Related Experiment Video
Updated: Aug 8, 2025
Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions
Published on: September 22, 2013
Fluorescence molecular optomic signatures improve identification of tumors in head and neck specimens
Yao Chen1, Samuel S Streeter1,2,3, Brady Hunt1
1Thayer School of Engineering, Dartmouth College, Hanover, NH, United States.
Background:
Fluorescence molecular imaging using ABY-029, an epidermal growth factor receptor (EGFR)-targeted, synthetic Affibody peptide labeled with a near-infrared fluorophore, is under investigation for surgical guidance during head and neck squamous cell carcinoma (HNSCC) resection. However, tumor-to-normal tissue contrast is confounded by intrinsic physiological limitations of heterogeneous EGFR expression and non-specific agent uptake.
Objective:
In this preliminary study, radiomic analysis was applied to optical ABY-029 fluorescence image data for HNSCC tissue classification through an approach termed "optomics." Optomics was employed to improve tumor identification by leveraging textural pattern differences in EGFR expression conveyed by fluorescence. The study objective was to compare the performance of conventional fluorescence intensity thresholding and optomics for binary classification of malignant vs. non-malignant HNSCC tissues.
Materials And Methods:
Fluorescence image data collected through a Phase 0 clinical trial of ABY-029 involved a total of 20,073 sub-image patches (size of 1.8 × 1.8 mm2) extracted from 24 bread-loafed slices of HNSCC surgical resections originating from 12 patients who were stratified into three dose groups (30, 90, and 171 nanomoles). Each dose group was randomly partitioned on the specimen-level 75%/25% into training/testing sets, then all training and testing sets were aggregated. A total of 1,472 standardized radiomic features were extracted from each patch and evaluated by minimum redundancy maximum relevance feature selection, and 25 top-ranked features were used to train a support vector machine (SVM) classifier. Predictive performance of the SVM classifier was compared to fluorescence intensity thresholding for classifying testing set image patches with histologically confirmed malignancy status.
Results:
Optomics provided consistent improvement in prediction accuracy and false positive rate (FPR) and similar false negative rate (FNR) on all testing set slices, irrespective of dose, compared to fluorescence intensity thresholding (mean accuracies of 89% vs. 81%, P = 0.0072; mean FPRs of 12% vs. 21%, P = 0.0035; and mean FNRs of 13% vs. 17%, P = 0.35).
Conclusions:
Optomics outperformed conventional fluorescence intensity thresholding for tumor identification using sub-image patches as the unit of analysis. Optomics mitigate diagnostic uncertainties introduced through physiological variability, imaging agent dose, and inter-specimen biases of fluorescence molecular imaging by probing textural image information. This preliminary study provides a proof-of-concept that applying radiomics to fluorescence molecular imaging data offers a promising image analysis technique for cancer detection in fluorescence-guided surgery.
Insights
Optomics, a radiomic analysis of fluorescence imaging, improved head and neck cancer detection. This method enhances tumor identification by analyzing textural patterns, outperforming traditional intensity thresholding for surgical guidance.
Area of Science:
- Medical imaging analysis
- Oncology
- Radiomics
Background:
- Fluorescence molecular imaging with ABY-029 targets epidermal growth factor receptor (EGFR) for head and neck squamous cell carcinoma (HNSCC) surgery.
- Tumor contrast is limited by heterogeneous EGFR expression and non-specific uptake, complicating surgical guidance.
Purpose of the Study:
- To introduce and evaluate "optomics," a radiomic approach applied to fluorescence imaging data for HNSCC tissue classification.
- To compare the efficacy of optomics against conventional fluorescence intensity thresholding for distinguishing malignant from non-malignant HNSCC tissues.
Main Methods:
- Radiomic features were extracted from optical ABY-029 fluorescence image patches (n=20,073) from HNSCC surgical resections.
- A support vector machine (SVM) classifier was trained using 25 top-ranked radiomic features after minimum redundancy maximum relevance selection.
- Performance was assessed by comparing SVM-based optomics classification with fluorescence intensity thresholding on a held-out test set.
Main Results:
- Optomics demonstrated superior performance compared to fluorescence intensity thresholding, achieving higher mean accuracy (89% vs. 81%, P=0.0072).
- Optomics significantly reduced the false positive rate (12% vs. 21%, P=0.0035) while maintaining a comparable false negative rate (13% vs. 17%, P=0.35).
- These improvements were consistent across different ABY-029 doses and patient specimens.
Conclusions:
- Optomics, by analyzing textural information in fluorescence images, effectively mitigates diagnostic uncertainties associated with physiological variability and imaging parameters.
- This radiomic approach provides a promising method for enhancing tumor identification in fluorescence-guided surgery for HNSCC.
- The study establishes a proof-of-concept for applying optomics in cancer detection within fluorescence molecular imaging.
