Detection of Acute Lymphoblastic Leukemia using watershed transformation technique

The objective of this work is to create a diagnostic tool for the early diagnosis of leukaemia which is a serious type of cancer affecting bones and blood. Acute lymphoblastic leukemia (ALL) is the most dangerous form of leukemia. Doctors diagnose it by blood samples under powerful microscopes with enhanced lenses which can be slow and is sometimes affected by disagreements among experts. Therefore, the purpose of this work was to create a profound diagnostic tool for the early diagnosis of leukaemia.We proposes an Optimized Light Weight CNN to detect ALL at the early stage. Fragmentation and classification based on preprocessing are the two main components of the suggested method. Artificial images are created during the segmentation process and then tamed by chromatic modification. The proposed model is used to extract the best deep features from every blood smear image to predict the presence of ALL. The work was tested by two lymphoblastic leukaemia image databases (ALL_IDB1 and ALL_IDB2). Deep-learning (DL) models-based segmentation and classification techniques have recently been introduced for detecting ALL; however they still have certain drawbacks. The proposed approach was assessed with few DL parameters like accuracy, F1 score, precision, recall and area under the curve. In comparison to the most recent research studies already published; the suggested strategy produced exceptional classification accuracy as 99.56%, F1 score as 99.53%.

Leucocyte classification for leukaemia detection using image processing techniques.

Blood and bone marrow smears from 49 dogs and cats, believed to have myeloproliferative disorders (MPD), were examined by a panel of 10 clinical pathologists to develop proposals for classification of acute myeloid leukemia (AML) in these species. French-American-British (FAB) group and National Cancer Institute (NCI) workshop definitions and criteria developed for classification of AML in humans were adapted. Major modifications entailed revision of definitions of blast cells as applied to the dog and cat, broadening the scope of leukemia classification, and making provisions for differentiating erythremic myelosis and undifferentiated MPD. A consensus cytomorphologic diagnosis was reached in 39 (79.6%) cases comprising 26 of AML, 10 of myelodysplastic syndrome (MDS), and 3 of acute lymphoblastic leukemia (ALL). Diagnostic concordance for these diseases varied from 60 to 81% (mean 73.3 +/- 7.1%) and interobserver agreement ranged from 51.3 to 84.6% (mean 73.1 +/- 9.3%). Various subtypes of AML identified included Ml, M2, M4, M5a, M5b, and M6. Acute undifferentiated leukemia (AUL) was recognized as a specific entity. M3 was not encountered, but this subclass was retained as a diagnostic possibility. The designations M6Er and MDS-Er were introduced where the suffix "Er" indicated preponderance of erythroid component. Chief hematologic abnormalities included circulating blast cells in 98% of the cases, with 36.7% cases having >30% blast cells, and thrombocytopenia and anemia in approximately 86 to 88% of the cases. Bone marrow examination revealed panmyeloid dysplastic changes, particularly variable numbers of megaloblastoid rubriblasts and rubricytes in all AML subtypes and increased numbers of eosinophils in MDS. Cytochemical patterns of neutrophilic markers were evident in most cases of Ml and M2, while monocytic markers were primarily seen in M5a and M5b cases. It is proposed that well-prepared, Romanowsky-stained blood and bone marrow smears should be examined to determine blast cell types and percentages for cytomorphologic diagnosis of AML. Carefully selected areas of stained films presenting adequate cellular details should be used to count a minimum of 200 cells. In cases with borderline diagnosis, at least 500 cells should be counted. The identity of blast cells should be ascertained using appropriate cytochemical markers of neutrophilic, monocytic, and megakaryocytic differentiation. A blast cell count of > 30% in blood and/or bone marrow indicates AML or AUL, while a count of < 30% blasts in bone marrow suggests MDS, chronic myeloid leukemias, or even a leukemoid reaction. Myeloblasts, monoblasts, and megakaryoblasts comprise the blast cell count. The FAB approach with additional criteria should be used to distinguish AUL and various subtypes of AML (Ml to M7 and M6Er) and to differentiate MDS, MDS-ER, chronic myeloid leukemias, and leukemoid reaction. Bone marrow core biopsy and electron microscopy may be required to confirm the specific diagnosis. Immunophenotyping with lineage specific antibodies is in its infancy in veterinary medicine. Development of this technique is encouraged to establish an undisputed identity of blast cells. Validity of the proposed criteria needs to be substantiated in large prospective and retrospective studies. Similarly, clinical relevance of cytomorphologic, cytochemical, and immunophenotypic characterizations of AML in dogs and cats remains to be determined.

A Novel Automated Image Analysis System Using Deep Convolutional Neural Networks to Diagnose MDS

Hematology-Oncology| March 01 2001 Initial Traumatic LP Adversely Affects Outcome in ALL AAP Grand Rounds (2001) 5 (3): 24. https://doi.org/10.1542/gr.5-3-24 Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Share Icon Share Twitter LinkedIn Tools Icon Tools Get Permissions Cite Icon Cite Search Site Citation Initial Traumatic LP Adversely Affects Outcome in ALL. AAP Grand Rounds March 2001; 5 (3): 24. https://doi.org/10.1542/gr.5-3-24 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search toolbar search search input Search input auto suggest filter your search All PublicationsAll JournalsAAP Grand RoundsPediatricsHospital PediatricsPediatrics In ReviewNeoReviewsAAP NewsAll AAP Sites Search Advanced Search Topics: blast cells, cerebrospinal fluid, leukemia, lipopolysaccharides, traumatic lumbar puncture, treatment outcome, van der woude syndrome, acute lymphocytic leukemia, atypical, central nervous system dysfunction Source: Gajjar A, Harrison PL, Sandlund JT, et al. Traumatic lumbar puncture at diagnosis adversely affects outcome in childhood acute lymphoblastic leukemia. Blood. 2000;96: 3381–3384 This retrospective study was conducted to answer an important, controversial question: does a traumatic lumbar puncture (TLP) at the time of the initial diagnostic work-up and/or induction treatment have any effect on the treatment outcome in children with acute lymphoblastic leukemia (ALL)? The authors reviewed the cerebrospinal fluid (CSF) findings of lumbar punctures (LP) performed in 546 patients enrolled on two consecutive therapeutic trials at St. Jude Children’s Research Hospital, Memphis, Tennessee between 1984 to 1991. All patients underwent 2 LPs, usually within 24–48 hrs of each other at the time of initial diagnostic evaluation and at the beginning of the induction chemotherapy. A complete blood count and examination of a centrifuged and stained CSF cell pellet were performed in all patients. The patients were divided into 5 groups depending on their central nervous system (CNS) status: LP not traumatic with <10 red blood cells (RBCs) per μL in the CNS and no leukemic blast cells (n=336), LP not traumatic with <5 white blood cells (WBCs) per μL and containing leukemic blast cells (n=80), LP not traumatic with ≥5 WBCs per μL and containing leukemic blast cells (n=16), LP traumatic with ≥10 RBCs per μL and no leukemic blast cells (TLP−, n=54), and LP traumatic with leukemic blast cells (TLP+, n=60). There were 26 patients who had 2 consecutive TLPs with blast cells (TLP++). The 5-year event-free survival (EFS± 1 SE) for the 5 groups is shown in the tableT1: The EFS was similar between patients with an atraumatic LP and no blast cells and those who were TLP− (P=.85). The EFS of patients who were TLP+ was worse than that for those who had an atraumatic LP with no blast cells (P=.026) and comparable to those who had an atraumatic LP with <5 WBCs and leukemic blast cells (P=.59). The authors conclude that a TLP during initial diagnostic evaluation and treatment of ALL leads to contamination of the CSF with circulating leukemic blast cells and will adversely affect the treatment outcome of children with ALL. Furthermore, the EFS of patients with 2 TLPs with blast cells (TLP++) was comparable to that of patients with overt CNS disease (≥5 WBCs with blast cells). The definition of CNS leukemia is controversial when the CSF contains a small number of WBCs and blasts are seen on a stained cytospin preparation. Most physicians follow the recommendation of the Rome Leukemia Workshop,1 which characterizes patients who have >5 WBCs μL with identifiable blasts as having CNS involvement. The problem is positively identifying the few “atypical” looking cells as true blasts, thus justifying more intensive CNS directed therapy. This is true even if more specific tests such as determination of surface markers by staining or flow cytometry... You do not currently have access to this content.

Fuzzy clustering of Acute Lymphoblastic Leukemia images assisted by Eagle strategy and morphological reconstruction

We examined the stimulatory effects of recombinant human granulocyte-macrophage colony-stimulating factor (GM-CSF) and interleukin 6 (IL)-6 on the in vitro proliferation of leukemic blast cells from patients with acute leukemia. Bone marrow or peripheral blood leukemic blast cells were obtained from 21 patients, including 14 cases of acute myeloblastic leukemia (AML), four cases of acute lymphoblastic leukemia (ALL), two cases of acute undifferentiated leukemia, and one case of acute mixed-lineage leukemia. The proliferation of leukemic blast cells was evaluated by measuring the incorporation of 3H-thymidine into cells incubated with various concentrations of cytokines for 3 days. GM-CSF stimulated the DNA synthesis (with greater than 2.0 stimulation index) of blast cells in 9 of 14 (64%) AML cases, two cases of acute undifferentiated leukemia and one case of acute mixed-lineage leukemia. Only two cases of AML blasts responded to IL-6 to grow in the short-term suspension cultures. GM-CSF and IL-6 did not display a synergistic effect on the growth of leukemic cells. Moreover, GM-CSF and IL-6 did not stimulate the proliferation of ALL blast cells. Binding study also revealed the specific binding of GM-CSF on the blast cells of acute undifferentiated leukemia and acute mixed-lineage leukemia. Our results indicated that leukemic blast cells of acute undifferentiated leukemia and acute mixed-lineage leukemia possessed functional GM-CSF receptors.

Relevance: Acute lymphoblastic leukemia (ALL) is the most common cancer among children, accounting for nearly a quarter of all childhood cancers.&#x0D; The study aimed to determine the risk factors and signs of critical conditions in children with acute lymphoblastic leukemia admitted to an intensive care unit (ICU).&#x0D; Methods: The approach used was a systematic review. Data was collected from sources published in 2019-2023. Four cohort studies, four retrospective analyses, two literature reviews, one case-control study, and one case study were included in this systematic review.&#x0D; Results: The prognosis in pediatric ALL depends on the initial number of blast cells in the peripheral blood. Patients with B-cell precursor acute lymphoblastic leukemia (BCP ALL) and low blast cell numbers survived better than patients with T-cell acute lymphoblastic leukemia (T-ALL) and low cell count. IL1B and NLRP1 genetic polymorphisms enhanced ALL risk and reduced infectious comorbidity. However, these gene polymorphisms must be confirmed in juvenile leukemia. KRAS, FLT3, NRAS, PTPN11, KMT2D, PTEN, and NOTCH1 gene mutations affected pediatric ALL patient features and treatment results. These mutations demonstrate the relevance of genetic profiling in risk classification and tailored management. Gene variations and availability of effective medication contributed. Pediatric BCP-ALL patients with the PAX5P80R mutation had worse 5-year overall survival, higher white blood cell counts, male preponderance, and more genetic abnormalities. Pediatric BCP-ALL focused on genetic analysis and risk stratification. Children of African American and European American ancestry showed varied incidence, recurrence, and outcome rates for ALL. African American children exhibited lower incidence but greater recurrence rates and poorer prognosis than European American children.&#x0D; Conclusion: Risk factors for these patients’ admission to ICU include comorbidities, infectious diseases, hypoxia, and hemodynamic instability, as well as age and baseline white blood cell count at diagnosis.

Identification of GPAT1 As a Novel Therapeutic Target for Acute Leukemia By Inhibiting Leukemia Specific Metabolism

Value of Day 21 Flow Cytometry Minimal Residual Disease Assessment in Childhood Acute Lymphoblastic Leukemia (ALL) for Early Identification of Good Responders

Acute lymphoblastic leukemia (ALL) with translocation t(4;11) is a high-risk leukemia found in 60–85% of infants with ALL and is often refractory to conventional chemotherapeutics after relapse. To evaluate the efficacy of dietary resveratrol in vivo, 5-week-old NOD.CB17-Prkdcscid/J mice were fed a control diet or a diet containing 0.2% w/w resveratrol. After 3 weeks of dietary treatment, mice were engrafted with the human t(4;11) ALL line SEM by tail vein injection. Engraftment was monitored by evaluating the presence of human CD19+ cells in peripheral blood using flow cytometry. Relative to control diet, dietary resveratrol did not delay the engraftment of the leukemia cells. To determine if dietary resveratrol could increase efficacy of a chemotherapeutic agent, vincristine was injected intraperitoneally into leukemic mice fed the control or supplemented diet. Survival curves and monitoring the percentage of human leukemia cells in peripheral blood showed that resveratrol did not inhibit leukemia cell growth or influence the activity of vincristine. Mass spectrometric analysis of mouse serum revealed that the majority of resveratrol was present as glucuronidated and sulfated metabolites. These data do not support the concept that dietary resveratrol has potential as a preventative agent against the growth of high-risk t(4;11) ALL.

The examination, counting, and classification of white blood cells (WBCs), also known as leukocytes, are essential processes in the diagnosis of many disorders, including leukemia, a kind of blood cancer characterized by the uncontrolled proliferation of carcinogenic leukocytes in the marrow of the bone. Blood smears can be chemically or microscopically studied to better understand hematological diseases and blood disorders. Detecting, identifying, and categorizing the many blood cell types are essential for disease diagnosis and therapy planning. A theoretical and practical issue. However, methods based on deep learning (DL) have greatly helped blood cell classification. Images of blood cells in a microscopic smear were collected from GitHub, a public source that uses the MIT license. An end-to-end computer-aided diagnosis (CAD) system for leukocytes has been created and implemented as part of this study. The introduced system comprises image preprocessing and enhancement, image segmentation, feature extraction and selection, and WBC classification. By combining the DenseNet-161 and the cyclical learning rate (CLR), we contribute an approach that speeds up hyperparameter optimization. We also offer the one-cycle technique to rapidly optimize all hyperparameters of DL models to boost training performance. The dataset has been split into two sets: approximately 80% of the data (9,966 images) for the training set and 20% (2,487 images) for the validation set. The validation set has 623, 620, 620, and 624 eosinophil, lymphocyte, monocyte, and neutrophil images, whereas the training set has 2,497, 2,483, 2,487, and 2,499, respectively. The suggested method has 100% accuracy on the training set of images and 99.8% accuracy on the testing set. Using a combination of the recently developed pretrained convolutional neural network (CNN), DenseNet, and the one fit cycle policy, this study describes a technique of training for the classification of WBCs for leukemia detection. The proposed method is more accurate compared to the state of the art.

Artificial intelligence (AI) has emerged as a cutting-edge tool, simultaneously accelerating, securing, and enhancing the diagnosis and treatment of patients. An exemplification of this capability is evident in the analysis of peripheral blood smears (PBS). In university medical centers, hematologists routinely examine hundreds of PBS slides daily to validate or correct outcomes produced by advanced hematology analyzers assessing samples from potentially problematic patients. This process may logically lead to erroneous PBC readings, posing risks to patient health. AI functions as a transformative tool, significantly improving the accuracy and precision of readings and diagnoses. This study reshapes the parameters of blood cell classification, harnessing the capabilities of AI and broadening the scope from 5 to 11 specific blood cell categories with the challenging 11-class PBC dataset. This transformation facilitates a more profound exploration of blood cell diversity, surpassing prior constraints in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking “Naturalize” augmentation technique produces remarkable results. The 2K-PBC dataset generated with “Naturalize” boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The “Naturalize” technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.

Blood cell classification and counting are vital for the diagnosis of various blood-related diseases, such as anemia, leukemia, lymphoma, and thrombocytopenia. The manual process of blood cell classification and counting is time-consuming, prone to errors, and labor-intensive. Therefore, we have proposed a deep learning (DL)-based automated system for blood cell classification and counting from microscopic blood smear images. We classify a total of nine types of blood cells, including Erythrocyte, Erythroblast, Neutrophil, Basophil, Eosinophil, Lymphocyte, Monocyte, Immature Granulocytes, and Platelet. Several preprocessing steps like image resizing, rescaling, contrast enhancement and augmentation are utilized. To segment the blood cells from the entire microscopic images, we employed the U-Net model. This segmentation technique aids in extracting the region of interest (ROI) by removing complex and noisy background elements. Both pixel-level metrics such as accuracy, precision, and sensitivity, and object-level evaluation metrics like Intersection over Union (IOU) and Dice coefficient are considered to comprehensively evaluate the performance of the U-Net model. The segmentation model achieved impressive performance metrics, including 98.23% accuracy, 98.40% precision, 98.26% sensitivity, 95.97% Intersection over Union (IOU), and 97.92% Dice coefficient. Subsequently, a watershed algorithm is applied to the segmented images to separate overlapped blood cells and extract individual cells. We have proposed a BloodCell-Net approach incorporated with custom light weight convolutional neural network (LWCNN) for classifying individual blood cells into nine types. Comprehensive evaluation of the classifier’s performance is conducted using metrics including accuracy, precision, recall, and F1 score. The classifier achieved an average accuracy of 97.10%, precision of 97.19%, recall of 97.01%, and F1 score of 97.10%. A 5-fold cross-validation technique is applied to split the data, which not only aids in reducing overfitting but also helps in generalizing the model.

The problem of identifying and counting blood cells within the blood smear is of both theoretical and practical interest. The differential counting of blood cells provides invaluable information to pathologist for diagnosis and treatment of many diseases. In this paper we propose an efficient hierarchical blood cell image identification and classification method based on multi-class support vector machine. In this automated process, segmentation and classification of blood cells are the most important stages. We segment the stained blood cells in digital microscopic images and extract the geometric features for each segment to identify and classify the different types of blood cells. The experimental results are compared with the manual results obtained by the pathologist, and demonstrate the effectiveness of the proposed method.