Development of a Deep Learning Model to Identify Lymph Node Metastasis on Magnetic Resonance Imaging in Patients With Cervical Cancer

Wu, Qingxia; Wang, Shuo; Zhang, Shuixing; Wang, Meiyun; Ding, Yingying; Jin, Fang; Qian, Wei; Liu, Zhenyu; Sun, Kai; Jin, Yan; Ma, He; Tian, Jie

doi:10.1001/jamanetworkopen.2020.11625

Cited by 66 publications

(52 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning involves the implementation of a pre-trained network that is further fine-tuned with samples specific to a desired task. Transfer learning has been explored for prediction of lymph node metastasis in patients with cervical cancer using MRI (AUC: 0.9) and breast cancer using CT (AUC: 0.8) with promising results [ 41 , 42 ]. In this work, we used a pretrained VGG model that was originally optimized to classify 1000 types of objects.…”

Section: Discussionmentioning

confidence: 99%

Preoperative prediction of lymph node metastasis using deep learning-based features

Cattell

Ying

Lan

et al. 2022

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

Lymph node involvement increases the risk of breast cancer recurrence. An accurate non-invasive assessment of nodal involvement is valuable in cancer staging, surgical risk, and cost savings. Radiomics has been proposed to pre-operatively predict sentinel lymph node (SLN) status; however, radiomic models are known to be sensitive to acquisition parameters. The purpose of this study was to develop a prediction model for preoperative prediction of SLN metastasis using deep learning-based (DLB) features and compare its predictive performance to state-of-the-art radiomics. Specifically, this study aimed to compare the generalizability of radiomics vs DLB features in an independent test set with dissimilar resolution. Dynamic contrast-enhancement images from 198 patients (67 positive SLNs) were used in this study. Of these subjects, 163 had an in-plane resolution of 0.7 × 0.7 mm2, which were randomly divided into a training set (approximately 67%) and a validation set (approximately 33%). The remaining 35 subjects with a different in-plane resolution (0.78 × 0.78 mm2) were treated as independent testing set for generalizability. Two methods were employed: (1) conventional radiomics (CR), and (2) DLB features which replaced hand-curated features with pre-trained VGG-16 features. The threshold determined using the training set was applied to the independent validation and testing dataset. Same feature reduction, feature selection, model creation procedures were used for both approaches. In the validation set (same resolution as training), the DLB model outperformed the CR model (accuracy 83% vs 80%). Furthermore, in the independent testing set of the dissimilar resolution, the DLB model performed markedly better than the CR model (accuracy 77% vs 71%). The predictive performance of the DLB model outperformed the CR model for this task. More interestingly, these improvements were seen particularly in the independent testing set of dissimilar resolution. This could indicate that DLB features can ultimately result in a more generalizable model.

show abstract

Section: Discussionmentioning

confidence: 99%

Preoperative prediction of lymph node metastasis using deep learning-based features

Cattell

Ying

Lan

et al. 2022

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

show abstract

“…Several CNNs using MRI have been constructed for the diagnosis of uterine tumors to date (19,20). (22), and T2WI + CE-T1WI (23).…”

Section: Discussionmentioning

confidence: 99%

The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: A comparison with radiologists

Urushibara

Mori

Ishiguro

et al. 2022

Preprint

View full text Add to dashboard Cite

Purpose: To compare the diagnostic performance of deep learning models using convolutional neural networks (CNN) with that of radiologists in diagnosing endometrial cancer and to verify suitable imaging conditions. Methods: This retrospective study included patients with endometrial cancer or non-cancerous lesions who underwent MRI between 2015 and 2020. In Experiment 1, single and combined image sets of several sequences from 204 patients with cancer and 184 patients with non-cancerous lesions were used to train CNNs. Subsequently, testing was performed using 97 images from 51 patients with cancer and 46 patients with non-cancerous lesions. The test image sets were independently interpreted by three blinded radiologists. Experiment 2 investigated whether the addition of different types of images for training using single image sets improved the diagnostic performance of CNNs. Results: The AUC of the CNNs pertaining to single and combined image sets were 0.88–0.95 and 0.87-0.93, respectively, indicating better or equivalent diagnostic performance than the radiologists. The AUC of the CNNs trained with the addition of other types of images was 0.88–0.95. Conclusion: CNNs demonstrated high diagnostic performance for the diagnosis of endometrial cancer using MRI. Although there were no significant differences, adding other types of images improved the diagnostic performance for some image sets.

show abstract

“…Furthermore, it was also reported that LNM was not only closely associated with prognosis but also with treatment planning. Patients with LNM may benefit from chemoradiotherapy rather than surgery as their first choice ( Wu et al, 2020 ). Therefore, the diagnosis of LNM in cervical cancer is critical for guiding individualized treatment and avoiding unnecessary surgical intervention.…”

Section: Discussionmentioning

confidence: 99%

Integrated Profiles Analysis Identified a Coding-Non-Coding Signature for Predicting Lymph Node Metastasis and Prognosis in Cervical Cancer

Sun

Song

Yang

et al. 2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Accumulating evidence has shown that lymph node metastasis (LNM) is not only an important prognostic factor but also an indicator of the need for postoperative chemoradiotherapy. Therefore, identifying risk factors or molecular markers related to LNM is critical for predicting the prognosis and guiding individualized treatment of patients with cervical cancer. In this study, we used the machine learning-based feature selection approach to identify eight optimal biomarkers from the list of 250 differentially expressed protein-coding genes and long non-coding RNAs (lncRNAs) in the TCGA cohort. Then a coding-non-coding signature (named CNC8SIG) was developed using the elastic-net logistic regression approach based on the expression levels of eight optimal biomarkers, which is useful in discriminating patients with LNM from those without LNM in the discovery cohort. The predictive performance of the CNC8SIG was further validated in two independent patient cohorts. Moreover, the CNC8SIG was significantly associated with patient’s survival in different patient cohorts. In silico functional analysis suggested that the CNC8SIG-associated mRNAs are enriched in known cancer-related biological pathways such as the Wnt signaling pathway, the Ras signaling pathway, Rap1 signaling pathway, and PI3K-Akt signaling pathway.

show abstract

Development of a Deep Learning Model to Identify Lymph Node Metastasis on Magnetic Resonance Imaging in Patients With Cervical Cancer

Cited by 66 publications

References 51 publications

Preoperative prediction of lymph node metastasis using deep learning-based features

Preoperative prediction of lymph node metastasis using deep learning-based features

The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: A comparison with radiologists

Integrated Profiles Analysis Identified a Coding-Non-Coding Signature for Predicting Lymph Node Metastasis and Prognosis in Cervical Cancer

Contact Info

Product

Resources

About