Advertisement
New Methods & Materials| Volume 54, ISSUE 5, P625-629, November 2001

Download started.

Ok

Neural network analysis of EUS images to differentiate between pancreatic malignancy and pancreatitis

  • Ian D. Norton
    Affiliations
    Division of Gastroenterology and Hepatology and the Department of Diagnostic Ultrasound, Mayo Clinic, Rochester, and the Department of Electrical Engineering, St. Cloud State University, Minnesota
    Search for articles by this author
  • Yi Zheng
    Affiliations
    Division of Gastroenterology and Hepatology and the Department of Diagnostic Ultrasound, Mayo Clinic, Rochester, and the Department of Electrical Engineering, St. Cloud State University, Minnesota
    Search for articles by this author
  • Maurits S. Wiersema
    Affiliations
    Division of Gastroenterology and Hepatology and the Department of Diagnostic Ultrasound, Mayo Clinic, Rochester, and the Department of Electrical Engineering, St. Cloud State University, Minnesota
    Search for articles by this author
  • James Greenleaf
    Affiliations
    Division of Gastroenterology and Hepatology and the Department of Diagnostic Ultrasound, Mayo Clinic, Rochester, and the Department of Electrical Engineering, St. Cloud State University, Minnesota
    Search for articles by this author
  • Jonathan E. Clain
    Affiliations
    Division of Gastroenterology and Hepatology and the Department of Diagnostic Ultrasound, Mayo Clinic, Rochester, and the Department of Electrical Engineering, St. Cloud State University, Minnesota
    Search for articles by this author
  • Eugene P. DiMagno
    Affiliations
    Division of Gastroenterology and Hepatology and the Department of Diagnostic Ultrasound, Mayo Clinic, Rochester, and the Department of Electrical Engineering, St. Cloud State University, Minnesota
    Search for articles by this author

      Abstract

      Background: The differentiation of focal pancreatitis and pancreatic adenocarcinoma is problematic and often resolved only by pancreaticoduodenectomy. EUS is the most sensitive imaging modality for both conditions, yet ultrasonic criteria for distinguishing the two have not been described and differentiation remains difficult. The aims of this study were to develop a self-learning computer program that can analyze EUS images and differentiate malignancy from pancreatitis, and to compare results obtained with this system with EUS interpretation by experienced endosonographers. Methods: Twenty-one patients with pancreatic cancer and 14 with focal pancreatitis were included. The diagnosis was confirmed histologically in all cases and each patient had undergone EUS. A single EUS image from each procedure was used for computer analysis. The results were compared with the EUS diagnosis reported at the actual procedure as well that of an endosonographer who reviewed videotapes of the procedures. Results: The software program differentiated focal pancreatitis from malignancy with a maximal 89% accuracy. With sensitivity set at 100% for malignancy, the program was 50% specific and accuracy was 80%. Sensitivity and accuracy of the endosonographer's impression at the time of EUS were, respectively, 89% and 85%. A sensitivity of 73% and accuracy of 83% were achieved with blinded interpretation of EUS videotapes. Conclusions: Analysis of EUS images with computer software programs is feasible and compares favorably with human interpretation. The application of this technology to EUS and other imaging scenarios could be a useful adjunct to diagnostic endoscopy and warrants further investigation.
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Gastrointestinal Endoscopy
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Boring CC
        • Squires TS
        • Tong T.
        Cancer statistics, 1993.
        CA Cancer J Clin. 1993; 43: 7-26
        • Anonymous
        SBBR cancer statistics review 1973-90. National Institutes of Health/National Cancer Institute, Bethesda1993
        • Moossa AR
        • Gamagami RA.
        Diagnosis and staging of pancreatic neoplasms.
        Surg Clin North Am. 1995; 75: 871-890
        • Lowenfels AB
        • Maisonneuve P
        • Cavallini G
        • Ammann RW
        • G LP
        • Anderson JR
        • et al.
        Pancreatitis and the risk of pancreatic cancer.
        New Engl J Med. 1993; 328: 1433-1437
        • Smith CD
        • Behms KB
        • van Heerden JA
        • Sarr MG.
        Radical pancreatoduodenectomy for misdiagnosed pancreatic mass.
        Br J Surg. 1994; 81: 585-589
        • Rösch T
        • Lorenz R
        • Braig C
        • Feuerbach S
        • Siewert JR
        • Schusdziarra V
        • et al.
        Endoscopic ultrasound in pancreatic tumor diagnosis.
        Gastrointest Endosc. 1991; 37: 347-352
        • Yasuda K
        • Mukai H
        • Nakajima M.
        Endoscopic ultrasonography diagnosis of pancreatic cancer.
        Gastrointest Endosc Clin N Am. 1995; 5: 699-712
        • Buscail L
        • Escourrou J
        • Moreau J
        • Delvaux M
        • Louvel D
        • Lapeyre F
        • et al.
        Endoscopic ultrasonography in chronic pancreatitis: a comparative prospective study with conventional ultrasonography, computed tomography, and ERCP.
        Pancreas. 1995; 10: 251-257
        • Hayashi Y
        • Nakazawa S
        • Kimoto B
        • Naito Y
        • Morita K.
        Clinicopathologic analysis of endoscopic ultrasonograms in pancreatic mass lesions.
        Endoscopy. 1989; 21: 121-125
        • O'Toole D
        • Palazzo L
        • Arotcarena R
        • Dancour A
        • Aubert A
        • Hammel P
        • et al.
        Assessment of complications of EUS-guided fine needle aspiration.
        Gastrointest Endosc. 2001; 53: 470-474
        • Wiersema MJ
        • Vilmann P
        • Giovannini M
        • Chang KJ
        • Wiersema LM.
        Endosonography-guided fine-needle aspiration biopsy: diagnostic accuracy and complication assessment.
        Gastroenterology. 1997; 112: 1087-1095
        • Gress F
        • Savides T
        • Cummings O
        • Sherman S
        • Lehman U
        • Zaidi S
        • et al.
        Radial scanning and linear array endosonography for staging pancreatic cancer: a prospective randomized comparison.
        Gastrointest Endosc. 1997; 45: 138-142
        • Pitt HA.
        Curative treatment for pancreatic neoplasms.
        Surg Clin North Am. 1995; 75: 891-904
        • Goldberg V
        • Manduca A
        • Ewert DL
        • Gisvold JJ
        • Greenleaf JF.
        Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligences.
        Med Phys. 1992; 19: 1475-1481
        • Zheng Y
        • Greenleaf JF
        • Gisvold JJ.
        Reduction of breast biopsies with a modified self-organizing map.
        IEEE Trans Neural Network. 1997; 8: 1386-1396
        • Niederau C
        • Grendell JH.
        Diagnosis of chronic pancreatitis.
        Gastroenterology. 1985; 88: 1973-1995
        • Van Gulik T
        • Reeders JWAJ
        • Bosma A
        • Moojen TM
        • Smits NJ
        • Allema JH
        • et al.
        Incidence and clinical findings of benign, inflammatory disease in patients resected for presumed pancreatic head cancer.
        Gastrointest Endosc. 1997; 46: 417-423
        • Cohen JR
        • Kutcha N
        • Geller N
        • Shires GT
        • Dineen P.
        Pancreaticoduodenectomy for benign disease.
        Ann Surg. 1983; 197: 68-71
        • Neff CC
        • Simeone JF
        • Wittenberg J
        • Mueller PR
        • Ferrucci Jr., JT
        Inflammatory pancreatic masses. Problems in differentiating focal pancreatitis from carcinoma.
        Radiology. 1984; 150: 35-38