The Dresden in vivo OCT dataset for automatic middle ear segmentation

Research output: Contribution to journalResearch articleContributedpeer-review



Endoscopic optical coherence tomography (OCT) offers a non-invasive approach to perform the morphological and functional assessment of the middle ear in vivo. However, interpreting such OCT images is challenging and time-consuming due to the shadowing of preceding structures. Deep neural networks have emerged as a promising tool to enhance this process in multiple aspects, including segmentation, classification, and registration. Nevertheless, the scarcity of annotated datasets of OCT middle ear images poses a significant hurdle to the performance of neural networks. We introduce the Dresden in vivo OCT Dataset of the Middle Ear (DIOME) featuring 43 OCT volumes from both healthy and pathological middle ears of 29 subjects. DIOME provides semantic segmentations of five crucial anatomical structures (tympanic membrane, malleus, incus, stapes and promontory), and sparse landmarks delineating the salient features of the structures. The availability of these data facilitates the training and evaluation of algorithms regarding various analysis tasks with middle ear OCT images, e.g. diagnostics.


Original languageEnglish
Article number242
Number of pages7
JournalScientific data
Volume11 (2024)
Issue number1
Publication statusPublished - 26 Feb 2024

External IDs

ORCID /0009-0002-1419-8698/work/154741460
ORCID /0000-0002-8160-3000/work/154741696
ORCID /0000-0003-0554-2178/work/154741779
ORCID /0009-0008-7642-8608/work/154742281
unpaywall 10.1038/s41597-024-03000-0
Scopus 85186407493
ORCID /0000-0002-4590-1908/work/163294012



  • Humans, Tomography, Optical Coherence/methods, Ear, Middle/diagnostic imaging, Neural Networks, Computer, Algorithms