Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma Article Swipe

PDF

Sumit Kumar Jha , Purnendu Mishra , Shubham Mathur , Gursewak Singh , Rajiv Kumar , Kiran Aatre , Suraj Rengarajan ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2406.10893

Immunohistochemistry (IHC) analysis is a well-accepted and widely used method for molecular subtyping, a procedure for prognosis and targeted therapy of breast carcinoma, the most common type of tumor affecting women. There are four molecular biomarkers namely progesterone receptor (PR), estrogen receptor (ER), antigen Ki67, and human epidermal growth factor receptor 2 (HER2) whose assessment is needed under IHC procedure to decide prognosis as well as predictors of response to therapy. However, IHC scoring is based on subjective microscopic examination of tumor morphology and suffers from poor reproducibility, high subjectivity, and often incorrect scoring in low-score cases. In this paper, we present, a deep learning-based semi-supervised trained, fully automatic, decision support system (DSS) for IHC scoring of invasive ductal carcinoma. Our system automatically detects the tumor region removing artifacts and scores based on Allred standard. The system is developed using 3 million pathologist-annotated image patches from 300 slides, fifty thousand in-house cell annotations, and forty thousand pixels marking of HER2 membrane. We have conducted multicentric trials at four centers with three different types of digital scanners in terms of percentage agreement with doctors. And achieved agreements of 95, 92, 88 and 82 percent for Ki67, HER2, ER, and PR stain categories, respectively. In addition to overall accuracy, we found that there is 5 percent of cases where pathologist have changed their score in favor of algorithm score while reviewing with detailed algorithmic analysis. Our approach could improve the accuracy of IHC scoring and subsequent therapy decisions, particularly where specialist expertise is unavailable. Our system is highly modular. The proposed algorithm modules can be used to develop DSS for other cancer types.

Related Topics

Artificial Intelligence

Concepts

Immunohistochemistry Ductal carcinoma Algorithm Breast carcinoma Computer science Carcinoma Artificial intelligence Medicine Pathology Breast cancer Internal medicine Cancer

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2406.10893
PDF: https://arxiv.org/pdf/2406.10893
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4399794647

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4399794647

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2406.10893

Digital Object Identifier
Title: Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-06-16

Full publication date if available
Authors: Sumit Kumar Jha, Purnendu Mishra, Shubham Mathur, Gursewak Singh, Rajiv Kumar, Kiran Aatre, Suraj Rengarajan

List of authors in order
Landing page: https://arxiv.org/abs/2406.10893

Publisher landing page
PDF URL: https://arxiv.org/pdf/2406.10893

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2406.10893

Direct OA link when available
Concepts: Immunohistochemistry, Ductal carcinoma, Algorithm, Breast carcinoma, Computer science, Carcinoma, Artificial intelligence, Medicine, Pathology, Breast cancer, Internal medicine, Cancer

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2024: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4399794647
doi	https://doi.org/10.48550/arxiv.2406.10893
ids.doi	https://doi.org/10.48550/arxiv.2406.10893
ids.openalex	https://openalex.org/W4399794647
fwci
type	preprint
title	Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10862
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9944999814033508
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	AI in cancer detection
topics[1].id	https://openalex.org/T12422
topics[1].field.id	https://openalex.org/fields/27
topics[1].field.display_name	Medicine
topics[1].score	0.9609000086784363
topics[1].domain.id	https://openalex.org/domains/4
topics[1].domain.display_name	Health Sciences
topics[1].subfield.id	https://openalex.org/subfields/2741
topics[1].subfield.display_name	Radiology, Nuclear Medicine and Imaging
topics[1].display_name	Radiomics and Machine Learning in Medical Imaging
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C204232928
concepts[0].level	2
concepts[0].score	0.6326323747634888
concepts[0].wikidata	https://www.wikidata.org/wiki/Q899285
concepts[0].display_name	Immunohistochemistry
concepts[1].id	https://openalex.org/C2780862961
concepts[1].level	4
concepts[1].score	0.49214857816696167
concepts[1].wikidata	https://www.wikidata.org/wiki/Q5311598
concepts[1].display_name	Ductal carcinoma
concepts[2].id	https://openalex.org/C11413529
concepts[2].level	1
concepts[2].score	0.47455650568008423
concepts[2].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[2].display_name	Algorithm
concepts[3].id	https://openalex.org/C3018521938
concepts[3].level	4
concepts[3].score	0.4399912357330322
concepts[3].wikidata	https://www.wikidata.org/wiki/Q128581
concepts[3].display_name	Breast carcinoma
concepts[4].id	https://openalex.org/C41008148
concepts[4].level	0
concepts[4].score	0.4348428249359131
concepts[4].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[4].display_name	Computer science
concepts[5].id	https://openalex.org/C2777546739
concepts[5].level	2
concepts[5].score	0.4280340075492859
concepts[5].wikidata	https://www.wikidata.org/wiki/Q33525
concepts[5].display_name	Carcinoma
concepts[6].id	https://openalex.org/C154945302
concepts[6].level	1
concepts[6].score	0.4249691367149353
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[6].display_name	Artificial intelligence
concepts[7].id	https://openalex.org/C71924100
concepts[7].level	0
concepts[7].score	0.2940724194049835
concepts[7].wikidata	https://www.wikidata.org/wiki/Q11190
concepts[7].display_name	Medicine
concepts[8].id	https://openalex.org/C142724271
concepts[8].level	1
concepts[8].score	0.28249651193618774
concepts[8].wikidata	https://www.wikidata.org/wiki/Q7208
concepts[8].display_name	Pathology
concepts[9].id	https://openalex.org/C530470458
concepts[9].level	3
concepts[9].score	0.26505720615386963
concepts[9].wikidata	https://www.wikidata.org/wiki/Q128581
concepts[9].display_name	Breast cancer
concepts[10].id	https://openalex.org/C126322002
concepts[10].level	1
concepts[10].score	0.2025623917579651
concepts[10].wikidata	https://www.wikidata.org/wiki/Q11180
concepts[10].display_name	Internal medicine
concepts[11].id	https://openalex.org/C121608353
concepts[11].level	2
concepts[11].score	0.11402150988578796
concepts[11].wikidata	https://www.wikidata.org/wiki/Q12078
concepts[11].display_name	Cancer
keywords[0].id	https://openalex.org/keywords/immunohistochemistry
keywords[0].score	0.6326323747634888
keywords[0].display_name	Immunohistochemistry
keywords[1].id	https://openalex.org/keywords/ductal-carcinoma
keywords[1].score	0.49214857816696167
keywords[1].display_name	Ductal carcinoma
keywords[2].id	https://openalex.org/keywords/algorithm
keywords[2].score	0.47455650568008423
keywords[2].display_name	Algorithm
keywords[3].id	https://openalex.org/keywords/breast-carcinoma
keywords[3].score	0.4399912357330322
keywords[3].display_name	Breast carcinoma
keywords[4].id	https://openalex.org/keywords/computer-science
keywords[4].score	0.4348428249359131
keywords[4].display_name	Computer science
keywords[5].id	https://openalex.org/keywords/carcinoma
keywords[5].score	0.4280340075492859
keywords[5].display_name	Carcinoma
keywords[6].id	https://openalex.org/keywords/artificial-intelligence
keywords[6].score	0.4249691367149353
keywords[6].display_name	Artificial intelligence
keywords[7].id	https://openalex.org/keywords/medicine
keywords[7].score	0.2940724194049835
keywords[7].display_name	Medicine
keywords[8].id	https://openalex.org/keywords/pathology
keywords[8].score	0.28249651193618774
keywords[8].display_name	Pathology
keywords[9].id	https://openalex.org/keywords/breast-cancer
keywords[9].score	0.26505720615386963
keywords[9].display_name	Breast cancer
keywords[10].id	https://openalex.org/keywords/internal-medicine
keywords[10].score	0.2025623917579651
keywords[10].display_name	Internal medicine
keywords[11].id	https://openalex.org/keywords/cancer
keywords[11].score	0.11402150988578796
keywords[11].display_name	Cancer
language	en
locations[0].id	pmh:oai:arXiv.org:2406.10893
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	https://arxiv.org/pdf/2406.10893
locations[0].version	submittedVersion
locations[0].raw_type
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2406.10893
locations[1].id	doi:10.48550/arxiv.2406.10893
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2406.10893
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5075978538
authorships[0].author.orcid	https://orcid.org/0000-0003-0354-2940
authorships[0].author.display_name	Sumit Kumar Jha
authorships[0].author_position	first
authorships[0].raw_author_name	Jha, Sumit Kumar
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5032671035
authorships[1].author.orcid	https://orcid.org/0000-0003-2060-8972
authorships[1].author.display_name	Purnendu Mishra
authorships[1].author_position	middle
authorships[1].raw_author_name	Mishra, Purnendu
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5012464938
authorships[2].author.orcid	https://orcid.org/0000-0002-5616-0877
authorships[2].author.display_name	Shubham Mathur
authorships[2].author_position	middle
authorships[2].raw_author_name	Mathur, Shubham
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5102300081
authorships[3].author.orcid
authorships[3].author.display_name	Gursewak Singh
authorships[3].author_position	middle
authorships[3].raw_author_name	Singh, Gursewak
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5002969277
authorships[4].author.orcid	https://orcid.org/0000-0002-7774-2673
authorships[4].author.display_name	Rajiv Kumar
authorships[4].author_position	middle
authorships[4].raw_author_name	Kumar, Rajiv
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5073519483
authorships[5].author.orcid
authorships[5].author.display_name	Kiran Aatre
authorships[5].author_position	middle
authorships[5].raw_author_name	Aatre, Kiran
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5104330981
authorships[6].author.orcid
authorships[6].author.display_name	Suraj Rengarajan
authorships[6].author_position	last
authorships[6].raw_author_name	Rengarajan, Suraj
authorships[6].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2406.10893
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-06-19T00:00:00
display_name	Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10862
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9944999814033508
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	AI in cancer detection
related_works	https://openalex.org/W2051487156, https://openalex.org/W2999877485, https://openalex.org/W2073681303, https://openalex.org/W2355920994, https://openalex.org/W2399421402, https://openalex.org/W2373084812, https://openalex.org/W2464212128, https://openalex.org/W2113335236, https://openalex.org/W2328395017, https://openalex.org/W2410574247
cited_by_count	1
counts_by_year[0].year	2024
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2406.10893
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	https://arxiv.org/pdf/2406.10893
best_oa_location.version	submittedVersion
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
best_oa_location.landing_page_url	http://arxiv.org/abs/2406.10893
primary_location.id	pmh:oai:arXiv.org:2406.10893
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	https://arxiv.org/pdf/2406.10893
primary_location.version	submittedVersion
primary_location.raw_type
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2406.10893
publication_date	2024-06-16
publication_year	2024
referenced_works_count	0
abstract_inverted_index.2	51
abstract_inverted_index.3	140
abstract_inverted_index.5	212
abstract_inverted_index.a	4, 13, 102
abstract_inverted_index.82	191
abstract_inverted_index.88	189
abstract_inverted_index.In	97, 202
abstract_inverted_index.PR	198
abstract_inverted_index.We	161
abstract_inverted_index.as	63, 65
abstract_inverted_index.at	166
abstract_inverted_index.be	262
abstract_inverted_index.in	94, 176, 222
abstract_inverted_index.is	3, 55, 74, 137, 211, 250, 254
abstract_inverted_index.of	20, 27, 67, 80, 116, 158, 173, 178, 186, 214, 224, 239
abstract_inverted_index.on	76, 132
abstract_inverted_index.to	60, 69, 204, 264
abstract_inverted_index.we	100, 207
abstract_inverted_index.300	146
abstract_inverted_index.92,	188
abstract_inverted_index.95,	187
abstract_inverted_index.And	183
abstract_inverted_index.DSS	266
abstract_inverted_index.ER,	196
abstract_inverted_index.IHC	58, 72, 114, 240
abstract_inverted_index.Our	120, 233, 252
abstract_inverted_index.The	135, 257
abstract_inverted_index.and	6, 17, 45, 83, 90, 129, 153, 190, 197, 242
abstract_inverted_index.are	32
abstract_inverted_index.can	261
abstract_inverted_index.for	10, 15, 113, 193, 267
abstract_inverted_index.the	23, 124, 237
abstract_inverted_index.HER2	159
abstract_inverted_index.cell	151
abstract_inverted_index.deep	103
abstract_inverted_index.four	33, 167
abstract_inverted_index.from	85, 145
abstract_inverted_index.have	162, 218
abstract_inverted_index.high	88
abstract_inverted_index.most	24
abstract_inverted_index.poor	86
abstract_inverted_index.that	209
abstract_inverted_index.this	98
abstract_inverted_index.type	26
abstract_inverted_index.used	8, 263
abstract_inverted_index.well	64
abstract_inverted_index.with	169, 181, 229
abstract_inverted_index.(DSS)	112
abstract_inverted_index.(ER),	42
abstract_inverted_index.(IHC)	1
abstract_inverted_index.(PR),	39
abstract_inverted_index.HER2,	195
abstract_inverted_index.Ki67,	44, 194
abstract_inverted_index.There	31
abstract_inverted_index.based	75, 131
abstract_inverted_index.cases	215
abstract_inverted_index.could	235
abstract_inverted_index.favor	223
abstract_inverted_index.fifty	148
abstract_inverted_index.forty	154
abstract_inverted_index.found	208
abstract_inverted_index.fully	107
abstract_inverted_index.human	46
abstract_inverted_index.image	143
abstract_inverted_index.often	91
abstract_inverted_index.other	268
abstract_inverted_index.score	221, 226
abstract_inverted_index.stain	199
abstract_inverted_index.terms	177
abstract_inverted_index.their	220
abstract_inverted_index.there	210
abstract_inverted_index.three	170
abstract_inverted_index.tumor	28, 81, 125
abstract_inverted_index.types	172
abstract_inverted_index.under	57
abstract_inverted_index.using	139
abstract_inverted_index.where	216, 247
abstract_inverted_index.while	227
abstract_inverted_index.whose	53
abstract_inverted_index.(HER2)	52
abstract_inverted_index.Allred	133
abstract_inverted_index.breast	21
abstract_inverted_index.cancer	269
abstract_inverted_index.cases.	96
abstract_inverted_index.common	25
abstract_inverted_index.decide	61
abstract_inverted_index.ductal	118
abstract_inverted_index.factor	49
abstract_inverted_index.growth	48
abstract_inverted_index.highly	255
abstract_inverted_index.method	9
abstract_inverted_index.namely	36
abstract_inverted_index.needed	56
abstract_inverted_index.paper,	99
abstract_inverted_index.pixels	156
abstract_inverted_index.region	126
abstract_inverted_index.scores	130
abstract_inverted_index.system	111, 121, 136, 253
abstract_inverted_index.trials	165
abstract_inverted_index.types.	270
abstract_inverted_index.widely	7
abstract_inverted_index.women.	30
abstract_inverted_index.antigen	43
abstract_inverted_index.centers	168
abstract_inverted_index.changed	219
abstract_inverted_index.detects	123
abstract_inverted_index.develop	265
abstract_inverted_index.digital	174
abstract_inverted_index.improve	236
abstract_inverted_index.marking	157
abstract_inverted_index.million	141
abstract_inverted_index.modules	260
abstract_inverted_index.overall	205
abstract_inverted_index.patches	144
abstract_inverted_index.percent	192, 213
abstract_inverted_index.scoring	73, 93, 115, 241
abstract_inverted_index.slides,	147
abstract_inverted_index.suffers	84
abstract_inverted_index.support	110
abstract_inverted_index.therapy	19, 244
abstract_inverted_index.However,	71
abstract_inverted_index.accuracy	238
abstract_inverted_index.achieved	184
abstract_inverted_index.addition	203
abstract_inverted_index.analysis	2
abstract_inverted_index.approach	234
abstract_inverted_index.decision	109
abstract_inverted_index.detailed	230
abstract_inverted_index.doctors.	182
abstract_inverted_index.estrogen	40
abstract_inverted_index.in-house	150
abstract_inverted_index.invasive	117
abstract_inverted_index.modular.	256
abstract_inverted_index.present,	101
abstract_inverted_index.proposed	258
abstract_inverted_index.receptor	38, 41, 50
abstract_inverted_index.removing	127
abstract_inverted_index.response	68
abstract_inverted_index.scanners	175
abstract_inverted_index.targeted	18
abstract_inverted_index.therapy.	70
abstract_inverted_index.thousand	149, 155
abstract_inverted_index.trained,	106
abstract_inverted_index.accuracy,	206
abstract_inverted_index.affecting	29
abstract_inverted_index.agreement	180
abstract_inverted_index.algorithm	225, 259
abstract_inverted_index.analysis.	232
abstract_inverted_index.artifacts	128
abstract_inverted_index.conducted	163
abstract_inverted_index.developed	138
abstract_inverted_index.different	171
abstract_inverted_index.epidermal	47
abstract_inverted_index.expertise	249
abstract_inverted_index.incorrect	92
abstract_inverted_index.low-score	95
abstract_inverted_index.membrane.	160
abstract_inverted_index.molecular	11, 34
abstract_inverted_index.procedure	14, 59
abstract_inverted_index.prognosis	16, 62
abstract_inverted_index.reviewing	228
abstract_inverted_index.standard.	134
abstract_inverted_index.agreements	185
abstract_inverted_index.assessment	54
abstract_inverted_index.automatic,	108
abstract_inverted_index.biomarkers	35
abstract_inverted_index.carcinoma,	22
abstract_inverted_index.carcinoma.	119
abstract_inverted_index.decisions,	245
abstract_inverted_index.morphology	82
abstract_inverted_index.percentage	179
abstract_inverted_index.predictors	66
abstract_inverted_index.specialist	248
abstract_inverted_index.subjective	77
abstract_inverted_index.subsequent	243
abstract_inverted_index.subtyping,	12
abstract_inverted_index.algorithmic	231
abstract_inverted_index.categories,	200
abstract_inverted_index.examination	79
abstract_inverted_index.microscopic	78
abstract_inverted_index.pathologist	217
abstract_inverted_index.annotations,	152
abstract_inverted_index.multicentric	164
abstract_inverted_index.particularly	246
abstract_inverted_index.progesterone	37
abstract_inverted_index.unavailable.	251
abstract_inverted_index.automatically	122
abstract_inverted_index.respectively.	201
abstract_inverted_index.subjectivity,	89
abstract_inverted_index.well-accepted	5
abstract_inverted_index.learning-based	104
abstract_inverted_index.semi-supervised	105
abstract_inverted_index.reproducibility,	87
abstract_inverted_index.Immunohistochemistry	0
abstract_inverted_index.pathologist-annotated	142
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	7
citation_normalized_percentile