Automated image analysis in histopathology: a valuable tool in medical diagnostics

Virtual pathology, the process of assessing digital images of histological slides, is gaining momentum in today’s laboratory environment. Indeed, digital image acquisition systems are becoming commonplace, and associated image analysis solutions are viewed by most as the next critical step in automated histological analysis. Here, we document the advances in the technology, with reference to past and current techniques in histological assessment. In addition, the demand for these technologies is analyzed with major players profiled. As there are several image analysis software programs focusing on the quantification of immunohistochemical staining, particular attention is paid to this application in this review. Oncology has been a primary target area for these approaches, with example studies in this therapeutic area being covered here. Toxicology-based image analysis solutions are also profiled as these are steadily increasing in popularity, especially within the pharmaceutical industry. Reinforced by the phenomenal growth of the virtual pathology field, it is envisioned that the market for automated image analysis tools will greatly expand over the next 10 years.

[1]  J. Itoh,et al.  Immunohistochemical Evaluation of Hormone Receptors in Breast Cancer: Which Scoring System Is Suitable for Highly Sensitive Procedures? , 2004, Applied immunohistochemistry & molecular morphology : AIMM.

[2]  E. Kay,et al.  C-erbB-2 immunostaining: problems with interpretation. , 1994, Journal of clinical pathology.

[3]  Maria Athelogou,et al.  Cognition Network Technology – A Novel Multimodal Image Analysis Technique for Automatic Identification and Quantification of Biological Image Contents , 2007 .

[4]  Katharina Glatz-Krieger,et al.  Factors to keep in mind when introducing virtual microscopy , 2006, Virchows Archiv.

[5]  Thomas Rüdiger,et al.  Quality Assurance in Immunohistochemistry: Results of an Interlaboratory Trial Involving 172 Pathologists , 2002, The American journal of surgical pathology.

[6]  Neal R. Harvey,et al.  Genetic algorithm for combining new and existing image processing tools for multispectral imagery , 2000, SPIE Defense + Commercial Sensing.

[7]  E Persohn,et al.  Cell proliferation measurement in cecum and colon of rats using scanned images and fully automated image analysis: validation of method. , 2007, Experimental and toxicologic pathology : official journal of the Gesellschaft fur Toxikologische Pathologie.

[8]  J. Kononen,et al.  A high‐throughput strategy for protein profiling in cell microarrays using automated image analysis , 2007, Proteomics.

[9]  Greg Yothers,et al.  Real-world performance of HER2 testing--National Surgical Adjuvant Breast and Bowel Project experience. , 2002, Journal of the National Cancer Institute.

[10]  T. Grogan,et al.  Discrepancies in clinical laboratory testing of eligibility for trastuzumab therapy: apparent immunohistochemical false-positives do not get the message. , 2001, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[11]  H A Lehr,et al.  Quantitative evaluation of HER-2/neu status in breast cancer by fluorescence in situ hybridization and by immunohistochemistry with image analysis. , 2001, American journal of clinical pathology.

[12]  F. Penault-Llorca,et al.  Comparison of different commercial kits for HER2 testing in breast cancer: looking for the accurate cutoff for amplification , 2007, Breast Cancer Research.

[13]  Peter A Dervan,et al.  Contribution of DNA and tissue microarray technology to the identification and validation of biomarkers and personalised medicine in breast cancer. , 2007, Cancer genomics & proteomics.

[14]  Juan F. García,et al.  Tumor microenvironment and mitotic checkpoint are key factors in the outcome of classic Hodgkin lymphoma. , 2006, Blood.

[15]  Thomas Rüdiger,et al.  Inter‐laboratory and inter‐observer reproducibility of immunohistochemical assessment of the Ki‐67 labelling index in a large multi‐centre trial , 2002, The Journal of pathology.

[16]  C. Cohen,et al.  Strong HER-2/neu protein overexpression by immunohistochemistry often does not predict oncogene amplification by fluorescence in situ hybridization. , 2003, Human pathology.

[17]  G. Fuller,et al.  Polypyrimidine tract binding protein and Notch1 are independently re-expressed in glioma , 2006, Modern Pathology.

[18]  N. Fleshner,et al.  Comparison of annexin II, p63 and α-methylacyl-CoA racemase immunoreactivity in prostatic tissue: a tissue microarray study , 2006, Journal of Clinical Pathology.

[19]  Joerg Schwock,et al.  Quantitative image analysis of immunohistochemical stains using a CMYK color model , 2007, Diagnostic pathology.

[20]  J. Kononen,et al.  Tissue microarrays for high-throughput molecular profiling of tumor specimens , 1998, Nature Medicine.

[21]  Matt van de Rijn,et al.  Tissue Microarrays Are an Effective Quality Assurance Tool for Diagnostic Immunohistochemistry , 2002, Modern Pathology.

[22]  G. Fuller,et al.  High‐Throughput Molecular Profiling of High‐Grade Astrocytomas: The Utility of Fluorescence In Situ Hybridization on Tissue Microarrays (TMA‐FISH) , 2002, Journal of neuropathology and experimental neurology.

[23]  T. Fehm,et al.  Image analysis systems for the detection of disseminated breast cancer cells on bone‐marrow cytospins , 2005, Journal of clinical laboratory analysis.

[24]  J. Horiguchi,et al.  The effects of fixation, processing and evaluation criteria on immunohistochemical detection of hormone receptors in breast cancer , 2007, Breast cancer.

[25]  D. Rimm,et al.  Automated subcellular localization and quantification of protein expression in tissue microarrays , 2002, Nature Medicine.

[26]  R. Ogilvie,et al.  Trends in histology laboratory teaching in United States medical schools. , 2006, Anatomical record. Part B, New anatomist.

[27]  Desok Kim,et al.  Immunohistochemical quantitation of androgen receptor expression using color video image analysis. , 1999, Cytometry.

[28]  Karen A Gelmon,et al.  Immunohistochemical detection using the new rabbit monoclonal antibody SP1 of estrogen receptor in breast cancer is superior to mouse monoclonal antibody 1D5 in predicting survival. , 2006, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[29]  Melanie Mitchell,et al.  Investigation of image feature extraction by a genetic algorithm , 1999, Optics + Photonics.

[30]  Anna Frolov,et al.  The prolyl isomerase Pin1 is a novel prognostic marker in human prostate cancer. , 2003, Cancer research.

[31]  L. Goldstein,et al.  Automated quantitative analysis of estrogen receptor expression in breast carcinoma does not differ from expert pathologist scoring: a tissue microarray study of 3,484 cases , 2008, Breast Cancer Research and Treatment.

[32]  Joel H. Saltz,et al.  Digital dynamic telepathology-the Virtual Microscope , 1998, AMIA.

[33]  Peter Houghton,et al.  Credentialing preclinical pediatric xenograft models using gene expression and tissue microarray analysis. , 2007, Cancer research.

[34]  J. Baak,et al.  The framework of pathology: good laboratory practice by quantitative and molecular methods , 2002, The Journal of pathology.

[35]  B. Molnár,et al.  Digital slide and virtual microscopy based routine and telepathology evaluation of routine gastrointestinal biopsy specimens , 2003 .

[36]  L. Sarian,et al.  Expression of cyclooxygenase-2 (COX-2) and Ki67 as related to disease severity and HPV detection in squamous lesions of the cervix. , 2006, Gynecologic oncology.

[37]  D. Rimm,et al.  Validation of Tissue Microarray Technology in Breast Carcinoma , 2000, Laboratory Investigation.

[38]  D. Rimm,et al.  Classification of Breast Cancer Using Genetic Algorithms and Tissue Microarrays , 2006, Clinical Cancer Research.

[39]  H. Bernstein,et al.  Perils of Immunohistochemistry: Variability in Staining Specificity of Commercially Available COX-2 Antibodies on Human Colon Tissue , 2004, Digestive Diseases and Sciences.

[40]  M. Hammond,et al.  Conference Summary, Strategic Science Symposium , 2009 .

[41]  Gloria Bueno García,et al.  Critical Comparison of 31 Commercially Available Digital Slide Systems in Pathology , 2006, International journal of surgical pathology.

[42]  Ross Foley,et al.  Automated Image Analysis Approaches in Histopathology , 2009 .

[43]  H. Moch,et al.  High-throughput tissue microarray analysis to evaluate genes uncovered by cDNA microarray screening in renal cell carcinoma. , 1999, The American journal of pathology.

[44]  J. R. Reeves,et al.  Evaluating HER2 amplification and overexpression in breast cancer , 2001, The Journal of pathology.

[45]  M. Piris,et al.  Frequency of BCL2 and BCL6 translocations in follicular lymphoma: Relation with histological and clinical features , 2008, Leukemia & lymphoma.

[46]  K A Matkowskyj,et al.  Quantitative Immunohistochemistry by Measuring Cumulative Signal Strength Using Commercially Available Software Photoshop and Matlab , 2000, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[47]  S. Asano,et al.  Quantitative image analysis in adipose tissue using an automated image analysis system: Differential effects of peroxisome proliferator‐activated receptor‐α and ‐γ agonist on white and brown adipose tissue morphology in AKR obese and db/db diabetic mice , 2007, Pathology international.

[48]  S. Merajver,et al.  Validation of a Tissue Microarray to Study Differential Protein Expression in Inflammatory and Non-Inflammatory Breast Cancer , 2004, Breast Cancer Research and Treatment.

[49]  Yukako Yagi,et al.  Primary histologic diagnosis using automated whole slide imaging: a validation study , 2006, BMC clinical pathology.

[50]  R. Uddman,et al.  Downregulation of peroxisome proliferator-activated receptors (PPARs) in nasal polyposis , 2005, Respiratory research.

[51]  S. Hewitt,et al.  Infrared spectroscopic imaging for histopathologic recognition , 2005, Nature Biotechnology.

[52]  Mikhail Teverovskiy,et al.  Multifeature Prostate Cancer Diagnosis and Gleason Grading of Histological Images , 2007, IEEE Transactions on Medical Imaging.

[53]  Jinha M. Park,et al.  Evaluation of HER-2/neu gene amplification and overexpression: comparison of frequently used assay methods in a molecularly characterized cohort of breast cancer specimens. , 2002, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[54]  Johannes Bernarding,et al.  Digital pathology: DICOM-conform draft, testbed, and first results , 2007, Comput. Methods Programs Biomed..

[55]  John J Spinelli,et al.  HER-2/neu in Breast Cancer: Interobserver Variability and Performance of Immunohistochemistry with 4 Antibodies Compared with Fluorescent In Situ Hybridization , 2001, Modern Pathology.

[56]  Wh Sit,et al.  Cancer Genomics & Proteomics , 2007 .

[57]  C. Street,et al.  The Cancer Biomedical Informatics Grid (caBIGTM) , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[58]  C. Wells,et al.  Predictive markers in breast cancer – the present , 2007, Histopathology.

[59]  J Lundin,et al.  A public-domain image processing tool for automated quantification of fluorescence in situ hybridisation signals , 2007, Journal of Clinical Pathology.

[60]  H. Battifora.  The multitumor (sausage) tissue block: novel method for immunohistochemical antibody testing. , 1986, Laboratory investigation; a journal of technical methods and pathology.

[61]  Yu-Ping Wang,et al.  Normalization of multicolor fluorescence in situ hybridization (M‐FISH) images for improving color karyotyping , 2005, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[62]  R. Jones,et al.  Immunological Properties of an Antibody Containing a Fluorescent Group.∗ , 1941 .

[63]  John Calvin Reed,et al.  Claudin‐1 immunohistochemistry for distinguishing malignant from benign epithelial lesions of prostate , 2007, The Prostate.

[64]  C. Cordon-Cardo,et al.  Validation of tissue microarrays for immunohistochemical profiling of cancer specimens using the example of human fibroblastic tumors. , 2001, The American journal of pathology.

[65]  Anthony Rhodes,et al.  American Society of Clinical Oncology/College of American Pathologists guideline recommendations for human epidermal growth factor receptor 2 testing in breast cancer. , 2006, Archives of pathology & laboratory medicine.

[66]  R. Cardiff,et al.  Classification of Proliferative Pulmonary Lesions of the Mouse , 2004, Cancer Research.

[67]  M. Hammond,et al.  Conference summary, Strategic Science symposium. Her-2/neu testing of breast cancer patients in clinical practice. , 2003, Archives of pathology & laboratory medicine.

[68]  Mikhail Teverovskiy,et al.  Improved prediction of prostate cancer recurrence through systems pathology. , 2007, The Journal of clinical investigation.

[69]  J. L. Au,et al.  Application of automatic thresholding in image analysis scoring of cells in human solid tumors labeled for proliferation markers. , 1997, Cytometry.

[70]  Ronda Dulbandzhyan,et al.  Storage and distribution of pathology digital images using integrated web-based viewing systems. , 2002, Archives of pathology & laboratory medicine.

[71]  F J Leong,et al.  Automated complete slide digitization: a medium for simultaneous viewing by multiple pathologists , 2001, The Journal of pathology.

[72]  D. Rimm,et al.  Immunohistochemistry and quantitative analysis of protein expression. , 2009, Archives of pathology & laboratory medicine.

[73]  A brightness-area-product-based protocol for the quantitative assessment of antigen abundance in fluorescent immunohistochemistry. , 2005, Brain research. Brain research protocols.

[74]  B Fisher,et al.  Five versus more than five years of tamoxifen therapy for breast cancer patients with negative lymph nodes and estrogen receptor-positive tumors. , 1996, Journal of the National Cancer Institute.

[75]  David L Rimm,et al.  Quantitative analysis of breast cancer tissue microarrays shows that both high and normal levels of HER2 expression are associated with poor outcome. , 2003, Cancer research.

[76]  H. Moch,et al.  Tissue microarray (TMA) technology: miniaturized pathology archives for high‐throughput in situ studies , 2001, The Journal of pathology.

[77]  William M. Gallagher,et al.  Creation of a digital slide and tissue microarray resource from a multi-institutional predictive toxicology study in the rat: an initial report from the PredTox group. , 2008, Experimental and toxicologic pathology : official journal of the Gesellschaft fur Toxikologische Pathologie.

[78]  P. Sanders,et al.  Effects of griseofulvin in medium-term liver carcinogenesis assay and peripheral blood micronucleus test in rat. , 2001, Teratogenesis, carcinogenesis, and mutagenesis.

[79]  T. Lörch,et al.  Automatic telomere length measurements in interphase nuclei by IQ‐FISH , 2005, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[80]  Aedín C Culhane,et al.  Altered Cytoplasmic-to-Nuclear Ratio of Survivin Is a Prognostic Indicator in Breast Cancer , 2008, Clinical Cancer Research.

[81]  J. Giltnane,et al.  AQUA and FISH analysis of HER‐2/neu expression and amplification in a small cell lung carcinoma tissue microarray , 2006, Histopathology.

[82]  J. Żurawski,et al.  A quantitative analysis of the expression of alpha-smooth muscle actin in mesangioproliferative (GnMes) glomerulonephritis. , 2003, Folia morphologica.

[83]  Peter A Kaufman,et al.  HER2 testing by local, central, and reference laboratories in specimens from the North Central Cancer Treatment Group N9831 intergroup adjuvant trial. , 2006, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[84]  D. Rimm,et al.  Automated quantitative analysis (AQUA) of in situ protein expression, antibody concentration, and prognosis. , 2005, Journal of the National Cancer Institute.

[85]  Rohit Bhargava,et al.  High throughput assessment of cells and tissues: Bayesian classification of spectral metrics from infrared vibrational spectroscopic imaging data. , 2006, Biochimica et biophysica acta.

[86]  Charles A Blake,et al.  Teaching medical histology at the University of South Carolina School of Medicine: Transition to virtual slides and virtual microscopes. , 2003, Anatomical record. Part B, New anatomist.

[87]  J. Weinstein,et al.  Biomarkers in Cancer Staging, Prognosis and Treatment Selection , 2005, Nature Reviews Cancer.

[88]  E. Kaczmarek,et al.  Techniques of image analysis for quantitative immunohistochemistry. , 2004, Roczniki Akademii Medycznej w Bialymstoku.

[89]  A. Seth,et al.  Computer based receptogram approach: an objective way of assessing immunohistochemistry of androgen receptor staining and its correlation with hormonal response in metastatic carcinoma of prostate , 2004, Journal of Clinical Pathology.

[90]  D Butler,et al.  Biopsy of a biopsy: validation of immunoprofiling in gastric cancer biopsy tissue microarrays , 2003, Histopathology.

[91]  J. Bryant,et al.  Treatment of lymph-node-negative, oestrogen-receptor-positive breast cancer: long-term findings from National Surgical Adjuvant Breast and Bowel Project randomised clinical trials , 2004, The Lancet.

[92]  S S Cross,et al.  Observer accuracy in estimating proportions in images: implications for the semiquantitative assessment of staining reactions and a proposal for a new system , 2001, Journal of clinical pathology.

[93]  M. J. van de Vijver,et al.  Assessment of a HER2 scoring system for gastric cancer: results from a validation study , 2008, Histopathology.

[94]  Joel H. Saltz,et al.  The virtual microscope , 2003, IEEE Transactions on Information Technology in Biomedicine.