MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation

Background: A leading cause of emergency abdominal surgery, appendicitis is a common condition affecting millions of people worldwide. Automatic and accurate segmentation of the appendix from medical imaging is a challenging task, due to its small size, variability in shape, and proximity to other a...

Full description

Saved in:
Bibliographic Details
Main Authors: Emre Dandıl, Betül Tiryaki Baştuğ, Mehmet Süleyman Yıldırım, Kadir Çorbacı, Gürkan Güneri
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/21/2346
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173514921410560
author Emre Dandıl
Betül Tiryaki Baştuğ
Mehmet Süleyman Yıldırım
Kadir Çorbacı
Gürkan Güneri
author_facet Emre Dandıl
Betül Tiryaki Baştuğ
Mehmet Süleyman Yıldırım
Kadir Çorbacı
Gürkan Güneri
author_sort Emre Dandıl
collection DOAJ
description Background: A leading cause of emergency abdominal surgery, appendicitis is a common condition affecting millions of people worldwide. Automatic and accurate segmentation of the appendix from medical imaging is a challenging task, due to its small size, variability in shape, and proximity to other anatomical structures. Methods: In this study, we propose a backbone-enriched Mask R-CNN architecture (MaskAppendix) on the Detectron platform, enhanced with Gradient-weighted Class Activation Mapping (Grad-CAM), for precise appendix segmentation on computed tomography (CT) scans. In the proposed MaskAppendix deep learning model, ResNet101 network is used as the backbone. By integrating Grad-CAM into the MaskAppendix network, our model improves feature localization, allowing it to better capture subtle variations in appendix morphology. Results: We conduct extensive experiments on a dataset of abdominal CT scans, demonstrating that our method achieves state-of-the-art performance in appendix segmentation, outperforming traditional segmentation techniques in terms of both accuracy and robustness. In the automatic segmentation of the appendix region in CT slices, a DSC score of 87.17% was achieved with the proposed approach, and the results obtained have the potential to improve clinical diagnostic accuracy. Conclusions: This framework provides an effective tool for aiding clinicians in the diagnosis of appendicitis and other related conditions, reducing the potential for diagnostic errors and enhancing clinical workflow efficiency.
format Article
id doaj-art-344d3ec54c134c9c82ba6d69f5c91cf7
institution Kabale University
issn 2075-4418
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-344d3ec54c134c9c82ba6d69f5c91cf72024-11-08T14:34:37ZengMDPI AGDiagnostics2075-44182024-10-011421234610.3390/diagnostics14212346MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix SegmentationEmre Dandıl0Betül Tiryaki Baştuğ1Mehmet Süleyman Yıldırım2Kadir Çorbacı3Gürkan Güneri4Department of Computer Engineering, Faculty of Engineering, Bilecik Seyh Edebali University, 11230 Bilecik, TürkiyeRadiology Department, Faculty of Medicine, Bilecik Şeyh Edebali University, 11230 Bilecik, TürkiyeDepartment of Söğüt Vocational School, Computer Technology, Bilecik Şeyh Edebali University, Söğüt, 11600 Bilecik, TürkiyeGeneral Surgery Department, Bilecik Osmaneli Mustafa Selahattin Çetintaş Hospital, 11500 Bilecik, TürkiyeGeneral Surgery Department, Faculty of Medicine, Bilecik Şeyh Edebali University, 11230 Bilecik, TürkiyeBackground: A leading cause of emergency abdominal surgery, appendicitis is a common condition affecting millions of people worldwide. Automatic and accurate segmentation of the appendix from medical imaging is a challenging task, due to its small size, variability in shape, and proximity to other anatomical structures. Methods: In this study, we propose a backbone-enriched Mask R-CNN architecture (MaskAppendix) on the Detectron platform, enhanced with Gradient-weighted Class Activation Mapping (Grad-CAM), for precise appendix segmentation on computed tomography (CT) scans. In the proposed MaskAppendix deep learning model, ResNet101 network is used as the backbone. By integrating Grad-CAM into the MaskAppendix network, our model improves feature localization, allowing it to better capture subtle variations in appendix morphology. Results: We conduct extensive experiments on a dataset of abdominal CT scans, demonstrating that our method achieves state-of-the-art performance in appendix segmentation, outperforming traditional segmentation techniques in terms of both accuracy and robustness. In the automatic segmentation of the appendix region in CT slices, a DSC score of 87.17% was achieved with the proposed approach, and the results obtained have the potential to improve clinical diagnostic accuracy. Conclusions: This framework provides an effective tool for aiding clinicians in the diagnosis of appendicitis and other related conditions, reducing the potential for diagnostic errors and enhancing clinical workflow efficiency.https://www.mdpi.com/2075-4418/14/21/2346appendix segmentationdeep learningCT imagingmask R-CNNgrad-CAMDetectron
spellingShingle Emre Dandıl
Betül Tiryaki Baştuğ
Mehmet Süleyman Yıldırım
Kadir Çorbacı
Gürkan Güneri
MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation
Diagnostics
appendix segmentation
deep learning
CT imaging
mask R-CNN
grad-CAM
Detectron
title MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation
title_full MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation
title_fullStr MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation
title_full_unstemmed MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation
title_short MaskAppendix: Backbone-Enriched Mask R-CNN Based on Grad-CAM for Automatic Appendix Segmentation
title_sort maskappendix backbone enriched mask r cnn based on grad cam for automatic appendix segmentation
topic appendix segmentation
deep learning
CT imaging
mask R-CNN
grad-CAM
Detectron
url https://www.mdpi.com/2075-4418/14/21/2346
work_keys_str_mv AT emredandıl maskappendixbackboneenrichedmaskrcnnbasedongradcamforautomaticappendixsegmentation
AT betultiryakibastug maskappendixbackboneenrichedmaskrcnnbasedongradcamforautomaticappendixsegmentation
AT mehmetsuleymanyıldırım maskappendixbackboneenrichedmaskrcnnbasedongradcamforautomaticappendixsegmentation
AT kadircorbacı maskappendixbackboneenrichedmaskrcnnbasedongradcamforautomaticappendixsegmentation
AT gurkanguneri maskappendixbackboneenrichedmaskrcnnbasedongradcamforautomaticappendixsegmentation