calibration results (MathWorks Inc)
Structured Review

Calibration Results, supplied by MathWorks Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/calibration results/product/MathWorks Inc
Average 90 stars, based on 1 article reviews
Images
1) Product Images from "Deep Learning-Based Quantification of Adenoid Hypertrophy and Its Correlation with Apnea-Hypopnea Index in Pediatric Obstructive Sleep Apnea"
Article Title: Deep Learning-Based Quantification of Adenoid Hypertrophy and Its Correlation with Apnea-Hypopnea Index in Pediatric Obstructive Sleep Apnea
Journal: Nature and Science of Sleep
doi: 10.2147/NSS.S492146
Figure Legend Snippet: Calculation process of the A/N ratio using MATLAB and deep learning model architecture. ( A ) A fiberoptic nasopharyngoscopy image was selected, highlighting the adenoid cross-sectional area and the nasopharynx. The developed algorithm was then applied to automatically calculate the A/N ratio. ( B ) The network architecture used for both training and testing stages consisted of identical components, including essential modules such as Backbone, Neck, Decoder Head, and Loss, along with optional modules like the Neck and Auxiliary Head.
Techniques Used:
Figure Legend Snippet: Scatterplot of the Mann–Whitney U -test for A/N ratio evaluations. ( A ) Each scatter point represents an individual A/N ratio value assessed by the two experts. ( B ) Each scatter point corresponds to an individual A/N ratio value calculated by the MATLAB algorithm, based on calibration performed by the same two experts. This visual representation offers a comprehensive comparison between the expert evaluations and the MATLAB-calculated A/N ratio values.
Techniques Used: MANN-WHITNEY, Comparison
Figure Legend Snippet: Confusion matrix of adenoid hypertrophy degree performance for deep learning method and MATLAB algorithm. Adenoid hypertrophy degree is classified into three categories: small (A/N ratio 0–50%), medium (A/N ratio 50–75%), and large (A/N ratio 75–100%). In each confusion matrix, the horizontal axis represents the MATLAB results (actual class), while the vertical axis represents the deep learning results (predicted class).
Techniques Used:
