Skip to Main content Skip to Navigation

Champ visuel augmenté pour l'exploration vidéo de la rétine

Abstract : The main objective of this thesis is toincrease the visual comfort of theophthalmologists during examinations orsurgeries. To do so, we decided toartificially increase in real time the field ofview in videos of retinal exploration. Thetools used for the acquisition of thesevideos are the slit lamp and theendoscope. The increase of the field ofview passes by the establishment ofdynamic 3D maps of the retina.To our knowledge, there is still no suchmethod in the state of the art.In order to implement our solution, westudied the different methods of motionestimations between two images. Wegrouped them into "classical" methods, onthe one hand, including methods based onSIFT or SURF algorithms. On the otherhand, we grouped deep learning methods(or "CNN" methods for ConvolutionalNeural Network).Some of these methods, such as thoseusing FlowNet networks, required groundtruth annotation of movement betweenimages.Since such bases are very difficult to set upin the medical field and do not exist inophthalmology, general databases havebeen used. In addition, we built twodatabases of artificial displacements whichbackgrounds are composed of images ofretinas. Finally, to get around this problemof annotations, a self-supervised deeplearning approach was studied.After comparing the results, it appears thatmethods using convolutional neuralnetworks outperform conventional methodsfor estimating movements in retinal videos.Moreover, only a strong supervision allowsacceptable results. In the future, we hopethat this work will enable surgeons to bemore confident and effective inenvironments where it is sometimesdifficult to find their bearings.
Document type :
Complete list of metadatas

Cited literature [128 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Monday, November 16, 2020 - 3:03:12 PM
Last modification on : Tuesday, November 24, 2020 - 10:41:25 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03007756, version 1


Alexandre Guerre. Champ visuel augmenté pour l'exploration vidéo de la rétine. Médecine humaine et pathologie. Université de Bretagne occidentale - Brest, 2019. Français. ⟨NNT : 2019BRES0110⟩. ⟨tel-03007756⟩



Record views


Files downloads