Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration
<b>Background/Objectives:</b> An accurate assessment of mitotic activity is crucial in the histopathological diagnosis of invasive breast carcinoma. However, this task is time-consuming and labor-intensive, and suffers from high variability between pathologists. <b>Methods</b>...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/9/1127 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030425675661312 |
|---|---|
| author | Clara Simmat Loris Guichard Stéphane Sockeel Nicolas Pozin Rémy Peyret Magali Lacroix-Triki Catherine Miquel Arnaud Gauthier Marie Sockeel Sophie Prévot |
| author_facet | Clara Simmat Loris Guichard Stéphane Sockeel Nicolas Pozin Rémy Peyret Magali Lacroix-Triki Catherine Miquel Arnaud Gauthier Marie Sockeel Sophie Prévot |
| author_sort | Clara Simmat |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> An accurate assessment of mitotic activity is crucial in the histopathological diagnosis of invasive breast carcinoma. However, this task is time-consuming and labor-intensive, and suffers from high variability between pathologists. <b>Methods</b>: To assist pathologists in routine diagnostics, we developed an artificial intelligence (AI)-based tool that uses whole slide images (WSIs) to detect mitoses, identify mitotic hotspots, and assign mitotic scores according to the Elston and Ellis grading system. To our knowledge, this study is the first to evaluate such a tool fully integrated into the pathologist’s routine workflow. <b>Results:</b> A clinical study evaluating the tool’s performance on routine data clearly demonstrated the value of this approach. With AI assistance, pathologists achieved a greater accuracy and reproducibility in mitotic scoring, mainly because the tool automatically and consistently identified hotspots. Inter-observer reproducibility improved significantly: Cohen’s kappa coefficients increased from 0.378 and 0.457 (low agreement) without AI to 0.629 and 0.726 (moderate agreement) with AI. <b>Conclusions:</b> This preliminary clinical study demonstrates, for the first time in a routine diagnostic setting, that AI can reliably identify mitotic hotspots and enhance pathologists’ performance in scoring mitotic activity on breast cancer WSIs. |
| format | Article |
| id | doaj-art-3ddc6363d8a64bfcbf21e4f2cd85d477 |
| institution | DOAJ |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-3ddc6363d8a64bfcbf21e4f2cd85d4772025-08-20T02:59:14ZengMDPI AGDiagnostics2075-44182025-04-01159112710.3390/diagnostics15091127Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice IntegrationClara Simmat0Loris Guichard1Stéphane Sockeel2Nicolas Pozin3Rémy Peyret4Magali Lacroix-Triki5Catherine Miquel6Arnaud Gauthier7Marie Sockeel8Sophie Prévot9Primaa, 75002 Paris, FranceHôpital Bicêtre (AP-HP), Paris-Saclay University, 94270 Kremin-Bicêtre, FrancePrimaa, 75002 Paris, FrancePrimaa, 75002 Paris, FrancePrimaa, 75002 Paris, FranceGustave-Roussy Cancer Campus—Grand Paris, 94800 Villejuif, FranceHôpital Saint-Louis (AP-HP), Paris Cité University, 75010 Paris, FranceInstitut Curie, PSL University, 75005 Paris, FrancePrimaa, 75002 Paris, FranceHôpital Bicêtre (AP-HP), Paris-Saclay University, 94270 Kremin-Bicêtre, France<b>Background/Objectives:</b> An accurate assessment of mitotic activity is crucial in the histopathological diagnosis of invasive breast carcinoma. However, this task is time-consuming and labor-intensive, and suffers from high variability between pathologists. <b>Methods</b>: To assist pathologists in routine diagnostics, we developed an artificial intelligence (AI)-based tool that uses whole slide images (WSIs) to detect mitoses, identify mitotic hotspots, and assign mitotic scores according to the Elston and Ellis grading system. To our knowledge, this study is the first to evaluate such a tool fully integrated into the pathologist’s routine workflow. <b>Results:</b> A clinical study evaluating the tool’s performance on routine data clearly demonstrated the value of this approach. With AI assistance, pathologists achieved a greater accuracy and reproducibility in mitotic scoring, mainly because the tool automatically and consistently identified hotspots. Inter-observer reproducibility improved significantly: Cohen’s kappa coefficients increased from 0.378 and 0.457 (low agreement) without AI to 0.629 and 0.726 (moderate agreement) with AI. <b>Conclusions:</b> This preliminary clinical study demonstrates, for the first time in a routine diagnostic setting, that AI can reliably identify mitotic hotspots and enhance pathologists’ performance in scoring mitotic activity on breast cancer WSIs.https://www.mdpi.com/2075-4418/15/9/1127invasive breast carcinomamitoseshotspotsdigital pathologyWSIartificial intelligence |
| spellingShingle | Clara Simmat Loris Guichard Stéphane Sockeel Nicolas Pozin Rémy Peyret Magali Lacroix-Triki Catherine Miquel Arnaud Gauthier Marie Sockeel Sophie Prévot Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration Diagnostics invasive breast carcinoma mitoses hotspots digital pathology WSI artificial intelligence |
| title | Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration |
| title_full | Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration |
| title_fullStr | Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration |
| title_full_unstemmed | Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration |
| title_short | Evaluating AI-Based Mitosis Detection for Breast Carcinoma in Digital Pathology: A Clinical Study on Routine Practice Integration |
| title_sort | evaluating ai based mitosis detection for breast carcinoma in digital pathology a clinical study on routine practice integration |
| topic | invasive breast carcinoma mitoses hotspots digital pathology WSI artificial intelligence |
| url | https://www.mdpi.com/2075-4418/15/9/1127 |
| work_keys_str_mv | AT clarasimmat evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT lorisguichard evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT stephanesockeel evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT nicolaspozin evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT remypeyret evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT magalilacroixtriki evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT catherinemiquel evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT arnaudgauthier evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT mariesockeel evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration AT sophieprevot evaluatingaibasedmitosisdetectionforbreastcarcinomaindigitalpathologyaclinicalstudyonroutinepracticeintegration |