Image-Guided Biopsy, Nasopharyngeal Carcinoma
Conditions
Keywords
Artificial Intelligence, Classification, Nasopharyngeal Carcinoma, Nasopharyngoscope, Image-Guided Biopsy
Brief summary
Due to the occult anatomic location of the nasopharynx and frequent presence of adenoid hyperplasia, the positive rate for nasopharyngeal carcinoma identification during biopsy is low, thus leading to delayed or missed diagnosis for nasopharyngeal carcinoma upon initial attempt. Here, we aimed to develop an artificial intelligence tool to detect nasopharyngeal malignancies and guide biopsy under endoscopic examination based on deep learning.
Detailed description
Due to the occult anatomic location of the nasopharynx and frequent presence of adenoid hyperplasia, the positive rate for nasopharyngeal carcinoma identification during biopsy is low, thus leading to delayed or missed diagnosis for nasopharyngeal carcinoma upon initial attempt. Here, we aimed to develop an artificial intelligence tool to detect nasopharyngeal malignancies and guide biopsy under endoscopic examination based on deep learning.
Interventions
DIAGNOSTIC_TESTNasopharyngeal Endoscopy image-guided Biopsy
For each participant presenting with a suspicious nasopharyngeal lesion, the attending physician will assess the lesion and determine the appropriate biopsy approach. The physician may decide on multiple biopsies from the lesion area, including one sample from within the lesion itself, another from 5-8 mm outside the lesion, and a third from 8-10 mm beyond the lesion. Alternatively, a single biopsy may be deemed sufficient based on the clinical judgment. Each of these specimens will undergo pathological examination to confirm whether they are carcinomatous or non-carcinomatous.
Sponsors
Sun Yat-sen University
Guangdong Provincial People's Hospital
Nanfang Hospital, Southern Medical University
Fujian Cancer Hospital
Hainan People's Hospital
Chinese Academy of Sciences
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* The patient was found to have a nasopharyngeal lesion through the nasopharyngeal endoscopy and the clinicans considered it necessary to perform an biopsy. * Hemilateral lesion with limited size.
Exclusion criteria
* Patients with nasopharyngeal cancer, oropharyngeal cancer, hypopharyngeal cancer, etc. who have already been treated.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Aera under the receiver operating characteristic curve (AUC) | three months | AUC of an deep learning-based model in discriminating nasopharyngeal carcinoma from bengin lesion. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Accuray | three months | The agreement between the deep learning-based model and the histopathological diagnosis of the three biopsy specimens (inside the lesion, 5-8 mm outside the lesion, and 8-10 mm outside the lesion). |
Other
| Measure | Time frame | Description |
|---|---|---|
| Statistical significance | Three years | Statistical significance (P value) of DFS (time from diagnosis to disease progression or death from any cause) in nasopharyngeal carcinoma patients between high-risk and low-risk group identified by deep learning-based model. |
Countries
China
Contacts
Primary ContactDi Dong, Ph.D
Backup ContactYali Zang, ph.D
Outcome results
None listed