Automatic multi-resolution shape modeling of multi-organ structures

Cerrolaza, Juan J.; Summers, Ronald M.; González-Ballester, Miguel Ángel; Linguraru, Marius George

doi:10.1016/j.media.2015.04.003

Cited by 49 publications

(42 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-organ segmentation has attracted considerable interest over the years. Classical approaches include statistical shape models (Cerrolaza et al, 2015;Okada et al, 2015), and/or employ techniques based on image registration. So called multi-atlas label fusion (Rohlfing et al, 2004;Wang et al, 2013;Iglesias and Sabuncu, 2015) has found wide application in clinical research and practice.…”

Section: Related Workmentioning

confidence: 99%

An application of cascaded 3D fully convolutional networks for medical image segmentation

Roth¹,

Oda²,

Zhou³

et al. 2018

Computerized Medical Imaging and Graphics

285

163

View full text Add to dashboard Cite

Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of volumetric images. In this work, we show that a multi-class 3D FCN trained on manually labeled CT scans of several anatomical structures (ranging from the large organs to thin vessels) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training class-specific models. To this end, we propose a two-stage, coarse-to-fine approach that will first use a 3D FCN to roughly define a candidate region, which will then be used as input to a second 3D FCN. This reduces the number of voxels the second FCN has to classify to ∼10% and allows it to focus on more detailed segmentation of the organs and vessels. We utilize training and validation sets consisting of 331 clinical CT images and test our models on a completely unseen data collection acquired at a different hospital that includes 150 CT scans, targeting three anatomical organs (liver, spleen, and pancreas). In challenging organs such as the pancreas, our cascaded approach improves the mean Dice score from 68.5 to 82.2%, achieving the highest reported average score on this dataset. We compare with a 2D FCN method on a separate dataset of 240 CT scans with 18 classes and achieve a significantly higher performance in small organs and vessels. Furthermore, we explore fine-tuning our models to different datasets. Our experiments illustrate the promise and robustness of current 3D FCN based semantic segmentation of medical images, achieving state-of-the-art results..

show abstract

Section: Related Workmentioning

confidence: 99%

An application of cascaded 3D fully convolutional networks for medical image segmentation

Roth¹,

Oda²,

Zhou³

et al. 2018

Computerized Medical Imaging and Graphics

285

163

View full text Add to dashboard Cite

show abstract

“…Endoscope navigation through the gastrointestinal tract could benefit from segmentations of multiple gastrointestinal and surrounding organs. Many previous studies have proposed methods for multi-organ segmentation of abdominal CT, principally based on multi-atlas segmentation [16,9,14,13,12] or statistical shape models [2,9]. Organs surrounding the GI tract, such as the liver and pancreas, are included in many of these studies, but esophagus and stomach segmentation has received little attention, likely due to the lack of available reference segmentations.…”

Section: Discussionmentioning

confidence: 99%

“…Multi-organ segmentation has been the subject of extensive study. The most common approaches, statistical shape models [2,9] and multi-atlas label fusion [16,9,14,13,12], rely on registration to establish anatomical correspondence. However, interpatient image registration is less accurate for abdominal imaging than for other anatomical sites (e.g.…”

Section: Introductionmentioning

confidence: 99%

Towards Image-Guided Pancreas and Biliary Endoscopy: Automatic Multi-organ Segmentation on Abdominal CT with Dense Dilated Networks

Gibson

Giganti

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Segmentation of anatomy on abdominal CT enables patientspecific image guidance in clinical endoscopic procedures and in endoscopy training. Because robust interpatient registration of abdominal images is necessary for existing multi-atlas-and statistical-shape-modelbased segmentations, but remains challenging, there is a need for automated multi-organ segmentation that does not rely on registration. We present a deep-learning-based algorithm for segmenting the liver, pancreas, stomach, and esophagus using dilated convolution units with dense skip connections and a new spatial prior. The algorithm was evaluated with an 8-fold cross-validation and compared to a joint-label-fusionbased segmentation based on Dice scores and boundary distances. The proposed algorithm yielded more accurate segmentations than the jointlabel-fusion-based algorithm for the pancreas (median Dice scores 66 vs 37), stomach (83 vs 72) and esophagus (73 vs 54) and marginally less accurate segmentation for the liver (92 vs 93). We conclude that dilated convolutional networks with dense skip connections can segment the liver, pancreas, stomach and esophagus from abdominal CT without image registration and have the potential to support image-guided navigation in gastrointestinal endoscopy procedures.

show abstract

“…GlM► Akhoundi- Asl and Soltanian-Zadeh, 2007;Bossa and Olmos, 2006;Bossa and Olmos, 2007;Bossa et al, 2011;Cootes et al, 1994;Duta and Sonka, 1998;Gorczowski et al, 2010;Poupon et al, 1998;Styner et al, 2006;InM► Akhoundi-Asl and Soltanian-Zadeh, 2007;Asl and Soltanian-Zadeh, 2008;CoDeM► Bazin and Pham, 2006;Fan et al, 2008a;Fan et al, 2008b;Gao et al, 2011;Gao et al, 2017;Han and Prince, 2003;Han et al, 2002;Ho and Shi, 2004;Holtzman-Gazit et al, 2003;Jeon et al, 2005;Kim et al, 2014;Litvin and Karl, 2005;MacDonald et al, 1994;Mangin et al, 1995;Merino-Caviedes et al, 2010;Pohl et al, 2007;Samson et al, 2000;Tsai et al, 2001;Uzunbas et al, 2010;Vese and Chan, 2002;Yan et al, 2009;Yang et al, 2004;Zeng et al, 1999;MuLeM► Cerrolaza et al, 2011;Cerrolaza et al, 2012;Cerrolaza et al, 2014;Cerrolaza et al, 2015;Cerrolaza et al, 2016;Joohwi Leea, Sun Hyung Kimb, 2016;Shen et al, 2001;…”

Section: Brainmentioning

confidence: 99%

Computational anatomy for multi-organ analysis in medical imaging: A review

Cerrolaza

Picazo

Humbert³

et al. 2019

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

The medical image analysis field has traditionally been focused on the development of organ-, and disease-specific methods. Recently, the interest in the development of more comprehensive computational anatomical models has grown, leading to the creation of multi-organ models. Multi-organ approaches, unlike traditional organ-specific strategies, incorporate inter-organ relations into the model, thus leading to a more accurate representation of the complex human anatomy. Inter-organ relations are not only spatial, but also functional and physiological. Over the years, the strategies proposed to efficiently model multi-organ structures have evolved from the simple global modeling, to more sophisticated approaches such as sequential, hierarchical, or machine learning-based models. In this paper, we present a review of the state of the art on multi-organ analysis and associated computation anatomy methodology. The manuscript follows a methodology-based classification of the different techniques available for the analysis of multi-organs and multi-anatomical structures, from techniques using point distribution models to the most recent deep learning-based approaches. With more than 300 papers included in this review, we reflect on the trends and challenges of the field of computational anatomy, the particularities of each anatomical region, and the potential of multi-organ analysis to increase the impact of medical imaging applications on the future of healthcare.

show abstract

Automatic multi-resolution shape modeling of multi-organ structures

Cited by 49 publications

References 36 publications

An application of cascaded 3D fully convolutional networks for medical image segmentation

An application of cascaded 3D fully convolutional networks for medical image segmentation

Towards Image-Guided Pancreas and Biliary Endoscopy: Automatic Multi-organ Segmentation on Abdominal CT with Dense Dilated Networks

Computational anatomy for multi-organ analysis in medical imaging: A review

Contact Info

Product

Resources

About