Automated histological classification of whole-slide images of gastric biopsy specimens

BackgroundAutomated image analysis has been developed currently in the field of surgical pathology. The aim of the present study was to evaluate the classification accuracy of the e-Pathologist image analysis software.MethodsA total of 3062 gastric biopsy specimens were consecutively obtained and stained. The specimen slides were anonymized and digitized. At least two experienced gastrointestinal pathologists evaluated each slide for pathological diagnosis. We compared the three-tier (positive for carcinoma or suspicion of carcinoma; caution for adenoma or suspicion of a neoplastic lesion; or negative for a neoplastic lesion) or two-tier (negative or non-negative) classification results of human pathologists and of the e-Pathologist.ResultsOf 3062 cases, 33.4% showed an abnormal finding. For the three-tier classification, the overall concordance rate was 55.6% (1702/3062). The kappa coefficient was 0.28 (95% CI, 0.26–0.30; fair agreement). For the negative biopsy specimens, the concordance rate was 90.6% (1033/1140), but for the positive biopsy specimens, the concordance rate was less than 50%. For the two-tier classification, the sensitivity, specificity, positive predictive value, and negative predictive value were 89.5% (95% CI, 87.5–91.4%), 50.7% (95% CI, 48.5–52.9%), 47.7% (95% CI, 45.4–49.9%), and 90.6% (95% CI, 88.8–92.2%), respectively.ConclusionsAlthough there are limitations and requirements for applying automated histopathological classification of gastric biopsy specimens in the clinical setting, the results of the present study are promising.

[1]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[2]  Grgoire Montavon,et al.  Neural Networks: Tricks of the Trade , 2012, Lecture Notes in Computer Science.

[3]  M F Dixon,et al.  The Vienna classification of gastrointestinal epithelial neoplasia , 2000, Gut.

[4]  Shaimaa Al-Janabi,et al.  Digital pathology: current status and future perspectives , 2012, Histopathology.

[5]  R. Sirota,et al.  Derivation of a new hematopoietic cell line with endothelial features from a patient with transformed myeloproliferative syndrome , 2000, Cancer.

[6]  D. Park,et al.  Practical Points in Gastric Pathology. , 2016, Archives of pathology & laboratory medicine.

[7]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[8]  Hiroshi Nishimoto,et al.  An updated report on the trends in cancer incidence and mortality in Japan, 1958-2013. , 2015, Japanese journal of clinical oncology.

[9]  A. Renshaw,et al.  Interpretive Diagnostic Error Reduction in Surgical Pathology and Cytology: Guideline From the College of American Pathologists Pathology and Laboratory Quality Center and the Association of Directors of Anatomic and Surgical Pathology. , 2016, Archives of pathology & laboratory medicine.

[10]  Joseph Bockhorst,et al.  Automatic classification of white regions in liver biopsies by supervised machine learning. , 2014, Human pathology.

[11]  T. Aiko,et al.  New Japanese classifications and treatment guidelines for gastric cancer: revision concepts and major revised points , 2011, Gastric Cancer.

[12]  Mark G. Eramian,et al.  Automated classification of four types of developmental odontogenic cysts , 2014, Comput. Medical Imaging Graph..

[13]  Mattias Rantalainen,et al.  Digital image analysis outperforms manual biomarker assessment in breast cancer , 2016, Modern Pathology.

[14]  Marianne U. Prey,et al.  The AutoPap System for Primary Screening in Cervical Cytology , 1998, Acta Cytologica.

[15]  D. de Jong,et al.  Interobserver variation in the histopathological assessment of malt/malt lymphoma: towards a consensus. , 2005, Blood cells, molecules & diseases.

[16]  Measuring errors in surgical pathology in real-life practice: defining what does and does not matter. , 2007, American journal of clinical pathology.

[17]  Christopher Naugler,et al.  The history of pathology informatics: A global perspective , 2013, Journal of pathology informatics.

[18]  K. Sugano,et al.  Screening of gastric cancer in Asia. , 2015, Best practice & research. Clinical gastroenterology.

[19]  Akira Saito,et al.  Automated gastric cancer diagnosis on H&E-stained sections; ltraining a classifier on a large scale with multiple instance machine learning , 2013, Medical Imaging.

[20]  S. El Hallani,et al.  Evaluation of Quantitative Digital Pathology in the Assessment of Barrett Esophagus-Associated Dysplasia. , 2015, American journal of clinical pathology.

[21]  A. Renshaw,et al.  Comparison of disagreement and amendment rates by tissue type and diagnosis: identifying cases for directed blinded review. , 2006, American journal of clinical pathology.

[22]  J. Sim,et al.  The kappa statistic in reliability studies: use, interpretation, and sample size requirements. , 2005, Physical therapy.