The following abstract is drawn from a recently published paper in Journal of Pathology Informatics | ScienceDirect.com by Elsevier. We invite you to read the full paper and join the conversation, become a member of the Pathology News community to share your thoughts, ask questions, and engage with others around this work.

Authors: Alfred Githuka^a,l, Ulysses G.J. Balis^b,l, Ye Chan Kim^c,d, Eileen M. Weinheimer-Haus^c,d, Christopher L. Williams^e, Jerome I. Cheng^b, Kelou Yao^f, John Blau^g, Jessica A. Baker^d, Priscilla Njenga^h, Winny Chepkemoiⁱ, Robert K. Parker^i,j, Akbar K. Waljee^c,d,m, Shahin Sayed^h,m, Mansoor N. Saleh^a,k,m

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.

Read the full article: Lessons learned from the validation of a machine learning-based colorectal carcinoma screening pipeline in sub-Saharan Africa – ScienceDirect

^aDepartment of Hematology-Oncology, Aga Khan University Hospital Nairobi, Nairobi, Kenya

^bDepartment of Pathology, University of Michigan Health System, Ann Arbor, MI, USA

^cDepartment of Learning Health Sciences, University of Michigan Medical School, Ann Arbor, MI, USA

^dCenter for Global Health and Equity, University of Michigan, Ann Arbor, MI, USA

^eDepartment of Pathology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA

^fDepartment of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA

^gDepartment of Pathology, University of Iowa, Iowa, IA, USA

^hDepartment of Pathology, Aga Khan University, Nairobi, Kenya

ⁱDepartment of Surgery, AGC Tenwek Hospital, Bomet, Kenya

^jDepartment of Surgery, Brown University, Providence, RI, USA

^kO’Neal Comprehensive Cancer Center, The University of Alabama at Birmingham, Birmingham, AL, USA