 94 |
| abstract_inverted_index.embryo | 49, 68 |
| abstract_inverted_index.error, | 170 |
| abstract_inverted_index.likely | 141 |
| abstract_inverted_index.method | 46 |
| abstract_inverted_index.noting | 62, 116 |
| abstract_inverted_index.region | 77, 100 |
| abstract_inverted_index.select | 8, 138 |
| abstract_inverted_index.weakly | 97 |
| abstract_inverted_index.because | 89 |
| abstract_inverted_index.clinics | 5 |
| abstract_inverted_index.decoder | 132 |
| abstract_inverted_index.despite | 171 |
| abstract_inverted_index.develop | 129 |
| abstract_inverted_index.earlier | 126 |
| abstract_inverted_index.embryo. | 87 |
| abstract_inverted_index.embryos | 10, 118 |
| abstract_inverted_index.improve | 110 |
| abstract_inverted_index.isolate | 85 |
| abstract_inverted_index.jointly | 74 |
| abstract_inverted_index.methods | 148 |
| abstract_inverted_index.network | 79, 102 |
| abstract_inverted_index.numbers | 157 |
| abstract_inverted_index.papers, | 160 |
| abstract_inverted_index.propose | 43 |
| abstract_inverted_index.several | 53 |
| abstract_inverted_index.smaller | 174 |
| abstract_inverted_index.sources | 54 |
| abstract_inverted_index.stages, | 127 |
| abstract_inverted_index.stages. | 146 |
| abstract_inverted_index.staging | 50 |
| abstract_inverted_index.through | 125 |
| abstract_inverted_index.vanilla | 150 |
| abstract_inverted_index.various | 27 |
| abstract_inverted_index.videos. | 41 |
| abstract_inverted_index.Notably, | 88 |
| abstract_inverted_index.accuracy | 166 |
| abstract_inverted_index.bounding | 93 |
| abstract_inverted_index.clinical | 2 |
| abstract_inverted_index.exploits | 52 |
| abstract_inverted_index.formulas | 17 |
| abstract_inverted_index.learning | 108 |
| abstract_inverted_index.manually | 33 |
| abstract_inverted_index.measured | 162 |
| abstract_inverted_index.networks | 152 |
| abstract_inverted_index.occupies | 69 |
| abstract_inverted_index.optimize | 1 |
| abstract_inverted_index.progress | 123 |
| abstract_inverted_index.proposal | 78, 101 |
| abstract_inverted_index.reaching | 119 |
| abstract_inverted_index.required | 24 |
| abstract_inverted_index.residual | 151 |
| abstract_inverted_index.sequence | 143 |
| abstract_inverted_index.Moreover, | 115 |
| abstract_inverted_index.annotated | 32 |
| abstract_inverted_index.automatic | 48 |
| abstract_inverted_index.durations | 23 |
| abstract_inverted_index.expressed | 18 |
| abstract_inverted_index.fertility | 4 |
| abstract_inverted_index.monotonic | 142 |
| abstract_inverted_index.operating | 172 |
| abstract_inverted_index.outcomes, | 3 |
| abstract_inverted_index.per-frame | 165 |
| abstract_inverted_index.selection | 14 |
| abstract_inverted_index.structure | 56 |
| abstract_inverted_index.supervise | 98 |
| abstract_inverted_index.transfer. | 12 |
| abstract_inverted_index.blastocyst | 121 |
| abstract_inverted_index.classifier | 83 |
| abstract_inverted_index.downstream | 82, 112 |
| abstract_inverted_index.heuristics | 15 |
| abstract_inverted_index.optimizing | 103 |
| abstract_inverted_index.outperform | 149 |
| abstract_inverted_index.parameters | 105 |
| abstract_inverted_index.prediction | 169 |
| abstract_inverted_index.quantities | 30 |
| abstract_inverted_index.subregion, | 72 |
| abstract_inverted_index.time-lapse | 39, 59 |
| abstract_inverted_index.transition | 168 |
| abstract_inverted_index.EmbryoScope | 40 |
| abstract_inverted_index.experienced | 35 |
| abstract_inverted_index.milestones, | 29 |
| abstract_inverted_index.predictions | 136 |
| abstract_inverted_index.classifier's | 113 |
| abstract_inverted_index.contemporary | 159 |
| abstract_inverted_index.ground-truth | 92 |
| abstract_inverted_index.historically | 31 |
| abstract_inverted_index.developmental | 28, 145 |
| abstract_inverted_index.embryologists | 36 |
| abstract_inverted_index.monotonically | 124 |
| abstract_inverted_index.reinforcement | 107 |
| abstract_inverted_index.strategically | 7 |
| abstract_inverted_index.post-processes | 134 |
| abstract_inverted_index.dynamic-programming-based | 131 |
| cited_by_percentile_year.max | 93 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/2 |
| sustainable_development_goals[0].score | 0.4000000059604645 |
| sustainable_development_goals[0].display_name | Zero hunger |
| citation_normalized_percentile.value | 0.64170244 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |