Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Endometrial Pipelle Biopsy Computer-Aided Diagnosis: A Feasibility Study

S. Vermorgen, T. Gelton, P. Bult, HVN. Kusters-Vandevelde, J. Hausnerová, K. Van de Vijver, B. Davidson, IM. Stefansson, LFS. Kooreman, A. Qerimi, J. Huvila, B. Gilks, M. Shahi, S. Zomer, C. Bartosch, JMA. Pijnenborg, J. Bulten, F. Ciompi, M. Simons

. 2024 ; 37 (2) : 100417. [pub] 20231227

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc24007321

Endometrial biopsies are important in the diagnostic workup of women who present with abnormal uterine bleeding or hereditary risk of endometrial cancer. In general, approximately 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI)-assisted preselection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (endometrial Pipelle biopsy computer-aided diagnosis), trained on daily-practice whole-slide images instead of highly selected images. Endometrial biopsies were classified into 6 clinically relevant categories defined as follows: nonrepresentative, normal, nonneoplastic, hyperplasia without atypia, hyperplasia with atypia, and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2819 endometrial biopsies) rated the same 91 cases, and we compared its performance using the pathologist's classification as the reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign vs (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the 6 categories with a moderate Cohen's kappa of 0.43 but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissues, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc24007321
003      
CZ-PrNML
005      
20240423155857.0
007      
ta
008      
240412s2024 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.modpat.2023.100417 $2 doi
035    __
$a (PubMed)38154654
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Vermorgen, Sanne $u Department of Pathology, Radboudumc, Nijmegen, the Netherlands
245    10
$a Endometrial Pipelle Biopsy Computer-Aided Diagnosis: A Feasibility Study / $c S. Vermorgen, T. Gelton, P. Bult, HVN. Kusters-Vandevelde, J. Hausnerová, K. Van de Vijver, B. Davidson, IM. Stefansson, LFS. Kooreman, A. Qerimi, J. Huvila, B. Gilks, M. Shahi, S. Zomer, C. Bartosch, JMA. Pijnenborg, J. Bulten, F. Ciompi, M. Simons
520    9_
$a Endometrial biopsies are important in the diagnostic workup of women who present with abnormal uterine bleeding or hereditary risk of endometrial cancer. In general, approximately 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI)-assisted preselection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (endometrial Pipelle biopsy computer-aided diagnosis), trained on daily-practice whole-slide images instead of highly selected images. Endometrial biopsies were classified into 6 clinically relevant categories defined as follows: nonrepresentative, normal, nonneoplastic, hyperplasia without atypia, hyperplasia with atypia, and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2819 endometrial biopsies) rated the same 91 cases, and we compared its performance using the pathologist's classification as the reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign vs (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the 6 categories with a moderate Cohen's kappa of 0.43 but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissues, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.
650    _2
$a lidé $7 D006801
650    _2
$a ženské pohlaví $7 D005260
650    _2
$a studie proveditelnosti $7 D005240
650    _2
$a hyperplazie $7 D006965
650    12
$a umělá inteligence $7 D001185
650    _2
$a reprodukovatelnost výsledků $7 D015203
650    _2
$a biopsie $7 D001706
650    12
$a počítače $7 D003201
655    _2
$a časopisecké články $7 D016428
700    1_
$a Gelton, Thijs $u Department of Pathology, Radboudumc, Nijmegen, the Netherlands
700    1_
$a Bult, Peter $u Department of Pathology, Radboudumc, Nijmegen, the Netherlands
700    1_
$a Kusters-Vandevelde, Heidi V N $u Department of Pathology, Canisius-Wilhelmina Hospital, Nijmegen, the Netherlands
700    1_
$a Hausnerová, Jitka $u Department of Pathology, University Hospital Brno, Brno, Czech Republic
700    1_
$a Van de Vijver, Koen $u Department of Pathology, UZ Gent, Gent, Belgium
700    1_
$a Davidson, Ben $u Department of Pathology, Oslo University Hospital, Norwegian Radium Hospital, Oslo, Norway; University of Oslo, Faculty of Medicine, Institute of Clinical Medicine, Oslo, Norway
700    1_
$a Stefansson, Ingunn Marie $u Centre for Cancer Biomarkers CCBIO, Department of Clinical Medicine, Section for Pathology, University of Bergen, Bergen, Norway; Department of Pathology, Haukeland University Hospital Bergen, Bergen, Norway
700    1_
$a Kooreman, Loes F S $u Department of Pathology, GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands
700    1_
$a Qerimi, Adelina $u Department of Pathology, ViraTherapeutics GmbH, Innsbruck, Austria
700    1_
$a Huvila, Jutta $u Department of Pathology, University of Turku, Turku University Hospital, Turku, Finland
700    1_
$a Gilks, Blake $u Department of Pathology, University of British Columbia, Vancouver, Canada
700    1_
$a Shahi, Maryam $u Department of Pathology, Mayo Clinic, Rochester, Minnesota
700    1_
$a Zomer, Saskia $u Department of Pathology, Canisius-Wilhelmina Hospital, Nijmegen, the Netherlands
700    1_
$a Bartosch, Carla $u Department of Pathology, Portuguese Oncology Institute Lisbon, Lisbon, Portugal
700    1_
$a Pijnenborg, Johanna M A $u Department of Gynecology, Radboudumc, Nijmegen, the Netherlands
700    1_
$a Bulten, Johan $u Department of Pathology, Radboudumc, Nijmegen, the Netherlands
700    1_
$a Ciompi, Francesco $u Department of Pathology, Radboudumc, Nijmegen, the Netherlands
700    1_
$a Simons, Michiel $u Department of Pathology, Radboudumc, Nijmegen, the Netherlands. Electronic address: Michiel.Simons@radboudumc.nl
773    0_
$w MED00003380 $t Modern pathology $x 1530-0285 $g Roč. 37, č. 2 (2024), s. 100417
856    41
$u https://pubmed.ncbi.nlm.nih.gov/38154654 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20240412 $b ABA008
991    __
$a 20240423155853 $b ABA008
999    __
$a ok $b bmc $g 2081355 $s 1217088
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2024 $b 37 $c 2 $d 100417 $e 20231227 $i 1530-0285 $m Modern pathology $n Mod Pathol $x MED00003380
LZP    __
$a Pubmed-20240412

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace