Table 2_AI-driven spatial analysis of tumor-infiltrating lymphocytes predicts chemo-immuno

32 hematoxylin-eosin-stained breast cancer images were analyzed using an AI pipeline to quantify spatial tumor-immune interactions. Hai Liang authored this dataset, which was last updated on April 16, 2026. The analysis framework achieved a TIL classifier accuracy of 0.92 and a predictive model AUC of 0.81 for chemo-immunotherapy response.

Use Cases

• Training predictive models for chemo-immunotherapy response based on spatial lymphocyte features.
• Analyzing correlations between stromal lymphocyte density and Miller-Payne response grades.
• Studying the relationship between lymphocyte proximity to tumor cells and treatment outcomes.
• Validating AI-based frameworks for automated analysis of HE-stained pathology samples.

Strengths

• The AI pipeline demonstrated substantial agreement with pathologists (κ=0.73) for TLS recognition.
• The TIL classifier achieved a reported accuracy of 0.92.
• The spatial-feature-based prediction model achieved an AUC of 0.81 (95% CI: 0.76–0.86).

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is small in scale at 10.1 KB, indicating limited scope.

Provenance

Source

Hai Liang via figshare.

Collection Method

AI-based quantitative analysis of 32 HE-stained breast cancer samples from TNBC cases treated with neoadjuvant chemo-immunotherapy.

Time Range

null

Freshness

Last updated 2026-04-16 05:26:03; freshness should be verified.

Geography

null