Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i4.32408
We present Connected-Component (CC)-Metrics, a novel semantic segmentation evaluation protocol, targeted to align existing semantic segmentation metrics to a multi-instance detection scenario in which each connected component matters. We motivate this setup in the common medical scenario of semantic metastases segmentation in a full-body PET/CT. We show how existing semantic segmentation metrics suffer from a bias towards larger connected components contradicting the clinical assessment of scans in which tumor size and clinical relevance are uncorrelated. To rebalance existing segmentation metrics, we propose to evaluate them on a per-component basis thus giving each tumor the same weight irrespective of its size. To match predictions to ground-truth segments, we employ a proximity-based matching criterion, evaluating common metrics locally at the component of interest. Using this approach, we break free of biases introduced by large metastasis for overlap-based metrics such as Dice or Surface Dice. CC-Metrics also improves distance-based metrics such as Hausdorff Distances which are uninformative for small changes that do not influence the maximum or 95th percentile, and avoids pitfalls introduced by directly combining counting-based metrics with overlap-based metrics as it is done in Panoptic Quality.
Related Topics
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i4.32408
- https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563
- OA Status
- diamond
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409368620
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409368620Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i4.32408Digital Object Identifier
- Title
-
Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation TasksWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Alexander Jaus, Constantin Seibold, Simon Reiß, Zdravko Marinov, Keyi Li, Ziqi Ye, Stefan Krieg, Jens Kleesiek, Rainer StiefelhagenList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i4.32408Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563Direct OA link when available
- Concepts
-
Segmentation, Component (thermodynamics), Measure (data warehouse), Computer science, Artificial intelligence, Natural language processing, Data mining, Physics, ThermodynamicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4409368620 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i4.32408 |
| ids.doi | https://doi.org/10.1609/aaai.v39i4.32408 |
| ids.openalex | https://openalex.org/W4409368620 |
| fwci | 0.0 |
| type | article |
| title | Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks |
| biblio.issue | 4 |
| biblio.volume | 39 |
| biblio.last_page | 3912 |
| biblio.first_page | 3904 |
| topics[0].id | https://openalex.org/T11636 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9010999798774719 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2718 |
| topics[0].subfield.display_name | Health Informatics |
| topics[0].display_name | Artificial Intelligence in Healthcare and Education |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C89600930 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8041812181472778 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[0].display_name | Segmentation |
| concepts[1].id | https://openalex.org/C168167062 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7422454953193665 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1117970 |
| concepts[1].display_name | Component (thermodynamics) |
| concepts[2].id | https://openalex.org/C2780009758 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6420834064483643 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q6804172 |
| concepts[2].display_name | Measure (data warehouse) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5874323844909668 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5262994766235352 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3678475618362427 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C124101348 |
| concepts[6].level | 1 |
| concepts[6].score | 0.16033971309661865 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[6].display_name | Data mining |
| concepts[7].id | https://openalex.org/C121332964 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[7].display_name | Physics |
| concepts[8].id | https://openalex.org/C97355855 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11473 |
| concepts[8].display_name | Thermodynamics |
| keywords[0].id | https://openalex.org/keywords/segmentation |
| keywords[0].score | 0.8041812181472778 |
| keywords[0].display_name | Segmentation |
| keywords[1].id | https://openalex.org/keywords/component |
| keywords[1].score | 0.7422454953193665 |
| keywords[1].display_name | Component (thermodynamics) |
| keywords[2].id | https://openalex.org/keywords/measure |
| keywords[2].score | 0.6420834064483643 |
| keywords[2].display_name | Measure (data warehouse) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5874323844909668 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5262994766235352 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.3678475618362427 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/data-mining |
| keywords[6].score | 0.16033971309661865 |
| keywords[6].display_name | Data mining |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i4.32408 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v39i4.32408 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5051426025 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0669-0300 |
| authorships[0].author.display_name | Alexander Jaus |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Alexander Jaus |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5084474018 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6042-8437 |
| authorships[1].author.display_name | Constantin Seibold |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Constantin Marc Seibold |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5091379199 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1953-6211 |
| authorships[2].author.display_name | Simon Reiß |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Simon Reiß |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5079221964 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-0373-3958 |
| authorships[3].author.display_name | Zdravko Marinov |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zdravko Marinov |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5109743031 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Keyi Li |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Keyi Li |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5051523008 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3156-7267 |
| authorships[5].author.display_name | Ziqi Ye |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zeling Ye |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5101730873 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-8417-9823 |
| authorships[6].author.display_name | Stefan Krieg |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Stefan Krieg |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5017161970 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8686-0682 |
| authorships[7].author.display_name | Jens Kleesiek |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Jens Kleesiek |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5087051920 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-8046-4945 |
| authorships[8].author.display_name | Rainer Stiefelhagen |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Rainer Stiefelhagen |
| authorships[8].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11636 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9010999798774719 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2718 |
| primary_topic.subfield.display_name | Health Informatics |
| primary_topic.display_name | Artificial Intelligence in Healthcare and Education |
| related_works | https://openalex.org/W4255837520, https://openalex.org/W2357256365, https://openalex.org/W2387011115, https://openalex.org/W2348502264, https://openalex.org/W2365486383, https://openalex.org/W2362059367, https://openalex.org/W4234808182, https://openalex.org/W2382043075, https://openalex.org/W2350084742, https://openalex.org/W3204019825 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i4.32408 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v39i4.32408 |
| primary_location.id | doi:10.1609/aaai.v39i4.32408 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/32408/34563 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v39i4.32408 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 18, 42, 54, 86, 108 |
| abstract_inverted_index.To | 75, 100 |
| abstract_inverted_index.We | 0, 28, 45 |
| abstract_inverted_index.as | 137, 148, 178 |
| abstract_inverted_index.at | 116 |
| abstract_inverted_index.by | 130, 170 |
| abstract_inverted_index.do | 158 |
| abstract_inverted_index.in | 22, 32, 41, 66, 182 |
| abstract_inverted_index.is | 180 |
| abstract_inverted_index.it | 179 |
| abstract_inverted_index.of | 37, 64, 97, 119, 127 |
| abstract_inverted_index.on | 85 |
| abstract_inverted_index.or | 139, 163 |
| abstract_inverted_index.to | 11, 17, 82, 103 |
| abstract_inverted_index.we | 80, 106, 124 |
| abstract_inverted_index.and | 70, 166 |
| abstract_inverted_index.are | 73, 152 |
| abstract_inverted_index.for | 133, 154 |
| abstract_inverted_index.how | 47 |
| abstract_inverted_index.its | 98 |
| abstract_inverted_index.not | 159 |
| abstract_inverted_index.the | 33, 61, 93, 117, 161 |
| abstract_inverted_index.95th | 164 |
| abstract_inverted_index.Dice | 138 |
| abstract_inverted_index.also | 143 |
| abstract_inverted_index.bias | 55 |
| abstract_inverted_index.done | 181 |
| abstract_inverted_index.each | 24, 91 |
| abstract_inverted_index.free | 126 |
| abstract_inverted_index.from | 53 |
| abstract_inverted_index.same | 94 |
| abstract_inverted_index.show | 46 |
| abstract_inverted_index.size | 69 |
| abstract_inverted_index.such | 136, 147 |
| abstract_inverted_index.that | 157 |
| abstract_inverted_index.them | 84 |
| abstract_inverted_index.this | 30, 122 |
| abstract_inverted_index.thus | 89 |
| abstract_inverted_index.with | 175 |
| abstract_inverted_index.Dice. | 141 |
| abstract_inverted_index.Using | 121 |
| abstract_inverted_index.align | 12 |
| abstract_inverted_index.basis | 88 |
| abstract_inverted_index.break | 125 |
| abstract_inverted_index.large | 131 |
| abstract_inverted_index.match | 101 |
| abstract_inverted_index.novel | 5 |
| abstract_inverted_index.scans | 65 |
| abstract_inverted_index.setup | 31 |
| abstract_inverted_index.size. | 99 |
| abstract_inverted_index.small | 155 |
| abstract_inverted_index.tumor | 68, 92 |
| abstract_inverted_index.which | 23, 67, 151 |
| abstract_inverted_index.avoids | 167 |
| abstract_inverted_index.biases | 128 |
| abstract_inverted_index.common | 34, 113 |
| abstract_inverted_index.employ | 107 |
| abstract_inverted_index.giving | 90 |
| abstract_inverted_index.larger | 57 |
| abstract_inverted_index.suffer | 52 |
| abstract_inverted_index.weight | 95 |
| abstract_inverted_index.PET/CT. | 44 |
| abstract_inverted_index.Surface | 140 |
| abstract_inverted_index.changes | 156 |
| abstract_inverted_index.locally | 115 |
| abstract_inverted_index.maximum | 162 |
| abstract_inverted_index.medical | 35 |
| abstract_inverted_index.metrics | 16, 51, 114, 135, 146, 174, 177 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.propose | 81 |
| abstract_inverted_index.towards | 56 |
| abstract_inverted_index.Panoptic | 183 |
| abstract_inverted_index.Quality. | 184 |
| abstract_inverted_index.clinical | 62, 71 |
| abstract_inverted_index.directly | 171 |
| abstract_inverted_index.evaluate | 83 |
| abstract_inverted_index.existing | 13, 48, 77 |
| abstract_inverted_index.improves | 144 |
| abstract_inverted_index.matching | 110 |
| abstract_inverted_index.matters. | 27 |
| abstract_inverted_index.metrics, | 79 |
| abstract_inverted_index.motivate | 29 |
| abstract_inverted_index.pitfalls | 168 |
| abstract_inverted_index.scenario | 21, 36 |
| abstract_inverted_index.semantic | 6, 14, 38, 49 |
| abstract_inverted_index.targeted | 10 |
| abstract_inverted_index.Distances | 150 |
| abstract_inverted_index.Hausdorff | 149 |
| abstract_inverted_index.approach, | 123 |
| abstract_inverted_index.combining | 172 |
| abstract_inverted_index.component | 26, 118 |
| abstract_inverted_index.connected | 25, 58 |
| abstract_inverted_index.detection | 20 |
| abstract_inverted_index.full-body | 43 |
| abstract_inverted_index.influence | 160 |
| abstract_inverted_index.interest. | 120 |
| abstract_inverted_index.protocol, | 9 |
| abstract_inverted_index.rebalance | 76 |
| abstract_inverted_index.relevance | 72 |
| abstract_inverted_index.segments, | 105 |
| abstract_inverted_index.CC-Metrics | 142 |
| abstract_inverted_index.assessment | 63 |
| abstract_inverted_index.components | 59 |
| abstract_inverted_index.criterion, | 111 |
| abstract_inverted_index.evaluating | 112 |
| abstract_inverted_index.evaluation | 8 |
| abstract_inverted_index.introduced | 129, 169 |
| abstract_inverted_index.metastases | 39 |
| abstract_inverted_index.metastasis | 132 |
| abstract_inverted_index.percentile, | 165 |
| abstract_inverted_index.predictions | 102 |
| abstract_inverted_index.ground-truth | 104 |
| abstract_inverted_index.irrespective | 96 |
| abstract_inverted_index.segmentation | 7, 15, 40, 50, 78 |
| abstract_inverted_index.(CC)-Metrics, | 3 |
| abstract_inverted_index.contradicting | 60 |
| abstract_inverted_index.overlap-based | 134, 176 |
| abstract_inverted_index.per-component | 87 |
| abstract_inverted_index.uncorrelated. | 74 |
| abstract_inverted_index.uninformative | 153 |
| abstract_inverted_index.counting-based | 173 |
| abstract_inverted_index.distance-based | 145 |
| abstract_inverted_index.multi-instance | 19 |
| abstract_inverted_index.proximity-based | 109 |
| abstract_inverted_index.Connected-Component | 2 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile.value | 0.4 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |