Main challenges on the curation of large scale datasets for pancreas segmentation using deep learning in multi-phase CT scans: Focus on cardinality, manual refinement, and annotation quality.

Autor: Cavicchioli M; Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, Milano, 20133, Italy; Fondazione MIAS (AIMS Academy), Piazza dell'Ospedale Maggiore 3, Milano, 20162, Italy. Electronic address: matteo.cavicchioli@polimi.it., Moglia A; Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, Milano, 20133, Italy., Pierelli L; Fondazione MIAS (AIMS Academy), Piazza dell'Ospedale Maggiore 3, Milano, 20162, Italy., Pugliese G; Fondazione MIAS (AIMS Academy), Piazza dell'Ospedale Maggiore 3, Milano, 20162, Italy., Cerveri P; Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, Milano, 20133, Italy; Department of Industrial and Information Engineering, University of Pavia, Via Adolfo Ferrata 5, Pavia, 27100, Italy.
Jazyk: angličtina
Zdroj: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society [Comput Med Imaging Graph] 2024 Oct; Vol. 117, pp. 102434. Date of Electronic Publication: 2024 Sep 13.
DOI: 10.1016/j.compmedimag.2024.102434
Abstrakt: Accurate segmentation of the pancreas in computed tomography (CT) holds paramount importance in diagnostics, surgical planning, and interventions. Recent studies have proposed supervised deep-learning models for segmentation, but their efficacy relies on the quality and quantity of the training data. Most of such works employed small-scale public datasets, without proving the efficacy of generalization to external datasets. This study explored the optimization of pancreas segmentation accuracy by pinpointing the ideal dataset size, understanding resource implications, examining manual refinement impact, and assessing the influence of anatomical subregions. We present the AIMS-1300 dataset encompassing 1,300 CT scans. Its manual annotation by medical experts required 938 h. A 2.5D UNet was implemented to assess the impact of training sample size on segmentation accuracy by partitioning the original AIMS-1300 dataset into 11 smaller subsets of progressively increasing numerosity. The findings revealed that training sets exceeding 440 CTs did not lead to better segmentation performance. In contrast, nnU-Net and UNet with Attention Gate reached a plateau for 585 CTs. Tests on generalization on the publicly available AMOS-CT dataset confirmed this outcome. As the size of the partition of the AIMS-1300 training set increases, the number of error slices decreases, reaching a minimum with 730 and 440 CTs, for AIMS-1300 and AMOS-CT datasets, respectively. Segmentation metrics on the AIMS-1300 and AMOS-CT datasets improved more on the head than the body and tail of the pancreas as the dataset size increased. By carefully considering the task and the characteristics of the available data, researchers can develop deep learning models without sacrificing performance even with limited data. This could accelerate developing and deploying artificial intelligence tools for pancreas surgery and other surgical data science applications.
Competing Interests: Declaration of competing interest The authors declare no conflict of interest.
(Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: