Lessons learned from the validation of a machine learning-based colorectal carcinoma screening pipeline in sub-Saharan Africa

Authors

• Alfred Githuka, Aga Khan UniversityFollow
• Ulysses Balis, University of Michigan Health System, USA
• Ye Chan Kim, University of Michigan Medical School, USA
• Eileen Weinheimer-Haus, University of Michigan Medical School, USA
• Christopher Williams, University of Oklahoma Health Sciences Center, USA
• Jerome Cheng, University of Michigan Health System, USA
• Kelou Yao, Cedars-Sinai Medical Center, USA
• John Blau, University of Iowa, USA
• Shahin Sayed, Aga Khan UniversityFollow
• Mansoor SalehFollow

Document Type

Article

Department

Haematology and Oncology, East Africa; Pathology (East Africa)

Abstract

Background Artificial intelligence for digital pathology may improve cancer detection and workflow efficiency in low- and middle-income countries, but most models are trained and validated in high-income settings, creating uncertainty about generalizability and real-world deployability under differing pre-analytic and infrastructure conditions.

Objective To validate a locally optimized colorectal carcinoma screening pipeline, retrained on data from a local Kenyan cohort, and to assess its feasibility as a sensitivity-forward assistive pre-screening workflow.

Methods Formalin-fixed, paraffin-embedded hematoxylin and eosin-stained slides from 136 biopsy-proven colonic adenocarcinoma cases and 20 normal controls from 2 Kenyan institutions were digitized at 40× using a Grundium Ocus scanner. Whole-slide images were partitioned at the case level. A feature-enrichment and candidate tile-selection step identified adenocarcinoma-rich regions. Candidate 512 × 512 RGB tiles were then adjudicated by a gastrointestinal pathologist into adenocarcinoma-containing and benign/non-neoplastic tile libraries. These expert-curated tiles were used to train and validate a supervised convolutional neural network classifier, which generated tile-level malignancy probabilities. Tile scores were aggregated into case-level predictions using Top-K pooling and positive-tile burden rules to support sensitivity-forward screening.

Results Among 14,452 tiles from 70 quality-controlled cases and 19 controls, the model achieved strong tile-level discrimination (sensitivity 0.9548, specificity 0.9926, F1 score 0.9686, and AUROC curve 0.966); case-level Top-K aggregation achieved an AUROC of 1.0.

Conclusion A locally optimized computational pathology screening pipeline, based on data from a local population, demonstrated robust colorectal adenocarcinoma detection in a Kenyan cohort. These findings suggest that existing machine-learning models can be adapted to local populations through retraining with locally derived data.

Publication (Name of Journal)

Journal of Pathology Informatics

DOI

https://doi.org/10.1016/j.jpi.2026.100691

Recommended Citation

Githuka, A., Balis, U., Kim, Y., Weinheimer-Haus, E., Williams, C., Cheng, J., Yao, K., Blau, J., Sayed, S., Saleh, M. (2026). Lessons learned from the validation of a machine learning-based colorectal carcinoma screening pipeline in sub-Saharan Africa. Journal of Pathology Informatics, 22, 1-10.
Available at: https://ecommons.aku.edu/eastafrica_fhs_mc_haematol_oncol/168

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.