Automated pancreatic mass segmentation in computer tomography images using a voting ensemble method based on encoder-decoder architectures

Pancreatic cancer poses significant challenges in early diagnosis, with a high mortality rate of 98%, and is responsible for 4.7% of cancer deaths. Early diagnosis, mainly done by imaging exams, is the main factor that determines prognosis. While it is common to perform cascaded segmentation, the us...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Procedia computer science Jg. 256; S. 1167 - 1174
Hauptverfasser: Araújo, Alexandre de Carvalho, de Almeida, João Dallyson Sousa, de Paiva, Anselmo Cardoso, Júnior, Geraldo Braz
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 2025
Schlagworte:
Encoder-Decoder architecture
Ensemble Model
Pancreatic mass
Pancreatic mass
Ensemble Model
Encoder-Decoder architecture
ISSN:1877-0509, 1877-0509
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Pancreatic cancer poses significant challenges in early diagnosis, with a high mortality rate of 98%, and is responsible for 4.7% of cancer deaths. Early diagnosis, mainly done by imaging exams, is the main factor that determines prognosis. While it is common to perform cascaded segmentation, the use of ensemble strategies is rarely explored in the literature for pancreatic mass segmentation. In cascaded methods, the performance of the pancreatic mass segmentation step is also directly affected by the previous steps. In this paper we aim to study the impact of a localization step in three levels of precision while using an ensemble method to carry out pancreatic mass segmentation. A voting ensemble method is proposed that combine three encoder-decoder based networks, namely U-Net, Feature Pyramid Network (FPN) and LinkNet. The results obtained were competitive with existing literature, achieving a Dice Score of 63.89 ± 2.88% on the smallest resolution and 60.35 ± 4.86% on the biggest resolution on the MSD dataset. The results show that an ensemble method can mitigate the impact of previous steps in a cascaded method without significant loss in performance.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2025.02.225