The online version of this article (https://doi.org/10.1186/s13000-018-0739-3) contains supplementary material, which is available to authorized users.
Tumor budding, meaning a detachment of tumor cells at the invasion front of colorectal carcinoma (CRC) into single cells or clusters (<=5 tumor cells), has been shown to correlate to an inferior clinical outcome by several independent studies. Therefore, it has been discussed as a complementary prognostic factor to the TNM staging system, and it is already included in national guidelines as an additional prognostic parameter. However, its application by manual evaluation in routine pathology is hampered due to the use of several slightly different assessment systems, a time-consuming manual counting process and a high inter-observer variability. Hence, we established and validated an automatic image processing approach to reliably quantify tumor budding in immunohistochemically (IHC) stained sections of CRC samples.
This approach combines classical segmentation methods (like morphological operations) and machine learning techniques (k-means and hierarchical clustering, convolutional neural networks) to reliably detect tumor buds in colorectal carcinoma samples immunohistochemically stained for pan-cytokeratin. As a possible application, we tested it on whole-slide images as well as on tissue microarrays (TMA) from a clinically well-annotated CRC cohort.
Our automatic tumor budding evaluation tool detected the absolute number of tumor buds per image with a very good correlation to the manually segmented ground truth (R2 value of 0.86).
Furthermore the automatic evaluation of whole-slide images from 20 CRC-patients, we found that neither the detected number of tumor buds at the invasion front nor the number in hotspots was associated with the nodal status. However, the number of spatial clusters of tumor buds (budding hotspots) significantly correlated to the nodal status (p-value = 0.003 for N0 vs. N1/N2). TMAs were not feasible for tumor budding evaluation, as the spatial relationship of tumor buds (especially hotspots) was not preserved.
Automatic image processing is a feasible and valid assessment tool for tumor budding in CRC on whole-slide images. Interestingly, only the spatial clustering of the tumor buds in hotspots (and especially the number of hotspots) and not the absolute number of tumor buds showed a clinically relevant correlation with patient outcome in our data.
Additional file 1: Table S1. Architecture of the applied CNN. The 8-layer CNN has been designed to classify (100x100x3 pixel) images to the classes “tumor bud” and “no tumor” bud. It consists of two block of a combination of convolutional, rectifier and pooling layers and a fully connected layer. (DOCX 14 kb)13000_2018_739_MOESM1_ESM.docx
Additional file 2: Figure S3. Finding the corresponding core on two separate TMA-slides. Thumbnail of an HE-stained (A) and a pan-cytokeratin-stained (B) TMA-slide. The green circle highlights the same core on both slides, which has due morphological variations different numbers by the image processing based automatic counting. (PDF 6510 kb)13000_2018_739_MOESM2_ESM.pdf
Additional file 3: Pseudocode 1 create TMA-map. Pseudocode 2 combine TMA-maps of different staining. Pseudocode 3 image analysis part I. Pseudocode 4 image analysis part II. (DOCX 16 kb)13000_2018_739_MOESM3_ESM.docx
Additional file 4: Figure S2. Dealing with spatial heterogeneity by different means. Histogram: On basis of the Z-score the vTMAs with values outside the underlying normal distribution could be identified. By doing so the histogram for the number of tumor buds per vTMA could be binarized into vTMA within and outside. Overlay WIS and heatmap for the ROI border: Furthermore by plotting the Z-score values against the coordinates on the WSI, a heatmap with the hotspot-probability could be obtained. In this map values > 1.67 are regarded as significant. (PDF 4012 kb)13000_2018_739_MOESM4_ESM.pdf
WHO. Classification of Tumors of the Digestive System. 4th ed; 2010.
Wittekind C. TNM: Klassifikation maligner Tumoren: Wiley; 2017.
Gospodarowicz MK, Brierley JD, Wittekind C. TNM classification of malignant tumors: Wiley; 2017.
Puppa G, Sonzogni A, Colombari R, Pelosi G. TNM staging system of colorectal carcinoma: a critical appraisal of challenging issues. Arch Pathol Lab Med. 2010;134:837–52. PubMed
Imai T. The growth of human carcinoma: a morphological analysis. Fukuoka Igaku Zasshi. 1954;45:102.
Leitlinienprogramm Onkologie (Deutsche Krebsgesellschaft, Deutsche Krebshilfe, AWMF): S3-Leitlinie Kolorektales Karzinom, Langversion 2.0, 2017. vol. AWMF Registrierungsnummer: 021/007OL: Arbeitsgemeinschaft der Wissenschaftlichen Medizinischen Fachgesellschaften e. V. Deutschen Krebsgesellschaft e.V. Deutschen Krebshilfe; 2017.
Kawachi H, Eishi Y, Ueno H, Nemoto T, Fujimori T, Iwashita A, Ajioka Y, Ochiai A, Ishiguro S, Shimoda T, et al. A three-tier classification system based on the depth of submucosal invasion and budding/sprouting can improve the treatment strategy for T1 colorectal cancer: a retrospective multicenter study. Mod Pathol. 2015;28:872–9. CrossRefPubMed
Welsch U, Mulisch M. Romeis Mikroskopische Technik: Spektrum Akademischer Verlag; 2010.
Taylor CR, Rudbeck L. Immunohistochemical staining methods: Dako; 2013.
OMERO [ https://www.openmicroscopy.org/site].
Johnson R. Matlab programming style guidelines. USA Datatool Version. 2002;1
Johnson R. MATLAV Style Guidelines 2.0. In: Datatool; 2014.
MATLAB Object-Oriented Programming . The MathWorks, Inc.; 2015.
Altman YM. Accelerating MATLAB performance: 1001 tips to speed up MATLAB programs: CRC Press; 2014.
MatConvNet: CNNs for MATLAB [ http://www.vlfeat.org/matconvnet/].
OMERO.matlab toolbox [ https://www.openmicroscopy.org/omero/downloads/].
Ruifrok AC, Johnston DA. Quantification of histochemical staining by color deconvolution. Anal Quant Cytol Histol. 2001;23:291–9. PubMed
Gonzalez RC, Woods RE, Eddins SL. Digital image processing using MATLAB: McGraw Hill Education; 2013.
Reinhard Stain Normalization [ https://de.mathworks.com/matlabcentral/fileexchange/42580-reinhard-stain-normalization].
Magee D, Treanor D, Crellin D, Shires M, Smith K, Mohee K, Quirke P. Colour normalisation in digital histopathology images. In: Elson D, editor. Proc Optical Tissue Image analysis in Microscopy, Histopathology and Endoscopy (MICCAI Workshop); 2009.
Reinhard E, Adhikhmin M, Gooch B, Shirley P. Color transfer between images. IEEE Comput Graph Appl. 2001;21:34–41. CrossRef
R Project [ http://www.r-project.org].
Weis CA, Aban IB, Cutter G, Kaminski HJ, Scharff C, Grießmann BW, Deligianni M, Kayser K, Wolfe GI, Ströbel P, Marx A. Histopathology of thymectomy specimens from the MGTX-trial: Entropy analysis as strategy to quantify spatial heterogeneity of lymphoid follicle and fat distribution. PLoS One. 2018;13(6):e0197435. https://doi.org/10.1371/journal.pone.0197435. eCollection 2018. PMCID: PMC5999223. PMID: 29897907.
Shannon CE. A mathematical theory of communication. Bell Syst Tech J. 1948;27:379–423. CrossRef
Shannon CE. A mathematical theory of communication. SIGMOBILE Mob Comput Commun Rev. 2001;5:3–55. CrossRef
Kayser K, Kayser G, Metze K. The concept of structural entropy in tissue-based diagnosis. Anal Quant Cytol Histol. 2007;29:296–308. PubMed
Nakamura T, Mitomi H, Kikuchi S, Ohtani Y, Sato K. Evaluation of the usefulness of tumor budding on the prediction of metastasis to the lung and liver after curative excision of colorectal cancer. Hepatogastroenterology. 2005;52:1432–5. PubMed
Hengl T. A Practical Guide to Geostatistical Mapping: BPR Publishers; 2011.
Trauth MH, Gebbers R, Marwan N. MATLAB® recipes for earth sciences: Springer; 2007.
Wainwright J, Mulligan M. Environmental modelling: finding simplicity in complexity: Wiley; 2013.
Mahajan S, Mead CA. Street-fighting mathematics: the art of educated guessing and opportunistic problem solving: MIT Press; 2010.
Weis CA, Aban IB, Cutter GR, Kaminski HJ, Scharff C, Grießmann BW, Deligianni M, Kayser K, Ströbel P, Marx A: Histopathology of thymectomy specimens from the MGTX-trial: strategies to reveal spatial heterogeneity of lymphoid follicle and fat distribution. 2017. manuscript submitted.
Graham RP, Vierkant RA, Tillmans LS, Wang AH, Laird PW, Weisenberger DJ, Lynch CF, French AJ, Slager SL, Raissian Y, et al. Tumor budding in colorectal carcinoma: confirmation of prognostic significance and histologic cutoff in a population-based cohort. Am J Surg Pathol. 2015;39:1340–6. CrossRefPubMedPubMedCentral
Koelzer VH, Assarzadegan N, Dawson H, Mitrovic B, Grin A, Messenger DE, Kirsch R, Riddell RH, Lugli A, Zlobec I. Cytokeratin-based assessment of tumor budding in colorectal cancer: analysis in stage II patients and prospective diagnostic experience. J Pathol Clin Res. 2017;3:171–8. CrossRefPubMedPubMedCentral
- Automatic evaluation of tumor budding in immunohistochemically stained colorectal carcinomas and correlation to clinical outcome
Jakob Nikolas Kather
Marion J. Pollheimer
- BioMed Central