Automatic recognition of different types of acute leukaemia in peripheral blood by image analysis

Aims Morphological differentiation among different blast cell lineages is a difficult task and there is a lack of automated analysers able to recognise these abnormal cells. This study aims to develop a machine learning approach to predict the diagnosis of acute leukaemia using peripheral blood (PB) images. Methods A set of 442 smears was analysed from 206 patients. It was split into a training set with 75% of these smears and a testing set with the remaining 25%. Colour clustering and mathematical morphology were used to segment cell images, which allowed the extraction of 2,867 geometric, colour and texture features. Several classification techniques were studied to obtain the most accurate classification method. Afterwards, the classifier was assessed with the images of the testing set. The final strategy was to predict the patient’s diagnosis using the PB smear, and the final assessment was done with the cell images of the smears of the testing set. Results The highest classification accuracy was achieved with the selection of 700 features with linear discriminant analysis. The overall classification accuracy for the six groups of cell types was 85.8%, while the overall classification accuracy for individual smears was 94% as compared with the true confirmed diagnosis. Conclusions The proposed method achieves a high diagnostic precision in the recognition of different types of blast cells among other mononuclear cells circulating in blood. It is the first encouraging step towards the idea of being a diagnostic support tool in the future.

[1]  Saeed Kermani,et al.  Computer aided detection and classification of acute lymphoblastic leukemia cell subtypes based on microscopic image analysis , 2016, Microscopy research and technique.

[2]  J Rodellar,et al.  Optimizing morphology through blood cell image analysis , 2018, International journal of laboratory hematology.

[3]  Sos S. Agaian,et al.  A new acute leukaemia-automated classification system , 2018, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[4]  M. Y. Mashor,et al.  Classification of blasts in acute leukemia blood samples using k-nearest neighbour , 2012, 2012 IEEE 8th International Colloquium on Signal Processing and its Applications.

[5]  A. Merino,et al.  Acute myeloid leukaemia: How to combine multiple tools , 2018, International journal of laboratory hematology.

[6]  Sos S. Agaian,et al.  New decision support tool for acute lymphoblastic leukemia classification , 2012, Electronic Imaging.

[7]  E. Estey,et al.  Management of acute promyelocytic leukemia: recommendations from an expert panel on behalf of the European LeukemiaNet. , 2009, Blood.

[8]  B. Bain.  Leukaemia Diagnosis: Bain/Leukaemia Diagnosis , 2010 .

[9]  Cecilia Di Ruberto,et al.  Leucocyte classification for leukaemia detection using image processing techniques , 2014, Artif. Intell. Medicine.

[10]  Jie Hu,et al.  Abnormal localization of immature precursors (ALIP) detection for early prediction of acute myelocytic leukemia (AML) relapse , 2014, Medical & Biological Engineering & Computing.

[11]  N. Ranganathan,et al.  Gabor filter-based edge detection , 1992, Pattern Recognit..

[12]  Babak Nadjar Araabi,et al.  Automatic Recognition of Acute Myelogenous Leukemia in Blood Microscopic Images Using K-means Clustering and Support Vector Machine , 2016, Journal of medical signals and sensors.

[13]  D. Chabot-Richards,et al.  Does morphology matter in 2017? An approach to morphologic clues in non‐neoplastic blood and bone marrow disorders , 2017, International journal of laboratory hematology.

[14]  B. B. Zaidan,et al.  A review of the automated detection and classification of acute leukaemia: Coherent taxonomy, datasets, validation and performance measurements, motivation, open challenges and recommendations , 2018, Comput. Methods Programs Biomed..

[15]  Alférez Baquero,et al.  Methodology for automatic classification of atypical lymphoid cells from peripheral blood cell images , 2015 .

[16]  Antonio Jesús Arriaza Gómez,et al.  Estadística Básica con R y R-Commander , 2008 .

[17]  Calyampudi Radhakrishna Rao,et al.  Signal Processing and its Applications , 1993, Handbook of Statistics.

[18]  A. Porwit,et al.  Acute myeloid leukemia with expanded erythropoiesis , 2011, Haematologica.

[19]  F. Scotti,et al.  Automatic morphological analysis for acute leukemia identification in peripheral blood microscope images , 2005, CIMSA. 2005 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, 2005..

[20]  D. Grimwade,et al.  The pathogenesis and management of the coagulopathy of acute promyelocytic leukaemia , 2012, British journal of haematology.

[21]  Francesc Pozo,et al.  Wind turbine fault detection and classification by means of image texture analysis , 2018, Mechanical Systems and Signal Processing.

[22]  J Rodellar,et al.  Automatic classification of atypical lymphoid B cells using digital blood image processing , 2014, International journal of laboratory hematology.

[23]  Hayan Tareq Abdul Wahhab.  Classification of acute leukemia using image processing and machine learning techniques / Hayan Tareq Abdul Wahhab , 2015 .

[24]  J M Jou,et al.  EQAS for peripheral blood morphology in Spain: a 6‐year experience , 2007, International journal of laboratory hematology.

[25]  Mario Cazzola,et al.  The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia. , 2016, Blood.

[26]  Xiaofeng Yang,et al.  Ultrasound GLCM texture analysis of radiation-induced parotid-gland injury in head-and-neck cancer radiotherapy: an in vivo study of late toxicity. , 2012, Medical physics.

[27]  F. Cendes,et al.  Texture analysis of medical images. , 2004, Clinical radiology.

[28]  José Rodellar,et al.  New quantitative features for the morphological differentiation of abnormal lymphoid cell images from peripheral blood , 2017, Journal of Clinical Pathology.

[29]  José Rodellar,et al.  Color clustering segmentation framework for image analysis of malignant lymphoid cells in peripheral blood , 2019, Medical & Biological Engineering & Computing.

[30]  Banshidhar Majhi,et al.  Gray level co-occurrence matrix and random forest based acute lymphoblastic leukemia detection , 2017, Biomed. Signal Process. Control..

[31]  Sos S. Agaian,et al.  Automated Screening System for Acute Myelogenous Leukemia Detection in Blood Microscopic Images , 2014, IEEE Systems Journal.

[32]  Stephen Johnson,et al.  Stephen Johnson on digital photography , 2006 .

[33]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[34]  Gavin Brown,et al.  Conditional Likelihood Maximisation: A Unifying Framework for Information Theoretic Feature Selection , 2012, J. Mach. Learn. Res..

[35]  José Rodellar,et al.  Feature Analysis and Automatic Identification of Leukemic Lineage Blast Cells and Reactive Lymphoid Cells from Peripheral Blood Cell Images , 2017, Journal of clinical laboratory analysis.

[36]  C Briggs,et al.  Can automated blood film analysis replace the manual differential? An evaluation of the CellaVision DM96 automated image analysis system , 2009, International journal of laboratory hematology.

[37]  J Rodellar,et al.  Image processing and machine learning in the morphological analysis of blood cells , 2018, International journal of laboratory hematology.

[38]  Dipti Patra,et al.  An ensemble classifier system for early diagnosis of acute lymphoblastic leukemia in blood microscopic images , 2013, Neural Computing and Applications.

[39]  Chris Johnson.  The Zone System and Digital Photography , 2006 .

[40]  Barbara J. Bain,et al.  LEUKAEMIA DIAGNOSIS , 2013 .