Abstract B049: Deep Learning Enables Identification of Cell Types and Clusters (iCTC) in Immune Tumor Ecosystems for Prognostic Assessment in Cancer
Bibliographic record
Abstract
Abstract Background: Spatial multiomic profiling has been transforming the understanding of local tumor ecosystems. Yet, the spatial analyses of tumor-immune interactions at systemic levels, such as in liquid biopsies, are challenging. Within the last 10 years, we have longitudinally collected nearly 3,000 patient blood samples for multiplexing imaging of circulating tumor cells (CTCs) and their interactions with white blood cells (WBCs). Multicellular CTC clusters exhibit enhanced metastatic potential. The detection of CTCs and characterization of tumor immune ecosystems are constrained by (1) low frequency of CTCs in blood samples; (2) specific lineages of immune cells are not recognized by limited channels of current imaging methods, (3) reliance on labor-intensive manual analysis slows down the discovery of biomarkers for predicting therapy response and survival in cancer patients. We hypothesize that an AI-powered platform will accelerate the lineage and spatial characterization of tumor immune ecosystems for prognostic evaluations. Methods: Leveraging FDA-approved CellSearch technology, we collected 2,853 blood specimens longitudinally from 1358 patients with advanced cancer (breast, prostate, etc. Integrating machine learning and deep learning tools, we developed a novel platform -identification of Cell Types and Clusters (iCTC) - to automate the detection and identification of CTCs, immune cell types , and their interactions. Using machine-learning image analysis, we extracted over 270 cellular and nuclear features of cytokeratin, CD45, and DAPI expression patterns, enabling precise characterization of CTCs and WBCs including differentiation of sub-types of WBCs, CTC clusters, and their intercellular interactions with one another. Results: The iCTC platform enabled automated identification of CTCs and WBCs (granulocytes, T cells, monocytes, B cells, NK) at specificity and sensitivity >0.97-1.0. It also recognized homotypic CTC clusters, heterogenous CTC-WBC clusters, and immune cell clusters, providing insights into cell morphology and spatial organization within hours for 50+ millions cells from nearly 3,000 blood tests. These features correlated with patient survival, disease progression, and treatment response. Our findings highlight the clinical significance of CTC–immune cell interactions and dynamic alterations of CTCs (singles and clusters) and underscore their potential in stratifying patients into distinct risk categories. Conclusions: This study demonstrates the transformative potential of machine learning in accelerating and enabling large-scale spatial data analyses of tumor immune ecosystem in blood biopsies and can readily extend the method to other imaging data analyses, integrating imaging data with large cohorts of patient data. By automating and enhancing the analysis of CTC-immune cell interactions, we present a robust framework for developing predictive models with direct clinical relevance. This work opens avenues for personalized treatment strategies, underscoring the impact of AI in advancing precision oncology. Citation Format: Joshua R. Squires, Yuanfei Sun, Andrew D. Hoffmann, Youbin Zhang, Allegra C. Minor, Anmol Singh, David Scholten, Hannah Ding, Chengsheng Mao, Leonidas C. Platanias, Yuan Luo, Deyu Fang, William J. Gradishar, Massimo Cristofanilli, Carsen Stringer, Huiping Liu. Deep Learning Enables Identification of Cell Types and Clusters (iCTC) in Immune Tumor Ecosystems for Prognostic Assessment in Cancer [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr B049.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".