Computer-Aided Diagnosis for Distinguishing Pancreatic Mucinous Cystic Neoplasms From Serous Oligocystic Adenomas in Spectral CT Images

Objective: This preliminary study aims to verify the effectiveness of the additional information provided by spectral computed tomography (CT) with the proposed computer-aided diagnosis (CAD) scheme to differentiate pancreatic serous oligocystic adenomas (SOAs) from mucinous cystic neoplasms of pancreas cystic lesions. Materials and Methods: This study was conducted from January 2010 to October 2013. Twenty-three patients (5 men and 18 women; mean age, 43.96 years old) with SOA and 19 patients (3 men and 16 women; mean age, 41.74 years old) with MCN were included in this retrospective study. Two types of features were collected by dual-energy spectral CT imaging as follows: conventional and additional quantitative spectral CT features. Classification results of the CAD scheme were compared using the conventional features and full feature data set. Important features were selected using support vector machine classification method combined with feature-selection technique. The optimal cutoff values of selected features were determined through receiver–operating characteristic curve analyses. Results: Combining conventional features with additional spectral CT features improved the overall accuracy from 88.37% to 93.02%. The selected features of the proposed CAD scheme were tumor size, contour, location, and low-energy CT values (43 keV). Iodine–water basis material pair densities in both arterial phase (AP) and portal venous phase (PP) were important factors for differential diagnosis of SOA and MCN. The optimal cutoff values of long axis, short axis, 40 keV monochromatic CT value in AP, iodine (water) density in AP, 43 keV monochromatic CT value in PP, and iodine (water) density in PP were 3.4 mm, 3.1 mm, 35.7 Hu, 0.32533 mg/mL, 39.4 Hu, and 0.348 mg/mL, respectively. Conclusion: The combination of conventional features and additional information provided by dual-energy spectral CT shows a high accuracy in the CAD scheme. The quantitative information of spectral CT may prove useful in the diagnosis and classification of SOAs and MCNs with machine learning algorithms.

[1]  Chih-Jen Lin,et al.  Combining SVMs with Various Feature Selection Strategies , 2006, Feature Extraction.

[2]  L. Chu,et al.  Characterization of Pancreatic Serous Cystadenoma on Dual-Phase Multidetector Computed Tomography , 2014, Journal of computer assisted tomography.

[3]  Giuseppe Piccinni,et al.  Management of mucinous cystic neoplasms of the pancreas. , 2010, World journal of gastroenterology.

[4]  L L Berland,et al.  Single-source dual-energy spectral multidetector CT of pancreatic adenocarcinoma: optimization of energy level viewing significantly increases lesion contrast. , 2013, Clinical radiology.

[5]  Concha Bielza,et al.  Machine Learning in Bioinformatics , 2008, Encyclopedia of Database Systems.

[6]  Kuni Ohtomo,et al.  Preliminary report on virtual monochromatic spectral imaging with fast kVp switching dual energy head CT: comparable image quality to that of 120-kVp CT without increasing the radiation dose , 2013, Japanese Journal of Radiology.

[7]  Xiaozhu Lin,et al.  Spectral CT imaging in differential diagnosis of pancreatic serous oligocystic adenoma and mucinous cystic neoplasms , 2011 .

[8]  Freddy T. Nguyen,et al.  Clinical Feasibility of Microscopically-Guided Breast Needle Biopsy Using a Fiber-Optic Probe with Computer-Aided Detection , 2009, Technology in cancer research & treatment.

[9]  Y. B. Kim,et al.  MRI features of serous oligocystic adenoma of the pancreas: differentiation from mucinous cystic neoplasm of the pancreas. , 2012, The British journal of radiology.

[10]  Jing Xie,et al.  Differentiating Pancreatic Ductal Adenocarcinoma from Pancreatic Serous Cystadenoma, Mucinous Cystadenoma, and a Pseudocyst with Detailed Analysis of Cystic Features on CT Scans: a Preliminary Study , 2011, Korean journal of radiology.

[11]  Ke-min Chen,et al.  Spectral CT: Preliminary Studies in the Liver Cirrhosis , 2012, Korean journal of radiology.

[12]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[13]  Andrew L Warshaw,et al.  Cystic Neoplasms of the Pancreas , 2006 .

[14]  M. Verma.  Pancreatic Cancer Epidemiology , 2005, Technology in cancer research & treatment.

[15]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[16]  A. Sauvanet,et al.  Macrocystic pancreatic cystadenoma: The role of EUS and cyst fluid analysis in distinguishing mucinous and serous lesions. , 2004, Gastrointestinal endoscopy.

[17]  Kemin Chen,et al.  Gastric Cancer Staging with Dual Energy Spectral CT Imaging , 2013, PloS one.

[18]  D. Sahani,et al.  Cystic pancreatic lesions: a simple imaging-based classification system for guiding management. , 2005, Radiographics : a review publication of the Radiological Society of North America, Inc.

[19]  C. F. Fernandez-del Castillo,et al.  Pancreatic cystic neoplasms: management and unanswered questions. , 2013, Gastroenterology.

[20]  R. Hruban,et al.  Diagnosis andManagement of Cystic Lesions of the Pancreas , 2014 .

[21]  D. Lu,et al.  Pancreatic Cystic Lesions: Discrimination Accuracy based on Clinical Data and High Resolution CT Features , 2007, Journal of computer assisted tomography.

[22]  Jiawei Han,et al.  Generalized Fisher Score for Feature Selection , 2011, UAI.

[23]  X-Z Lin,et al.  Differential diagnosis of pancreatic serous oligocystic adenoma and mucinous cystic neoplasm with spectral CT imaging: initial results. , 2014, Clinical radiology.

[24]  C. Matos,et al.  Unilocular macrocystic serous cystadenoma of the pancreas--atypical features: a case report. , 2014, Clinical imaging.

[25]  Pierre Baldi,et al.  A machine learning information retrieval approach to protein fold recognition. , 2006, Bioinformatics.

[26]  A. Saftoiu,et al.  Pancreatic cyst fluid analysis--a review. , 2011, Journal of gastrointestinal and liver diseases : JGLD.

[27]  MMed Brian K.P. Goh MBBS,et al.  Pancreatic Serous Oligocystic Adenomas: Clinicopathologic Features and a Comparison with Serous Microcystic Adenomas and Mucinous Cystic Neoplasms , 2005, World Journal of Surgery.

[28]  Y Cui,et al.  Which should be the routine cross-sectional reconstruction mode in spectral CT imaging: monochromatic or polychromatic? , 2012, The British journal of radiology.

[29]  Kelly H. Zou,et al.  Optimal thresholds by maximizing or minimizing various metrics via ROC-type analysis. , 2013, Academic radiology.

[30]  Jian Ying Li,et al.  High-Definition CT Gemstone Spectral Imaging of the Brain: Initial Results of Selecting Optimal Monochromatic Image for Beam-Hardening Artifacts and Image Noise Reduction , 2011, Journal of computer assisted tomography.

[31]  Lei Zhang,et al.  Feature extraction based on Laplacian bidirectional maximum margin criterion , 2009, Pattern Recognit..

[32]  Zhi-Hua Zhou,et al.  Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed Samples , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[33]  B. Goh,et al.  Cystic neoplasms of the pancreas: current diagnostic modalities and management. , 2009, Annals of the Academy of Medicine, Singapore.

[34]  Kemin Chen,et al.  Differentiation of small hepatic hemangioma from small hepatocellular carcinoma: recently introduced spectral CT method. , 2011, Radiology.

[35]  W. Nealon,et al.  Clinical decision making in the management of pancreatic cystic neoplasms , 2013, Expert review of gastroenterology & hepatology.

[36]  B. Choi,et al.  Macrocystic neoplasms of the pancreas: CT differentiation of serous oligocystic adenoma from mucinous cystadenoma and intraductal papillary mucinous tumor. , 2006, AJR. American journal of roentgenology.