Explore the vast range of titles available.

Leukemia is the most prevalent form of blood cancer, affecting individuals across all age groups. Early and accurate diagnosis is crucial for effective treatment and improved clinical outcomes. Peripheral blood smear analysis, a key non-invasive diagnostic tool, often suffers from subjective interpretation, inter-observer variability, and a lack of readily available expertise. Although deep learning approaches, particularly Convolutional Neural Networks (CNNs), have demonstrated exceptional performance in binary classification tasks, multiclass classification of leukemia subtypes remains challenging due to limited data availability and morphological similarities between subtypes. This study presents a novel hybrid methodology that combines pre-trained CNN architectures, including VGG16, InceptionV3, and ResNet50, with advanced classification models such as Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and the deep learning-based Multi-Layer Perceptron (MLP). The method leverages publicly available datasets, the Acute Lymphoblastic Leukemia Image Database (ALL-IDB) and the Munich AML Morphology Dataset, to classify healthy cells, lymphoblasts, and myeloblasts. Pre-trained CNNs are employed for feature extraction, while the classifiers refine the predictions for improved accuracy. The proposed approach demonstrated exceptional performance, with the InceptionV3 + SVM combination achieving the highest accuracy of 88%, followed closely by VGG16 + XGBoost at 87%. MLP-based models also achieved strong results, effectively capturing non-linear patterns in the data. In contrast, ResNet50 exhibited limitations, likely due to overfitting caused by the small dataset. The novelty of this work lies in the integration of pre-trained deep learning architectures with hybrid classification techniques, enabling robust multiclass classification in data-constrained scenarios. This innovative approach offers a scalable and precise diagnostic tool, improving the speed and reliability of leukemia subtype identification and providing significant potential to enhance clinical decision-making and patient care.

Background 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. 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. Results 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. Conclusion 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 undifferentiated leukemia is a rare type of acute leukemia that shows no evidence of differentiation along any lineage. Clinical, immunophenotypic and genetic data is limited and it is uncertain if acute undifferentiated leukemia is biologically distinct from acute myeloid leukemia with minimal differentiation, which also shows limited myeloid marker expression and has been reported to have a poor prognosis. We identified 92 cases initially diagnosed as acute undifferentiated leukemia or acute myeloid leukemia with minimal differentiation from pathology databases of nine academic institutions with available diagnostic flow cytometric data, cytogenetic findings, mutational and clinical data. Outcome analysis was performed using Kaplan Meier test for the 53 patients who received induction chemotherapy. Based on cytogenetic abnormalities ( N  = 30) or history of myelodysplastic syndrome ( N  = 2), 32 cases were re-classified as acute myeloid leukemia with myelodysplasia related changes. The remaining 24 acute undifferentiated leukemia patients presented with similar age, blood counts, bone marrow cellularity, and blast percentage as the remaining 30 acute myeloid leukemia with minimal differentiation patients. Compared to acute myeloid leukemia with minimal differentiation, acute undifferentiated leukemia cases were characterized by more frequent mutations in PHF6 (5/15 vs 0/19, p  = 0.016) and more frequent expression of TdT on blasts ( p  = 0.003) while acute myeloid leukemia with minimal differentiation cases had more frequent CD123 expression ( p  = 0.042). Outcome data showed no difference in overall survival, relapse free survival, or rates of complete remission between acute undifferentiated leukemia and acute myeloid leukemia with minimal differentiation groups ( p  > 0.05). Acute myeloid leukemia with myelodysplasia-related changes patients showed shorter survival when censoring for bone marrow transplant as compared to acute undifferentiated leukemia ( p  = 0.03) and acute myeloid leukemia with minimal differentiation ( p  = 0.002). In this largest series to date, the acute undifferentiated leukemia group shows distinct characteristics from acute myeloid leukemia with minimal differentiation, including more frequent PHF6 mutations and expression of TdT.

Acute leukemia with a mixed phenotype is a rare disease and comprises 2–5% of all acute leukemias. These disorders have been known historically by a variety of names, such as mixed lineage leukemia, bilineal leukemia and biphenotypic leukemia, and the criteria for diagnosis have often been arbitrary. The scoring criteria proposed by the European Group for the Immunological Characterization of Leukemias represented a major attempt to define this disorder. However, the relative weight given to some markers and the lack of lineage specificity of most markers have raised questions regarding the significance of this approach. In 2008, the World Health Organization classification of hematopoietic and lymphoid tumors proposed a simpler diagnostic algorithm, which relies on fewer and more lineage-specific markers to define mixed-phenotype acute leukemia (MPAL). MPAL with t(9;22) and MLL rearrangement have been separated. Several studies have suggested that patients with acute leukemia of mixed phenotype have a worse clinical outcome when compared with matched controls with acute myeloid leukemia or acute lymphoblastic leukemia. Further studies are needed to confirm the significance of MPAL as currently defined, to determine a standardized treatment approach and to better understand the biological and clinical aspects of this disease.

Leukemia is highly heterogeneous, meaning that different types of leukemia require different treatments and have different prognoses. Current clinical diagnostic and typing tests are complex and time‐consuming. In particular, all of these tests rely on bone marrow aspiration, which is invasive and leads to poor patient compliance, exacerbating treatment delays. Morphological analysis of peripheral blood cells (PBC) is still primarily used to distinguish between benign and malignant hematologic disorders, but it remains a challenge to diagnose and type these diseases solely by direct observation of peripheral blood(PB) smears by human experts. In this study, we apply a segmentation‐based enhanced residual network that uses progressive multigranularity training with jigsaw patches. It is trained on a self‐built annotated dataset of 21,208 images from 237 patients, including five types of benign white blood cells(WBCs) and eight types of leukemic cells. The network is not only able to discriminate between benign and malignant cells, but also to typify leukemia using a single peripheral blood cell. The network effectively differentiated acute promyelocytic leukemia (APL) from other types of acute myeloid leukemia (non‐APL), achieving a precision rate of 89.34%, a recall rate of 97.37%, and an F1 score of 93.18% for APL. In contrast, for non‐APL cases, the model achieved a precision rate of 92.86%, but a recall rate of 74.63% and an F1 score of 82.75%. In addition, the model discriminates acute lymphoblastic leukemia(ALL) with the Ph chromosome from those without. This approach could improve patient compliance and enable faster and more accurate typing of leukemias for early diagnosis and treatment to improve survival. This pioneering research investigates the manner in which cellular morphological responses are linked to the nature of genome information using deep learning.

Although cancer classification has improved over the past 30 years, there has been no general approach for identifying new cancer classes (class discovery) or for assigning tumors to known classes (class prediction). Here, a generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemias as a test case. A class discovery procedure automatically discovered the distinction between acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) without previous knowledge of these classes. An automatically derived class predictor was able to determine the class of new leukemia cases. The results demonstrate the feasibility of cancer classification based solely on gene expression monitoring and suggest a general strategy for discovering and predicting cancer classes for other types of cancer, independent of previous biological knowledge.

In 2022, leukemia ranked as the second most common hematological malignancy after non-Hodgkin lymphoma worldwide. However, updated global estimates of leukemia incidence by subtype are unavailable. We estimated leukemia incidences for different leukemia subtypes by country, world region, and human developmental index using data from the Cancer Incidence in Five Continents databases combined with the GLOBOCAN 2022 estimates of leukemia in 185 countries. We estimated sex-specific age-standardized rates (ASRs) per 100 000 for children (0-19 years) and adults (20+ years). In adults, the most common leukemia worldwide was AML (males: 38%, ASR = 3·1; females: 43%, ASR = 2·4), followed by CLL (males: 28%, ASR = 2·2; females: 24%, ASR = 1·3). In very high HDI countries, the ASR of CLL was higher than the ASR of AML among males (5·2 versus 4·3, respectively) and similar among females (2·9 and 3·0, respectively). In children, the most common leukemia was ALL (boys: 70%, ASR = 2·4; girls: 68%, ASR = 1·8) followed by AML (boys: 22%, ASR = 0·76; girls: 25%, ASR = 0·65). ALL proportions varied across world sub-regions from 57 to 78% among boys, and from 49 to 80% among girls. Our findings suggest clear geographical patterns of leukemia subtypes in adults and children. Further research into underlying causes that explain these variations is needed to support cancer control strategies for prevention and plan national healthcare needs.

Chromosomal rearrangements of the human MLL (mixed lineage leukemia) gene are associated with high-risk infant, pediatric, adult and therapy-induced acute leukemias. We used long-distance inverse-polymerase chain reaction to characterize the chromosomal rearrangement of individual acute leukemia patients. We present data of the molecular characterization of 1590 MLL -rearranged biopsy samples obtained from acute leukemia patients. The precise localization of genomic breakpoints within the MLL gene and the involved translocation partner genes (TPGs) were determined and novel TPGs identified. All patients were classified according to their gender (852 females and 745 males), age at diagnosis (558 infant, 416 pediatric and 616 adult leukemia patients) and other clinical criteria. Combined data of our study and recently published data revealed a total of 121 different MLL rearrangements, of which 79 TPGs are now characterized at the molecular level. However, only seven rearrangements seem to be predominantly associated with illegitimate recombinations of the MLL gene (∼90%): AFF1/AF4 , MLLT3/AF9 , MLLT1/ENL , MLLT10/AF10 , ELL , partial tandem duplications ( MLL PTDs) and MLLT4/AF6 , respectively. The MLL breakpoint distributions for all clinical relevant subtypes (gender, disease type, age at diagnosis, reciprocal, complex and therapy-induced translocations) are presented. Finally, we present the extending network of reciprocal MLL fusions deriving from complex rearrangements.

Acute lymphoblastic leukemias carrying a chromosomal translocation involving the mixed-lineage leukemia gene ( MLL , ALL1 , HRX ) have a particularly poor prognosis. Here we show that they have a characteristic, highly distinct gene expression profile that is consistent with an early hematopoietic progenitor expressing select multilineage markers and individual HOX genes. Clustering algorithms reveal that lymphoblastic leukemias with MLL translocations can clearly be separated from conventional acute lymphoblastic and acute myelogenous leukemias. We propose that they constitute a distinct disease, denoted here as MLL, and show that the differences in gene expression are robust enough to classify leukemias correctly as MLL, acute lymphoblastic leukemia or acute myelogenous leukemia. Establishing that MLL is a unique entity is critical, as it mandates the examination of selectively expressed genes for urgently needed molecular targets.