Leukemia detection using SegNet and faster region-based convolutional neural network

Leukemia is a group of lethal diseases characterized by hematological neoplasm with complex and abnormalities in proliferation of bone marrow stem cells, that cause sever loss of functional capacity of hematopoietic tissue. Four most common types of leukemia are included acute lymphoblastic leukemia (ALL), acute myeloid leukemia (AML), chronic lymphocytic leukemia (CLL) and chronic myeloid leukemia (CML). It has been reported that opium besides of pain killer effects, may have positive effects on cardiovascular disease treatments. Opium may consider as a potential treatment method in cancer. The present study aimed to assess the gene expression pattern alterations in the rat models of four types of Leukemia (ALL, AML, CLL, and CML) under taper up-off treatment method with of opium. Present study was included twelve group, referred to four type of Leukemia (ALL, AML, CLL, and CML) that each type studied in three group. Group one contented normal rats, group two rat model of each type of leukemia with no treatment and group three the rat model of that type of leukemia with 26 days period of opium taper up-off treatment. After the scarification of rats, the bone marrow tissue were extracted. Then, RNA extraction and cDNA synthesis had been conducted on bone marrow tissues. Whole genome expression profiling was conducted by using the Affymetrix GeneChip Array Platform. Microarray results were confirmed by Real time PCR. Microarray analysis detected that hundreds of genes which were involved in Ontogenesis and apoptosis, humoral immune system, tool like receptors, natural killer cells regulators and metabolic pathways and were deregulated in leukemic models, were partially reregulated in treatment groups. Results showed that opium may have positive effects on reregulation of affected gene expression patterns in all types of leukemia. It may suggest that opium taper up-off treatment could be consider as re-regulator of immune system and a novel potential treatment for leukemia with low side effects and high viability.

Minimal Residual Disease following Allogeneic Hematopoietic Stem Cell Transplantation

Risk Factors for Outcomes of Family Haploidentical Allogeneic Stem Cell Transplantation for Adults with Acute Leukemias: A Survey on Behalf of the Acute Leukemia Working Party of the European Group for Blood and Marrow Transplantation (EBMT).

Automatic identification of blast leukemic cells types using deep learning with vision transformers.

Leptomeningeal infiltration in rat models for human acute myelocytic and lymphocytic leukemia

Retrospective Study of Incidence and Survival for Patients with Hematologic Malignancies Residing at the U.S./Mexico Border

pl6 Gene Homozygous Deletions in Acute Lymphoblastic Leukemia

Autophagy intensity decreases in most blood malignancies, promoting cancer cell proliferation. Acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) are two main variants of leukemia. LC3, an important autophagy gene, and its protein, MAP1LC3B, precisely predict autophagy initiation and progression. The main objective of this systematic review is to investigate the correlation between changes in the expression of the LC3 gene in patients with ALL and AML. We performed a literature search in PubMed, Scopus, and Web of Science database in November 20, 2025, using the keywords and MeSH terms. All searches were restricted to sources in the English language, andwe focused on human case-control studies where definitive diagnosis was performed using hematological parameters. Initial identification included 1282 articles. Duplicates were removed, leaving 821 papers for screening. From these, 787 articles were removed for inappropriate titles and abstracts, leaving 34 for further review. Ultimately, 10 papers met the criteria for this systematic review. Five AML investigations demonstrated considerably lower LC3 gene expression than healthy controls. Downregulation was similar in one research. Upregulation was seen in two investigations. In two papers, ALL patients had considerably lower expression than healthy controls. Upregulation was significant in one study and non-significant in another one. The LC3 gene appears to be downregulated more consistently in AML, suggesting potential diagnostic or prognostic value. However, findings in ALL are inconsistent, and no definitive conclusion can be drawn. Further high-quality studies are required to clarify the role of LC3 in acute leukemias.

Leukemia, a heterogeneous group of blood cancers, poses significant challenges to global health due to its complexity, diverse risk factors, and variable outcomes. Accurate and early diagnosis is critical but remains a significant hurdle, particularly in low-resource settings. Recent advancements in artificial intelligence (AI) and image processing offer transformative solutions to improve leukemia detection and classification, addressing limitations in traditional diagnostic methods. This study systematically reviewed over 25,000 scientific articles sourced from Scopus, employing a PRISMA-guided methodology to ensure a comprehensive and rigorous analysis. The analysis focused on the application of AI, particularly convolutional neural networks (CNNs), in diagnosing four primary leukemia types: acute lymphoblastic leukemia (ALL), acute myeloid leukemia (AML), chronic lymphocytic leukemia (CLL), and chronic myeloid leukemia (CML). It also examined global epidemiological trends, risk factors, and disparities in healthcare access. Key risk factors for leukemia include genetic syndromes like Down syndrome, environmental exposures to toxins such as benzene, ionizing radiation, and viral infections. Socio-economic disparities and geographical differences significantly impact leukemia incidence and outcomes. AI-based models, especially CNNs, demonstrated enhanced accuracy, speed, and reliability in diagnosing leukemia compared to traditional methods. However, challenges such as data variability, model scalability, and unequal access to AI technologies continue to hinder widespread adoption. AI and image processing technologies hold immense potential to revolutionize leukemia diagnostics by enabling early detection, precise classification, and personalized treatment planning. Addressing critical challenges, including data standardization and equitable access to these technologies, will be vital for global application. This review highlights the transformative role of AI in improving leukemia outcomes and advancing precision medicine worldwide.

Acute leukemia (AL), classified as acute myeloid leukemia (AML) and acute lymphocytic leukemia (ALL), is a hematologic malignancy caused by the uncontrolled proliferation of leucocytes in the bone marrow. Early detection of AL is crucial for clinical treatment. Detection methods of AL are currently blood tests, bone marrow tests, imaging, and spinal fluid tests. However, these tests have drawbacks, such as high cost and time consumption. Liquid biopsy using biological fluids such as blood or serum is an emerging technique for noninvasive cancer detection and monitoring. Surface-enhanced Raman spectroscopy (SERS), which enhanced Raman signals by the interaction of plasmonic nanostructures with the analyte, is a highly sensitive and specific detection method with simple sample preparation that has been used in combination with machine learning techniques to analyze liquid biopsy. In this study, we developed a SERS-based liquid biopsy approach that enables accurate classification of AML and ALL subtypes and the prediction of disease recurrence. SERS spectra of serum samples from 24 healthy individuals, 43 AML patients, and 18 ALL patients were obtained using an Ag-based SERS substrate and clustered using hierarchical cluster analysis (HCA). The spectra were then classified using three commonly used classifiers, namely, support vector machine (SVM), random forest (RF), and k-nearest neighbor (kNN). Our findings demonstrate that the RF classifier has the highest accuracy values, with 96.1, 95.5, and 98.5% for classifying three groups and predicting the recurrence of AML and ALL, respectively. The combination of SERS-based serum analysis with machine learning algorithms represents a remarkable advancement in the realm of hematological disease diagnostics, particularly for AML and ALL. This approach not only facilitates the precise differentiation of disease subtypes but also introduces the novel capability of prognosticating disease recurrence.

Purpose: To describe and compare the pre-treatment bone marrow metagenomes of childhood acute lymphoblastic leukemia (ALL) and childhood acute myeloid leukemia (AML).Background: Leukemia is the most common cancer in children, comprised mainly of ALL (~80%) followed by AML (~17%). The role of infections and their timing in the etiology of pre B-cell ALL’s (but not AML’s) is supported by a considerable body of epidemiologic evidence developed in the past 20 years (Gilham, Peto et al. 2005, Ma, Urayama et al. 2009). There are two main infection related hypotheses. Greaves postulates that delayed infection, akin to the hygiene hypothesis, increases risk of leukemia (Greaves and Alexander 1993, Greaves 1997). The second hypothesis set forth by Kinlen is not mutually exclusive and postulates the role of a transforming yet common virus where introduction of the infectious agent to previously naive communities trigger leukemia (Kinlen 1995). While many viral agents have been investigated (reviewed in (O’Connor and Boneva 2007)) no definitive infectious agent has been identified but, until recently, broad surveys of the microbiome were not possible. Recent developments in next generation sequencing and bioinformatics now allow for unbiased investigation into the totality of organisms that inhabit the human body.Methods: Pre-treatment bone marrow specimens were collected in pre B-cell ALL and AML cases participating in the California Childhood Leukemia Study. AML’s with similar age distribution to the ALL’s were utilized as controls, to represent the infection history of an immune suppressed child. We interrogated the viral metagenomes of 60 ALL’s and 30 AML’s, pooled and reduced with ribosomal capture, then sequenced with high coverage next generation RNA sequencing on an Illumina HiSeq 2500. The resulting sequences were analyzed using a custom bioinformatics pipeline, DARK, to remove human sequences, to identify viral transcripts, and to categorize all transcripts present in the pre-treatment bone marrow. Bacterial metagenomes of the same subjects were analyzed using 16S rRNA amplicon sequencing and the QIIME pipeline.Results: We analyzed over 500 million 100bp reads and categorized human, non-human and unknown sequences. We found striking differences between the viral metagenomes of childhood ALL and AML, with ALL subjects presenting with a greater viral infection load than AML’s. Furthermore, differences in the presence of transcripts aligning to both exogenous viruses and endogenous retroviruses were observed with some viruses occurring exclusively in ALL’s. We found no difference between the bacterial metagenomes of childhood ALL and AML suggesting no differential contamination occurred during collection and analysis.Discussion: This study provides the first measurement of all identifiable infectious agents in both childhood ALL an AML. Our data suggest that bacteria do not play a role in the etiology of ALL. The greater number and frequency of viral infectious agents were observed in ALL versus AML contribute to an etiologic hypothesis of ALL involving viral infections yet require replication and additional follow up. Moreover the clinical relevance of these infections and their relation to outcome should be investigated.ReferencesGilham, C., J. Peto, J. Simpson, E. Roman, T. O. Eden, M. F. Greaves, F. E. Alexander and U. Investigators (2005). "Day care in infancy and risk of childhood acute lymphoblastic leukaemia: findings from UK case-control study." BMJ 330(7503): 1294.Greaves, M. F. (1997). "Aetiology of acute leukaemia." Lancet 349(9048): 344-349.Greaves, M. F. and F. E. Alexander (1993). "An infectious etiology for common acute lymphoblastic leukemia in childhood?" Leukemia 7(3): 349-360.Kinlen, L. J. (1995). "Epidemiological evidence for an infective basis in childhood leukaemia." Br J Cancer 71(1): 1-5.Ma, X., K. Urayama, J. Chang, J. L. Wiemels and P. A. Buffler (2009). "Infection and pediatric acute lymphoblastic leukemia." Blood Cells Mol Dis 42(2): 117-120.O’Connor, S. M. and R. S. Boneva (2007). "Infectious etiologies of childhood leukemia: plausibility and challenges to proof." Environ Health Perspect 115(1): 146-150. DisclosuresNo relevant conflicts of interest to declare.

Knowledge of the number and distribution of oil palm trees during the crop cycle is vital for sustainable management and predicting yields. The accuracy of the conventional image processing method is limited for the hand-crafted feature extraction method and the overfitting problem occurs due to the insufficient dataset. We propose a modification of the Faster Region-based Convolutional Neural Network (FRCNN) for palm tree detection to reduce the overfitting problem and improve the detection accuracy. The enhanced FRCNN (EFRCNN) leads to improved performance for detecting objects (in the same image) when they are of multiple sizes by using a feature concatenation method. Transfer learning based on a ResNet50 model is used to extract the features of the input image. High-resolution images of oil palm trees from a drone are used to form the data set, containing mature, young, and mixed oil palm tree regions. We train and test the EFRCNN, the FRCNN, a CNN used recently for oil palm image detection, and two standard methods, namely, the support vector machine (SVM) and template matching (TM). The results reveal an overall accuracy of ≥96.8% for the EFRCNN on the three test sets. The accuracy is higher than the CNN and FRCNN and substantially higher than SVM and TM. For large-scale plantations, the accuracy improvement is significant. This research provides a method for automatically counting the oil palm trees in large-scale plantations.

White blood cell cancer is additionally mentioned as leukemia could also be a really perilous disease. To this day, the tactic of recognizing white blood cell cancer or leukemia remains done conventionally, which if done by different doctors, can cause a difference within the diagnosis. To retort these problems, a computer-assisted method is proposed during which leukemia is detected from microscopic images employing a mixture of SVM and KNN. Initially, preprocessing is performed to arrange the image for processing. Later support vector machine (SVM) and K-nearest neighbor are used for classification. The proposed algorithm classifies healthy and cancerous cells into one of the four types such as acute lymphocytic leukemia (ALL), acute myeloid leukemia (AML), chronic lymphocytic leukemia (CLL), and chronic myeloid leukemia (CML). Additionally, the counting of the infected cells is also performed.

Geographic, demographic, and risk factor profiles of acute myeloid and acute lymphoblastic leukemia in the United States: Insights from the global burden of disease study 2021

Development of a Human Therapeutic L-Cyst(e)Ine-Degrading Enzyme for the Treatment of Hematological Malignancies