FISICO: Fast Image SegmentatIon COrrection

• Published in: PloS one 2016-05, Vol.11 (5), p.e0156035-e0156035
• Main Authors: Valenzuela, Waldo, Ferguson, Stephen J, Ignasiak, Dominika, Diserens, Gaëlle, Häni, Levin, Wiest, Roland, Vermathen, Peter, Boesch, Chris, Reyes, Mauricio
• Format: Article
• Language: English
• Subjects: Algorithms; Biology and Life Sciences; Biomechanics; Biomedical engineering; Computer and Information Sciences; Computer graphics; Deformation; Diagnosis; Diagnostic imaging; Engineering and Technology; Hospitals; Humans; Image acquisition; Image Enhancement - methods; Image processing; Image segmentation; Imaging, Three-Dimensional - methods; Knee; Knee Joint - diagnostic imaging; Lumbosacral Region - diagnostic imaging; Magnetic Resonance Imaging; Medical imaging; Medicine and Health Sciences; Methods; Muscle, Skeletal - diagnostic imaging; Muscles; Physical Sciences; Research and Analysis Methods; Software development tools; Usability
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0156035

In clinical diagnosis, medical image segmentation plays a key role in the analysis of pathological regions. Despite advances in automatic and semi-automatic segmentation techniques, time-effective correction tools are commonly needed to improve segmentation results. Therefore, these tools must provide faster corrections with a lower number of interactions, and a user-independent solution to reduce the time frame between image acquisition and diagnosis. We present a new interactive method for correcting image segmentations. Our method provides 3D shape corrections through 2D interactions. This approach enables an intuitive and natural corrections of 3D segmentation results. The developed method has been implemented into a software tool and has been evaluated for the task of lumbar muscle and knee joint segmentations from MR images. Experimental results show that full segmentation corrections could be performed within an average correction time of 5.5±3.3 minutes and an average of 56.5±33.1 user interactions, while maintaining the quality of the final segmentation result within an average Dice coefficient of 0.92±0.02 for both anatomies. In addition, for users with different levels of expertise, our method yields a correction time and number of interaction decrease from 38±19.2 minutes to 6.4±4.3 minutes, and 339±157.1 to 67.7±39.6 interactions, respectively.