Diagnosis Of Acute Lymphoblastic Leukemia Research Articles

Hemophagocytic lymphohistiocytosis caused by multiple infections during primary chemotherapy for pediatric acute lymphoblastic leukemia: a case report

Hemophagocytic lymphohistiocytosis (HLH) is a life-threatening hyperinflammatory disorder that occurs as a consequence of immune dysregulation. HLH can be primary (familial or non-familial) or secondary to infection, autoimmune disease or malignancy. Malignancy-associated HLH is often accompanied by hematologic and lymphoid neoplasms. This report describes the case of a 3-year-old girl with an initial diagnosis of acute lymphoblastic leukemia who subsequently developed HLH during primary chemotherapy. She was admitted with a pulmonary infection, and initial blood tests showed thrombocytopenia and anemia. Whole-exome sequencing of gene and whole transcriptome RNA sequencing data indicated mutations of UNC13D. The hospital course was complicated by multiple infections, altered mental status and acute respiratory distress syndrome. HLH secondary to multiple infections that achieved remission following targeted therapy with ruxolitinib, in conjunction with corticosteroids and other complementary treatments. This report provides a synopsis of the diagnostic and treatment procedures implemented in this case.

Diagnosis of acute lymphoblastic leukaemia: an overview of the current genomic classification, diagnostic approaches, and future directions.

B-acute lymphoblastic leukaemia (B-ALL) is a haematological disease resulting from haematopoietic system dysfunction, leading to the unchecked growth of immature B lymphoblasts. The disease's complexity is underscored by the spectrum of genetic aberrations that underlie B-ALL entities, necessitating advanced genetic analyses for precise classification and risk determination. Prior to the adoption of next-generation sequencing into standard diagnostic practices, up to 30% of B-ALL cases were not assigned to specific entities due to the limitations of traditional diagnostic methods. The advent of comprehensive genomic analysis, especially whole-genome transcriptome sequencing, has significantly enhanced our understanding of B-ALL's molecular heterogeneity, paving the way for the exploration of novel, tailored treatment strategies. Furthermore, recent technological innovations, such as optical genome mapping, methylation profiling, and single-cell sequencing, have propelled forward the fields of cancer research and B-ALL management. These innovations introduce novel diagnostic approaches and prognostic markers, facilitating a deeper, more nuanced understanding of individual patient disease profiles. This review focuses on the latest diagnostic standards and assays for B-ALL, the importance of new technologies and biomarkers in enhancing diagnostic accuracy, and the expected role of innovative advancements in the future diagnosis and treatment of B-ALL.

Deep and Machine Learning for Acute Lymphoblastic Leukemia Diagnosis: A Comprehensive Review

The medical condition known as acute lymphoblastic leukemia (ALL) is characterized by an excess of immature lymphocyte production, and it can affect people across all age ranges. Detecting it at an early stage is extremely important to increase the chances of successful treatment. Conventional diagnostic techniques for ALL, such as bone marrow and blood tests, can be expensive and time-consuming. They may be less useful in places with scarce resources. The primary objective of this research is to investigate automated techniques that can be employed to detect ALL at an early stage. This analysis covers both machine learning models (ML), such as support vector machine (SVM) & random forest (RF), as well as deep learning algorithms (DL), including convolution neural network (CNN), AlexNet, ResNet50, ShuffleNet, MobileNet, RNN. The effectiveness of these models in detecting ALL is evident through their ability to enhance accuracy and minimize human errors, which is essential for early diagnosis and successful treatment. In addition, the study also highlights several challenges and limitations in this field, including the scarcity of data available for ALL types, and the significant computational resources required to train and operate deep learning models.

Virtual reality as a non-medical tool in the treatment of anxiety, pain, and perception of time in children in the maintenance phase of acute lymphoblastic leukemia treatment.

Management of pediatric cancer patients involves invasive procedures such as punctures, injections, catheter placements, and chemotherapy which can generate fatigue, nausea, vomiting, anxiety, and pain. Virtual Reality (VR) is a nonpharmacological intervention classified as a cognitive-behavioral method to relieve symptoms. We designed a crossover protocol and included 20 patients between 9 and 12 years old; ten were male. All patients had acute lymphoblastic leukemia diagnosis and were treatedwith St. Jude's XV protocol in the maintenance phase. Pain and anxiety were measured with validated scales in the pediatric population. Although we used a small group of patients, we found statistical difference in the reduction of anxiety and perception of time. These results open a window to non-pharmacological treatments and show a strategy to improve quality of life in children inside the hospital.

Advancing the Diagnosis of Acute Lymphoblastic Leukemia with Hybrid Neural Networks

Acute Lymphoblastic Leukemia (ALL) is a malignancy of B or T lymphoblasts characterized by the uncontrolled replication of abnormal cells in the blood. The difficulty in diagnosing ALL arises from its visual similarity with other cells (HEM) in the blood, and misdiagnosis rates are high with other diseases. Thus, we seek an alternate solution to help medical professionals with the diagnosis of ALL. Recent solutions have utilized hybrid models that have delivered better performance than prior models, so we utilize a hybrid architecture unused for ALL detection. Our proposed architecture consists of EfficientNetB0 as our feature extractor and XGBoost classifier for its gradient boosting framework to perform a binary classification between ALL and HEM cells. The model maintains an accuracy of 85% when diagnosing ALL, proving the effectiveness of a data-driven approach for diagnosis. In the future, our model could be trained with other ALL datasets in order to become more versatile. Our work can assist doctors in providing an accurate and efficient diagnosis of leukemia, allowing for early intervention of the disease.

Flow cytometric detection of leukemic blasts in Libyan pediatric patients with acute lymphoblastic leukemia

ABSTRACT The diagnosis of acute lymphoblastic leukemia (ALL), which is the most common type of cancer in children, has become more accurate with the use of flow cytometry. Here, this technology was used to immunophenotype leukemic cells in peripheral blood samples from Libyan pediatric ALL patients. We recruited 152 newly diagnosed patients at Tripoli Medical Center (Tripoli, Libya) by morphological examination of blood and bone marrow. Twenty-three surface and cytoplasmic antigen markers were used to characterize B and T cells in circulating blood cells by four-color flow cytometry. Six children (3.9%) turned out to have biphenotypic acute leukemia, 88 (57.9%) had B ALL, and 58 (38.1%) had T ALL. There were 68 cases of pro-B ALL CD10-positive (44.7%), 8 cases of pro-B ALL CD10-negative (5.2%), 6 cases of pre-B ALL (3.9%), and 6 of mature-B ALL (3.9%). CD13 was the most commonly expressed myeloid antigen in ALL. We present immunophenotypic data for the first time describing ALL cases in Libya. The reported results indicate that the most common subtype was pro-B ALL, and the frequency of T-ALL subtype was higher compared to previous studies. Six cases were positive for both myeloid and B lymphoid markers. Our findings may provide the basis for future studies to correlate immunophenotypic profile and genetic characteristics with treatment response among ALL patients.

The influence of cytotoxic drugs on the immunophenotype of blast cells in paediatric B precursor acute lymphoblastic leukaemia.

Flow cytometry plays is important in the diagnosis of acute lymphoblastic leukaemia (ALL) and when antigen-specific immunotherapy is indicated. We have investigated the effects of prednisolone, vincristine, daunorubicin, asparaginase and methotrexate on the antigen expression on blast cells that could influence the planning of antigen-specific therapy as well as risk-based treatment assignment. Patients aged ≤ 17 years with de novo B-cell ALL (B-ALL) were enrolled in the study. Blast cells were isolated and exposed in vitro to 5 individual cytotoxic drugs in logarithmically increasing concentrations. Then, the expression of CD10, CD19, CD20, CD27, CD34, CD45, CD58, CD66c and CD137 antigens was determined by quantitative flow cytometry. Cytotoxic drugs caused dose-dependent or dose-independent modulation of antigen expression. Daunorubicin caused a dose-dependent down-modulation of CD10, CD19, CD34, CD45 and CD58 and an up-modulation of CD137. Vincristine caused a dose-dependent down-modulation of CD19 and CD58 and an up-modulation of CD45. Daunorubicin also caused dose-independent down-modulation of CD27 and prednisolone down-modulation of CD10, CD19, CD27, CD34 and CD58. Down-modulation of CD20 was detected only in relation to the specific dose of daunorubicin. The results of the study have shown that cytotoxic drugs can alter the expression of antigens that are important for immunotherapy. Importantly, daunorubicin, prednisolone and vincristine caused down-modulation of CD19 and CD58, suggesting that these drugs are better avoided during bridging therapy prior to bispecific antibodies or CAR-T cell therapy. In addition, immunophenotypic changes on blast cells induced by different drugs could also influence risk-based treatment assignment.

Acute Lymphoblastic Leukemia: About a Case Observed at the Renaissance University Hospital in N'Djamena.

Introduction: Childhood acute lymphoblastic leukaemia is the most common paediatric cancer. The objective of our work is to focus on a haematological manifestation such as pancytopenia inaugurating the picture of acute lymphoblastic leukaemia. Observation: 11-year-old AI, who has been reporting repeated anaemia and haemoglobinuria for 6 months. The clinical examination reveals an alteration of the general condition, severe mucocutaneous pallor, splenomegaly. The initial blood count showed pancytopenia. The diagnosis of acute lymphoblastic leukaemia was confirmed by a myelogram requested in the presence of pancytopenia. Conclusion: Through this observation, we report the clinical and biological manifestations of acute lymphoblastic leukaemia, emphasizing the interest in eliminating haematological malignancy in the face of any pancytopenia.

An ensemble-acute lymphoblastic leukemia model for acute lymphoblastic leukemia image classification.

The timely diagnosis of acute lymphoblastic leukemia (ALL) is of paramount importance for enhancing the treatment efficacy and the survival rates of patients. In this study, we seek to introduce an ensemble-ALL model for the image classification of ALL, with the goal of enhancing early diagnostic capabilities and streamlining the diagnostic and treatment processes for medical practitioners. In this study, a publicly available dataset is partitioned into training, validation, and test sets. A diverse set of convolutional neural networks, including InceptionV3, EfficientNetB4, ResNet50, CONV_POOL-CNN, ALL-CNN, Network in Network, and AlexNet, are employed for training. The top-performing four individual models are meticulously chosen and integrated with the squeeze-and-excitation (SE) module. Furthermore, the two most effective SE-embedded models are harmoniously combined to create the proposed ensemble-ALL model. This model leverages the Bayesian optimization algorithm to enhance its performance. The proposed ensemble-ALL model attains remarkable accuracy, precision, recall, F1-score, and kappa scores, registering at 96.26, 96.26, 96.26, 96.25, and 91.36%, respectively. These results surpass the benchmarks set by state-of-the-art studies in the realm of ALL image classification. This model represents a valuable contribution to the field of medical image recognition, particularly in the diagnosis of acute lymphoblastic leukemia, and it offers the potential to enhance the efficiency and accuracy of medical professionals in the diagnostic and treatment processes.

The assessment of computational intelligence technique for the diagnosis of acute lymphoblastic leukemia

The assessment of computational intelligence technique for the diagnosis of acute lymphoblastic leukemia

Outcome Disparities Among Hispanic and Non-Hispanic Patients with Acute Lymphoblastic Leukemia

Introduction: Acute lymphoblastic leukemia (ALL) is the predominant type of leukemia diagnosed in children and accounts for approximately 20% of all cases of acute leukemia in adults. In pediatric cases, ALL generally exhibits a favorable prognosis and outcome. Unfortunately, this optimistic scenario does not extend to adults, as the majority of deaths related to ALL occur in this age group. The outcomes observed in children with ALL are linked to the favorable cytogenetic profile of their leukemia. However, as individuals age, the cytogenetic profile progressively shifts towards high-risk groups. Furthermore, several epidemiologic studies have identified ethnicity, specifically Hispanic and African American backgrounds, as independent factors associated with worse outcomes. The factors contributing to these outcomes are diverse and include limited healthcare access, insurance coverage, immigration status, treatment adherence, socioeconomic status, and timeliness of treatment initiation, among others. Additionally, individuals of Hispanic ethnicity are more prone to complex cytogenetics and Central Nervous System involvement, both of which are commonly associated with a poor prognosis. Our study aimed to assess the differences in treatment outcomes among adults diagnosed with ALL by conducting a specific comparison between non-Hispanic and Hispanic individuals. Methods: In this retrospective observational study, we collected data from the electronic medical records (EMR) of patients aged 18 years and older who received a diagnosis of Acute Lymphoblastic Leukemia between February 1, 2011, and February 28, 2020 at Ascension Seton Hospitals in Texas. The collected data included sociodemographic factors such as gender, ethnicity, and age at diagnosis, as well as clinical characteristics such as cytogenetics, immunophenotype, treatment, and overall survival. Bivariate and multivariate analyses were conducted using a chi-squared test. Statistical significance was defined as a P-value less than 0.05. Results: A total of 56 patients with ALL were identified, with 45% being non-Hispanic and 55% being Hispanic. The incidence of ALL did not show significant variation based on gender or age, but it exhibited a significant difference depending on insurance status. The analysis revealed that Hispanic patients had a significantly higher likelihood of lacking insurance coverage (75%) compared to non-Hispanic patients (25%), with a statistically significant p-value of 0.001. With the exception of one non-Hispanic patient diagnosed with T-cell ALL, almost all participants in the study had B-cell ALL. Among the patients who received chemotherapy, 44% were non-Hispanic, while 56% were Hispanic. Among patients with t(9;22)/BCR-ABL1 positive ALL, non-Hispanics represented 76% and Hispanics represented 23%. Other cytogenetic abnormalities, including CRLF2-IGH fusion, IgH rearrangement, CRLF2 rearrangement, PBX1/TCF3 fusion, t(1;19) with PBX1/TCF3 fusion, ETV6 deletion, near haploidy, and 9p deletion, were more prevalent in Hispanic patients (79%) compared to non-Hispanic patients (21%). The overall survival rates at 1 year were 64% for non-Hispanic patients and 67.7% for Hispanic patients. However, at 3 years, the overall survival rates decreased to 32% for non-Hispanic patients and 25.8% for Hispanic patients. Conclusions: Our study provides important insights into the demographic and clinical characteristics of patients with ALL and highlights notable disparities between non-Hispanic and Hispanic patients. A higher proportion of Hispanic patients lacked any form of health insurance coverage at the time of diagnosis. Interestingly, the incidence of Philadelphia-positive ALL was found to be higher among non-Hispanic patients, whereas other cytogenetic abnormalities were more prevalent among Hispanic patients. Additionally, Hispanic patients experienced lower rates of overall survival at 3 years, suggesting potential disparities in outcomes. The differences observed between Hispanic and non-Hispanic patients highlight the necessity for additional investigation and tailored interventions to address the specific challenges faced by Hispanic patients, including access to healthcare, insurance coverage, and the prevalence of unfavorable cytogenetic abnormalities.

Deep Learning Models for the Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Images : A Comprehensive Literature Review

Introduction: Acute lymphoblastic leukemia (ALL) is an aggressive blood cancer that begins in the bone marrow. It is the most common childhood cancer and requires early and accurate diagnosis for optimal treatment outcomes. Through automated image analysis of peripheral blood smears and bone marrow biopsies, artificial intelligence (AI), particularly Deep Learning (DL), have opened new avenues for improving ALL diagnosis. While bone marrow testing is the gold standard for ALL confirmation, AI applications in diagnosing ALL from bone marrow images have received less attention in the literature than peripheral blood smears. This review aims to assess the current state of AI in ALL diagnosis using bone marrow aspirates and biopsies, with a focus on Deep Learning (DL) models such as Convolutional Neural Networks (CNNs). Methods: A comprehensive literature search, conducted on June 11th, 2023, covered major medical databases, including PubMed/MEDLINE, Scopus, Embase, and Web of Science. Relevant keywords like “acute lymphoblastic leukemia,” “deep learning,” and “neural network” were employed, without time frame restrictions. Articles were included if they assessed the metrics of AI applications for ALL diagnosis in bone marrow aspirates. Articles were excluded if they: (1) had different outcomes, (2) were reviews, (3) were abstracts only, or (4) only reported peripheral blood smear metrics. Results: The search yielded 496 articles. After eliminating duplicates (282), title and abstract screening on the Rayyan platform excluded 204 records, leaving 214 articles eligible for full-text screening. Ten relevant articles were ultimately included in the review. Diverse approaches were presented to enhance diagnostic accuracy and efficiency. One study achieved 100% accuracy in classifying leukemic cells using a unique Convolutional Leaky RELU with CatBoost and XGBoost (CLR-CXG) design. Another study employed transfer learning with CNNs, obtaining 95.3% accuracy for AML, ALL, and CML classification with DenseNet121. Furthermore, the novel “i-Net” model demonstrated 99.18% validation accuracy for white blood cancer segmentation and classification. Adaptive Multi-objective CAT algorithms achieved 99.45% accuracy in detecting bone marrow cancer cells. An AI-based system using deep learning exhibited 97.2% accuracy in diagnosing ALL, while a robust fuzzy logic algorithm combined with a radial basis function neural network achieved 82.93% accuracy in diagnosing ALL in developing countries. Additionally, AI technologies based on computer microscopy demonstrated 95% and 97.5% accuracy in diagnosing ALL and minimal residual disease, respectively. A computer-aided system achieved 97.78% accuracy in classifying ALL subtypes. Conclusion: The potential of AI-driven approaches, particularly deep learning models like CNNs, in improving ALL diagnosis from bone marrow images is highlighted in this review. Because of their superior sensitivity and specificity over peripheral blood smears, bone marrow samples are the gold standard for ALL confirmation. The morphological and cellular properties of bone marrow samples provide important information for disease classification and monitoring. While DL and CNNs have shown promise in diagnosing ALL from peripheral blood smears, their use in bone marrow samples has yet to be investigated deeply. More research and external validation are required to fully realize AI's potential in ALL diagnosis from bone marrow specimens.

A combined neural network mechanism for categorizing the normal and cancer cells

The dangerous form of acute lymphocytic leukemia damages the bone marrow tissue and white blood cells. Unformed white blood cells multiply and exchange healthy cells in the bone marrow. Everything spreads fast and, if not noticed, can be dangerous in some months. As a result, computer assisted diagnosis of acute lymphocytic leukemia has the possible to protect several lives, but it needs a high-precision categorization of malignant cells, that is difficult due to the graphical similarity of malignant and normal cells. Though deep convolutional neural networks and the classic machine learning algorithms have exposed excellent results in classifying blood cell images, they have not been able to make effective use of the long-term correlation between some important image attributes and image labeling. This study introduced Long short-term memory (LSTM) to solve this difficulty. This study actually combines VGG16 neural networks and LSTM, which provide the VGG16-LSTM framework, which improves the recognizing of image content and learns the structural features of images, as well as initiate big data training in clinical image processing. The transfer learning approach was used to transfer pre-trained weight parameters to the VGG16 area in the ImageNet database, and the custom loss function was used to train and integrate the network quickly and accurately with the weight parameters. Experimental findings reveal that the suggested network approach is more relevant and effective in categorizing cancer cell images than other existing methods.

Disseminated aspergillosis due to Aspergillus flavus in a pediatric patient with a recent diagnosis of acute lymphoblastic leukemia

Disseminated aspergillosis due to Aspergillus flavus in a pediatric patient with a recent diagnosis of acute lymphoblastic leukemia

RETRACTED ARTICLE: Peripheral Blood Smear Images Classification for Acute Lymphoblastic Leukemia Diagnosis with an Improved Convolutional Neural Network

RETRACTED ARTICLE: Peripheral Blood Smear Images Classification for Acute Lymphoblastic Leukemia Diagnosis with an Improved Convolutional Neural Network

B-242 Fast and Cost-effective RNA Extraction in Onco-hematology Laboratories

Abstract Background Chronic myeloid leukemia (CML) is a myeloproliferative neoplasm characterized by the presence of a BCR-ABL1 rearrangement; its detection and quantification by real-time quantitative PCR (RQ-PCR) plays a central role in CML diagnosis, therapy monitoring, and sequencing to identify resistance mutations in case of therapy failure. To evaluate the molecular response of CML, BCR-ABL1 quantification must be calculated on the international scale (IS%) for which RQ-PCR has the necessary sensitivity (up to 10−5). Currently, BCR-ABL1 quantifications are ubiquitous in onco-hematology laboratories (OHLs; ∼70% of tests performed in our OHL), whereby quality, cost, and turn-around-time are of critical importance. Today, the majority of OHLs in Brazil rely on laborious manual RNA-extraction methods (e.g., Trizol) that usually require 8 mL of peripheral blood (PB) to monitor CML. Here, we report a strategy that requires only 2 mL of PB in combination with the automated magnetic DNA/RNA-extraction kit Extracta-MPTA (Loccus do Brasil) for CML diagnosis and monitoring. Methods: BCR:ABL1 was quantified and its IS% determined using our developed kit, which was calibrated using ERM-AD263 and UK-NEQAS (external quality assessment). Total RNA was extracted from 40 PB samples, after erythrocyte lysis using two different methods: 1) Leukocytes from 8 mL of PB were extracted manually using Trizol; 2) leukocytes from 2 mL of PB were automatically extracted using Extracta-MPTA (Loccus do Brasil). BCR-ABL1 quantification, BCR-ABL1 IS%, and BCR quantification (internal control) were compared statistically (paired t-test). The reproducibility was evaluated by analyzing 20 replicates; the low limit of the leucocyte number to BCR:ABL1 quantification using Extracta-MPTA were also evaluated. Median and moving means of 135 unpaired samples were used to monitor BCR-ABL1 IS% between Trizol, Extracta-MPTA, while EQA from UK-NEQAS was also evaluated using both methods. In parallel, RNA was extracted by both methods from 20 samples for the diagnosis of acute lymphoblastic leukemia (ALL) (BCR-ABL p190 transcript) and acute promyelocytic leukemia (APL) (PML-RARA transcript). Results A comparison of BRC-ABL1, BCR, and %IS in 40 paired samples showed that the results obtained from Trizol or Extracta-MPTA are comparable (paired t-test: P = 0.4222, P = 0.9263, and P = 0.071, respectively). The reproducibility was evaluated by BCR quantification (24%). A comparison of the medians from 135 unpaired samples extracted using Trizol and Extracta-MPTA revealed that BCR-ABL1 IS% distribution among our patients is stable over time (P = 0.7704; Mann Whitney: r2 = 0.0012). EQA was extracted using both methods and the results were identical. A comparison between Trizol and EXTRACTA_MPTA for ALL and APL was 100% identical (Fischer; P = 1.000). Conclusion Both RNA extraction methods are suitable for OHLs for PML-RARA and BCR-ABL (p190 and p210) detection and CML diagnosis/monitoring by BCR-ABL1 detection/quantification. By using Extracta-MPTA the amount of PB used to obtain RNA can be reduced by 75%, test results can be obtained within 4 h, and direct reagent costs are reduced by 25% with a minimum of hands-on time.

Leukocyte classification for acute lymphoblastic leukemia timely diagnosis by interpretable artificial neural network

Leukemia is a blood cancer characterized by leukocyte overproduction. Clinically, the reference for acute lymphoblastic leukemia diagnosis is a blood biopsy that allows obtain microscopic images of leukocytes, whose early-stage classification into leukemic (LEU) and healthy (HEA) may be disease predictor. Thus, the aim of this study is to propose an interpretable artificial neural network (ANN) for leukocyte classification to timely diagnose acute lymphoblastic leukemia. The “ALL_IDB2” dataset was used. It contains 260 microscopic images showing leukocytes acquired from 130 LEU and 130 HEA subjects. Each microscopic image shows a single leukocyte that was characterized by 8 morphological and 4 statistical features. An ANN was developed to distinguish microscopic images acquired from LEU and HEA subjects, considering 12 features as inputs and the local-interpretable model-agnostic explanatory (LIME) algorithm as an interpretable post-processing algorithm. The ANN was evaluated by the leave-one-out cross-validation procedure. The performance of our ANN is promising, presenting a testing area under the curve of the receiver operating characteristic equal to 87%. Being implemented using standard features and having LIME as a post-processing algorithm, it is clinically interpretable. Therefore, our ANN seems to be a reliable instrument for leukocyte classification to timely diagnose acute lymphoblastic leukemia, guaranteeing a high clinical interpretability level.

Unusual Diffuse and Heterogeneous FDG Uptake in Appendicular Bone Marrow Space in a Patient with Acute Lymphoblastic Leukemia.

We describe a case of F-18-2-fluoro-2-deoxyglucose (FDG) uptake in the appendicular bones on a positron emission tomography/computed tomography (PET/CT) scan in a 20-year-old woman with a diagnosis of acute lymphoblastic leukemia. An FDG PET/CT was performed on this patient because of fever of unknown origin, revealing diffuse and heterogeneous FDG uptake in the bone marrow space of both humeri, femurs, and tibiae. The patient underwent magnetic resonance imaging, which demonstrated bone infarction with heterogeneous high, intermediate, and dark signal intensities on T1- and T2-weighted images in the same areas.

Differences between leukemic arthritis and juvenile idiopathic arthritis

ObjectivesTo determine the clinical and laboratory differences between leukemic arthritis (LA) and juvenile idiopathic arthritis (JIA) at the onset of the disease.Material and methodsPatients under 16 years of age, both genders, who presented for the first time to the pediatric rheumatology service with a diagnosis of probable JIA, with arthritis and without peripheral blood blasts, in which the final diagnosis was acute lymphoblastic leukemia (ALL) or JIA. The clinical and laboratory characteristics of the patients were compared, chi-square and relative risk were used for categorical variables, and the Mann–Whitney U and T-test for the comparison of means between groups. A binary logistic regression model was developed to differentiate leukemic arthritis from JIA.ResultsA total of 76 patients, 14 with LA and 62 with JIA, were analyzed. The mean age at diagnosis was lower in the leukemic arthritis group, the female gender prevailed in the JIA group, and the time to onset of symptoms was lower in the leukemic arthritis group. Patients with leukemic arthritis showed increased pain intensity, fever, weight loss, nocturnal diaphoresis, lymph node enlargement, hepatosplenomegaly, and pain that did not improve with analgesic administration. Laboratory parameters with statistical significance were the presence of anemia, leukopenia, and neutropenia. The platelet count was significant but in a low normal value, compared to the JIA. A binary logistic regression model was developed to differentiate leukemic arthritis from JIA. The probability associated with the statistic (Chi-square) was 0.000, and the Cox and Snell R2 and Nagelkerke R2 values were 0.615 and 1, respectively. The developed model correctly classified 100% of the cases.ConclusionsThe diagnosis of acute lymphoblastic leukemia should be ruled out in patients who present with arthritis and hematological alterations, mainly leukopenia and neutropenia, with joint pain disproportionate to the degree of arthritis, predominantly at night and that does not improve with the use of analgesics, fever, lymph nodes, and hepatosplenomegaly. Criteria are suggested to differentiate both diseases.

Hybrid Techniques for the Diagnosis of Acute Lymphoblastic Leukemia Based on Fusion of CNN Features.

Acute lymphoblastic leukemia (ALL) is one of the deadliest forms of leukemia due to the bone marrow producing many white blood cells (WBC). ALL is one of the most common types of cancer in children and adults. Doctors determine the treatment of leukemia according to its stages and its spread in the body. Doctors rely on analyzing blood samples under a microscope. Pathologists face challenges, such as the similarity between infected and normal WBC in the early stages. Manual diagnosis is prone to errors, differences of opinion, and the lack of experienced pathologists compared to the number of patients. Thus, computer-assisted systems play an essential role in assisting pathologists in the early detection of ALL. In this study, systems with high efficiency and high accuracy were developed to analyze the images of C-NMC 2019 and ALL-IDB2 datasets. In all proposed systems, blood micrographs were improved and then fed to the active contour method to extract WBC-only regions for further analysis by three CNN models (DenseNet121, ResNet50, and MobileNet). The first strategy for analyzing ALL images of the two datasets is the hybrid technique of CNN-RF and CNN-XGBoost. DenseNet121, ResNet50, and MobileNet models extract deep feature maps. CNN models produce high features with redundant and non-significant features. So, CNN deep feature maps were fed to the Principal Component Analysis (PCA) method to select highly representative features and sent to RF and XGBoost classifiers for classification due to the high similarity between infected and normal WBC in early stages. Thus, the strategy for analyzing ALL images using serially fused features of CNN models. The deep feature maps of DenseNet121-ResNet50, ResNet50-MobileNet, DenseNet121-MobileNet, and DenseNet121-ResNet50-MobileNet were merged and then classified by RF classifiers and XGBoost. The RF classifier with fused features for DenseNet121-ResNet50-MobileNet reached an AUC of 99.1%, accuracy of 98.8%, sensitivity of 98.45%, precision of 98.7%, and specificity of 98.85% for the C-NMC 2019 dataset. With the ALL-IDB2 dataset, hybrid systems achieved 100% results for AUC, accuracy, sensitivity, precision, and specificity.