Validating a semi-quantitative method for assessment of degree of methylene blue staining in sentinel lymph nodes
Ram, A. S.; Oblak, M. L.; Matuszewska, K.; Singh, A.; Petrik, J.
Show abstract
Purpose To develop a digital algorithm and validate a semi-quantitative scoring method for surface methylene blue (MB) staining in whole lymph nodes (LN).Methods Lymph nodes from canine models undergoing sentinel lymph node (SLN) mapping were prospectively assessed ex vivo and photographed. Two blinded observers evaluated all images and assigned a semi-quantitative score based on surface staining (0 – no blue stain, 1 – 1-50% stained, 2 – 51-100% stained). A standard reference for degree of blue staining was based on signal-to-background ratios using computer-based imaging software with an output measurement of percentage of staining of the LN. Agreement between observers was assessed using the Kappa coefficient.Results 124 lymph nodes were included and demonstrated strong agreement (K = 0.8007, p < 0.0001) between results of semi-quantitative scoring and image analysis. Also, strong interobserver and intraobserver agreement was observed for the scoring system (K = 0.8051, p < 0.0001 and K = 0.9493, p < 0.0001, respectively).Discussion Agreement between the observer-based scoring system and imaging software illustrates a validated method in assessing MB staining, without the need for analysis software. The use of a semi-quantitative scoring system shows promise for a simple, objective assessment of MB staining in surgery and for future study. Lymph nodes can have variable surface colour, which can make assessment of blue staining challenging for novice observers in certain cases. This study describes a digital algorithm for quantitative analysis of blue staining in LN thereby providing a novel and objective reporting mechanism in scientific research involving SLN mapping.Competing Interest StatementThe authors have declared no competing interest.View Full Text
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluation of the efficacy of using indocyanine green associated with fluorescence in sentinel lymph node biopsy 96%
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 93%
- Machine learning based prediction of recurrence after curative resection for rectal cancer 93%
Similar papers in this journal
- Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment 92%
- Content-based image retrieval assists radiologists in diagnosing eye and orbital mass lesions in MRI 92%
- Prediction and analysis of skin cancer progression using genomics profiles of patients 91%
Similar papers in this journal
- Creating virtual H&E images using samples imaged on a commercial CODEX platform 94%
- Using an Anomaly Detection Approach for the Segmentation of Colorectal Cancer Tumors in Whole Slide Images 93%
- Independent assessment of a deep learning system for lymph node metastasis detection on the Augmented Reality Microscope 92%
Similar papers in this journal
Similar papers in this journal
- A digital score of peri-epithelial lymphocytic activity predicts malignant transformation in oral epithelial dysplasia 94%
- Development of a multi-scanner facility for data acquisition for digital pathology artificial intelligence 93%
- Spatial Effects of Infiltrating T cells on Neighbouring Cancer Cells and Prognosis in Stage III CRC patients 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.