Background Differentiating pancreatic cancer (PC) from normal tissue by computer-aided diagnosis of EUS images were quite useful. The current study was designed to investigate the feasibility of using computer-aided diagnostic (CAD) techniques to extract EUS image parameters for the differential diagnosis of PC and chronic pancreatitis (CP). Methodology/Principal Findings This study recruited 262 patients with PC and 126 patients with CP. Typical EUS images were selected from the sample sets. Texture features were extracted from the region of interest using computer-based techniques. Then the distance between class algorithm and sequential forward selection (SFS) algorithm were used for a better combination of features; and, later, a support vector machine (SVM) predictive model was built, trained, and validated. Overall, 105 features of 9 categories were extracted from the EUS images for pattern classification. Of these features, the 16 were selected as a better combination of features. Then, SVM predictive model was built and trained. The total cases were randomly divided into a training set and a testing set. The training set was used to train the SVM, and the testing set was used to evaluate the performance of the SVM. After 200 trials of randomised experiments, the average accuracy, sensitivity, specificity, the positive and negative predictive values of pancreatic cancer were 94.2±0.1749%,96.25±0.4460%, 93.38±0.2076%, 92.21±0.4249% and 96.68±0.1471%, respectively. Conclusions/Significance Digital image processing and computer-aided EUS image differentiation technologies are highly accurate and non-invasive. This technology provides a kind of new and valuable diagnostic tool for the clinical determination of PC.
References
[1]
Doi K (2007) Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 31: 198–211.
[2]
Nishikawa RM, Schmidt RA, Linver MN, Edwards AV, Papaioannou J, et al. (2012) Clinically missed cancer: how effectively can radiologists use computer-aided detection? AJR Am J Roentgenol 198: 708–716.
[3]
Fujita H, Uchiyama Y, Nakagawa T, Fukuoka D, Hatanaka Y, et al. (2008) Computer-aided diagnosis: the emerging of three CAD systems induced by Japanese health care needs. Comput Methods Programs Biomed 92: 238–248.
[4]
Zhang MM, Yang H, Jin ZD, Yu JG, Cai ZY, et al. (2010) Differential diagnosis of pancreatic cancer from normal tissue with digital imaging processing and pattern recognition based on a support vector machine of EUS images. Gastrointest Endosc 72: 978–985.
[5]
Goh KL, Yoon BK (2012) Early detection of pancreatic cancer: a possibility in some cases but not a reality in most. J Dig Dis 13: 389–392.
[6]
Xu Q, Zhang TP, Zhao YP (2011) Advances in early diagnosis and therapy of pancreatic cancer. Hepatobiliary Pancreat Dis Int 10: 128–135.
[7]
Vincent A, Herman J, Schulick R, Hruban RH, Goggins M (2011) Pancreatic cancer. Lancet 378: 607–620.
[8]
Eloubeidi MA, Jhala D, Chhieng DC, Chen VK, Eltoum I, et al. (2003) Yield of endoscopic ultrasound-guided fine-needle aspiration biopsy in patients with suspected pancreatic carcinoma. Cancer 99: 285–292.
[9]
Harewood GC, Wiersema MJ (2002) Endosonography-guided fine needle aspiration biopsy in the evaluation of pancreatic masses. Am J Gastroenterol 97: 1386–1391.
[10]
Hewitt MJ, McPhail MJ, Possamai L, Dhar A, Vlavianos P, et al. (2012) EUS-guided FNA for diagnosis of solid pancreatic neoplasms: a meta-analysis. Gastrointest Endosc 75: 319–331.
[11]
Varadarajulu S, Tamhane A, Eloubeidi MA (2005) Yield of EUS-guided FNA of pancreatic masses in the presence or the absence of chronic pancreatitis. Gastrointest Endosc 62: 728–736; quiz 751, 753.
[12]
Fritscher-Ravens A, Brand L, Knofel WT, Bobrowski C, Topalidis T, et al. (2002) Comparison of endoscopic ultrasound-guided fine needle aspiration for focal pancreatic lesions in patients with normal parenchyma and chronic pancreatitis. Am J Gastroenterol 97: 2768–2775.
[13]
Prachayakul V, Sriprayoon T, Asawakul P, Pongprasobchai S, Pausawasdi N, et al. (2012) Repeated endoscopic ultrasound guided fine needle aspiration (EUS-FNA) improved diagnostic yield of inconclusive initial cytology for suspected pancreatic cancer and unknown intra-abdominal lymphadenopathy. J Med Assoc Thai 95 Suppl 2S68–74.
[14]
Hasan MK, Hawes RH (2012) EUS-guided FNA of solid pancreas tumors. Gastrointest Endosc Clin N Am 22: 155–167, vii.
[15]
Othman MO, Wallace MB (2012) The role of endoscopic ultrasonography in the diagnosis and management of pancreatic cancer. Gastroenterol Clin North Am 41: 179–188.
[16]
Horwhat JD, Paulson EK, McGrath K, Branch MS, Baillie J, et al. (2006) A randomized comparison of EUS-guided FNA versus CT or US-guided FNA for the evaluation of pancreatic mass lesions. Gastrointest Endosc 63: 966–975.
[17]
Van Holsbeke C, Van Calster B, Valentin L, Testa AC, Ferrazzi E, et al. (2007) External validation of mathematical models to distinguish between benign and malignant adnexal tumors: a multicenter study by the International Ovarian Tumor Analysis Group. Clin Cancer Res 13: 4440–4447.
[18]
Van Holsbeke C, Van Calster B, Testa AC, Domali E, Lu C, et al. (2009) Prospective internal validation of mathematical models to predict malignancy in adnexal masses: results from the international ovarian tumor analysis study. Clin Cancer Res 15: 684–691.
[19]
Garra BS, Krasner BH, Horii SC, Ascher S, Mun SK, et al. (1993) Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis. Ultrason Imaging 15: 267–285.
[20]
Levman J, Leung T, Causer P, Plewes D, Martel AL (2008) Classification of dynamic contrast-enhanced magnetic resonance breast lesions by support vector machines. IEEE Trans Med Imaging 27: 688–696.
[21]
Mavroforakis ME, Georgiou HV, Dimitropoulos N, Cavouras D, Theodoridis S (2006) Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artif Intell Med 37: 145–162.
[22]
Das A, Nguyen CC, Li F, Li B (2008) Digital image analysis of EUS images accurately differentiates pancreatic cancer from chronic pancreatitis and normal tissue. Gastrointest Endosc 67: 861–867.
[23]
Sahai AV (2002) EUS and chronic pancreatitis. Gastrointest Endosc 56: S76–81.
[24]
Norton ID, Zheng Y, Wiersema MS, Greenleaf J, Clain JE, et al. (2001) Neural network analysis of EUS images to differentiate between pancreatic malignancy and pancreatitis. Gastrointest Endosc 54: 625–629.
