Public articles linked to the same research event.
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.