Attention U-Net-Based Segmentation and Hybrid Classification for Detection of Circulating Tumor-Associated Cells.
Simple Summary: Blood-based cancer detection is challenged by the rarity of tumor-associated cells among abundant peripheral blood nucleated cells. This study evaluates a predefined image-analysis pipeline that combines dual-channel fluorescence microscopy, an Attention U-Net segmentation stage, CTA...
| Publicado en: | Cancers Vol. 18; no. 16; pp. 2691 - 2711 |
|---|---|
| Autores principales: | , , , , , , , , , , , , , , , , , |
| Formato: | pictorial research tables/charts Journal Article |
| Publicado: |
MDPI
Aug2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=196664981&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 196664981 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Aug2026 vid: 18 iid: 16 pid: 97109 pub: MDPI artinfo: ui: 196664981 196664981 196664981 10.3390/cancers18162691 196664981 ppf: 2691 ppct: 20 formats: tig: atl: Attention U-Net-Based Segmentation and Hybrid Classification for Detection of Circulating Tumor-Associated Cells. aug: au: Cristofanilli, Massimo Limaye, Sewanti Rohatgi, Nitesh Crook, Timothy Al-Shamsi, Humaid O. Gaya, Andrew Page, Raymond Shreenivas, Aditya Patil, Darshana Datta, Vineet Akolkar, Dadasaheb Schuster, Stefan Kumar, Prashant Patel, Shoeb Shejwalkar, Pradyumna Golar, Snehal Srinivasan, Ajay Datar, Rajan affil: Department of Medical Oncology, Weill Cornell Medicine and New York Presbyterian Hospital, New York, NY 10065, USA sug: subj: Neoplasms Diagnosis Neoplasms Classification Tumor Markers, Biological Blood Convolutional Neural Networks Artificial Intelligence Image Processing, Computer Assisted Detection Algorithms Human Validation Studies Multicenter Studies Prospective Studies Retrospective Design Record Review Medical Records Case Control Studies Descriptive Statistics Data Analysis Software Microscopy Random Forest Erythrocytes Analysis Staining and Labeling Cell Line, Tumor Analysis Machine Learning Deep Learning Sensitivity and Specificity Predictive Value of Tests ab: Simple Summary: Blood-based cancer detection is challenged by the rarity of tumor-associated cells among abundant peripheral blood nucleated cells. This study evaluates a predefined image-analysis pipeline that combines dual-channel fluorescence microscopy, an Attention U-Net segmentation stage, CTAC-specific post-processing, extraction of 64 predefined cytological features, and a Random Forest classifier. The attention gates follow established Attention U-Net principles; the study-specific contribution is the integration of these components for CTAC detection and their evaluation across case–control and prospective cohorts. The results support the potential clinical utility of the integrated framework for CTAC detection. Background/Objectives: Circulating tumor-associated cells (CTACs) are rare among peripheral blood nucleated cells (PBNCs), creating a challenge for image-based multi-cancer detection. We evaluated a predefined CTAC-detection pipeline incorporating Attention U-Net segmentation, post-processing, cytological feature extraction, and Random Forest classification. Methods: Model suitability was explored in asymptomatic individuals and patients with advanced solid tumors. Clinical performance was assessed in a case–control cohort of therapy-naive stage I/II cancers, benign conditions, and asymptomatic individuals, followed by four prospective cohort evaluations performed within the same laboratory and imaging workflow: recurrent cancer with low radiological tumor burden, peri-operative solid tumors, suspected cancer, and asymptomatic screening. PBNCs were stained with EpCAM/Hoechst 33342 and imaged. Pathologists' review established ground truth annotations. Results: The model had 90.68% sensitivity and 99.53% specificity in the exploratory study. In the case–control cohort, sensitivity was 88.65% in therapy-naive stage I/II cancers, while specificity was 78.95% in benign conditions and >99.9% in asymptomatic individuals. In the prospective cohorts, CTAC detection sensitivity was 91.96% in pretreated low tumor burden cases; CTACs were detected in 100% of pre-surgery specimens and 29.41% of post-surgery specimens; and in suspected cancer cases, the Positive Predictive Value (PPV) and Negative Predictive Value (NPV) were 96.34% and 32.35%, respectively. In the asymptomatic screening cohort, 44/7183 participants were CTAC-positive; 16 had confirmed Stage I/II cancer, 10 had no radiologically detectable disease at the available assessment, and 18 remained unresolved. The conservative lower-bound PPV was 36.36%, and the NPV was 99.97%; estimates remain provisional pending complete follow-up. Conclusions: The integrated Attention U-Net/feature-based classification pipeline demonstrated consistent CTAC detection across the evaluated cohorts and supports its potential clinical utility for cancer detection. pubtype: Academic Journal doctype: pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|