Diagnosis Of Acute Lymphoblastic Leukemia Research Articles

An exploratory study of distractions during the induction phase of pediatric procedural sedation with propofol.

Distractions are a leading cause of disturbance to workflow during medical care. Distractions affecting the anesthetic team in the operating room are frequent and have a negative impact on patient care one-fifth of the time. The objective of this study was to evaluate the frequency, source, target, and impact of distractions during the induction phase of pediatric procedural sedation outside the operating room. Distractions were analyzed during propofol induction for oncology procedures from 45 video recordings. Distraction was defined as any event that disturbs or has potential to disturb the sedation team from performing their primary tasks. The type of distraction was cataloged into communication, coordination, extraneous events, equipment, layout, and usability. A five-point Likert scale was used to quantify the impact on the sedation team or its members. All patients had a diagnosis of acute lymphocytic leukemia and had a mean age of 8.4 years. Five hundred and sixty-seven distractions occurred and averaged 12.6 events (±5.6) per induction (mean induction time 3 min 12 s). Extraneous events were most common, accounting for 55% (312/567) of all distractions. Most distractions had an impact on the sedation team's workflow, resulting in multitasking (46%, n = 262), and in either brief or complete disruption from a primary task (17%). Sedation nurses were impacted most often, 62% of the time. Coordination and usability issues resulted in the greatest negative impact, mean ± SD, 3.7 ± 1.0 and 3.5 ± 0.9, respectively. There was no significant association between distractions and adverse events or induction length. Distractions are common during procedural sedation, with extraneous events being most frequent. Coordination issues within the team and usability problems had the greatest negative impact on sedation team workflow. Nurses were the most frequent target. Distractions impacted sedation team workflow but had no association with patient outcomes.

Вирусные инфекции – причина или триггер развития гемобластоза?

In recent decades, there has been an increase in the number of oncological cases in children. Most common diseases are hemoblastoses, which are characterized by clinical polymorphism in the disease onset, so differential diagnosis should be made. This article presents a clinical case of serous meningitis in a child with increasing dynamics of lymphocytic pleocytosis. The clinical diagnosis of lymphocytic choriomeningitis was based on clinical and anamnestic data (accommodation in the private sector, moderate severity of the general infectious syndrome in combination with severe cerebral and meningeal symptoms), laboratory data (increasing lymphocytic pleocytosis and cell-protein dissociation in the cerebrospinal fluid). The therapy correction included antiviral therapy, which helped to achieve normalization of the cerebrospinal fluid and clinical recovery of the child from an acute neuroinfectious disease in a short time. This clinical case is unique in that 2.5 months after the disease onset, the patient developed convergent strabismus and was hospitalized. Routine blood analysis revealed 25% of blast forms. Further, the diagnosis of acute lymphoblastic leukemia was confirmed, and specific therapy was initiated. It is generally recognized that a prolonged infectious process can be a trigger for both autoimmune and paraneoplastic processes, so long-time patient observation should be provided by a group of specialists (pediatrician, neurologist, infectionist, etc.), and control laboratory examination should be done. Key words: herpesviruses, children, leukemia, lymphocytic choriomeningitis, meningitis, cytoflavin

Latent Space Representational Learning of Deep Features for Acute Lymphoblastic Leukemia Diagnosis

Acute Lymphoblastic Leukemia (ALL) is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow. Early prognosis of ALL is indispensable for the effectual remediation of this disease. Initial screening of ALL is conducted through manual examination of stained blood smear microscopic images, a process which is time-consuming and prone to errors. Therefore, many deep learning-based computer-aided diagnosis (CAD) systems have been established to automatically diagnose ALL. This paper proposes a novel hybrid deep learning system for ALL diagnosis in blood smear images. The introduced system integrates the proficiency of autoencoder networks in feature representational learning in latent space with the superior feature extraction capability of standard pretrained convolutional neural networks (CNNs) to identify the existence of ALL in blood smears. An augmented set of deep image features are formed from the features extracted by GoogleNet and Inception-v3 CNNs from a hybrid dataset of microscopic blood smear images. A sparse autoencoder network is designed to create an abstract set of significant latent features from the enlarged image feature set. The latent features are used to perform image classification using Support Vector Machine (SVM) classifier. The obtained results show that the latent features improve the classification performance of the proposed ALL diagnosis system over the original image features. Moreover, the classification performance of the system with various sizes of the latent feature set is evaluated. The retrieved results reveal that the introduced ALL diagnosis system superiorly compete the state of the art.

Escalated doses of methotrexate and L‐asparaginase in critically ill children with a concurrent diagnosis of acute lymphoblastic leukemia and appendicitis

Escalated doses of methotrexate and L‐asparaginase in critically ill children with a concurrent diagnosis of acute lymphoblastic leukemia and appendicitis

Risk Factors for Readmission Following Febrile Neutropenia in Pediatric Oncology Patients.

Febrile neutropenia is the most common reason for admission from the emergency department for pediatric oncology patients. We identified pediatric inpatients age 1 to 21 years with an International Classification of Diseases, Ninth Revision (ICD-9) diagnosis code of malignancy and either fever with neutropenia or fever alone over a 6-year period (2007-2012) using the PHIS+ database. We evaluated factors associated with readmission within 7 days after index hospitalization. There were 4029 index hospitalizations among 2349 patients in 6 hospitals, 294 encounters (7.3%) were followed by readmission within 7 days. Factors associated with increased odds of readmission included being in the lowest quartile for median household income (odds ratio [OR]=1.64, P =0.009), diagnosis of acute lymphoblastic leukemia (OR=1.37, P =0.016), lack of anerobic coverage during index hospitalization (OR=1.48, P =0.026), and absolute neutrophil count <200cells/μL at discharge from index hospitalizations (OR=1.55, P =0.008). Patients who required readmission had a longer median length of stay and greater hospitalization costs during the index hospitalization. There was a trend towards increasing hospitalization rates for febrile neutropenia over time. While absolute neutrophil count is incorporated into many risk stratification strategies for fever management, further work should focus on addressing socioeconomic factors which may impact readmission rates.

A Deep Learning-Based Approach for the Diagnosis of Acute Lymphoblastic Leukemia

Leukemia is a deadly disease caused by the overproduction of immature white blood cells (WBS) in the bone marrow. If leukemia is detected at the initial stages, the chances of recovery are better. Typically, morphological analysis for the identification of acute lymphoblastic leukemia (ALL) is performed manually on blood cells by skilled medical personnel, which has several disadvantages, including a lack of medical personnel, sluggish analysis, and prediction that is dependent on the medical personnel’s expertise. Therefore, we proposed the Multi-Attention EfficientNetV2S and EfficientNetB3 state-of-the-art deep learning architectures using transfer learning-based fine-tuning approach to distinguish the normal and blast cells from microscopic blood smear images that both are pretrained on large-scale ImageNet database. We simply modified the last block of both models and added additional layers to both models. After including this Multi-Attention Mechanism, it not only reduces the model’s complexities but also generalizes its network quite well. By using the proposed technique, the accuracy has improved and the overall loss is also minimized. Our Multi-Attention EfficientNetV2S and EfficientNetB3 models achieved 99.73% and 99.25% accuracy, respectively. We have further compared the proposed model’s performance to other individual and ensemble models. Upon comparison, the proposed model outclassed the existing literature and other benchmark models, thus proving its efficiency.

ALL-018 Application of Machine Learning in the Diagnosis of Acute Lymphoblastic Leukemia

The ordinary morphologic diagnosis of acute lymphoblastic leukemia (ALL) by a pathologist depends on examining the patient's peripheral blood (PB) together with the bone marrow (BM) blood films. However, this manual aspect of diagnosis is susceptible to discrepancies. We now have a newly introduced technology that allows us to overcome individual variation in the diagnosis of ALL, so-named machine learning, which depends on a complex, preprogrammed convolutional networks matrix. Challenging machine-aided systems that utilize microscopic blood film images to recognize and diagnose ALL based on a preprogrammed deep convolutional neural network (CNN), i.e., machine learning algorithms. We collected a dataset of images composed of PB and BM smear images of two classes: ALL and normal control blood. We analyzed 192 samples of digital images: 96 images of patients with ALL and 96 images of healthy normal controls. For each smear sample, we collected the results of clinical data (clinical history and examination) and laboratory data (morphological, cytochemical, and immunophenotyping assessment). We challenged seven types of CNN models to diagnose ALL: AlexNet, VGG16, VGG19, GoogLeNet, ResNet50, ResNet101, and Inception-v3. Comparing the ability of seven models to diagnose ALL revealed that the AlexNet had the lowest accuracy of 95.51%, followed by VGG16 (92.13%) and VGG19 (93.83%). Inception-v3 had the highest accuracy (99.98%) and was able to detect almost all ALL cases. The statistical measures of the Inception-v3 performance revealed promising results in detecting ALL cases: the sensitivity, specificity, and accuracy of Inception-v3 reached 99.98% for detection of ALL.

Pancreatitis in Acute Lymphoblastic Leukemia

Pancreatitis is inflammation of the pancreatic parenchyma and diagnosed based on symptoms of heartburn accompanied by increased levels of pancreatic enzymes. Acute pancreatitis in acute lymphoblastic leukemia in addition to being caused by therapy can also be caused by other factors. 13-year-old female patient with a diagnosis of acute lymphoblastic leukemia complained of heartburn which was felt through to the back. Patients also experience nausea, vomiting, decreased appetite, difficulty in bowel movements, and fever. Physical examination found an increase in body temperature, anemic eyes, multiple neck gland enlargement, and enlargement of the liver. The results of complete blood tests showed leukocytosis, anemia, and thrombocytopenia. The results of examination of bone marrow aspiration show a picture of the bone marrow in accordance with acute lymphoblastic leukemia (ALL-L2). Clinical chemistry tests showed an increase in amylase, lipase, SGOT, BUN, creatinine, LDH, ferritin, calcium, and procalcitonin. The patient has never received chemotherapy for the ALL. Acute pancreatitis in ALL in addition to being caused by administration of leukemia can also be caused by sepsis conditions which are complications of the ALL. ALL patients who experience acute pancreatitis in this case show a poor prognosis.

Investigating causes and risk factors of pre-chemotherapy viremia in acute lymphoblastic leukemia pediatric patients

BackgroundLeukemia patients are immune-compromised even before starting chemotherapy because the malignant cells invade the bone marrow and destroy WBC precursors. Leukemic patients are more susceptible to infection by a wide range of microorganisms. Viral infections and reactivations are common and may result in severe complications. The aim of this study is to investigate different causes of viremia in ALL pediatric patients as well as the clinical and the laboratory characteristics associated with viral infections.MethodsQualitative real-time PCR was used to detect (polyoma BK, parvo B19 and herpes simplex virus) DNA in the blood of ALL patients and routine hospital records were used to provide the data of hepatitis B & C virus infection.ResultsPolyoma BK was the most common detected virus (51.2%) followed by herpes simplex (30.2%). Viremia by single virus was found in 16 (37.2%) cases, while viremia by multiple viruses was found in 15 (34.8%) cases. The most frequent co-detected viruses were herpes simplex and polyoma BK (11.6%) followed by herpes simplex, parvo B19 and polyoma BK (9.3%).ConclusionThere is a high frequency of viremia by single virus and viremia by multiple viruses at the time of diagnosis of acute lymphoblastic leukemia in pediatric patients admitted to South Egypt Cancer Institute (SECI) compared to studies in other regions. Polyoma BK is the most common detected virus and is mainly associated with lymphopenia. It was also significantly associated with herpes simplex viremia. HCV infection was associated with increased incidence of CNS leukemia.

P362: MINIMAL-LOSS-CYTOMETRY FOR EVALUATION OF CEREBROSPINAL FLUID IN PEDIATRIC ACUTE LYMPHOBLASTIC LEUKEMIA. SINGLE CENTER STUDY.

Background: Central nervous system (CNS) involvement at diagnosis of acute lymphoblastic leukemia (ALL) represents a risk factor for CNS relapse. Currently, examination of the cerebrospinal fluid (CSF) is performed and evaluated quantitatively using a counting chamber and qualitatively using cytomorphological analysis of cytospin. Recently, flow cytometry (FC) evaluation of CSF was shown to provide more reliable results and to predict relapse risk (de Haas et al., 2021, Thastrup et al., 2020). Independently of these studies, we applied a lyse-no wash technique aiming at minimizing cell loss during preparation and at improved cell concentration estimate. Aims: Our aim was to compare our findings with morphological criteria and published data and correlate them with clinical outcome in pediatric patients with ALL. Methods: We included pediatric patients with newly diagnosed ALL (04/2014 – 01/2022), whose CSF examination was performed in CLIP laboratory (n=208). Patients were classified as B cell precursor ALL (BCP ALL; 85%) and T ALL (15%) and treated according to following protocols: AIEOP-BFM ALL 2009 (n=118), AIEOP-BFM ALL 2017 (n=71), EsPhALL(n=8), Interfant06 (n=5), off-protocol (n=6). During follow up, 14 patients relapsed (5 CNS incl. combined, 9 non-CNS). CSF (drawn into tube with no fixative agent and processed within 2 hours) was concentrated by centrifugation and incubated with combination of antibodies (CD20/CD10/CD45/CD34/CD19/CD3/Syto41 in BCP ALL and CD4/CD99/CD5/CD3/CD7/CD16 + 56/CD8/CD45/Syto41 in T ALL). Residual erythrocytes were lysed with NH4Cl solution, followed by immediate acquisition on BD FACS Lyric or BD LSRII cytometers. Blasts were quantified to initial CSF volume. Cluster of 20 events was required to assign samples as FC positive (FC+). In parallel, CNS status was concluded according to morphological criteria, being classified as CNS1 (no blasts), CNS2a/b (≤5 WBC/μL with blasts), CNS2c/CNS3 (≥5 WBC/μL with blasts) according to treatment protocol guidelines. Continuous variables were compared with the Mann–Whitney test, survival data were analyzed using Mantel-Cox test. P values<0.05 were considered as significant. Results: Using FC, we identified atypical blasts in 50 out of the 208 analyzed samples (24%). Median of analyzed CSF volume was 367µL (range 143-1033µL), which enabled median sensitivity 0.054 events/µL (range 0.02-0.14ev/µL). Mean blast concentration was 0.47ev/µL (range 0-25ev/µL) in all samples and 2 ev/µL (range 0.01-25ev/µL, median 0.53ev/µL) in FC+ samples. We observed significantly higher blast concentration in patients with T ALL, in patients with CNS2 and CNS3 and those who subsequently relapsed. Patients with FC+ had significantly lower relapse-free survival than FC- patients (55% vs 94%), which provided better separation than CNS status (68% vs.85% for CNS2/3 vs. CNS1, respectively). Image:Summary/Conclusion: Using fresh CSF sample with lyse-no wash protocol enabled us to detect approximately 10x higher blast count (0.24ev/µL in FC+CNS1 and 1.25ev/µL in FC+CNS2/3) than was recently published (0.015ev/µL in FC+CNS1 and 0.073ev/µL in FC+CNS2/3 in Thastrup et al., 2020), and thus it better correlates to cytomorphological data. Interestingly, the proportion of FC+ patients in our cohort is comparable to (24% vs 25%), showing that although in our method we lose fewer cells, we identify the same proportion of FC+ patients. The presented study shows a higher impact of FC positivity on relapse risk than described previously. The disadvantage of our method is a need for a fresh sample, which is investigated locally. Supported by UNCE/MED/015, NU20J-07-00028.

Clinico-Haematologic Parameters And Assessment Of Post-Induction Status In Acute Lymphoblastic Leukaemia.

Acute Leukaemia is a malignant disorder characterized by an abnormal proliferation of immature cells, called blasts. Classically, acute leukaemia is classified into acute myeloid leukaemia and acute lymphoblastic leukaemia depending on the lineage of the immature cells. Objective of the study was to evaluate the clinical presentations, analyze the haematologic parameters at time of diagnosis and assess the post-induction status in newly diagnosed ALL patients. This cross-sectional study was conducted in the Department of Haematology, Armed Forces Institute of Pathology, Rawalpindi from June to November 2019. A total of 55 newly diagnosed ALL patients were recruited including children, adults and elderly. Detailed medical history and physical findings were noted. Haematologic parameters were documented. Each patient was treated as per standard protocol and remission induction status was determined on day 29 of treatment. The median age of the study cohort of 55 newly diagnosed ALL patients was 8.5 years. Males were 37 (67.3%) and females were 18 (32.7%) with a male to female ratio of 2:1. Paediatric group included 31 (56.4%) patients. Nine (16.4%) patients were in the adult group and 15 (27.3%) in the elderly age group. The time from onset of symptoms to diagnosis of acute lymphoblastic leukaemia was 98.87±79.21 days. Fever was the most common symptom but body aches were common among paediatric group while pallor was the most common sign. Mean WBC was 29.1±27.9 x109/l, Hb was 8.1±2.9 g/dl and platelet count was 60±41.8 x109/l B-acute lymphoblastic leukaemia was more common than T-acute lymphoblastic leukaemia. A total of 52 patients were assessed on day 29 to evaluate for post-induction remission status. The remission rate of our cohort of patients was 82.7%. Most of the patients were in paediatric age group and remission rate was better in this age group compared to elderly population. B-ALL was associated with good response to induction chemotherapy while patients with BCR-ABL1 gene rearrangement did not respond well to treatment. Identification of prognostic features at diagnosis will further help our clinicians to predict outcomes of the disease.

Nutritional Interventions in Pediatric Patients With Acute Lymphoblastic Leukemia: A Systematic Review

ObjectivesTo evaluate the effect of different nutritional interventions in children with a diagnosis of acute lymphoblastic leukemia (ALL) receiving antineoplastic treatment. MethodsThis systematic review (SR) was conducted based on a predefined protocol (PROSPERO: CRD42021266761). We searched for published or unpublished randomized trials in the following databases: Cochrane CENTRAL, MEDLINE, EMBASE, LILACS, SciELO and conducted complementary searches. Studies with at least 50% of the participants had a diagnosis of ALL, were ≤18 years of age, were receiving antineoplastic treatment and a nutritional intervention, were selected. Study selection, data extraction and assessment of risk of bias were conducted independently by three reviewers. Variables related to nutritional status were evaluated for meta-analysis and narrative review. ResultsA total of 4097 records were found. Twenty-four full text papers (25 records) met the inclusion criteria. Seventeen studies had a high risk of bias. Intervention tested included honey, ω-3 fatty acids, black seed oil, whey protein hydrolyzate, parenteral and enteral nutrition, probiotics, vitamin A, E, K and C, zinc and calcium. A random effect meta-analysis of mean difference for glutamine and vitamin D variables was performed. In the case of glutamine, a decrease in the number of days of hospitalization was seen in the intervention group vs control group (–3.44 days; 95% CI: –5.1, –1.79; 2 studies, I2 = 85%). ConclusionsRandomized trials focused on the nutritional treatment of pediatric patients with ALL are limited and the methodologies used are diverse. This SR highlights the need to develop high quality studies focused on these patients and their nutritional treatment, as well as standardizing nutritional intervention methodology depending on the patients’ needs, to develop quality evidence that helps clinical decision making. Funding SourcesAEGL received a PhD grant from CONACyT (National Council for Science and Technology) and project resources by the IAEA (International Atomic Energy Agency).

Acute lymphoblastic leukemia with "masked" Philadelphia chromosome

A 76-year-old woman with leukocytosis and thrombocytopenia was admitted to our hospital. A bone marrow examination showed a composition of 82.0% blasts, i.e., positive for TdT, CD10, CD19, CD34, and HLA-DR and negative for cyCD3, CD13, CD33, MPO, and cyµ. The reverse transcription-polymerase chain reaction analysis revealed a minor BCR-ABL1 fusion gene, leading to a diagnosis of acute lymphocytic leukemia (ALL) with a BCR-ABL1 fusion gene. G-band assay was negative for Philadelphia (Ph) chromosome and also revealed add (21) (q22. 1) and del (20) (q11. 2q13.3). Fluorescence in situ hybridization (FISH) assaying revealed a positive BCR-ABL1 fusion signal. Thus, this patient was diagnosed as Ph chromosome-negative and BCR-ABL1-positive fusion gene ALL, which suggested the presence of ALL with the "masked" Ph chromosome found in approximately 1% of chronic myeloid leukemia. Therefore, the FISH analysis may complement cytogenetic analysis when cytogenetic and molecular genetic findings are contradictory in ALL.

Maladie de Still de l’enfant et Leucémie aigüe lymphoblastique, une association exceptionnelle: à propos d’un cas

Still's disease, also known as systemic juvenile idiopathic arthritis (SJIA), and acute lymphoblastic leukemia have similar clinical and biological features posing diagnostic and treatment challenges. Indeed, while Still's disease is a diagnosis of exclusion in rheumatology, polyarthritis associated with hyperleukocytosis and fever, which is characteristic of this disease, are often detected in early stages of acute lymphocytic leukaemias. We here report the case of a 4-year-old girl, treated for Still's disease, in whom the diagnosis of acute lymphoblastic leukemia was made after 2 months, based on bone marrow biopsy.

Children With Asparaginase-associated Pancreatitis Present Elevated Levels of Insulin, Total Cholesterol, and HOMA-IR Before Starting Acute Lymphoblastic Leukemia Treatment.

Asparaginase-associated pancreatitis frequently occurs in children with cancer. It is unknown if other factors can influence the development of pancreatitis. A total of 33 pediatric patients with a confirmed diagnosis of acute lymphoblastic leukemia were included in this study. Before acute lymphoblastic leukemia drug treatment, the metabolic parameters (glucose, insulin, homeostasis model assessment insulin resistance, total cholesterol, triglycerides) and body mass index percentile were compared. Children who had acute pancreatitis had higher levels of insulin, homeostasis model assessment insulin resistance, and total cholesterol, compared with children who did not develop acute pancreatitis. These metabolic alterations could play a role in the development of pancreatitis.

Weakly Supervised Ternary Stream Data Augmentation Fine-Grained Classification Network for Identifying Acute Lymphoblastic Leukemia.

Due to the high incidence of acute lymphoblastic leukemia (ALL) worldwide as well as its rapid and fatal progression, timely microscopy screening of peripheral blood smears is essential for the rapid diagnosis of ALL. However, screening manually is time-consuming and tedious and may lead to missed or misdiagnosis due to subjective bias; on the other hand, artificially intelligent diagnostic algorithms are constrained by the limited sample size of the data and are prone to overfitting, resulting in limited applications. Conventional data augmentation is commonly adopted to expand the amount of training data, avoid overfitting, and improve the performance of deep models. However, in practical applications, random data augmentation, such as random image cropping or erasing, is difficult to realistically occur in specific tasks and may instead introduce tremendous background noises that modify actual distribution of data, thereby degrading model performance. In this paper, to assist in the early and accurate diagnosis of acute lymphoblastic leukemia, we present a ternary stream-driven weakly supervised data augmentation classification network (WT-DFN) to identify lymphoblasts in a fine-grained scale using microscopic images of peripheral blood smears. Concretely, for each training image, we first generate attention maps to represent the distinguishable part of the target by weakly supervised learning. Then, guided by these attention maps, we produce the other two streams via attention cropping and attention erasing to obtain the fine-grained distinctive features. The proposed WT-DFN improves the classification accuracy of the model from two aspects: (1) in the images can be seen details since cropping attention regions provide the accurate location of the object, which ensures our model looks at the object closer and discovers certain detailed features; (2) images can be seen more since erasing attention mechanism forces the model to extract more discriminative parts’ features. Validation suggests that the proposed method is capable of addressing the high intraclass variances located in lymphocyte classes, as well as the low interclass variances between lymphoblasts and other normal or reactive lymphocytes. The proposed method yields the best performance on the public dataset and the real clinical dataset among competitive methods.

A fast and efficient CNN model for B‐ALL diagnosis and its subtypes classification using peripheral blood smear images

The definitive diagnosis of acute lymphoblastic leukemia (ALL), as a highly prevalent cancer, requires invasive, expensive, and time-consuming diagnostic tests. ALL diagnosis using peripheral blood smear (PBS) images plays a vital role in the initial screening of cancer from non-cancer cases. The examination of these PBS images by laboratory users is riddled with problems such as diagnostic error because the nonspecific nature of ALL signs and symptoms often leads to misdiagnosis. Herein, a model based on deep convolutional neural networks (CNNs) is proposed to detect ALL from hematogone cases and then determine ALL subtypes. In this paper, we build a publicly available ALL data set, comprised 3562 PBS images from 89 patients suspected of ALL, including 25 healthy individuals with a benign diagnosis (hematogone) and 64 patients with a definitive diagnosis of ALL subtypes. After color thresholding-based segmentation in the HSV color space by designing a two-channel network, 10 well-known CNN architectures (EfficientNet, MobileNetV3, VGG-19, Xception, InceptionV3, ResNet50V2, VGG-16, NASNetLarge, InceptionResNetV2, and DenseNet201) were employed for feature extraction of different data classes. Of these 10 models, DenseNet201 achieved the best performance in diagnosis and classification. Finally, a model was developed and proposed based on this state-of-the-art technology. This deep learning-based model attained an accuracy, sensitivity, and specificity of 99.85, 99.52, and 99.89%, respectively. The proposed method may help to distinguish ALL from benign cases. This model is also able to assist hematologists and laboratory personnel in diagnosing ALL subtypes and thus determining the treatment protocol associated with these subtypes. The proposed data set is available at https://www.kaggle.com/mehradaria/leukemia and the implementation (source code) of proposed method is made publicly available at https://github.com/MehradAria/ALL-Subtype-Classification.

A clinical case of pulmonary form of mucormycosis in a child with acute lymphoblastic leukemia

Mucormycosis of the lungs is a severe infectious complication in patients with acute lymphoblastic leukemia, which develops at the stage of high-dose cytostatic therapy. It is characterized by an extremely aggressive, rapidly progressive course and, without specific treatment, is fatal in a short time. Reliable verification of mucor is necessary due to its resistance to the most commonly used antifungal drugs, particularly to voriconazole.The article presents a clinical case of pulmonary mucormycosis in a 12‑year-old child at the stage of diagnosis of acute lymphoblastic leukemia. The first symptoms of the disease (headaches, malaise and weakness, pallor), changes in the general blood count (hyperleukocytosis up to 200 thousand cells/μl, single platelets). Based on the results of the examination, the main diagnosis was verified for acute lymphoblastic leukemia L2, IFT T-II, CD1a-. At the stage of diagnosis of acute lymphoblastic leukemia, the underlying disease was complicated by the development of right-sided pneumonia according to X-ray examination. To verify the etiology of infiltration of lung tissue, broncho-alveolar lavage was directed to microbiological diagnostics, which included studies: enzyme immunoassay, microscopic and cultural. On the aggregate of all the results obtained, invasive mucormycosis was diagnosed and antifungal therapy was started immediately.

Клинический случай легочной формы мукормикоза у ребенка с острым лимфобластным лейкозом

The article presents a clinical case of pulmonary mucormycosis in a 12‑year-old child at the stage of diagnosis of acute lymphoblastic leukemia. The first symptoms of the disease (headaches, malaise and weakness, pallor), changes in the general blood count (hyperleukocytosis up to 200 thousand cells/μl, single platelets). Based on the results of the examination, the main diagnosis was verified for acute lymphoblastic leukemia L2, IFT T-II, CD1a-. At the stage of diagnosis of acute lymphoblastic leukemia, the underlying disease was complicated by the development of right-sided pneumonia according to X-ray examination. To verify the etiology of infiltration of lung tissue, broncho-alveolar lavage was directed to microbiological diagnostics, which included studies: enzyme immunoassay, microscopic and cultural. On the aggregate of all the results obtained, invasive mucormycosis was diagnosed and antifungal therapy was started immediately.

A clinical case of pulmonary form of mucormycosis in a child with acute lymphoblastic leukemia

Mucormycosis of the lungs is a severe infectious complication in patients with acute lymphoblastic leukemia, which develops at the stage of high-dose cytostatic therapy. It is characterized by an extremely aggressive, rapidly progressive course and, without specific treatment, is fatal in a short time. Reliable verification of mucor is necessary due to its resistance to the most commonly used antifungal drugs, particularly to voriconazole.The article presents a clinical case of pulmonary mucormycosis in a 12‑year-old child at the stage of diagnosis of acute lymphoblastic leukemia. The first symptoms of the disease (headaches, malaise and weakness, pallor), changes in the general blood count (hyperleukocytosis up to 200 thousand cells/μl, single platelets). Based on the results of the examination, the main diagnosis was verified for acute lymphoblastic leukemia L2, IFT T-II, CD1a-. At the stage of diagnosis of acute lymphoblastic leukemia, the underlying disease was complicated by the development of right-sided pneumonia according to X-ray examination. To verify the etiology of infiltration of lung tissue, broncho-alveolar lavage was directed to microbiological diagnostics, which included studies: enzyme immunoassay, microscopic and cultural. On the aggregate of all the results obtained, invasive mucormycosis was diagnosed and antifungal therapy was started immediately.