Acute lymphoblastic leukemia diagnosis using machine learning techniques based on selected features

Early detection of cancer can increase patients' survivability and treatment options. Medical images such as Mammogram, Ultrasound, Magnetic Resonance Imaging, and microscopic images are the common method for cancer diagnosis. Recently, computer-aided diagnosis (CAD) systems have been used to help physicians in cancer diagnosis so that the diagnosis accuracy can be improved. CAD can help in decreasing missed cancer lesions due to physician fatigue, reducing the burden of workload and data overloading, and decreasing variability of inter- and intra-readers of images. In this research, a framework of CAD systems for cancer diagnosis based on medical images has been proposed. The proposed work helps physicians in detection of suspicion regions using different medical images modalities and in classifying the detected suspicious regions as normal or abnormal with the highest possible accuracy. The proposed framework of CAD system consists of four stages which are: preprocessing, segmentation of regions of interest, feature extraction and selection, and finally classification. In this research, the framework has been applied on blood smear images to diagnose the cases as normal or abnormal for Acute Lymphoblastic Leukemia (ALL) cases. Ant Colony Optimization (ACO) has been used to select the subsets of features from the features extracted from segmented cell parts which can maximize the classification performance as possible. Different classifiers which are Decision Tree (DT), K-nearest neighbor (K-NN), Naïve Bayes (NB), and Support Vector Machine (SVM) have been applied. The framework has been yielding promising results which reached 96.25% accuracy, 97.3% sensitivity, and 95.35% specificity using decision tree classifier.

In order to assess the prognostic value of nephromegaly (kidney enlargement > or = 2 SD from mean for age) in children at diagnosis of acute lymphoblastic leukemia (ALL), kidney size was investigated by intravenous pyelogram (IP), according to the method of Ekl of and Ringertz, in 101 children diagnosed with ALL in the period of 1975-1983. In the same period 103 additional patients with ALL were not investigated with IP for logistical reasons. Characteristics at the diagnosis of ALL in the patients of the investigated and non-investigated (with IP) groups were quite similar and event-free-survival (EFS) curves superimposable. Eighty-nine (50 males and 39 females, median age 61 months) out of 101 patients underwent IP before starting any therapy and were evaluated in the study; 27 (30.3%) presented with nephromegaly (bilateral in 13 cases and unilateral in 14). With a median follow-up time of 14.4 years (range 11-19 years), the EFS at 15 years from diagnosis was 18.5% (SE 9.5) in the nephromegalic group and 48.4% (SE 6.4) in the non-nephromegalic group. The association of poorer EFS with nephromegaly was confirmed when the comparison was adjusted by white blood cell count and age at diagnosis in a Cox regression model. Nephromegaly at diagnosis of childhood ALL may have an independent prognostic value in patients treated with 'not intensive' protocols; however, this finding should be confirmed in patients treated uniformly with contemporary intensive protocols.

Beyond the 2008 World Health Organization classification: the role of the hematopathology laboratory in the diagnosis and management of acute lymphoblastic leukemia

We report a 2-year-old female with a subcutaneous tumor who was initially misdiagnosed as suffering from Ewing sarcoma with a positive EWSR1 rearrangement and EWS/FLI1 transcript. After finding lymphoblasts in peripheral blood, the diagnosis of acute lymphoblastic leukemia was established. This necessitated further analysis of the subcutaneous tumor. The tissue was positive for immature B-cell markers and an immunoglobulin heavy chain gene rearrangement, which confirmed the final diagnosis of common type acute lymphoblastic leukemia with bulk extramedullary disease. The patient was treated with chemotherapy and was in remission 30 months after the diagnosis.

To contain the spread of the new severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which causes coronavirus disease 2019 (COVID-19), the Norwegian government implemented lock-down restrictions from 13.03.2020: schools, day cares and after-school activities were closed, 2-week quarantine was required following international travel, physical distancing (2 metres) was recommended and groups were restricted to 5 people.

As a new point, some very rare features can be revealed as initial diagnosis of acute lymphoblastic leukemia (ALL) without any evidence of lymphoma-like behavior which after initial recovery, presents with new evidence of lymphoma. Herein, a case of the immunophenotypes of blast cells in B-cell precursor acute lymphoblastic leukemia originated from MYC gene-related that was evidenced later by burkitt lymphoma feature. Our case was initially diagnosed as a typical B-cell ALL cells with L1 morphology in peripheral blood smear and bone marrow aspiration that was not recovered and referred again that was finally featured as burkitt's lymphoma with L3 morphological feature. Thus, in the primary diagnosis of B-cell ALL and especially in cases with treatment failure, the final feature of burkitt's lymphoma should be potentially in mind.

Prognostic Significance of Cytogenetic Abnormalities in Patients with Philadelphia-Negative ALL Undergoing Allogeneic Hematopoietic Stem Cell Transplantation in Complete Remission: A CIBMTR Analysis

An efficient EGWO algorithm as feature selection for B-ALL diagnoses and its subtypes classification using peripheral blood smear images

Background: It is very important to early diagnosis of cancer because it gives an opportunity for early treatment and prognosis. Unfortunately, late presentation and delayed diagnosis of childhood cancer remains a problem in developing countries including Bangladesh. Objectives: The purpose of the present study was to evaluate the factors behind parents’ delay in the diagnosis of acute lymphoblastic leukemia among children in a tertiary care hospital in Bangladesh. Methodology: This was a descriptive cross sectional study carried out in the Department of Pediatrics at Mymensingh Medical College Hospital, Mymensingh, Bangladesh from April 2013 to September 2013. Information was obtained from hospital records of children diagnosed as acute leukemia Information included socio-demographic variables, urbanization, parent education and other causes to delayed diagnosis of leukemia. Results: Seventy children (44 males, 26 females) were included where the most common age group was 5 to 10 years which was 37(52.9%). Among 70 acute leukemia patients 66 (94.3%) lived in rural area and 4(5.7%) lived in urban area. Most of the patients 59(89.3%) belongs to the low socioeconomic status and 11(15.7%) were from middle class family. Among the parents, 27(38.6%) fathers and 33(47.1%) mothers were illiterate. Delayed reaching tertiary care hospital after suspicion were lack of personal 2 (2.85%), economic constrain 6 (8.57%), lack of information about availability of proper treatment 1 (1.42%), other causes 30 (42.85%) and none 31(44.28%). Median lag time was 60 days. Conclusion: In conclusion factors contributing to delayed diagnosis are rural areas, parents’ education, economic constrain and urbanization. Journal of National Institute of Neurosciences Bangladesh, January 2024;10(1):26-31

To detect genes with CpG sites that display methylation patterns that are characteristic of acute lymphoblastic leukemia (ALL) cells, we compared the methylation patterns of cells taken at diagnosis from 20 patients with pediatric ALL to the methylation patterns in mononuclear cells from bone marrow of the same patients during remission and in non-leukemic control cells from bone marrow or blood. Using a custom-designed assay, we measured the methylation levels of 1,320 CpG sites in regulatory regions of 413 genes that were analyzed because they display allele-specific gene expression (ASE) in ALL cells. The rationale for our selection of CpG sites was that ASE could be the result of allele-specific methylation in the promoter regions of the genes. We found that the ALL cells had methylation profiles that allowed distinction between ALL cells and control cells. Using stringent criteria for calling differential methylation, we identified 28 CpG sites in 24 genes with recurrent differences in their methylation levels between ALL cells and control cells. Twenty of the differentially methylated genes were hypermethylated in the ALL cells, and as many as nine of them (AMICA1, CPNE7, CR1, DBC1, EYA4, LGALS8, RYR3, UQCRFS1, WDR35) have functions in cell signaling and/or apoptosis. The methylation levels of a subset of the genes were consistent with an inverse relationship with the mRNA expression levels in a large number of ALL cells from published data sets, supporting a potential biological effect of the methylation signatures and their application for diagnostic purposes.

Flow Cytometry Immunophemotyping Evaluation in the Diagnosis of Acute Lymphoblastic Leukemia in Patients from Rio Grande Do Norte State, Brazil

Histopathological analysis is important for detection of the breast cancer (BC). Computer-aided diagnosis and detection systems are developed to assist the radiologist in the diagnosis process and to relieve the patient from unnecessary pain. In this study, a computer-aided diagnosis system for the early detection of benign and malignant breast cancer is proposed. The proposed system consists of feature extraction, feature ensemble, and classification stages. Various preprocessing steps such as grayscale conversion, noise filtering, and image resizing are employed on the input histopathological images. The local texture descriptors namely Local Binary Pattern (LBP), Frequency Decoded LBP (FDLBP), Binary Gabor Pattern (BGP), Local Phase Quantization (LPQ), Binarized Statistical Image Features (BSIF), CENsus TRansform hISTogram (CENTRIST), and Pyramid Histogram of Oriented Gradients (PHOG) are employed for feature extraction from the histopathologic images. The obtained features are then concatenated for the construction of the ensemble of the features. Three classifiers namely Support Vector Machines (SVM), K-nearest neighbor (KNN), and Neural Networks (NN) are used in the detection of the BC and the classification accuracy score is used for performance evaluation. A dataset called BreaKHis is used in the studies. There are 9109 microscopic pictures in BreaKHis, with 2480 benign samples and 5429 malignant samples. During the collection of the data, 82 patients' breast tumor tissues were envisioned using various magnification factors such as 40X, 100X, 200X, and 400X. The accuracy score is used to assess the acquired findings. The results show that the proposed method has the potential to use accurate BC detection.

Caries is the most well-known disease and relates to the oral health of billions of people around the world. Despite the importance and necessity of a well-designed detection method, studies in caries detection are still limited and show a restriction in performance. In this paper, we proposed a computer-aided diagnosis (CAD) method to detect caries among normal patients using dental radiographs. The proposed method mainly consists of two processes: feature extraction and classification. In the feature extraction phase, the chosen 2D tooth image was employed to extract deep activated features using a deep pre-trained model and geometric features using mathematic formulas. Both feature sets were then combined, called fusion feature, to complement each other defects. Then, the optimal fusion feature set was fed into well-known classification models such as support vector machine (SVM), k-nearest neighbor (KNN), decision tree (DT), Naïve Bayes (NB), and random forest (RF) to determine the best classification model that fit the fusion features set and perform the most preeminent result. The results show 91.70%, 90.43%, and 92.67% for accuracy, sensitivity, and specificity, respectively. The proposed method has outperformed the previous state-of-the-art and shows promising results when none of the measured factors is less than 90%; therefore, the method is promising for dentists and capable of wide-scale implementation caries detection in hospitals.

Osteonecrosis and decline of bone density are serious side effects during and after treatment of childhood acute lymphoblastic leukemia. It is unknown whether osteonecrosis and low bone density occur together in the same patients, or whether these two osteogenic side-effects can mutually influence each other's development. Bone density and the incidence of symptomatic osteonecrosis were prospectively assessed in a national cohort of 466 patients with acute lymphoblastic leukemia (4-18 years of age) who were treated according to the dexamethasone-based Dutch Child Oncology Group-ALL9 protocol. Bone mineral density of the lumbar spine (BMDLS) (n=466) and of the total body (BMDTB) (n=106) was measured by dual X-ray absorptiometry. Bone density was expressed as age- and gender-matched standard deviation scores. Thirty patients (6.4%) suffered from symptomatic osteonecrosis. At baseline, BMDLS and BMDTB did not differ between patients who did or did not develop osteonecrosis. At cessation of treatment, patients with osteonecrosis had lower mean BMDLS and BMDTB than patients without osteonecrosis (respectively, with osteonecrosis: -2.16 versus without osteonecrosis: -1.21, P<0.01 and with osteonecrosis: -1.73 versus without osteonecrosis: -0.57, P<0.01). Multivariate linear models showed that patients with osteonecrosis had steeper BMDLS and BMDTB declines during follow-up than patients without osteonecrosis (interaction group time, P<0.01 and P<0.01). We conclude that bone density status at the diagnosis of acute lymphoblastic leukemia does not seem to influence the occurrence of symptomatic osteonecrosis. Bone density declines from the time that osteonecrosis is diagnosed; this suggests that the already existing decrease in bone density during acute lymphoblastic leukemia therapy is further aggravated by factors such as restriction of weight-bearing activities and destruction of bone architecture due to osteonecrosis. Osteonecrosis can, therefore, be considered a risk factor for low bone density in children with acute lymphoblastic leukemia.

The chest digital tomosynthesis(CDT) is recently developed medical device that has several advantage for diagnosing lung disease. For example, CDT provides depth information with relatively low radiation dose compared to computed tomography (CT). However, a major problem with CDT is the image artifacts associated with data incompleteness resulting from limited angle data acquisition in CDT geometry. For this reason, the sensitivity of lung disease was not clear compared to CT. In this study, to improve sensitivity of lung disease detection in CDT, we developed computer aided diagnosis (CAD) systems based on machine learning. For design CAD systems, we used 100 cases of lung nodules cropped images and 100 cases of normal lesion cropped images acquired by lung man phantoms and proto type CDT. We used machine learning techniques based on support vector machine and Gabor filter. The Gabor filter was used for extracting characteristics of lung nodules and we compared performance of feature extraction of Gabor filter with various scale and orientation parameters. We used 3, 4, 5 scales and 4, 6, 8 orientations. After extracting features, support vector machine (SVM) was used for classifying feature of lesions. The linear, polynomial and Gaussian kernels of SVM were compared to decide the best SVM conditions for CDT reconstruction images. The results of CAD system with machine learning showed the capability of automatically lung lesion detection. Furthermore detection performance was the best when Gabor filter with 5 scale and 8 orientation and SVM with Gaussian kernel were used. In conclusion, our suggested CAD system showed improving sensitivity of lung lesion detection in CDT and decide Gabor filter and SVM conditions to achieve higher detection performance of our developed CAD system for CDT.