EUVIMEDEUVIMED entdecken
Crossref

Artificial Intelligence for histopathological diagnosis and grading of breast cancer in Ethiopia

Tewodros Yalew Gebremariam, Constance Boissin, Amanuel Demie Jiffar, Wenwen Sun, Moti Sori, Tove Ekdahl Hjelm, Mathewos Assefa, Endale Anberber, Marcus Bauer, Bethlehem Getachew Ayele, Johan Hartman, Jenny Löfgren und 2 weitere

Pathology - Research and Practice · 2026-07 · 283 · 156493

DOI: 10.1016/j.prp.2026.156493 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pathology - Research and Practice, 2026-07. Verfasst von Tewodros Yalew Gebremariam und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, School of Medicine, College of Health Sciences,Tikur Anbessa Specialized Hospital, Addis Ababa University, Addis Ababa, Ethi…. Hauptthemen laut MEDLINE: Breast Neoplasms, Neoplasm Grading, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Addis Ababa University, Vetenskapsrådet, Cancerfonden.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND Recent advances in computational pathology enables AI-assisted diagnosis and risk stratification of breast cancer. This advance in technology will reduce the inconsistent reporting of breast cancer grading using Nottingham Histologic grading system. This study evaluated the implementation of the DeepGrade model for breast cancer grading using H&E-stained slides from breast cancer patients in Ethiopia. OBJECTIVE To assess the accuracy, specificity, and sensitivity of the DeepGrade model in distinguishing between grade 1 and grade 3 tumours. Additionally, the study aimed to explore the model's ability to further classify Nottingham Histologic Grade 2 tumours into two distinct risk categories. METHODS A retrospective analysis was conducted using data from 200 tumour samples from the Department of Pathology, Tikur Anbessa Specialized Hospital, Addis Ababa, Ethiopia. The performance of the DeepGrade model was compared with three pathologists' diagnosis using metrics such as specificity, sensitivity, area under the curve and agreement level. RESULTS The DeepGrade model reached a 100% specificity for low-grade tumours and an 82.05% sensitivity for high-grade tumours, with an AUC of 0.914 and an agreement level of 86.79%. Our findings illustrated the model's strong agreement with the pathologist, and a Kappa coefficient of 0.71 (95% CI: 0.51-0.90). CONCLUSION The study showed the potential significance of DeepGrade model utilization in enhancing breast cancer grading practices in resource-limited settings. By adopting this model, a consistent and standardized grading system for breast cancer can be established, significantly enhancing the effectiveness of breast cancer management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsNeoplasm GradingArtificial IntelligenceHumansFemaleEthiopiaRetrospective StudiesMiddle AgedAdultAged

Stichwörter der Autor:innen

Artificial intelligence (AI)Breast neoplasmDiagnostic accuracyTumour grading

Autor:innen und Institutionen

  • Department of Pathology, School of Medicine, College of Health Sciences,Tikur Anbessa Specialized Hospital, Addis Ababa University, Addis Ababa, Ethiopia; Department of Medical Epidemiology and Biostatistics, Karolinska…
  • Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm 171 77, Sweden. Electronic address: constance.boissin@ki.se.
  • Department of Pathology, School of Medicine, College of Health Sciences,Tikur Anbessa Specialized Hospital, Addis Ababa University, Addis Ababa, Ethiopia. Electronic address: amanuel.demie@aau.edu.et.
  • Department of Oncology-Pathology, Karolinska Institutet, Stockholm 171 77, Sweden. Electronic address: wenwen.sun@ki.se.
  • Department of Pathology, School of Medicine, College of Health Sciences,Tikur Anbessa Specialized Hospital, Addis Ababa University, Addis Ababa, Ethiopia. Electronic address: moti.sori@aaa.edu.et.
  • Department of Molecular Medicine and Surgery, Karolinska Institutet, K1 Molekylär medicin och kirurgi, K1 MMK Kärlkirurgi, Stockholm 171 76, Sweden; Department of Oncology, Södersjukhuset, Stockholm, Sweden. Electronic…

Förderung

  • Addis Ababa University
  • Vetenskapsrådet
  • Cancerfonden

Zitieren

APA

Gebremariam, T. Y., Boissin, C., Jiffar, A. D., Sun, W., Sori, M., Ekdahl Hjelm, T., Assefa, M., Anberber, E., Bauer, M., Ayele, B. G., Hartman, J., Löfgren, J., Rantalainen, M., & Ashenafi, S. (2026). Artificial Intelligence for histopathological diagnosis and grading of breast cancer in Ethiopia. Pathology - Research and Practice, 283, 156493. https://doi.org/10.1016/j.prp.2026.156493

Vancouver

Gebremariam TY, Boissin C, Jiffar AD, Sun W, Sori M, Ekdahl Hjelm T, et al. Artificial Intelligence for histopathological diagnosis and grading of breast cancer in Ethiopia. Pathology - Research and Practice. 2026;283:156493. doi:10.1016/j.prp.2026.156493

BibTeX
@article{Gebremariam2026,
  author = {Gebremariam, Tewodros Yalew and Boissin, Constance and Jiffar, Amanuel Demie and Sun, Wenwen and Sori, Moti and Ekdahl Hjelm, Tove and Assefa, Mathewos and Anberber, Endale and Bauer, Marcus and Ayele, Bethlehem Getachew and Hartman, Johan and Löfgren, Jenny and Rantalainen, Mattias and Ashenafi, Senait},
  title = {Artificial Intelligence for histopathological diagnosis and grading of breast cancer in Ethiopia},
  journal = {Pathology - Research and Practice},
  year = {2026},
  volume = {283},
  pages = {156493},
  doi = {10.1016/j.prp.2026.156493}
}
Kostenlos starten →