English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Manual or automatic delineation of the esophageal tumor in CT images is knownto be very challenging. This is due to the low contrast between the tumor andadjacent tissues, the anatomical variation of the esophagus, as well as theoccasional presence of foreign bodies (e.g. feeding tubes). Physicianstherefore usually exploit additional knowledge such as endoscopic findings,clinical history, additional imaging modalities like PET scans. Achieving hisadditional information is time-consuming, while the results are error-prone andmight lead to non-deterministic results. In this paper we aim to investigate ifand to what extent a simplified clinical workflow based on CT alone, allows oneto automatically segment the esophageal tumor with sufficient quality. For thispurpose, we present a fully automatic end-to-end esophageal tumor segmentationmethod based on convolutional neural networks (CNNs). The proposed network,called Dilated Dense Attention Unet (DDAUnet), leverages spatial and channelattention gates in each dense block to selectively concentrate on determinantfeature maps and regions. Dilated convolutional layers are used to manage GPUmemory and increase the network receptive field. We collected a dataset of 792scans from 288 distinct patients including varying anatomies with \mbox{airpockets}, feeding tubes and proximal tumors. Repeatability and reproducibilitystudies were conducted for three distinct splits of training and validationsets. The proposed network achieved a $\mathrm{DSC}$ value of $0.79 \pm 0.20$,a mean surface distance of $5.4 \pm 20.2mm$ and $95\%$ Hausdorff distance of$14.7 \pm 25.0mm$ for 287 test scans, demonstrating promising results with asimplified clinical workflow based on CT alone. Our code is publicly availablevia \url{https://github.com/yousefis/DenseUnet_Esophagus_Segmentation}.

Esophageal Tumor Segmentation in CT Images using Dilated Dense Attention Unet (DDAUnet)