1
|
Chen T, Zhang D, Chen S, Lu J, Guo Q, Cai S, Yang H, Wang R, Hu Z, Chen Y. Machine learning for differentiating between pancreatobiliary-type and intestinal-type periampullary carcinomas based on CT imaging and clinical findings. Abdom Radiol (NY) 2024; 49:748-761. [PMID: 38236405 PMCID: PMC10909762 DOI: 10.1007/s00261-023-04151-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Revised: 12/03/2023] [Accepted: 12/05/2023] [Indexed: 01/19/2024]
Abstract
PURPOSE To develop a diagnostic model for distinguishing pancreatobiliary-type and intestinal-type periampullary adenocarcinomas using preoperative contrast-enhanced computed tomography (CT) findings combined with clinical characteristics. METHODS This retrospective study included 140 patients with periampullary adenocarcinoma who underwent preoperative enhanced CT, including pancreaticobiliary (N = 100) and intestinal (N = 40) types. They were randomly assigned to the training or internal validation set in an 8:2 ratio. Additionally, an independent external cohort of 28 patients was enrolled. Various CT features of the periampullary region were evaluated and data from clinical and laboratory tests were collected. Five machine learning classifiers were developed to identify the histologic type of periampullary adenocarcinoma, including logistic regression, random forest, multi-layer perceptron, light gradient boosting, and eXtreme gradient boosting (XGBoost). RESULTS All machine learning classifiers except multi-layer perceptron used achieved good performance in distinguishing pancreatobiliary-type and intestinal-type adenocarcinomas, with the area under the curve (AUC) ranging from 0.75 to 0.98. The AUC values of the XGBoost classifier in the training set, internal validation set and external validation set are 0.98, 0.89 and 0.84 respectively. The enhancement degree of tumor, the growth pattern of tumor, and carbohydrate antigen 19-9 were the most important factors in the model. CONCLUSION Machine learning models combining CT with clinical features can serve as a noninvasive tool to differentiate the histological subtypes of periampullary adenocarcinoma, in particular using the XGBoost classifier.
Collapse
Affiliation(s)
- Tao Chen
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, Zhejiang, China
| | - Danbin Zhang
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, Zhejiang, China
| | - Shaoqing Chen
- Department of Radiology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, 109 Xueyuan West Road, Wenzhou, 325027, Zhejiang, China
| | - Juan Lu
- Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, 6009, Australia
- School of Medicine, The University of Western Australia, Crawley, WA, 6009, Australia
- Harry Perkins Institute of Medical Research, Murdoch, WA, 6150, Australia
| | - Qinger Guo
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, Zhejiang, China
| | - Shuyang Cai
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, Zhejiang, China
| | - Hong Yang
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, Zhejiang, China
| | - Ruixuan Wang
- School of Electronics and Computer Science, University of Liverpool, Brownlow Hill, Liverpool, Merseyside, L69 3BX, UK
| | - Ziyao Hu
- School of Electronics and Computer Science, University of Liverpool, Brownlow Hill, Liverpool, Merseyside, L69 3BX, UK
| | - Yang Chen
- Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart and Chest Hospital, William Henry Duncan Building, 6 West Derby St, Liverpool, Merseyside, L7 8TX, UK.
| |
Collapse
|
2
|
Lee DH, Lee SS, Lee JM, Choi JY, Lee CH, Ha HI, Kang BK, Yu MH, Chang W, Park SJ. Pancreas CT assessment for pancreatic ductal adenocarcinoma resectability: effect of tube voltage and slice thickness on image quality and diagnostic performance. Cancer Imaging 2023; 23:126. [PMID: 38111054 PMCID: PMC10729459 DOI: 10.1186/s40644-023-00637-9] [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: 08/25/2023] [Accepted: 11/22/2023] [Indexed: 12/20/2023] Open
Abstract
OBJECTIVES To assess the resectability of pancreatic ductal adenocarcinoma (PDAC), the evaluation of tumor vascular contact holds paramount significance. This study aimed to compare the image quality and diagnostic performance of high-resolution (HR) pancreas computed tomography (CT) using an 80 kVp tube voltage and a thin slice (1 mm) for assessing PDAC resectability, in comparison with the standard protocol CT using 120 kVp. METHODS This research constitutes a secondary analysis originating from a multicenter prospective study. All participants underwent both the standard protocol pancreas CT using 120 kVp with 3 mm slice thickness (ST) and HR-CT utilizing an 80 kVp tube voltage and 1 mm ST. The contrast-to-noise ratio (CNR) between parenchyma and tumor, along with the degree of enhancement of the abdominal aorta and main portal vein (MPV), were measured and subsequently compared. Additionally, the likelihood of margin-negative resection (R0) was evaluated using a five-point scale. The diagnostic performance of both CT protocols in predicting R0 resection was assessed through the area under the receiver operating characteristic curve (AUC). RESULTS A total of 69 patients (37 males and 32 females; median age, 66.5 years) were included in the study. The median CNR of PDAC was 10.4 in HR-CT, which was significantly higher than the 7.1 in the standard CT (P=0.006). Furthermore, HR-CT demonstrated notably higher median attenuation values for both the abdominal aorta (579.5 HU vs. 327.2 HU; P=0.002) and the MPV (263.0 HU vs. 175.6 HU; P=0.004) in comparison with standard CT. Following surgery, R0 resection was achieved in 51 patients. The pooled AUC for HR-CT in predicting R0 resection was 0.727, slightly exceeding the 0.699 of standard CT, albeit lacking a significant statistical distinction (P=0.128). CONCLUSION While HR pancreas CT using 80 kVp offered a notably greater degree of contrast enhancement in vessels and a higher CNR for PDAC compared to standard CT, its diagnostic performance in predicting R0 resection remained statistically comparable.
Collapse
Affiliation(s)
- Dong Ho Lee
- Department of Radiology, Seoul National University Hospital, Seoul, South Korea
| | - Seung Soo Lee
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea
| | - Jeong Min Lee
- Department of Radiology, Seoul National University Hospital, Seoul, South Korea.
- Department of Radiology, Seoul National University College of Medicine, National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, South Korea.
| | - Jin-Young Choi
- Department of Radiology and Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Chang Hee Lee
- Department of Radiology, Korea University Guro Hospital, South Korea University Medicine, Seoul, South Korea
| | - Hong Il Ha
- Department of Radiology, Hallym University Sacred Heart Hospital, Anyang, South Korea
| | - Bo-Kyeong Kang
- Department of Radiology, Hanyang University College of Medicine, Seoul, South Korea
| | - Mi Hye Yu
- Department of Radiology, Konkuk University College of Medicine, Seoul, South Korea
| | - Won Chang
- Department of Radiology, Seoul National University Bundang Hospital, Seoul, South Korea
| | - Sae Jin Park
- Department of Radiology, Seoul National University Hospital, Seoul, South Korea
| |
Collapse
|
3
|
Yoo J, Lee JM, Kang HJ, Bae JS, Jeon SK, Yoon JH. Comparison Between Contrast-Enhanced Computed Tomography and Contrast-Enhanced Magnetic Resonance Imaging With Magnetic Resonance Cholangiopancreatography for Resectability Assessment in Extrahepatic Cholangiocarcinoma. Korean J Radiol 2023; 24:983-995. [PMID: 37793669 PMCID: PMC10550738 DOI: 10.3348/kjr.2023.0368] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2023] [Revised: 07/19/2023] [Accepted: 07/31/2023] [Indexed: 10/06/2023] Open
Abstract
OBJECTIVE To compare the diagnostic performance and interobserver agreement between contrast-enhanced computed tomography (CECT) and contrast-enhanced magnetic resonance imaging (CE-MRI) with magnetic resonance cholangiopancreatography (MRCP) for evaluating the resectability in patients with extrahepatic cholangiocarcinoma (eCCA). MATERIALS AND METHODS This retrospective study included treatment-naïve patients with pathologically confirmed eCCA, who underwent both CECT and CE-MRI with MRCP using extracellular contrast media between January 2015 and December 2020. Among the 214 patients (146 males; mean age ± standard deviation, 68 ± 9 years) included, 121 (56.5%) had perihilar cholangiocarcinoma. R0 resection was achieved in 108 of the 153 (70.6%) patients who underwent curative-intent surgery. Four fellowship-trained radiologists independently reviewed the findings of both CECT and CE-MRI with MRCP to assess the local tumor extent and distant metastasis for determining resectability. The pooled area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of CECT and CE-MRI with MRCP were compared using clinical, surgical, and pathological findings as reference standards. The interobserver agreement of resectability was evaluated using Fleiss kappa (κ). RESULTS No significant differences were observed between CECT and CE-MRI with MRCP in the pooled AUC (0.753 vs. 0.767), sensitivity (84.7% [366/432] vs. 90.3% [390/432]), and specificity (52.6% [223/424] vs. 51.4% [218/424]) (P > 0.05 for all). The AUC for determining resectability was higher when CECT and CE-MRI with MRCP were reviewed together than when CECT was reviewed alone in patients with discrepancies between the imaging modalities or with indeterminate resectability (0.798 [0.754-0.841] vs. 0.753 [0.697-0.808], P = 0.014). The interobserver agreement for overall resectability was fair for both CECT (κ = 0.323) and CE-MRI with MRCP (κ = 0.320), without a significant difference (P = 0.884). CONCLUSION CECT and CE-MRI with MRCP showed no significant differences in the diagnostic performance and interobserver agreement in determining the resectability in patients with eCCA.
Collapse
Affiliation(s)
- Jeongin Yoo
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
| | - Jeong Min Lee
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea
| | - Hyo-Jin Kang
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Jae Seok Bae
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Sun Kyung Jeon
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
| | - Jeong Hee Yoon
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea.
| |
Collapse
|