Print Email Facebook Twitter Esophageal Tumor Segmentation in CT Images using a Dilated Dense Attention Unet (DDAUnet) Title Esophageal Tumor Segmentation in CT Images using a Dilated Dense Attention Unet (DDAUnet) Author Yousefi, Sahar (Leiden University Medical Center) Sokooti, Hessam (Leiden University Medical Center) Elmahdy, Mohamed S. (Leiden University Medical Center) Lips, Irene M. (Leiden University Medical Center) Shalmani, Mohammad T.Manzuri (Sharif University of Technology) Zinkstok, Roel T. (Leiden University Medical Center) Dankers, Frank J.W.M. (Leiden University Medical Center) Staring, M. (TU Delft Pattern Recognition and Bioinformatics; Leiden University Medical Center) Date 2021 Abstract Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presence of foreign bodies (e.g. feeding tubes). Physicians therefore usually exploit additional knowledge such as endoscopic findings, clinical history, additional imaging modalities like PET scans. Achieving his additional information is time-consuming, while the results are error-prone and might lead to non-deterministic results. In this paper we aim to investigate if and to what extent a simplified clinical workflow based on CT alone, allows one to automatically segment the esophageal tumor with sufficient quality. For this purpose, we present a fully automatic end-to-end esophageal tumor segmentation method based on convolutional neural networks (CNNs). The proposed network, called Dilated Dense Attention Unet (DDAUnet), leverages spatial and channel attention gates in each dense block to selectively concentrate on determinant feature maps and regions. Dilated convolutional layers are used to manage GPU memory and increase the network receptive field. We collected a dataset of 792 scans from 288 distinct patients including varying anatomies with air pockets, feeding tubes and proximal tumors. Repeatability and reproducibility studies were conducted for three distinct splits of training and validation sets. The proposed network achieved a DSC value of 0.79 ± 0.20, a mean surface distance of 5.4 ± 20.2mm and 95% Hausdorff distance of 14.7 ± 25.0mm for 287 test scans, demonstrating promising results with a simplified clinical workflow based on CT alone. Our code is publicly available via https://github.com/yousefis/DenseUnet_Esophagus_Segmentation. Subject attention gateComputed tomographyCT imagesdensely connected patterndilated convolutional layerEsophageal tumor segmentationEsophagusImage segmentationShapeThree-dimensional displaysTrainingTumorsUNet To reference this document use: http://resolver.tudelft.nl/uuid:dbedfd1f-f9bb-4716-aeaf-005f40d0d904 DOI https://doi.org/10.1109/ACCESS.2021.3096270 ISSN 2169-3536 Source IEEE Access, 9, 99235-99248 Part of collection Institutional Repository Document type journal article Rights © 2021 Sahar Yousefi, Hessam Sokooti, Mohamed S. Elmahdy, Irene M. Lips, Mohammad T.Manzuri Shalmani, Roel T. Zinkstok, Frank J.W.M. Dankers, M. Staring Files PDF Esophageal_Tumor_Segmenta ... DAUnet.pdf 7.54 MB Close viewer /islandora/object/uuid:dbedfd1f-f9bb-4716-aeaf-005f40d0d904/datastream/OBJ/view