Találati lista | Tudóstér

001-es BibID:	BIBFORM071120
Első szerző:	Török Péter (szülész-nőgyógyász)
Cím:	Digital Image Analysis with Full Connected Convolutional Neural Network to Facilitate Complete Fibroid Resection / Török P., Harangi B.
Dátum:	2017
ISSN:	1553-4650
Megjegyzések:	Study Objective Facilitate to find the correct layer between the fibroid and the normal myometrium by analyzing videos of hysteroscopic fibroid resection. Design Images are cut off of recorded videos of TCRMs. These images were analyzed by full connected convolutional neural network. Images and sub-images were created. Different filters and procedures were applied by the fully convolutional neural network (FCNN) for identifying previously annotated structures. Design Classification Canadian Task Force II-2 Setting On the images of surgery, different structures were signed and annotated for the training phase. After the appropriate training of the deep neural network with 4688 images from that training set, 1600 formerly unseen images were used for testing. Patients Indication for surgery was heavy menstrual bleeding and hysteroscopic finding was submucous fibroid. Operative intervention was fibroid resection. Recorded videos of transcervical resection of myoma are used for the study. Measurements and Main Results Previously manually annotated images and the manually drawn bitmasks were used for training the applied fully convolutional neural network and then this pre-trained network was used for automatic segmentation of normal myometrium in an unseen video frame. The segmentation pixel-wise accuracy achieved the 86.19% considering the Hausdorff metric. Conclusion Using deep learning technique in analyzing process of endoscopic video frame could help in real-time identification of structures while performing endoscopic surgery.
Tárgyszavak:	Orvostudományok Klinikai orvostudományok idézhető absztrakt neural network fibroid endoscopy digital image analysis
Megjelenés:	Journal Of Minimally Invasive Gynecology 24 : 7 (2017), p. 161. -
További szerzők:	Harangi Balázs (1986-) (programtervező matematikus)
Internet cím:	DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: