The evaluation of synthetic datasets on training AlexNet for surgical tool detection

Surgical tool recognition is a key task to analyze surgical workflow, in order to improve the efficiency and safety of laparoscopic surgeries. The laparoscopic videos are important sources to conduct this task, However, there are some challenges to analyze these videos. Focus on the imbalanced datas...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ding N., Jalal N. A., Alshirbaji T. A., Möller K.
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2020
Materias:	surgical tool recognition convolutional neural network Medicine R
Acceso en línea:	https://doaj.org/article/fc0bcc8fc2e346828f6b83dbcf6182a5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fc0bcc8fc2e346828f6b83dbcf6182a5
record_format	dspace
spelling	oai:doaj.org-article:fc0bcc8fc2e346828f6b83dbcf6182a52021-12-05T14:10:42ZThe evaluation of synthetic datasets on training AlexNet for surgical tool detection2364-550410.1515/cdbme-2020-3082https://doaj.org/article/fc0bcc8fc2e346828f6b83dbcf6182a52020-09-01T00:00:00Zhttps://doi.org/10.1515/cdbme-2020-3082https://doaj.org/toc/2364-5504Surgical tool recognition is a key task to analyze surgical workflow, in order to improve the efficiency and safety of laparoscopic surgeries. The laparoscopic videos are important sources to conduct this task, However, there are some challenges to analyze these videos. Focus on the imbalanced dataset problem, data augmentation method based on generate different synthetic datasets and evaluate their performance training on a convolutional neural network model are investigated in this research. The results show the effect on the model with different background patterns. A better performance was achieved when the model was trained by a structure background dataset. Further research will be needed to understand why the original background patterns support the correct classification. It is assumed that this is an overlearning effect, that will not hold if other procedures were included into the test set.Ding N.Jalal N. A.Alshirbaji T. A.Möller K.De Gruyterarticlesurgical tool recognitionconvolutional neural networkMedicineRENCurrent Directions in Biomedical Engineering, Vol 6, Iss 3, Pp 319-321 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	surgical tool recognition convolutional neural network Medicine R
spellingShingle	surgical tool recognition convolutional neural network Medicine R Ding N. Jalal N. A. Alshirbaji T. A. Möller K. The evaluation of synthetic datasets on training AlexNet for surgical tool detection
description	Surgical tool recognition is a key task to analyze surgical workflow, in order to improve the efficiency and safety of laparoscopic surgeries. The laparoscopic videos are important sources to conduct this task, However, there are some challenges to analyze these videos. Focus on the imbalanced dataset problem, data augmentation method based on generate different synthetic datasets and evaluate their performance training on a convolutional neural network model are investigated in this research. The results show the effect on the model with different background patterns. A better performance was achieved when the model was trained by a structure background dataset. Further research will be needed to understand why the original background patterns support the correct classification. It is assumed that this is an overlearning effect, that will not hold if other procedures were included into the test set.
format	article
author	Ding N. Jalal N. A. Alshirbaji T. A. Möller K.
author_facet	Ding N. Jalal N. A. Alshirbaji T. A. Möller K.
author_sort	Ding N.
title	The evaluation of synthetic datasets on training AlexNet for surgical tool detection
title_short	The evaluation of synthetic datasets on training AlexNet for surgical tool detection
title_full	The evaluation of synthetic datasets on training AlexNet for surgical tool detection
title_fullStr	The evaluation of synthetic datasets on training AlexNet for surgical tool detection
title_full_unstemmed	The evaluation of synthetic datasets on training AlexNet for surgical tool detection
title_sort	evaluation of synthetic datasets on training alexnet for surgical tool detection
publisher	De Gruyter
publishDate	2020
url	https://doaj.org/article/fc0bcc8fc2e346828f6b83dbcf6182a5
work_keys_str_mv	AT dingn theevaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT jalalna theevaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT alshirbajita theevaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT mollerk theevaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT dingn evaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT jalalna evaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT alshirbajita evaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection AT mollerk evaluationofsyntheticdatasetsontrainingalexnetforsurgicaltooldetection
_version_	1718371817875308544

The evaluation of synthetic datasets on training AlexNet for surgical tool detection

Ejemplares similares