1
|
Gao D, Tan BG, Chen XQ, Zhou C, Ou J, Guo WW, Zhou HY, Li R, Zhang XM, Chen TW. Contrast-enhanced CT radiomics features to preoperatively identify differences between tumor and proximal tumor-adjacent and tumor-distant tissues of resectable esophageal squamous cell carcinoma. Cancer Imaging 2024; 24:11. [PMID: 38243339 PMCID: PMC10797955 DOI: 10.1186/s40644-024-00656-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Accepted: 01/03/2024] [Indexed: 01/21/2024] Open
Abstract
BACKGROUND Esophagectomy is the main treatment for esophageal squamous cell carcinoma (ESCC), and patients with histopathologically negative margins still have a relatively higher recurrence rate. Contrast-enhanced CT (CECT) radiomics might noninvasively obtain potential information about the internal heterogeneity of ESCC and its adjacent tissues. This study aimed to develop CECT radiomics models to preoperatively identify the differences between tumor and proximal tumor-adjacent and tumor-distant tissues in ESCC to potentially reduce tumor recurrence. METHODS A total of 529 consecutive patients with ESCC from Centers A (n = 447) and B (n = 82) undergoing preoperative CECT were retrospectively enrolled in this study. Radiomics features of the tumor, proximal tumor-adjacent (PTA) and proximal tumor-distant (PTD) tissues were individually extracted by delineating the corresponding region of interest (ROI) on CECT and applying the 3D-Slicer radiomics module. Patients with pairwise tissues (ESCC vs. PTA, ESCC vs. PTD, and PTA vs. PTD) from Center A were randomly assigned to the training cohort (TC, n = 313) and internal validation cohort (IVC, n = 134). Univariate analysis and the least absolute shrinkage and selection operator were used to select the core radiomics features, and logistic regression was performed to develop radiomics models to differentiate individual pairwise tissues in TC, validated in IVC and the external validation cohort (EVC) from Center B. Diagnostic performance was assessed using area under the receiver operating characteristics curve (AUC) and accuracy. RESULTS With the chosen 20, 19 and 5 core radiomics features in TC, 3 individual radiomics models were developed, which exhibited excellent ability to differentiate the tumor from PTA tissue (AUC: 0.965; accuracy: 0.965), the tumor from PTD tissue (AUC: 0.991; accuracy: 0.958), and PTA from PTD tissue (AUC: 0.870; accuracy: 0.848), respectively. In IVC and EVC, the models also showed good performance in differentiating the tumor from PTA tissue (AUCs: 0.956 and 0.962; accuracy: 0.956 and 0.937), the tumor from PTD tissue (AUCs: 0.990 and 0.974; accuracy: 0.952 and 0.970), and PTA from PTD tissue (AUCs: 0.806 and 0.786; accuracy: 0.760 and 0.786), respectively. CONCLUSION CECT radiomics models could differentiate the tumor from PTA tissue, the tumor from PTD tissue, and PTA from PTD tissue in ESCC.
Collapse
Affiliation(s)
- Dan Gao
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
- Department of Radiology, Medical Center Hospital of Qionglai City, 172# Xinglin Road, Linqiong District, Chengdu, 611530, Sichuan, China
| | - Bang-Guo Tan
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
- Department of Radiology, Panzhihua Central Hospital, 34# Yikang Street, East District, Panzhihua, 617067, Sichuan, China
| | - Xiao-Qian Chen
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Chuanqinyuan Zhou
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Jing Ou
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Wen-Wen Guo
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Hai-Ying Zhou
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Rui Li
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Xiao-Ming Zhang
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 1# Maoyuan South Road, Shunqing District, Nanchong, 637000, Sichuan, China
| | - Tian-Wu Chen
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, 74# Linjiang Rd, Yuzhong District, Chongqing, 400010, China.
| |
Collapse
|
2
|
Tang S, Ou J, Liu J, Wu YP, Wu CQ, Chen TW, Zhang XM, Li R, Tang MJ, Yang LQ, Tan BG, Lu FL, Hu J. Application of contrast-enhanced CT radiomics in prediction of early recurrence of locally advanced oesophageal squamous cell carcinoma after trimodal therapy. Cancer Imaging 2021; 21:38. [PMID: 34039403 PMCID: PMC8157695 DOI: 10.1186/s40644-021-00407-5] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Accepted: 05/12/2021] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Early recurrence of oesophageal squamous cell carcinoma (SCC) is defined as recurrence after surgery within 1 year, and appears as local recurrence, distant recurrence, and lymph node positive and disseminated recurrence. Contrast-enhanced computed tomography (CECT) is recommended for diagnosis of primary tumor and initial staging of oesophageal SCC, but it cannot be used to predict early recurrence. It is reported that radiomics can help predict preoperative stages of oesophageal SCC, lymph node metastasis before operation, and 3-year overall survival of oesophageal SCC patients following chemoradiotherapy by extracting high-throughput quantitative features from CT images. This study aimed to develop models based on CT radiomics and clinical features of oesophageal SCC to predict early recurrence of locally advanced cancer. METHODS We collected electronic medical records and image data of 197 patients with confirmed locally advanced oesophageal SCC. These patients were randomly allocated to 137 patients in the training cohort and 60 in the test cohort. 352 radiomics features were extracted by delineating region-of-interest (ROI) around the lesion on CECT images and clinical signature was generated by medical records. The radiomics model, clinical model, the combined model of radiomics and clinical features were developed by radiomics features and/or clinical characteristics. Predicting performance of the three models was assessed with area under receiver operating characteristic curve (AUC), accuracy and F-1 score. RESULTS Eleven radiomics features and/or six clinical signatures were selected to build prediction models related to recurrence of locally advanced oesophageal SCC after trimodal therapy. The AUC of integration of radiomics and clinical models was better than that of radiomics or clinical model for the training cohort (0.821 versus 0.754 or 0.679, respectively) and for the validation cohort (0.809 versus 0.646 or 0.658, respectively). Integrated model of radiomics and clinical features showed good performance in predicting early recurrence of locally advanced oesophageal SCC for both the training and validation cohorts (accuracy = 0.730 and 0.733, and F-1score = 0.730 and 0.778, respectively). CONCLUSIONS The integrated model of CECT radiomics and clinical features may be a potential imaging biomarker to predict early recurrence of locally advanced oesophageal SCC after trimodal therapy.
Collapse
Affiliation(s)
- Sun Tang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Jing Ou
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Jun Liu
- Sichuan Key Laboratory of Medical Imaging, North Sichuan Medical College, Nanchong, Sichuan, China
| | - Yu-Ping Wu
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Chang-Qiang Wu
- Sichuan Key Laboratory of Medical Imaging, North Sichuan Medical College, Nanchong, Sichuan, China
| | - Tian-Wu Chen
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China.
| | - Xiao-Ming Zhang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Rui Li
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Meng-Jie Tang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Li-Qin Yang
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Bang-Guo Tan
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Fu-Lin Lu
- Sichuan Key Laboratory of Medical Imaging, Department of Radiology, Affiliated Hospital of North Sichuan Medical College, 63# Wenhua Road, 637000, Nanchong, Sichuan, China
| | - Jiani Hu
- Department of Radiology, Wayne State University, Detroit, Michigan, USA
| |
Collapse
|
3
|
Little BP, Mendoza DP, Fox A, Wu CC, Ackman JB, Shepard JA, Muniappan A, Digumarthy SR. Direct and indirect CT imaging features of esophago-airway fistula in adults. J Thorac Dis 2020; 12:3157-3166. [PMID: 32642237 PMCID: PMC7330784 DOI: 10.21037/jtd-20-244] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Background Esophago-airway fistula (EAF) is an abnormal connection between the esophagus and the trachea or a major bronchus. While contrast esophagography remains the primary radiographic tool for the diagnosis of EAF, computed tomography (CT) is often employed in its evaluation. A systematic analysis of CT findings of EAF in adults has not been previously published. The goal of our study is to determine the direct and indirect CT findings of EAF in adults. Methods We identified patients with EAF detected on CT at our institution between January 1, 2001 and December 31, 2019, with endoscopic or surgical confirmation. We collected patient clinicopathologic characteristics and assessed CTs for direct and indirect imaging features of EAF in these patients. Results Twenty-six patients (median age: 56 years; range, 25–79 years; F=13, 50% and M=13, 50%) with confirmed EAF were identified. Half of the patients had an underlying malignancy. On CT, a direct connection between the esophagus and the airway was identified in most cases (22/26; 85%). Common indirect CT findings of EAF included esophageal wall thickening (21/26, 81%), mediastinal fatty stranding (21/26, 81%), airway wall thickening (20/26, 77%), fluid or debris within the airways (17/26, 65%), and focal or diffuse esophageal dilation with air (17/26, 65%). Mediastinal fluid collections were infrequently seen (4/26, 15%), but findings of aspiration or other pneumonia were common (19/26, 73%). Conclusions CT plays an essential role in both the primary and secondary evaluation of adult EAF resulting from both malignant and benign etiologies. CT may be the first diagnostic exam to suggest and detect the presence of EAF and may precede clinical suspicion, and it can detect a subset of fistulas not demonstrated on esophagography. There are several direct and indirect imaging findings on CT that can help in the detection of EAF.
Collapse
Affiliation(s)
- Brent P Little
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Dexter P Mendoza
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Andrew Fox
- Department of Radiology, McGill University, Montreal, Quebec, Canada
| | - Carol C Wu
- Department of Thoracic Imaging, MD Anderson Cancer Center, Houston, TX, USA
| | - Jeanne B Ackman
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Jo-Anne Shepard
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Ashok Muniappan
- Department of Surgery, Massachusetts General Hospital, Boston, MA, USA
| | - Subba R Digumarthy
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| |
Collapse
|
4
|
Karmazanovsky GG, Buryakina SA, Kondratiev EV, Yang Q, Ruchkin DV, Kalinin DV. Value of two-phase dynamic multidetector computed tomography in differential diagnosis of post-inflammatory strictures from esophageal cancer. World J Gastroenterol 2015; 21:8878-8887. [PMID: 26269677 PMCID: PMC4528030 DOI: 10.3748/wjg.v21.i29.8878] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/26/2015] [Revised: 03/25/2015] [Accepted: 05/07/2015] [Indexed: 02/06/2023] Open
Abstract
AIM: To characterize the computed tomography (CT) findings in patients with post-inflammatory esophageal strictures (corrosive and peptic) and reveal the optimal scanning phase protocols for distinguishing post-inflammatory esophageal stricture and esophageal cancer.
METHODS: Sixty-five patients with esophageal strictures of different etiology were included in this study: 24 patients with 27 histopathologically confirmed corrosive strictures, 10 patients with 12 peptic strictures and 31 patients with esophageal cancer were evaluated with a two-phase dynamic contrast-enhanced MDCT. Arterial and venous phases at 10 and 35 s after the attenuation of 200 HU were obtained at the descending aorta, with a delayed phase at 6-8 min after the start of injection of contrast media. For qualitative analysis, CT scans of benign strictures were reviewed for the presence/absence of the following features: “target sign”, luminal mass, homogeneity of contrast medium uptake, concentric wall thickening, conically shaped suprastenotic dilatation, smooth boundaries of stenosis and smooth mucous membrane at the transition to stenosis, which were compared with a control group of 31 patients who had esophageal cancer. The quantitative analysis included densitometric parameter acquisition using regions-of-interest measurement of the zone of stenosis and normal esophageal wall and the difference between those measurements (ΔCT) at all phases of bolus contrast enhancement. Esophageal wall thickening, length of esophageal wall thickening and size of the regional lymph nodes were also evaluated.
RESULTS: The presence of a concentric esophageal wall, conically shaped suprastenotic dilatation, smooth upper and lower boundaries, “target sign” and smooth mucous membrane at the transition to stenosis were suggestive of a benign cause, with sensitivities of 92.31%, 87.17%, 94.87%, 76.92% and 82.05%, respectively, and specificities of 70.96%, 89.66%, 80.65%, 96.77% and 93.55%, respectively. The features that were most suggestive of a malignant cause were eccentric esophageal wall thickening, tuberous upper and lower boundaries of stenosis, absence of mucous membrane visualization, rupture of the mucous membrane at the upper boundary of stenosis, cup-shaped suprastenotic dilatation, luminal mass and enlarged regional lymph nodes with specificities of 92.31% 94.87%, 67.86%, 100%, 97.44%, 94.87% and 82.86%, respectively and sensitivities of 70.97%, 80.65%, 96.77%, 80.65%, 54.84%, 87.10% and 60%, respectively. The highest tumor attenuation occurred in the arterial phase (mean attenuation 74.13 ± 17.42 HU), and the mean attenuation difference between the tumor and the normal esophageal wall (mean ΔCT) in the arterial phase was 23.86 ± 19.31 HU. Here, 11.5 HU of ΔCT in the arterial phase was the cut-off value used to differentiate esophageal cancer from post-inflammatory stricture (P = 0.000). The highest attenuation of post-inflammatory strictures occurred in the delayed phase (mean attenuation 71.66 ± 14.28 HU), and the mean ΔCT in delayed phase was 34.03 ± 15.94 HU. Here, 18.5 HU of ΔCT in delayed phase was the cut-off value used to differentiate post-inflammatory stricture from esophageal cancer (P < 0.0001).
CONCLUSION: The described imaging findings reveal high diagnostic significance in the differentiation of benign strictures from esophageal cancer.
Collapse
|
5
|
Current World Literature. Curr Opin Anaesthesiol 2008; 21:85-8. [DOI: 10.1097/aco.0b013e3282f5415f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|