CONCLUSION
In summary, we developed a deep learning model which could be useful in helping junior otolaryngologists and non-otolaryngologists to diagnose attic retraction pocket and atelectasis.
CONFLICT OF INTEREST The authors have no potential conflicts of interest with respect to the research, authorship and/ or publication of this article.
CONSENT TO PARTICIPATE The participants signed formal consent to share in this study.
CONSENT FOR PUBLICATION Additional informed consent was obtained from all participants to share and publish their data in this article.
DATA AVAILABILITY STATEMENT The datasets used and analysed during the current study are available from the corresponding author on reasonable request.