Automatic Multi-organ Segmentation on Abdominal CT with Dense V-networks

By Eli Gibson, F. Giganti, Yipeng Hu, E. Bonmati, S. Bandula, K. Gurusamy, B. Davidson, S. Pereira, Matthew J. Clarkson, Dean C. Barratt. IEEE Transactions on Medical Imaging, 2018

662 citations recorded by the source corpus.

Automatic segmentation of abdominal anatomy on computed tomography (CT) images can support diagnosis, treatment planning, and treatment delivery workflows. Segmentation methods using statistical models and multi-atlas label fusion (MALF) require inter-subject image registrations, which are challenging for abdominal images, but alternative methods without registration have not yet achieved higher accuracy for most abdominal organs. We present a registration-free deep-learning-based segmentation algorithm for eight organs that are relevant for navigation in endoscopic pancreatic and biliary procedures, including the pancreas, the gastrointestinal tract (esophagus, stomach, and duodenum) and surrounding organs (liver, spleen, left kidney, and gallbladder). We directly compared the segmentation accuracy of the proposed method to the existing deep learning and MALF methods in a cross-validation on a multi-centre data set with 90 subjects. The proposed method yielded significantly higher Dice scores for all organs and lower mean absolute distances for most organs, including Dice scores of 0.78 versus 0.71, 0.74, and 0.74 for the pancreas, 0.90 versus 0.85, 0.87, and 0.83 for the stomach, and 0.76 versus 0.68, 0.69, and 0.66 for the esophagus. We conclude that the deep-learning-based segmentation represents a registration-free method for multi-organ abdominal CT segmentation whose accuracy can surpass current methods, potentially supporting image-guided navigation in gastrointestinal endoscopy procedures.

Subfields: Computer Vision and Pattern Recognition, Oncology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/e77d17d21941ed10adf14800d4a28bbd0f7c6eca

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Oncology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges (2019, methodology): “V-Net has been used in [26] with a larger receptive field (covers 50–100% of the input image) and multi-scale (four different resolutions) and delivered up to 12% higher Dice coefficient compared to original V-Net.”
UNETR: Transformers for 3D Medical Image Segmentation (2021, methodology): “CNN-based Segmentation Networks : Since the introduction of the seminal U-Net [36], CNN-based networks have achieved state-of-the-art results on various 2D and 3D various medical image segmentation tasks [15, 54, 49, 17, 28].”
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation (2020, methodology): “The dataset we use is a multi-organ re-annotated version from [19], combining two public datasets - The Cancer Image Archive (TCIA) Pancreas-CT data set [50] and Beyond the Cranial Vault (BTCV) Abdomen data set [34].”
Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis (2019, background): “arning Capability Initialization NCS (Dice %) LCS (Dice %) BMS (Dice %) Models Genesis (ours) 75.86 0.90 91.13 1.51 92.58 0.30 NiftyNet scratch [7] 69.65 2.56 91.09 0.76 90.68 0.24 NiftyNet model zoo [6] 69.24 1.77 90.84 0.63 90.65 0.54 p-value: 0.3433 0.2214 0.4301 :These p-values are calculated be”
UNETR++: Delving Into Efficient and Accurate 3D Medical Image Segmentation (2022, background): “In the case of 3D medical image segmentation [8,10,11,25, 31], the full volumetric image is typically processed as a sequence of 2D slices.”
CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, positive): “[49] introduced dense connection in each encoder”
AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation (2022, methodology): “With the development of related datasets [1, 11, 12, 5, 15], significant progress has been made in this area.”
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (2020, methodology): “Multi-organ Abdominal CT Reference Standard Segmentation(14) [53] 8 organs 90 2 Zenodo 2018”