The abstract is read at the publisher; the summary is JClub's.
SEE-TC, a deep learning system for circulating tumor cell imaging, segments and phenotypes cells at human-level accuracy across 8.5 million cells from 3,386 blood samples.
- Why it matters: Manual, subjective, low-throughput CTC identification limits clinical utility in multichannel fluorescence microscopy, especially for consistent analysis across changing imaging and staining conditions.
- What they did: SEE-TC was trained and clinically validated on more than 8.5 million cells from 3,386 blood samples spanning six cancer types, using automated single-cell segmentation and threshold-free CTC/background discrimination.
- The result: Longitudinal patient-level CTC burden quantified by SEE-TC is significantly associated with worse overall survival across multiple cancer types, enabling scalable digital liquid-biopsy monitoring.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.