1
|
Kalage D, Gupta P, Gulati A, Reddy KP, Sharma K, Thakur A, Yadav TD, Gupta V, Kaman L, Nada R, Singh H, Irrinki S, Gupta P, Das CK, Dutta U, Sandhu M. Contrast Enhanced CT Versus MRI for Accurate Diagnosis of Wall-thickening Type Gallbladder Cancer. J Clin Exp Hepatol 2024; 14:101397. [PMID: 38595988 PMCID: PMC10999705 DOI: 10.1016/j.jceh.2024.101397] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Accepted: 03/09/2024] [Indexed: 04/11/2024] Open
Abstract
Introduction Diagnosis of wall-thickening type gallbladder cancer (GBC) is challenging. Computed tomography (CT) and magnetic resonance imaging (MRI) are commonly utilized to evaluate gallbladder wall thickening. However, there is a lack of data comparing the performance of CT and MRI for the detection of wall-thickening type GBC. Aim We aim to compare the diagnostic accuracy of CT and MRI in diagnosis of wall-thickening type GBC. Materials and methods This prospective study comprised consecutive patients suspected of wall-thickening type GBC who underwent preoperative contrast-enhanced CT and MRI. The final diagnosis was based on the histopathology of the resected gallbladder lesion. Two radiologists independently reviewed the characteristics of gallbladder wall thickening at CT and MRI. The association of CT and MRI findings with histological diagnosis and the interobserver agreement of CT and MRI findings were assessed. Results Thirty-three patients (malignancy, 13 and benign, 20) were included. None of the CT findings were significantly associated with GBC. However, at MRI, heterogeneous enhancement, indistinct interface with the liver, and diffusion restriction were significantly associated with malignancy (P = 0.006, <0.001, and 0.005, respectively), and intramural cysts were significantly associated with benign lesions (P = 0.012). For all MRI findings, the interobserver agreement was substantial to perfect (kappa = 0.697-1.000). At CT, the interobserver agreement was substantial to perfect (k = 0.631-1.000). Conclusion These findings suggest that MRI may be preferred over CT in patients with suspected wall thickening type GBC. However, larger multicenter studies must confirm our findings.
Collapse
Affiliation(s)
- Daneshwari Kalage
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Pankaj Gupta
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Ajay Gulati
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Kakivaya P. Reddy
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Kritika Sharma
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Ati Thakur
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Thakur D. Yadav
- Department of Surgical Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Vikas Gupta
- Department of Surgical Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Lileswar Kaman
- Department of General Surgery, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Ritambhra Nada
- Department of Histopathology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Harjeet Singh
- Department of Surgical Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Santosh Irrinki
- Department of General Surgery, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Parikshaa Gupta
- Department of Cytology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Chandan K. Das
- Department of Medical Oncology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Usha Dutta
- Department of Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Manavjit Sandhu
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| |
Collapse
|
2
|
Qin Z, Ding J, Fu Y, Zhou H, Wang Y, Jing X. Preliminary study on diagnosis of gallbladder neoplastic polyps based on contrast-enhanced ultrasound and grey scale ultrasound radiomics. Front Oncol 2024; 14:1370010. [PMID: 38720810 PMCID: PMC11076697 DOI: 10.3389/fonc.2024.1370010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2024] [Accepted: 04/02/2024] [Indexed: 05/12/2024] Open
Abstract
Objective Neoplastic gallbladder polyps (GPs), including adenomas and adenocarcinomas, are considered absolute indications for surgery; however, the distinction of neoplastic from non-neoplastic GPs on imaging is often challenging. This study thereby aimed to develop a CEUS radiomics nomogram, and evaluate the role of a combined grey-scale ultrasound and CEUS model for the prediction and diagnosis of neoplastic GPs. Methods Patients with GPs of ≥ 1 cm who underwent CEUS between January 2017 and May 2022 were retrospectively enrolled. Grey-scale ultrasound and arterial phase CEUS images of the largest section of the GPs were used for radiomics feature extraction. Features with good reproducibility in terms of intraclass correlation coefficient were selected. Grey-scale ultrasound and CEUS Rad-score models were first constructed using the Mann-Whitney U and LASSO regression test, and were subsequently included in the multivariable logistic regression analysis as independent factors for construction of the combined model. Results A total of 229 patients were included in our study. Among them, 118 cholesterol polyps, 68 adenomas, 33 adenocarcinomas, 6 adenomyomatoses, and 4 inflammatory polyps were recorded. A total of 851 features were extracted from each patient. Following screening, 21 and 15 features were retained in the grey-scale and CEUS models, respectively. The combined model demonstrated AUCs of 0.88 (95% CI: 0.83 - 0.93) and 0.84 (95% CI: 0.74 - 0.93) in the training and testing set, respectively. When applied to the whole dataset, the combined model detected 111 of the 128 non-neoplastic GPs, decreasing the resection rate of non-neoplastic GPs to 13.3%. Conclusion Our proposed combined model based on grey-scale ultrasound and CEUS radiomics features carries the potential as a non-invasive, radiation-free, and reproducible tool for the prediction and identification of neoplastic GPs. Our model may not only guide the treatment selection for GPs, but may also reduce the surgical burden of such patients.
Collapse
Affiliation(s)
- Zhengyi Qin
- Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin, China
- Artificial Cell Engineering Technology Research Center, Tianjin, China
- Tianjin Institute of Hepatobiliary Disease, Tianjin Third Central Hospital, Tianjin, China
| | - Jianmin Ding
- Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin, China
- Artificial Cell Engineering Technology Research Center, Tianjin, China
- Tianjin Institute of Hepatobiliary Disease, Tianjin Third Central Hospital, Tianjin, China
| | - Yaling Fu
- Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin, China
- Artificial Cell Engineering Technology Research Center, Tianjin, China
- Tianjin Institute of Hepatobiliary Disease, Tianjin Third Central Hospital, Tianjin, China
| | - Hongyu Zhou
- Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin, China
- Artificial Cell Engineering Technology Research Center, Tianjin, China
- Tianjin Institute of Hepatobiliary Disease, Tianjin Third Central Hospital, Tianjin, China
| | - Yandong Wang
- Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin, China
- Artificial Cell Engineering Technology Research Center, Tianjin, China
- Tianjin Institute of Hepatobiliary Disease, Tianjin Third Central Hospital, Tianjin, China
| | - Xiang Jing
- Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China
- Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Tianjin, China
- Artificial Cell Engineering Technology Research Center, Tianjin, China
- Tianjin Institute of Hepatobiliary Disease, Tianjin Third Central Hospital, Tianjin, China
| |
Collapse
|
3
|
Wang R, Lv L, Li L. Diagnostic performance of the gallbladder reporting and data system combined with color doppler flow imaging for gallbladder cancer in the Asian population. Front Oncol 2024; 14:1367351. [PMID: 38686188 PMCID: PMC11056497 DOI: 10.3389/fonc.2024.1367351] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2024] [Accepted: 03/27/2024] [Indexed: 05/02/2024] Open
Abstract
Purpose Evaluating the performance of the Gallbladder Reporting and Data System (GB-RADS) combined with Color Doppler Flow Imaging (CDFI) for the diagnosis of gallbladder wall thickening disease in an Asian population. Methods In this study, the lesions were classified and the actual incidence rate of malignant tumors was calculated for each GB-RADS category, following the guidelines provided by GB-RADS. To evaluate the diagnostic performance of GB-RADS and GB-RADS combined with CDFI, we plotted Receiver Operator Characteristic (ROC) curves. The sensitivity (SE), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy (AC) were also calculated. Inter-observer agreement (IRA) between the two observers was assessed using Kappa values. Results The incidence of malignancy risk for GB-RADS 2, 3, 4, and 5 was 9%, 12.5%, 72.2%, and 100%. The AUC for GB-RADS was 0.855 (95% CI: 0.800-0.900), with a sensitivity of 82.5%, a specificity of 84.6%, and an accuracy of 83.8%. The AUC of GB-RADS combined with CDFI was 0.965 (95% CI: 0.930-0.985), with a sensitivity of 96.2%, a specificity of 94.6%, and an accuracy of 95.2%. The AUC, sensitivity, specificity, and accuracy of GB-RADS combined with CDFI for diagnosing gallbladder malignancy were higher than those of GB-RADS alone, and the differences were statistically significant (all P < 0.05). The IRA was excellent between the two observers (Kappa = 0.870). Conclusions GB-RADS combined with CDFI demonstrated excellent diagnostic accuracy when it comes to distinguishing various diseases that caused gallbladder wall thickening in the Asian population, which has good clinical value and can improve the detection rate of malignant tumors in patients with gallbladder wall thickening.
Collapse
Affiliation(s)
| | | | - Li Li
- Department of Ultrasound, Qilu Hospital of Shandong University, Qingdao, Shandong, China
| |
Collapse
|
4
|
Gupta P, Kambadakone A, Sirohi B. Editorial: Role of imaging in biliary tract cancer: diagnosis, staging, response prediction and image-guided therapeutics. Front Oncol 2024; 14:1387531. [PMID: 38567157 PMCID: PMC10985351 DOI: 10.3389/fonc.2024.1387531] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2024] [Accepted: 03/07/2024] [Indexed: 04/04/2024] Open
Affiliation(s)
- Pankaj Gupta
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Avinash Kambadakone
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | - Bhawna Sirohi
- Department of Medical Oncology, BALCO Medical Centre, Raipur, Chhattisgarh, India
| |
Collapse
|
5
|
Gupta P, Basu S, Arora C. Applications of artificial intelligence in biliary tract cancers. Indian J Gastroenterol 2024:10.1007/s12664-024-01518-0. [PMID: 38427281 DOI: 10.1007/s12664-024-01518-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/03/2023] [Accepted: 12/29/2023] [Indexed: 03/02/2024]
Abstract
Biliary tract cancers are malignant neoplasms arising from bile duct epithelial cells. They include cholangiocarcinomas and gallbladder cancer. Gallbladder cancer has a marked geographical preference and is one of the most common cancers in women in northern India. Biliary tract cancers are usually diagnosed at an advanced, unresectable stage. Hence, the prognosis is extremely dismal. The five-year survival rate in advanced gallbladder cancer is < 5%. Hence, early detection and radical surgery are critical to improving biliary tract cancer prognoses. Radiological imaging plays an essential role in diagnosing and managing biliary tract cancers. However, the diagnosis is challenging because the biliary tract is affected by many diseases that may have radiological appearances similar to cancer. Artificial intelligence (AI) can improve radiologists' performance in various tasks. Deep learning (DL)-based approaches are increasingly incorporated into medical imaging to improve diagnostic performance. This paper reviews the AI-based strategies in biliary tract cancers to improve the diagnosis and prognosis.
Collapse
Affiliation(s)
- Pankaj Gupta
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India.
| | - Soumen Basu
- Department of Computer Science and Engineering, Indian Institute of Technology - Delhi, New Delhi, 110 016, India
| | - Chetan Arora
- Department of Computer Science and Engineering, Indian Institute of Technology - Delhi, New Delhi, 110 016, India
| |
Collapse
|
6
|
Zhu L, Li N, Zhu Y, Han P, Jiang B, Li M, Luo Y, Clevert DA, Fei X. Value of high frame rate contrast enhanced ultrasound in gallbladder wall thickening in non-acute setting. Cancer Imaging 2024; 24:7. [PMID: 38191513 PMCID: PMC10775603 DOI: 10.1186/s40644-023-00651-x] [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: 09/20/2023] [Accepted: 12/25/2023] [Indexed: 01/10/2024] Open
Abstract
BACKGROUND Ultrasound (US) has been widely used in screening and differential diagnosis of gallbladder wall thickening (GWT). However, the sensitivity and specificity for diagnosing wall-thickening type gallbladder cancer are limited, leading to delayed treatment or overtreatment. We aim to explore the value of high frame rate contrast enhanced ultrasound (H-CEUS) in distinguishing wall-thickening type gallbladder cancer (malignant) from GWT mimicking malignancy (benign). METHODS This retrospective study enrolled consecutive patients with non-acute GWT who underwent US and H-CEUS examination before cholecystectomy. Clinical information, US image and H-CEUS image characteristics between malignant and benign GWT were compared. The independent risk factors for malignant GWT on H-CEUS images were selected by multivariate logistic regression analysis. The diagnostic performance of H-CEUS in determining malignant GWT was compared with that of the gallbladder reporting and data system (GB-RADS) score. RESULTS Forty-six patients included 30 benign GWTs and 16 malignant GWTs. Only mural layering and interface with liver on US images were significantly different between malignant and benign GWT (P < 0.05). Differences in enhancement direction, vascular morphology, serous layer continuity, wash-out time and mural layering in the venous phase of GWT on H-CEUS images were significant between malignant and benign GWT (P < 0.05). The sensitivity, specificity and accuracy of H-CEUS based on enhancement direction, vascular morphology and wash-out time in the diagnosis of malignant GWT were 93.75%, 90.00%, and 91.30%, respectively. However, the sensitivity, specificity and accuracy of the GB-RADS score were only 68.75%, 73.33% and 71.74%, respectively. The area under ROC curve (AUC) of H-CEUS was significantly higher than that of the GB-RADS score (AUC = 0.965 vs. 0.756). CONCLUSIONS H-CEUS can accurately detect enhancement direction, vascular morphology and wash-out time of GWT, with a higher diagnostic performance than the GB-RADS score in determining wall-thickening type gallbladder cancer. This study provides a novel imaging means with high accuracy for the diagnosis of wall-thickening type gallbladder cancer, thus may be better avoiding delayed treatment or overtreatment.
Collapse
Affiliation(s)
- Lianhua Zhu
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Nan Li
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Yaqiong Zhu
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Peng Han
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Bo Jiang
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Miao Li
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Yukun Luo
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China
| | - Dirk-André Clevert
- Department of Clinical Radiology, Interdisciplinary Ultrasound-Center, University of Munich, Grosshadern Campus, Munich, Germany.
| | - Xiang Fei
- Department of Ultrasound, the First Medical Center, Chinese PLA General Hospital, Beijing, China.
| |
Collapse
|
7
|
Gupta P, Basu S, Yadav TD, Kaman L, Irrinki S, Singh H, Prakash G, Gupta P, Nada R, Dutta U, Sandhu MS, Arora C. Deep-learning models for differentiation of xanthogranulomatous cholecystitis and gallbladder cancer on ultrasound. Indian J Gastroenterol 2023:10.1007/s12664-023-01483-0. [PMID: 38110782 DOI: 10.1007/s12664-023-01483-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/06/2023] [Accepted: 11/05/2023] [Indexed: 12/20/2023]
Abstract
BACKGROUND The radiological differentiation of xanthogranulomatous cholecystitis (XGC) and gallbladder cancer (GBC) is challenging yet critical. We aimed at utilizing the deep learning (DL)-based approach for differentiating XGC and GBC on ultrasound (US). METHODS This single-center study comprised consecutive patients with XGC and GBC from a prospectively acquired database who underwent pre-operative US evaluation of the gallbladder lesions. The performance of state-of-the-art (SOTA) DL models (GBCNet-convolutional neural network [CNN] and RadFormer, transformer) for XGC vs. GBC classification in US images was tested and compared with popular DL models and a radiologist. RESULTS Twenty-five patients with XGC (mean age, 57 ± 12.3, 17 females) and 55 patients with GBC (mean age, 54.6 ± 11.9, 38 females) were included. The performance of GBCNet and RadFormer was comparable (sensitivity 89.1% vs. 87.3%, p = 0.738; specificity 72% vs. 84%, p = 0.563; and AUC 0.744 vs. 0.751, p = 0.514). The AUCs of DenseNet-121, vision transformer (ViT) and data-efficient image transformer (DeiT) were significantly smaller than of GBCNet (p = 0.015, 0.046, 0.013, respectively) and RadFormer (p = 0.012, 0.027, 0.007, respectively). The radiologist labeled US images of 24 (30%) patients non-diagnostic. In the remaining patients, the sensitivity, specificity and AUC for GBC detection were 92.7%, 35.7% and 0.642, respectively. The specificity of the radiologist was significantly lower than of GBCNet and RadFormer (p = 0.001). CONCLUSION SOTA DL models have a better performance than radiologists in differentiating XGC and GBC on the US.
Collapse
Affiliation(s)
- Pankaj Gupta
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India.
| | - Soumen Basu
- Department of Computer Science and Engineering, Indian Institute of Technology, New Delhi, 110 016, India
| | - Thakur Deen Yadav
- Department of Surgical Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Lileswar Kaman
- Department of General Surgery, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Santosh Irrinki
- Department of General Surgery, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Harjeet Singh
- Department of Surgical Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Gaurav Prakash
- Department of Clinical Hematology and Medical Oncology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Parikshaa Gupta
- Department of Cytology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Ritambhra Nada
- Department of Histopathology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Usha Dutta
- Department of Gastroenterology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Manavjit Singh Sandhu
- Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, 160 012, India
| | - Chetan Arora
- Department of Computer Science and Engineering, Indian Institute of Technology, New Delhi, 110 016, India
| |
Collapse
|