Deep Q Learning Driven CT Pancreas Segmentation With Geometry-Aware U-Net

Man, Yunze; Huang, Yangsibo; Feng, Junyi; Li, Xi; Wu, Fei

doi:10.1109/tmi.2019.2911588

Cited by 133 publications

(71 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of time requirements, the average time for delineation of a case, including the data pre-processing and post-processing great application potential in disease diagnosis, [44][45][46][47] lesion recognition, [48][49][50][51][52] and image segmentation. 28,[52][53][54] Especially in image segmentation, accuracy has always been the focus of attention. Most previous studies developed several superior models to improve the accuracy of auto-segmentation, and some studies compared the accuracy of different auto-segmentation models.…”

Section: Resultsmentioning

confidence: 99%

Evaluation of deep learning‐based auto‐segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients

Zhi

Chang

Zhao

et al. 2020

J Applied Clin Med Phys

View full text Add to dashboard Cite

Objective: To evaluate the accuracy of a deep learning-based auto-segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician. Methods: This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral-head-left, and femoral-head-right. Results: The DSC values of the auto-segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral-head-right (P < 0.05), 0.88 and 0.84 for the femoral-head-left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral-head-right (P > 0.05), 6.17 and 6.31 for the femoral-head-left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto-segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task. Conclusion: The auto-segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto-segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Evaluation of deep learning‐based auto‐segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients

Zhi

Chang

Zhao

et al. 2020

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…The value range of Dice and Jaccard is [0, 1], and the closer the value is to 1, the better the segmentation result. 34,35 The calculation formulas of Dice and Jaccard are (4) and (5):…”

Section: B Quantitative Assessment Metricsmentioning

confidence: 99%

MAD‐UNet: A deep U‐shaped network combined with an attention mechanism for pancreas segmentation in CT images

Qin

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose Pancreas segmentation is a difficult task because of the high intrapatient variability in the shape, size, and location of the organ, as well as the low contrast and small footprint of the CT scan. At present, the U‐Net model is likely to lead to the problems of intraclass inconsistency and interclass indistinction in pancreas segmentation. To solve this problem, we improved the contextual and semantic feature information acquisition method of the biomedical image segmentation model (U‐Net) based on a convolutional network and proposed an improved segmentation model called the multiscale attention dense residual U‐shaped network (MAD‐UNet). Methods There are two aspects considered in this method. First, we adopted dense residual blocks and weighted binary cross‐entropy to enhance the semantic features to learn the details of the pancreas. Using such an approach can reduce the effects of intraclass inconsistency. Second, we used an attention mechanism and multiscale convolution to enrich the contextual information and suppress learning in unrelated areas. We let the model be more sensitive to pancreatic marginal information and reduced the impact of interclass indistinction. Results We evaluated our model using fourfold cross‐validation on 82 abdominal enhanced three‐dimensional (3D) CT scans from the National Institutes of Health (NIH‐82) and 281 3D CT scans from the 2018 MICCAI segmentation decathlon challenge (MSD). The experimental results showed that our method achieved state‐of‐the‐art performance on the two pancreatic datasets. The mean Dice coefficients were 86.10% ± 3.52% and 88.50% ± 3.70%. Conclusions Our model can effectively solve the problems of intraclass inconsistency and interclass indistinction in the segmentation of the pancreas, and it has value in clinical application. Code is available at https://github.com/Mrqins/pancreas-segmentation.

show abstract

“…Encoders with limited receptive fields or small kernels may not be suitable for representing semantic pixels. Therefore, convolution operations in a fully convolutional neural network are replaced with dilated convolutions [7] or deformable ones [41], and large kernels in a global convolutional network simultaneously localise and classify pixels [29, 42, 43]. However, encoders with small kernels might be faster for dense pixel classification.…”

Section: Related Workmentioning

confidence: 99%

“…Global information and local details can be independently processed. For instance, regions of pancreas are localised with a deep Q network and then segmented with a deformable U‐net [41]; shape details of target regions are recovered with saliency transformation modules and refined recurrently with a finer‐scaled network [66]; cell‐level architecture search spaces and network‐level ones are used to optimise the semantic segmentation architecture [27].…”

Section: Related Workmentioning

confidence: 99%