Automated morphometric classification of acute lymphoblastic leukaemia in blood microscopic images using an ensemble of classifiers

Author(s):  
Subrajeet Mohapatra ◽  
Dipti Patra ◽  
Sanghamitra Satpathy ◽  
Rabindra Kumar Jena ◽  
Sudha Sethy
2020 ◽  
Vol 65 (6) ◽  
pp. 759-773
Author(s):  
Segu Praveena ◽  
Sohan Pal Singh

AbstractLeukaemia detection and diagnosis in advance is the trending topic in the medical applications for reducing the death toll of patients with acute lymphoblastic leukaemia (ALL). For the detection of ALL, it is essential to analyse the white blood cells (WBCs) for which the blood smear images are employed. This paper proposes a new technique for the segmentation and classification of the acute lymphoblastic leukaemia. The proposed method of automatic leukaemia detection is based on the Deep Convolutional Neural Network (Deep CNN) that is trained using an optimization algorithm, named Grey wolf-based Jaya Optimization Algorithm (GreyJOA), which is developed using the Grey Wolf Optimizer (GWO) and Jaya Optimization Algorithm (JOA) that improves the global convergence. Initially, the input image is applied to pre-processing and the segmentation is performed using the Sparse Fuzzy C-Means (Sparse FCM) clustering algorithm. Then, the features, such as Local Directional Patterns (LDP) and colour histogram-based features, are extracted from the segments of the pre-processed input image. Finally, the extracted features are applied to the Deep CNN for the classification. The experimentation evaluation of the method using the images of the ALL IDB2 database reveals that the proposed method acquired a maximal accuracy, sensitivity, and specificity of 0.9350, 0.9528, and 0.9389, respectively.


Blood ◽  
2006 ◽  
Vol 108 (11) ◽  
pp. 2062-2062
Author(s):  
Christine J. Harrison ◽  
Kerry Barber ◽  
Zoë Broadfield ◽  
Adam Stewart ◽  
Sarah Wright ◽  
...  

Abstract Increasing numbers of genetic changes are being described in T lineage acute lymphoblastic leukaemia (T ALL), which may be used to classify patients into subgroups, defining multi-step oncogenic pathways. We have integrated the significant abnormalities into a comprehensive genetic classification of T ALL, using appropriate probes for fluorescence in situ hybridization (FISH). Break-apart probes were designed, which detected rearrangements of the TCR loci. Metaphase FISH, confirmed by informative break-apart probes for the significant oncogenes, were used to identify partner genes, as shown in the table. This approach revealed new recurrent translocation partners, as well as determining the incidence and simultaneous occurrence of the different abnormalities. The series included 295 patients, children 0–14 years (n=206) and adults ≥ 15 years (n=89), with a diagnosis of T ALL, entered to one of the UK MRC/NCRI ALL treatment trials. The incidences of the common cryptic abnormalities, SIL-TAL1 fusion and TLX3 were more prevalent in children (20% and 17%, respectively) compared to adults (9% each). There was no difference in event free survival between the childhood patients with SIL-TAL1 fusion and TLX3 rearrangements. CALM-AF10 fusion and MLL rearrangements accounted for 4% each. A single patient was found with a BCR-ABL fusion, but the same probe identified nine (3%) with NUP214-ABL1 amplification. Deletions involving CDKN2A were present in 49% of patients, in association with all abnormalities. Among the patients with NUP214-ABL1 amplification, associated abnormalities were: CDKN2A deletions (n=9), TRA@-TLX1 (n=2), BCL11B-TLX3 (n=2), TRB@-TLX3 (n=1). Concurrent rearrangements were found between the TCR genes, as well as associations between MYC, IGH and the other oncogenes. For example, (1) complex abnormalities between (a) TRA@, TRG@, BCL11B (n=2) and (b) HOXA@ (n=1); (2) deletions of 3′TRB@ in association with (a) complex ring chromosomes (n=2) and (b) cytogenetically visible deletions (n=2). FISH detected several novel, recurrent rearrangements, in particular a t(6;14) involving BCL11B and the 6q26 region (n=5) and a t(9;14)(p24;q31.1) involving JAK2 (n=2), the partners of which are currently being defined. BCL11B was also involved with (a) LMO2 and (b) the 2q23 region; LMO2 was rearranged with an unidentified partner in a complex translocation with chromosomes 16 and 18; TLX1 was involved in a translocation with 3q; new partners of TRB@ were found at (a) 1q11, (b) on 12p (n=2), (c) on 21q. These findings demonstrate the valuable role of FISH analysis, with a panel of carefully selected probes, to classify T ALL patients into genetic subgroups, including rare variants, and provide information on the relationship between them. A metaphase FISH approach has facilitated the identification of potential new target genes. In particular, multiple partners of TRB@ and BCL11B, other than the known TLX3 and HOXA@ genes, have emerged, highlighting the importance of these genes in the pathogenesis of T ALL. Promotor and Oncogenes in T ALL Promotor Genes Oncogenes BCL11B TRA@ TRB@ TRG@ CDK6 Novel***/Unknown *includes 3 telomeric deletions, **includes 3 centromeric deletions, ***listed in text TLX3 38* 3 1 2 TLX1 12 3 1 HOXA@ 1 5 1 LMO1 1 LMO2 1 14 3 1 4** LYL1 2 TAL2 6 NOTCH1 1 MYC 2 3 1 MYB 1 IGH@ 4


1983 ◽  
Vol 7 (3) ◽  
pp. 339-348 ◽  
Author(s):  
Po-Min Chen ◽  
Hung Chiang ◽  
Chen-Kung Chou ◽  
Tien-Szu Hwang ◽  
Benjamin N. Chiang ◽  
...  

2017 ◽  
Vol 76 (18) ◽  
pp. 19057-19085 ◽  
Author(s):  
Jyoti Rawat ◽  
Annapurna Singh ◽  
H. S. Bhadauria ◽  
Jitendra Virmani ◽  
J. S. Devgun

2019 ◽  
Vol 13 (13) ◽  
pp. 2548-2553 ◽  
Author(s):  
Komal Nain Sukhia ◽  
Abdul Ghafoor ◽  
Muhammad Mohsin Riaz ◽  
Naima Iltaf

1994 ◽  
Vol 7 (2) ◽  
pp. 235-262 ◽  
Author(s):  
Wolf-Dieter Ludwig ◽  
Anand Raghavachar ◽  
Eckhard Thiel

Sign in / Sign up

Export Citation Format

Share Document