Cargando…

A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector

Small bowel polyps exhibit variations related to color, shape, morphology, texture, and size, as well as to the presence of artifacts, irregular polyp borders, and the low illumination condition inside the gastrointestinal GI tract. Recently, researchers developed many highly accurate polyp detectio...

Descripción completa

Detalles Bibliográficos
Autores principales: Souaidi, Meryem, Lafraxo, Samira, Kerkaou, Zakaria, El Ansari, Mohamed, Koutti, Lahcen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955440/
https://www.ncbi.nlm.nih.gov/pubmed/36832221
http://dx.doi.org/10.3390/diagnostics13040733
_version_ 1784894346222370816
author Souaidi, Meryem
Lafraxo, Samira
Kerkaou, Zakaria
El Ansari, Mohamed
Koutti, Lahcen
author_facet Souaidi, Meryem
Lafraxo, Samira
Kerkaou, Zakaria
El Ansari, Mohamed
Koutti, Lahcen
author_sort Souaidi, Meryem
collection PubMed
description Small bowel polyps exhibit variations related to color, shape, morphology, texture, and size, as well as to the presence of artifacts, irregular polyp borders, and the low illumination condition inside the gastrointestinal GI tract. Recently, researchers developed many highly accurate polyp detection models based on one-stage or two-stage object detector algorithms for wireless capsule endoscopy (WCE) and colonoscopy images. However, their implementation requires a high computational power and memory resources, thus sacrificing speed for an improvement in precision. Although the single-shot multibox detector (SSD) proves its effectiveness in many medical imaging applications, its weak detection ability for small polyp regions persists due to the lack of information complementary between features of low- and high-level layers. The aim is to consecutively reuse feature maps between layers of the original SSD network. In this paper, we propose an innovative SSD model based on a redesigned version of a dense convolutional network (DenseNet) which emphasizes multiscale pyramidal feature maps interdependence called DC-SSDNet (densely connected single-shot multibox detector). The original backbone network VGG-16 of the SSD is replaced with a modified version of DenseNet. The DenseNet-46 front stem is improved to extract highly typical characteristics and contextual information, which improves the model’s feature extraction ability. The DC-SSDNet architecture compresses unnecessary convolution layers of each dense block to reduce the CNN model complexity. Experimental results showed a remarkable improvement in the proposed DC-SSDNet to detect small polyp regions achieving an mAP of 93.96%, F1-score of 90.7%, and requiring less computational time.
format Online
Article
Text
id pubmed-9955440
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99554402023-02-25 A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector Souaidi, Meryem Lafraxo, Samira Kerkaou, Zakaria El Ansari, Mohamed Koutti, Lahcen Diagnostics (Basel) Article Small bowel polyps exhibit variations related to color, shape, morphology, texture, and size, as well as to the presence of artifacts, irregular polyp borders, and the low illumination condition inside the gastrointestinal GI tract. Recently, researchers developed many highly accurate polyp detection models based on one-stage or two-stage object detector algorithms for wireless capsule endoscopy (WCE) and colonoscopy images. However, their implementation requires a high computational power and memory resources, thus sacrificing speed for an improvement in precision. Although the single-shot multibox detector (SSD) proves its effectiveness in many medical imaging applications, its weak detection ability for small polyp regions persists due to the lack of information complementary between features of low- and high-level layers. The aim is to consecutively reuse feature maps between layers of the original SSD network. In this paper, we propose an innovative SSD model based on a redesigned version of a dense convolutional network (DenseNet) which emphasizes multiscale pyramidal feature maps interdependence called DC-SSDNet (densely connected single-shot multibox detector). The original backbone network VGG-16 of the SSD is replaced with a modified version of DenseNet. The DenseNet-46 front stem is improved to extract highly typical characteristics and contextual information, which improves the model’s feature extraction ability. The DC-SSDNet architecture compresses unnecessary convolution layers of each dense block to reduce the CNN model complexity. Experimental results showed a remarkable improvement in the proposed DC-SSDNet to detect small polyp regions achieving an mAP of 93.96%, F1-score of 90.7%, and requiring less computational time. MDPI 2023-02-15 /pmc/articles/PMC9955440/ /pubmed/36832221 http://dx.doi.org/10.3390/diagnostics13040733 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Souaidi, Meryem
Lafraxo, Samira
Kerkaou, Zakaria
El Ansari, Mohamed
Koutti, Lahcen
A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector
title A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector
title_full A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector
title_fullStr A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector
title_full_unstemmed A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector
title_short A Multiscale Polyp Detection Approach for GI Tract Images Based on Improved DenseNet and Single-Shot Multibox Detector
title_sort multiscale polyp detection approach for gi tract images based on improved densenet and single-shot multibox detector
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955440/
https://www.ncbi.nlm.nih.gov/pubmed/36832221
http://dx.doi.org/10.3390/diagnostics13040733
work_keys_str_mv AT souaidimeryem amultiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT lafraxosamira amultiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT kerkaouzakaria amultiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT elansarimohamed amultiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT kouttilahcen amultiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT souaidimeryem multiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT lafraxosamira multiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT kerkaouzakaria multiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT elansarimohamed multiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector
AT kouttilahcen multiscalepolypdetectionapproachforgitractimagesbasedonimproveddensenetandsingleshotmultiboxdetector