An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

Liu, Zhikai; Chen, Wanqi; Guan, Hui; Zhen, Hongnan; Shen, Jing; Liu, Xia; Liu, An; Li, Richard; Geng, Jie; You, Jie; Wang, Weihu; Li, Zhouyu; Zhang, Yongfeng; Chen, Yuanyuan; Du, Junjie; Chen, Qi; Chen, Yu; Wang, Shaobin; Zhang, Fuquan; Qin, Jie

doi:10.3389/fonc.2021.702270

Cited by 12 publications

(16 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we have to focus on the robustness of U-net, once, deep learning was considered by clinicians to be a "black box algorithm" because of the uncertainty of its results [44]. Nowadays, the same excellent results (DSC > 0.8) have been achieved in several internal and external tests and even in multi-center blinded randomized controlled tests [5,9,24]. Moreover, we also noticed that the U-net achieved good segmentation results in glioma [18], head and neck tumors [19], prostate cancer [45], and breast cancer [46].…”

Section: Discussionmentioning

confidence: 99%

“…For a physician, it often takes half an hour to delineate the CTV, while for DLs it takes only 15 s to 2 min to complete [ 4 , 6 , 7 , 22 ]. The results of the evaluation of the metrics show that the current performance of deep learning segmentation of cervical cancer CTV and OARs can achieve good results (DSC > 0.8), and oncologists also say that the results of segmentation by DLs can be used directly or with minor modifications in clinical RT [ 5 , 6 , 8 , 23 , 24 ]. Therefore, with computer assistance, it will provide great convenience and optimize the work of clinical radiotherapy.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning in CT image segmentation of cervical cancer: a systematic review and meta-analysis

et al. 2022

View full text Add to dashboard Cite

Background This paper attempts to conduct a systematic review and meta-analysis of deep learning (DLs) models for cervical cancer CT image segmentation. Methods Relevant studies were systematically searched in PubMed, Embase, The Cochrane Library, and Web of science. The literature on DLs for cervical cancer CT image segmentation were included, a meta-analysis was performed on the dice similarity coefficient (DSC) of the segmentation results of the included DLs models. We also did subgroup analyses according to the size of the sample, type of segmentation (i.e., two dimensions and three dimensions), and three organs at risk (i.e., bladder, rectum, and femur). This study was registered in PROSPERO prior to initiation (CRD42022307071). Results A total of 1893 articles were retrieved and 14 articles were included in the meta-analysis. The pooled effect of DSC score of clinical target volume (CTV), bladder, rectum, femoral head were 0.86(95%CI 0.84 to 0.87), 0.91(95%CI 0.89 to 0.93), 0.83(95%CI 0.79 to 0.88), and 0.92(95%CI 0.91to 0.94), respectively. For the performance of segmented CTV by two dimensions (2D) and three dimensions (3D) model, the DSC score value for 2D model was 0.87 (95%CI 0.85 to 0.90), while the DSC score for 3D model was 0.85 (95%CI 0.82 to 0.87). As for the effect of the capacity of sample on segmentation performance, no matter whether the sample size is divided into two groups: greater than 100 and less than 100, or greater than 150 and less than 150, the results show no difference (P > 0.05). Four papers reported the time for segmentation from 15 s to 2 min. Conclusion DLs have good accuracy in automatic segmentation of CT images of cervical cancer with a less time consuming and have good prospects for future radiotherapy applications, but still need public high-quality databases and large-scale research verification.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep learning in CT image segmentation of cervical cancer: a systematic review and meta-analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Image segmentation is a key step in the radiation therapy (RT) workflow since precise delineation of the region of interest (ROI) will improve local tumor control and reduce the incidence of side effects in the surrounding normal tissues 1–3 . Automatic segmentation approaches based on deep learning (DL) have been proven to be time‐saving and to improve consistency among oncologists, and thus greatly shorten the turnaround time of patients 4–7 . Recently, a lightweight DL framework was developed by using a large‐scale dataset of 28 581 cases.…”

Section: Introductionmentioning

confidence: 99%

“…[1][2][3] Automatic segmentation approaches based on deep learning (DL) have been proven to be time-saving and to improve consistency among oncologists, and thus greatly shorten the turnaround time of patients. [4][5][6][7] Recently, a lightweight DL framework was developed by using a large-scale dataset of 28 581 cases.Superior accuracy with an average Dice of 0.95 was achieved on 67 delineation tasks and real-time delineation in whole-body organs at risk (OARs) and tumors was less than 2 s. 8 Despite the great promise of this technique, it is still necessary to evaluate its geometric accuracy before implementing it in clinical applications. [9][10][11] Generally, two main categories of evaluation metrics (region-based and boundary-based) were used for assessment of the goodness and usefulness of automatic delineation.…”

Section: Introductionmentioning

confidence: 99%

Geometric and dosimetric evaluation of deep learning based auto‐segmentation for clinical target volume on breast cancer

Yang

Guo

Fang

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background: Recently, target auto-segmentation techniques based on deep learning (DL) have shown promising results. However, inaccurate target delineation will directly affect the treatment planning dose distribution and the effect of subsequent radiotherapy work. Evaluation based on geometric metrics alone may not be sufficient for target delineation accuracy assessment. The purpose of this paper is to validate the performance of automatic segmentation with dosimetric metrics and try to construct new evaluation geometric metrics to comprehensively understand the dose-response relationship from the perspective of clinical application. Materials and Methods: A DL-based target segmentation model was developed by using 186 manual delineation modified radical mastectomy breast cancer cases. The resulting DL model were used to generate alternative target contours in a new set of 48 patients. The Auto-plan was reoptimized to ensure the same optimized parameters as the reference Manual-plan. To assess the dosimetric impact of target auto-segmentation,not only common geometric metrics but also new spatial parameters with distance and relative volume (R V ) to target were used. Correlations were performed using Spearman's correlation between segmentation evaluation metrics and dosimetric changes. Results: Only strong (|R 2 | > 0.6, p < 0.01) or moderate (|R 2 | > 0.4, p < 0.01) Pearson correlation was established between the traditional geometric metric and three dosimetric evaluation indices to target (conformity index,homogeneity index, and mean dose). For organs at risk (OARs), inferior or no significant relationship was found between geometric parameters and dosimetric differences. Furthermore, we found that OARs dose distribution was affected by boundary error of target segmentation instead of distance and R V to target. Conclusions: Current geometric metrics could reflect a certain degree of dose effect of target variation. To find target contour variations that do lead to OARs dosimetry changes, clinically oriented metrics that more accurately reflect how segmentation quality affects dosimetry should be constructed.

show abstract

“…DL-based networks were open-source, which were developed in many researches [11][12][13]. In addition, the cervical cancer automatic delineation DL models studies did not have external validation [10][11][12][13] and only few researches had clinical evaluation [9]. The generalization and robustness of the DL models are still unclear and the clinical applicability is also unknown.…”

Section: Introductionmentioning

confidence: 99%

Feasibility of clinical target volume (CTV) automatic delineation using deep learning network for cervical cancer radiotherapy: a study with external validation

Wu,

Liu,

Pang

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose To explore the accuracy and feasibility of a proposed deep learning (DL) algorithm for clinical target volume (CTV) delineation in cervical cancer radiotherapy and evaluate whether it can perform well to external cervical cancer and endometrial cancer cases for generalization validation. Materials and methods A total of 332 patients were enrolled in this study. A state-of-the-art network called AttResCNet, which adopted Resnet50 based on a channel and spatial attention as backbone was proposed. 236 cervical cancer cases were randomly grouped into training (n = 189) and internal validation (n = 47) cohorts. External validations were performed in a separate cohort of 54 cervical cancer and 42 endometrial cancer cases. The performances of the proposed network were evaluated by dice similarity coefficient (DSC), sensitivity (SEN), positive predictive value (PPV), 95% Hausdorff distance (95HD) and oncologist clinical score when comparing them with manual delineation in validation cohorts. Results In internal validation cohorts, the DSC, SEN, PPV, 95HD for AttResCNet achieved 0.775, 0.796, 0.740, 10.156 mm. In external independent validation cohorts, AttResCNet achieved 0.765, 0.805, 0.729, 12.075 mm for cervical cancer cases and 0.766, 0.803, 0.738, 11.527 mm for endometrial cancer cases, respectively. The clinical assessment score showed that minor and no revisions (delineation time was shortened to within 30 minutes) accounted for about 85% of all cases in DL-aided automatic delineation. Conclusions We demonstrated the problem of model generalizability for DL-based automatic delineation. The proposed network can improve the performance at automatic delineation for cervical cancer and shorten manual delineation time at no expense of quality. The network showed excellent clinical viability, which can also be even generalized for endometrial cancer with excellent performance.

show abstract

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

Cited by 12 publications

References 42 publications

Deep learning in CT image segmentation of cervical cancer: a systematic review and meta-analysis

Deep learning in CT image segmentation of cervical cancer: a systematic review and meta-analysis

Geometric and dosimetric evaluation of deep learning based auto‐segmentation for clinical target volume on breast cancer

Feasibility of clinical target volume (CTV) automatic delineation using deep learning network for cervical cancer radiotherapy: a study with external validation

Contact Info

Product

Resources

About