Reinforcement learning-based anatomical maps for pancreas subregion and duct segmentation

Amiri, Sepideh (avtor), Vrtovec, Tomaž (avtor), Mustafaev, Tamerlan (avtor), Deufel, Christopher L. (avtor), Thomsen, Henrik S. (avtor), Hylleholt Sillesen, Martin (avtor), Gudmann Steuble Brandt, Erik (avtor), Andersen, Michael Brun (avtor), Müller, Christoph Felix (avtor), Ibragimov, Bulat (avtor)

AbstractBackground: The pancreas is a complex abdominal organ with many anatom-ical variations, and therefore automated pancreas segmentation from medicalimages is a challenging application.Purpose: In this paper, we present a framework for segmenting individualpancreatic subregions and the pancreatic duct from three-dimensional (3D)computed tomography (CT) images.Methods: A multiagent reinforcement learning (RL) network was used to detectlandmarks of the head,neck,body,and tail of the pancreas,and landmarks alongthe pancreatic duct in a selected target CT image. Using the landmark detectionresults, an atlas of pancreases was nonrigidly registered to the target image,resulting in anatomical probability maps for the pancreatic subregions and duct.The probability maps were augmented with multilabel 3D U-Net architecturesto obtain the final segmentation results.Results: To evaluate the performance of our proposed framework, we com-puted the Dice similarity coefficient (DSC) between the predicted and groundtruth manual segmentations on a database of 82 CT images with manuallysegmented pancreatic subregions and 37 CT images with manually segmentedpancreatic ducts. For the four pancreatic subregions, the mean DSC improvedfrom 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shiftedwindowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, whenutilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperformingthe standard approaches and existing methods on different datasets.Conclusions: The resulting accuracy of the proposed RL-based segmentationframework demonstrates an improvement against segmentation with standardU-Net architectures.

• Jezik: Angleški jezik
• Ključne besede: medical image analysis, landmark detection, image segmentation, pancreas region, deep learning, reinforcement learning
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2024
• Št. strani: Str. 7378-7392
• Številčenje: Vol. 51, iss. 10
• PID: 20.500.12556/RUL-164044
• UDK: 004.93:61
• ISSN pri članku: 2473-4209
• DOI: 10.1002/mp.17300
• COBISS.SI-ID: 202626819
• Datum objave v RUL: 16.10.2024

Gradivo je del revije

• Naslov: Medical physics
• Skrajšan naslov: Med. phys.
• Založnik: American Institute of Physics
• ISSN: 2473-4209
• COBISS.SI-ID: 2725755

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: analiza medicinskih slik, razpoznavanje oslonilnih točk, segmentacija slik, trebušna slinavka, globoko učenje, spodbujevano učenje