Deep learning radiomic nomogram to predict recurrence in soft tissue sarcoma: a multi-institutional study

Liu, Shunli; Sun, Wei; Yang, Shifeng; Duan, Lisha; Huang, Chencui; Xu, Jingxu; Hou, Feng; Hao, Dapeng; Yu, Tengbo; Wang, Hexiang

doi:10.1007/s00330-021-08221-0

Cited by 27 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning model with CNN can learn the features of CT images from low to high dimensions and their correlation ( Yamashita et al, 2018 ), which may be the key reason for high performance in image analysis. Since most previous CT image based prognostic research have only used pretrained deep learning to extract images features, subsequent analysis required subjective screening of these features to build the machine learning model again ( Huang et al, 2020 ; Park et al, 2021 ; Liu et al, 2022 ). Besides, they did not consider the special characteristics of medical images which mean generic pretrained deep learning models were not suitable.…”

Section: Discussionmentioning

confidence: 99%

“…Deep learning, one kind of machine learning based on artificial neural networks, has a powerful ability in image analysis ( LeCun et al, 2015 ) with convolutional neural networks (CNNs). A few studies based on deep learning have proved its effectiveness in tumor assessment like lymph node status prediction ( Zheng et al, 2020 ) and tumor recurrence prediction ( Liu et al, 2022 ). Though with high prediction accuracy, deep learning is known as a black box as lacks the interpretation for its prediction, which makes it hard to be accepted by doctors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Size Deep Learning Based Preoperative Computed Tomography Signature for Prognosis Prediction of Colorectal Cancer

Cai

Zhong

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

Background: Preoperative and postoperative evaluation of colorectal cancer (CRC) patients is crucial for subsequent treatment guidance. Our study aims to provide a timely and rapid assessment of the prognosis of CRC patients with deep learning according to non-invasive preoperative computed tomography (CT) and explore the underlying biological explanations.Methods: A total of 808 CRC patients with preoperative CT (development cohort: n = 426, validation cohort: n = 382) were enrolled in our study. We proposed a novel end-to-end Multi-Size Convolutional Neural Network (MSCNN) to predict the risk of CRC recurrence with CT images (CT signature). The prognostic performance of CT signature was evaluated by Kaplan-Meier curve. An integrated nomogram was constructed to improve the clinical utility of CT signature by combining with other clinicopathologic factors. Further visualization and correlation analysis for CT deep features with paired gene expression profiles were performed to reveal the molecular characteristics of CRC tumors learned by MSCNN in radiographic imaging.Results: The Kaplan-Meier analysis showed that CT signature was a significant prognostic factor for CRC disease-free survival (DFS) prediction [development cohort: hazard ratio (HR): 50.7, 95% CI: 28.4–90.6, p < 0.001; validation cohort: HR: 2.04, 95% CI: 1.44–2.89, p < 0.001]. Multivariable analysis confirmed the independence prognostic value of CT signature (development cohort: HR: 30.7, 95% CI: 19.8–69.3, p < 0.001; validation cohort: HR: 1.83, 95% CI: 1.19–2.83, p = 0.006). Dimension reduction and visualization of CT deep features demonstrated a high correlation with the prognosis of CRC patients. Functional pathway analysis further indicated that CRC patients with high CT signature presented down-regulation of several immunology pathways. Correlation analysis found that CT deep features were mainly associated with activation of metabolic and proliferative pathways.Conclusions: Our deep learning based preoperative CT signature can effectively predict prognosis of CRC patients. Integration analysis of multi-omic data revealed that some molecular characteristics of CRC tumor can be captured by deep learning in CT images.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-Size Deep Learning Based Preoperative Computed Tomography Signature for Prognosis Prediction of Colorectal Cancer

Cai

Zhong

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…Radiomics relies on algorithm‐based automated data characterization to extract large amounts of image features from radiographic images 12,13 . In recent years, 14–16 radiomics methods have been used to identify benign and malignant soft tissue tumors, distinguish middle and high‐grade sarcomas 17 and predict recurrence or metastasis of the soft tissue sarcomas 18,19 …”

Section: Introductionmentioning

confidence: 99%

Differentiation Between Lipomas and Atypical Lipomatous Tumors of the Extremities Using Radiomics

Tang

Cui

Zhu

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background The differentiation of soft tissue lipomas from atypical lipoma tumors (ALTs) of the extremities is important because of the distinction of the cytogenetic profiles and the treatment decisions. Purpose To investigate a radiomics method to differentiate between lipomas and ALTs of the extremities. Study Type Retrospective. Population Imaging data of 122 patients including 90 cases of lipomas and 32 cases of ALTs. Field Strength/Sequence Axial T1‐weighted imaging and fat suppressed T2‐weighted imaging at 3.0T MRI. Assessment Analysis of variance and the least absolute shrinkage and selection operator methods were used for feature selection and the random forest method was used to build three radiomics models based on T1WI, FS T2WI, and their combination (T1&T2WI). Three independent radiologists classified the tumors based on the subjective assessments. Statistical Tests The area under the curve (AUC) of the receiver operating characteristic curve, accuracy, F1‐score, specificity, and sensitivity were employed. The differences of the classifiers and discriminating ability of the radiologists and the radiomics model were compared by Delong test. A P value <0.05 was considered significant. Kappa test was used to determine the inter‐reader agreements between the radiologists. Result The AUCs were 0.952 (95% confidence interval [CI]: 0.785–0.998), 0.944 (95% CI: 0.774–0.997), and 0.968 (95% CI: 0.809–1) for T1WI, FS T2WI, and T1&T2WI models in testing sets respectively. Delong test showed there were no significant difference between the different radiomics models (P > 0.05). The AUCs of the radiologists were 0.893 (95% CI: 0.824–0.942), 0.831 (95% CI: 0.752–0.893), and 0.893 (95% CI: 0.824–0.94), respectively. There were significant difference between radiomics model and radiologists' model in the training and entire cohorts (P < 0.05) while there were no significant difference in the testing sets (P > 0.05). Data Conclusion Radiomics has the potential to distinguish between lipomas and ALTs of the extremities and their discrimination ability is no weaker than the senor radiologists. Level of Evidence 3 Technical Efficacy Stage 2

show abstract

“…Radiomics extracts numerous and quantitative information from medical images, including CT, MRI and PET, with high throughput to facilitate clinical decision-making [ 9 ]. The goals of radiomics are to improve decision support and reliability of prediction inexpensively and non-invasively [ 10 ]. Non-invasiveness is very crucial for pediatric patients.…”

Section: Introductionmentioning

confidence: 99%

Clinical parameters combined with radiomics features of PET/CT can predict recurrence in patients with high-risk pediatric neuroblastoma

et al. 2022

View full text Add to dashboard Cite

Background This retrospective study aimed to develop and validate a combined model based [18F]FDG PET/CT radiomics and clinical parameters for predicting recurrence in high-risk pediatric neuroblastoma patients. Methods Eighty-four high-risk neuroblastoma patients were retrospectively enrolled and divided into training and test sets according to the ratio of 3:2. [18F]FDG PET/CT images of the tumor were segmented by 3D Slicer software and the radiomics features were extracted. The effective features were selected by the least absolute shrinkage and selection operator to construct the radiomics score (Rad_score). And the radiomics model (R_model) was constructed based on Rad_score for prediction of recurrence. Then, univariate and multivariate analyses were used to screen out the independent clinical risk parameters and construct the clinical model (C_model). A combined model (RC_model) was developed based on the Rad_score and independent clinical risk parameters and presented as radiomics nomogram. The performance of the above three models was assessed by the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). Results Seven radiomics features were selected for building the R_model. The AUCs of the C_model in training and test sets were 0.744 (95% confidence interval [CI], 0.595–0.874) and 0.750 (95% CI, 0.577–0.904), respectively. The R_model yielded AUCs of 0.813 (95% CI, 0.685–0.916) and 0.869 (95% CI, 0.715–0.985) in the training and test sets, respectively. The RC_model demonstrated the largest AUCs of 0.889 (95% CI, 0.794–0.963) and 0.892 (95% CI, 0.758–0.992) in the training and test sets, respectively. DCA demonstrated that RC_model added more net benefits than either the C_model or the R_model for predicting recurrence in high-risk pediatric neuroblastoma. Conclusions The combined model performed well for predicting recurrence in high-risk pediatric neuroblastoma, which can facilitate disease follow-up and management in clinical practice.

show abstract

Deep learning radiomic nomogram to predict recurrence in soft tissue sarcoma: a multi-institutional study

Cited by 27 publications

References 29 publications

Multi-Size Deep Learning Based Preoperative Computed Tomography Signature for Prognosis Prediction of Colorectal Cancer

Multi-Size Deep Learning Based Preoperative Computed Tomography Signature for Prognosis Prediction of Colorectal Cancer

Differentiation Between Lipomas and Atypical Lipomatous Tumors of the Extremities Using Radiomics

Clinical parameters combined with radiomics features of PET/CT can predict recurrence in patients with high-risk pediatric neuroblastoma

Contact Info

Product

Resources

About