RESUMEN
Accurate diagnosis of white blood cells from cytopathological images is a crucial step in evaluating leukaemia. In recent years, image classification methods based on fully convolutional networks have drawn extensive attention and achieved competitive performance in medical image classification. In this paper, we propose a white blood cell classification network called ResNeXt-CC for cytopathological images. First, we transform cytopathological images from the RGB color space to the HSV color space so as to precisely extract the texture features, color changes and other details of white blood cells. Second, since cell classification primarily relies on distinguishing local characteristics, we design a cross-layer deep-feature fusion module to enhance our ability to extract discriminative information. Third, the efficient attention mechanism based on the ECANet module is used to promote the feature extraction capability of cell details. Finally, we combine the modified softmax loss function and the central loss function to train the network, thereby effectively addressing the problem of class imbalance and improving the network performance. The experimental results on the C-NMC 2019 dataset show that our proposed method manifests obvious advantages over the existing classification methods, including ResNet-50, Inception-V3, Densenet121, VGG16, Cross ViT, Token-to-Token ViT, Deep ViT, and simple ViT about 5.5-20.43% accuracy, 3.6-23.56% F1-score, 3.5-25.71% AUROC and 8.1-36.98% specificity, respectively.
Asunto(s)
Leucocitos , Humanos , Leucocitos/citología , Redes Neurales de la Computación , Procesamiento de Imagen Asistido por Computador/métodos , Leucemia/patología , Leucemia/clasificación , Algoritmos , Aprendizaje ProfundoRESUMEN
Acute lymphoblastic leukemia, commonly referred to as ALL, is a type of cancer that can affect both the blood and the bone marrow. The process of diagnosis is a difficult one since it often calls for specialist testing, such as blood tests, bone marrow aspiration, and biopsy, all of which are highly time-consuming and expensive. It is essential to obtain an early diagnosis of ALL in order to start therapy in a timely and suitable manner. In recent medical diagnostics, substantial progress has been achieved through the integration of artificial intelligence (AI) and Internet of Things (IoT) devices. Our proposal introduces a new AI-based Internet of Medical Things (IoMT) framework designed to automatically identify leukemia from peripheral blood smear (PBS) images. In this study, we present a novel deep learning-based fusion model to detect ALL types of leukemia. The system seamlessly delivers the diagnostic reports to the centralized database, inclusive of patient-specific devices. After collecting blood samples from the hospital, the PBS images are transmitted to the cloud server through a WiFi-enabled microscopic device. In the cloud server, a new fusion model that is capable of classifying ALL from PBS images is configured. The fusion model is trained using a dataset including 6512 original and segmented images from 89 individuals. Two input channels are used for the purpose of feature extraction in the fusion model. These channels include both the original and the segmented images. VGG16 is responsible for extracting features from the original images, whereas DenseNet-121 is responsible for extracting features from the segmented images. The two output features are merged together, and dense layers are used for the categorization of leukemia. The fusion model that has been suggested obtains an accuracy of 99.89%, a precision of 99.80%, and a recall of 99.72%, which places it in an excellent position for the categorization of leukemia. The proposed model outperformed several state-of-the-art Convolutional Neural Network (CNN) models in terms of performance. Consequently, this proposed model has the potential to save lives and effort. For a more comprehensive simulation of the entire methodology, a web application (Beta Version) has been developed in this study. This application is designed to determine the presence or absence of leukemia in individuals. The findings of this study hold significant potential for application in biomedical research, particularly in enhancing the accuracy of computer-aided leukemia detection.
Asunto(s)
Aprendizaje Profundo , Internet de las Cosas , Humanos , Leucemia-Linfoma Linfoblástico de Células Precursoras/diagnóstico , Inteligencia Artificial , Leucemia/diagnóstico , Leucemia/clasificación , Leucemia/patología , Algoritmos , Procesamiento de Imagen Asistido por Computador/métodos , Redes Neurales de la ComputaciónRESUMEN
Background and Objectives: Leukemia, characterized by abnormal leukocyte production, exhibits clonal origin from somatic mutations. Globally, it ranked 15th in cancer incidence in 2020, with higher prevalence in developing countries. In Mexico, it was the ninth most frequent cancer. Regional registries are vital for understanding its epidemiology. This study aims to analyze the prevalence and age-standardized incidence rates of leukemias in a tertiary care hospital in the Mexican Bajio region. Materials and Methods: Leukemia cases from 2008-2018 were analyzed, and 535 medical records were included in this study. The prevalence, distribution, and age-specific incidence rate of different types and subtypes of leukemia were determined according to sex and age groups. Results: Overall, 65.79% consisted of lymphocytic leukemia, 33.64% of myeloid leukemia, and 0.56% of monocytic leukemia. No significant sex-based differences were found, but age-specific patterns were observed. Leukemia distribution by age revealed significant associations. Lymphocytic leukemia dominated in the pediatric population, particularly acute lymphocytic leukemia, while myeloid leukemia shifted towards adulthood. Age-specific incidence patterns showed, first, that lymphocytic leukemia is the most common leukemia in pediatric ages, and second, there is a shift from acute lymphocytic leukemia dominance in pediatric ages to myeloid leukemia incidence in late adulthood, emphasizing nuanced epidemiological dynamics. Conclusions: Acute leukemia cases occurred with high prevalence in our study population, with a high incidence in pediatric and adulthood populations, especially for acute lymphocytic leukemia, showing a (<18 years) 153.8 age-standardized incidence rate in the pediatric group, while in the adult population, the age-standardized rate was 59.84. In the age-specific analysis, we found that the childhood group (5-9 years) were the most affected by acute lymphocytic leukemia in the pediatric population, while in the adult population, the early-adulthood group (15-29 years) were the most affected age group. In contrast, chronic myeloid leukemia affected both adults and the pediatric populations, while chronic lymphocytic leukemia and monocytic leukemia were exclusive to adults. The study underscores the need for tailored diagnostic, treatment, and preventive strategies based on age, contributing valuable insights into the leukemia epidemiology of the Bajio region.
Asunto(s)
Leucemia , Humanos , México/epidemiología , Masculino , Femenino , Niño , Adolescente , Adulto , Preescolar , Persona de Mediana Edad , Incidencia , Anciano , Lactante , Leucemia/epidemiología , Leucemia/clasificación , Adulto Joven , Prevalencia , Factores de Edad , Anciano de 80 o más Años , Sistema de Registros/estadística & datos numéricosRESUMEN
Acute leukemia with ambiguous lineage (ALAL) is a rare and highly aggressive malignancy with limited molecular characterization and therapeutic recommendations. In this study, we retrospectively analyzed 1635 acute leukemia cases in our center from January 2012 to June 2018. The diagnose of ALAL was based on either EGIL or 2016 WHO criteria, a total of 39 patients were included. Four patients diagnosed as acute undifferentiated leukemia (AUL) by both classification systems. Among the patients underwent high-throughput sequencing, 89.5% were detected at least one mutation and the median number of gene mutation was 3 (0-8) per sample. The most frequently mutated genes were NRAS (4, 21%), CEBPA (4, 21%), JAK3 (3, 16%), RUNX1 (3, 16%). The mutations detected in mixed-phenotype acute leukemia (MPAL) enriched in genes related to genomic stability and transcriptional regulation; while AUL cases frequently mutated in genes involved in signaling pathway. The survival analysis strongly suggested that mutation burden may play important roles to predict the clinical outcomes of ALAL. In addition, the patients excluded by WHO criteria had even worse clinical outcome than those included. The association of the genetic complexity of blast cells with the clinical outcomes and rationality of the diagnostic criteria of WHO system need to be evaluated by more large-scale prospective clinical studies.
Asunto(s)
Inestabilidad Genómica , Leucemia , Mutación , Proteínas de Neoplasias , Enfermedad Aguda , Adolescente , Adulto , Femenino , Humanos , Leucemia/clasificación , Leucemia/diagnóstico , Leucemia/genética , Leucemia/metabolismo , Masculino , Persona de Mediana Edad , Proteínas de Neoplasias/genética , Proteínas de Neoplasias/metabolismo , Pronóstico , Estudios RetrospectivosRESUMEN
BACKGROUND: Conventional identification of blood disorders based on visual inspection of blood smears through microscope is time consuming, error-prone and is limited by hematologist's physical acuity. Therefore, an automated optical image processing system is required to support the clinical decision-making. MATERIALS AND METHODS: Blood smear slides (n = 250) were prepared from clinical samples, imaged and analyzed in Jimma Medical Center, Hematology department. Samples were collected, analyzed and preserved from out and in-patients. The system was able to categorize four common types of leukemia's such as acute and chronic myeloid leukemia; and acute and chronic lymphoblastic leukemia, through a robust image segmentation protocol, followed by classification using the support vector machine. RESULTS: The system was able to classify leukemia types with an accuracy, sensitivity, specificity of 97.69%, 97.86% and 100%, respectively for the test datasets, and 97.5%, 98.55% and 100%, respectively, for the validation datasets. In addition, the system also showed an accuracy of 94.75% for the WBC counts that include both lymphocytes and monocytes. The computer-assisted diagnosis system took less than one minute for processing and assigning the leukemia types, compared to an average period of 30 minutes by unassisted manual approaches. Moreover, the automated system complements the healthcare workers' in their efforts, by improving the accuracy rates in diagnosis from â¼70% to over 97%. CONCLUSION: Importantly, our module is designed to assist the healthcare facilities in the rural areas of sub-Saharan Africa, equipped with fewer experienced medical experts, especially in screening patients for blood associated diseases including leukemia.
Asunto(s)
Leucemia/sangre , Leucemia/clasificación , Aprendizaje Automático/normas , Adulto , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , Persona de Mediana EdadRESUMEN
PURPOSE OF REVIEW: The spread of the novel coronavirus SARS-CoV-2 and its associated disease, coronavirus disease of 2019 (COVID-19), has significantly derailed cancer care. Patients with leukemia are more likely to have severe infection and increased rates of mortality. There is paucity of information on how to modify care of leukemia patients in view of the COVID-19 risks and imposed restrictions. We review the available literature on the impact of COVID-19 on different types of leukemia patients and suggest general as well as disease-specific recommendations on care based on available evidence. RECENT FINDINGS: The COVID-19 infection impacts leukemia subtypes in variable ways and the standard treatments for leukemia have similarly, varying effects on the course of COVID-19 infection. Useful treatment strategies include deferring treatment when possible, use of less intensive regimens, outpatient targeted oral agents requiring minimal monitoring, and prioritization of curative or life-prolonging strategies. Reducing health care encounters, rational transfusion standards, just resource allocation, and pre-emptive advance care planning will serve the interests of leukemia patients. Ad hoc modifications based on expert opinions and extrapolations of previous well-designed studies are the way forward to navigate the crisis. This should be supplanted with more rigorous prospective evidence.
Asunto(s)
COVID-19/epidemiología , Leucemia/terapia , COVID-19/prevención & control , COVID-19/terapia , Humanos , Leucemia/clasificación , Leucemia/diagnóstico , Leucemia/epidemiología , Atención al Paciente , Factores de Riesgo , SARS-CoV-2RESUMEN
In view of the challenges of the group Lasso penalty methods for multicancer microarray data analysis, e.g., dividing genes into groups in advance and biological interpretability, we propose a robust adaptive multinomial regression with sparse group Lasso penalty (RAMRSGL) model. By adopting the overlapping clustering strategy, affinity propagation clustering is employed to obtain each cancer gene subtype, which explores the group structure of each cancer subtype and merges the groups of all subtypes. In addition, the data-driven weights based on noise are added to the sparse group Lasso penalty, combining with the multinomial log-likelihood function to perform multiclassification and adaptive group gene selection simultaneously. The experimental results on acute leukemia data verify the effectiveness of the proposed method.
Asunto(s)
Algoritmos , Neoplasias/clasificación , Neoplasias/genética , Análisis por Conglomerados , Biología Computacional , Bases de Datos Genéticas/estadística & datos numéricos , Humanos , Leucemia/clasificación , Leucemia/genética , Funciones de Verosimilitud , Modelos Genéticos , Familia de Multigenes , Análisis de Secuencia por Matrices de Oligonucleótidos/estadística & datos numéricos , Oncogenes , Análisis de RegresiónRESUMEN
Background/aim: Graft-versus-host disease (GVHD) is a crucial complication leading to significant morbidity and mortality allogeneic hematopoietic stem cell transplantation which occurs in approximately half of the transplant recipients. Suppression of tumorigenicity 2 (ST2) and regenerating islet-derived 3-alpha(Reg3a) might be important biomarkers to predict acute GVHD. Materials and methods: In the present study, blood samples were collected from 17 patients with acute GVHD and 12 control patients after allogeneic stem cell transplantation. ST2 and Reg3a were measured in plasma samples compared in patients with acute GVHD and the controls. Results: Median age of the study population was 42 years (range 1949). When compared to controls, the mean ST2 levels was significant higher in acute GVHD (9794 ng/dL vs. 2646 ng/dL, P = 0.008). Mean Reg3a level did not show significant difference between control and acute GVHD group (8848 ng/dL vs. 5632 ng/dL, respectively, P = 0.190). Conclusion: The ST2 level might be used as a significant biomarker for predicting acute GVHD.
Asunto(s)
Enfermedad Injerto contra Huésped , Trasplante de Células Madre Hematopoyéticas , Proteína 1 Similar al Receptor de Interleucina-1/sangre , Proteínas Asociadas a Pancreatitis/sangre , Adulto , Biomarcadores/sangre , Femenino , Enfermedad Injerto contra Huésped/sangre , Enfermedad Injerto contra Huésped/diagnóstico , Enfermedad Injerto contra Huésped/etiología , Trasplante de Células Madre Hematopoyéticas/efectos adversos , Trasplante de Células Madre Hematopoyéticas/métodos , Humanos , Leucemia/clasificación , Leucemia/cirugía , Masculino , Valor Predictivo de las Pruebas , Pronóstico , Trasplante Homólogo/efectos adversos , Trasplante Homólogo/métodosRESUMEN
Classifying the hematological malignancies by assigning cells to their normal counterpart and describing the nature of disease progression are entirely reliant on an accurate picture for the development of the multifarious types of blood and immune cells. In recent years, our understanding of the complex relationships between the various hematopoietic stem cell-derived cell lineages has undergone substantial revision. There has been similar progress in how we describe the nature of the "target" cells that genetic insults transform to give rise to the hematological malignancies. Here I describe how both longstanding and new information has influenced classifying, for diagnosis, the hematological malignancies.
Asunto(s)
Leucemia/sangre , Leucemia/clasificación , Leucemia/inmunología , Leucemia/patología , Animales , HumanosRESUMEN
For the last few years, computer-aided diagnosis (CAD) has been increasing rapidly. Numerous machine learning algorithms have been developed to identify different diseases, e.g., leukemia. Leukemia is a white blood cells- (WBC-) related illness affecting the bone marrow and/or blood. A quick, safe, and accurate early-stage diagnosis of leukemia plays a key role in curing and saving patients' lives. Based on developments, leukemia consists of two primary forms, i.e., acute and chronic leukemia. Each form can be subcategorized as myeloid and lymphoid. There are, therefore, four leukemia subtypes. Various approaches have been developed to identify leukemia with respect to its subtypes. However, in terms of effectiveness, learning process, and performance, these methods require improvements. This study provides an Internet of Medical Things- (IoMT-) based framework to enhance and provide a quick and safe identification of leukemia. In the proposed IoMT system, with the help of cloud computing, clinical gadgets are linked to network resources. The system allows real-time coordination for testing, diagnosis, and treatment of leukemia among patients and healthcare professionals, which may save both time and efforts of patients and clinicians. Moreover, the presented framework is also helpful for resolving the problems of patients with critical condition in pandemics such as COVID-19. The methods used for the identification of leukemia subtypes in the suggested framework are Dense Convolutional Neural Network (DenseNet-121) and Residual Convolutional Neural Network (ResNet-34). Two publicly available datasets for leukemia, i.e., ALL-IDB and ASH image bank, are used in this study. The results demonstrated that the suggested models supersede the other well-known machine learning algorithms used for healthy-versus-leukemia-subtypes identification.
Asunto(s)
Aprendizaje Profundo , Diagnóstico por Computador , Internet de las Cosas , Leucemia/clasificación , Leucemia/diagnóstico , Reconocimiento de Normas Patrones Automatizadas , Algoritmos , COVID-19/epidemiología , Nube Computacional , Bases de Datos Factuales , Diagnóstico por Imagen , Humanos , Leucemia Linfocítica Crónica de Células B/diagnóstico , Leucemia Mielógena Crónica BCR-ABL Positiva/diagnóstico , Leucemia Mieloide Aguda/diagnóstico , Aprendizaje Automático , Redes Neurales de la Computación , Leucemia-Linfoma Linfoblástico de Células Precursoras/diagnóstico , TelemedicinaRESUMEN
Myeloid/lymphoid neoplasms with eosinophilia and gene rearrangement are a unique category in the WHO classification, and include cases with rearrangement of PDGFRA, PDGFRB, FGFR1, and PCM1-JAK2. We report three patients presented with eosinophilia and FLT3 rearrangement: the first case with chronic eosinophilic leukemia, not otherwise specified and T-lymphoblastic leukemia/lymphoma; the second case with myeloid sarcoma; and the last case with high-grade myelodysplastic syndrome. The first case showed t(13;14)(q12;q32), which encoded FLT3-TRIP11. The patient was treated with intense chemotherapy and subsequently sorafenib with clinical improvement. Unfortunately, the patient showed persistent residual disease and passed away 9 months after the diagnosis from pneumonia. The other two cases both showed ETV6-FLT3. The second patient was treated with local radiation and systemic chemotherapy including sorafenib and was alive. The third patient was treated with chemotherapy but showed transformation to acute myeloid leukemia and died 15 months after diagnosis. These cases are among a growing number of cases with FLT3 rearrangement that all showed similar clinicopathologic features characterized by myeloproliferative neoplasm with eosinophilia and frequent T lymphoblastic leukemia/lymphoma. Therefore, we propose that the myeloid/lymphoid neoplasms with eosinophilia and FLT3 rearrangement be included in the WHO category of myeloid/lymphoid neoplasms with eosinophilia and gene rearrangement.
Asunto(s)
Eosinofilia/genética , Síndrome Hipereosinofílico/genética , Leucemia/clasificación , Linfoma/clasificación , Síndromes Mielodisplásicos/genética , Proteínas de Fusión Oncogénica/genética , Leucemia-Linfoma Linfoblástico de Células T Precursoras/genética , Proteínas Proto-Oncogénicas c-ets/genética , Proteínas Represoras/genética , Sarcoma Mieloide/genética , Tirosina Quinasa 3 Similar a fms/genética , Cariotipo Anormal , Anciano , Médula Ósea/patología , Cromosomas Humanos Par 13/genética , Cromosomas Humanos Par 13/ultraestructura , Cromosomas Humanos Par 14/genética , Cromosomas Humanos Par 14/ultraestructura , Progresión de la Enfermedad , Eosinofilia/complicaciones , Eosinofilia/patología , Humanos , Síndrome Hipereosinofílico/complicaciones , Síndrome Hipereosinofílico/patología , Ganglios Linfáticos/patología , Masculino , Persona de Mediana Edad , Síndromes Mielodisplásicos/complicaciones , Síndromes Mielodisplásicos/patología , Leucemia-Linfoma Linfoblástico de Células T Precursoras/complicaciones , Leucemia-Linfoma Linfoblástico de Células T Precursoras/patología , Sarcoma Mieloide/complicaciones , Sarcoma Mieloide/patología , Translocación Genética , Organización Mundial de la Salud , Proteína ETS de Variante de Translocación 6RESUMEN
The Superposing Significant Interaction Rules (SSIR) method is a combinatorial procedure that deals with symbolic descriptors of samples. It is able to rank the series of samples when those items are classified into two classes. The method selects preferential descriptors and, with them, generates rules that make up the rank by means of a simple voting procedure. Here, two application examples are provided. In both cases, binary or multilevel strings encoding gene expressions are considered as descriptors. It is shown how the SSIR procedure is useful for ranking the series of patient transcription data to diagnose two types of cancer (leukemia and prostate cancer) obtaining Area Under Receiver Operating Characteristic (AU-ROC) values of 0.95 (leukemia prediction) and 0.80-0.90 (prostate). The preferential selected descriptors here are specific gene expressions, and this is potentially useful to point to possible key genes.
Asunto(s)
Minería de Datos/métodos , Leucemia/genética , Análisis de Secuencia por Matrices de Oligonucleótidos/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Neoplasias de la Próstata/genética , Algoritmos , Interpretación Estadística de Datos , Perfilación de la Expresión Génica , Humanos , Leucemia/clasificación , Masculino , Neoplasias de la Próstata/clasificación , Curva ROC , Relación Estructura-ActividadRESUMEN
The ability to identify a specific type of leukemia using minimally invasive biopsies holds great promise to improve the diagnosis, treatment selection, and prognosis prediction of patients. Using genome-wide methylation profiling and machine learning methods, we investigated the utility of CpG methylation status to differentiate blood from patients with acute lymphocytic leukemia (ALL) or acute myelogenous leukemia (AML) from normal blood. We established a CpG methylation panel that can distinguish ALL and AML blood from normal blood as well as ALL blood from AML blood with high sensitivity and specificity. We then developed a methylation-based survival classifier with 23 CpGs for ALL and 20 CpGs for AML that could successfully divide patients into high-risk and low-risk groups, with significant differences in clinical outcome in each leukemia type. Together, these findings demonstrate that methylation profiles can be highly sensitive and specific in the accurate diagnosis of ALL and AML, with implications for the prediction of prognosis and treatment selection.
Asunto(s)
Biomarcadores de Tumor/genética , Metilación de ADN/genética , Leucemia/genética , Pronóstico , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Niño , Preescolar , Islas de CpG/genética , Femenino , Regulación Neoplásica de la Expresión Génica/genética , Humanos , Lactante , Leucemia/clasificación , Leucemia/diagnóstico , Leucemia/patología , Aprendizaje Automático , Masculino , Persona de Mediana Edad , Regiones Promotoras Genéticas/genética , Adulto JovenRESUMEN
The rarity of mixed phenotype acute leukemia (MPAL) has precluded adequate data to incorporate minimal residual disease (MRD) monitoring into therapy. Fluidity in MPAL classification systems further complicates understanding its biology and outcomes; this includes uncertainty surrounding the impact of shifting diagnostic requirements even between iterations of the World Health Organization (WHO) classification. Our primary objective was to address these knowledge gaps. To do so, we analyzed clinicopathologic features, therapy, MRD, and survival in a centrally-reviewed, multicenter cohort of MPAL uniformly diagnosed by the WHO classification and treated with acute lymphoblastic leukemia (ALL) regimens. ALL induction therapy achieved an EOI MRD negative (<0.01%) remission in most patients (70%). EOI MRD positivity was predictive of 5-year EFS (HR = 6.00, p < 0.001) and OS (HR = 9.57, p = 0.003). Patients who cleared MRD by EOC had worse survival compared with those EOI MRD negative. In contrast to adults with MPAL, ALL therapy without transplantation was adequate to treat most pediatric patients. Earlier MRD clearance was associated with better treatment success and survival. Prospective trials are now necessary to validate and refine MRD thresholds within the pediatric MPAL population and to identify salvage strategies for those with poor predicted survival.
Asunto(s)
Trasplante de Células Madre Hematopoyéticas/mortalidad , Quimioterapia de Inducción/mortalidad , Leucemia/mortalidad , Neoplasia Residual/mortalidad , Leucemia-Linfoma Linfoblástico de Células Precursoras/mortalidad , Niño , Estudios de Cohortes , Femenino , Estudios de Seguimiento , Trasplante de Células Madre Hematopoyéticas/efectos adversos , Humanos , Leucemia/clasificación , Leucemia/patología , Leucemia/terapia , Masculino , Neoplasia Residual/epidemiología , Neoplasia Residual/patología , Fenotipo , Leucemia-Linfoma Linfoblástico de Células Precursoras/patología , Leucemia-Linfoma Linfoblástico de Células Precursoras/terapia , Pronóstico , Tasa de Supervivencia , Estados Unidos/epidemiologíaRESUMEN
The major aim of Session 1 of the 2018 European Association of Hematopathology/Society for Hematopathology Workshop was to collect examples of cutaneous lymphomas, excluding mycosis fungoides/Sezary syndrome, as defined in the current WHO classification of tumours of the haemetopoietic and lymphoid tissues. Overall 42 cases were submitted. These were considered in four main categories: primary cutaneous B cell lymphomas (12 cases), primary cutaneous T cell lymphomas/lymphoproliferations with CD8+/cytotoxic phenotype (12 cases), primary cutaneous CD30-positive lymphoproliferative disorders (15 cases) and primary cutaneous T cell lymphomas/leukaemias with CD4+ phenotype (4 cases). Using these cases as examples, we were able to present the full spectrum of cutaneous lymphoproliferations (excluding mycosis fungoides/Sezary syndrome), including examples of rare, provisional and new entities as listed in the 2017 update of the WHO classification. The findings are summarized in this report with emphasis on differential diagnostic considerations and the importance of clinico-pathological correlation for final subtyping. In presenting these findings we hope to raise awareness of this enigmatic group of neoplasms and to further our understanding of these rare disease entities.
Asunto(s)
Leucemia/patología , Linfoma de Células B/patología , Linfoma Cutáneo de Células T/patología , Trastornos Linfoproliferativos/patología , Neoplasias Cutáneas/patología , Humanos , Leucemia/clasificación , Linfoma de Células B/clasificación , Linfoma Cutáneo de Células T/clasificación , Trastornos Linfoproliferativos/clasificación , Neoplasias Cutáneas/clasificaciónRESUMEN
Leukaemia is the most common cancer in children. The presenting manifestations can be wide-ranging, from a relatively well child to life-threatening complications. Symptoms can be manifested in any of the bodily systems. Undertaking a thorough clinical assessment of the child, in addition to recognising and addressing parental concerns, is vital. Furthermore, recognising that children can commonly present with musculoskeletal or abdominal symptoms increases the diagnostic yield, thereby preventing missed or late diagnoses. Childhood cancer has a huge impact on the child and their family, both at diagnosis and in the long term; providing advice and signposting families to appropriate support groups is an important aspect of their management. Nurses play a vital role in managing children with cancers, starting from raising suspicion and identifying the child with leukaemia, ensuring that high-quality care is delivered throughout their treatment, managing complications, and providing support and information to children and their families. An illustrative case study is included to highlight some of the challenges that health professionals may encounter in their clinical practice.
Asunto(s)
Leucemia/enfermería , Diagnóstico de Enfermería , Enfermería Pediátrica , Niño , Diagnóstico Diferencial , Humanos , Leucemia/clasificación , Leucemia/epidemiología , Factores de RiesgoRESUMEN
AIMS: Morphological differentiation among different blast cell lineages is a difficult task and there is a lack of automated analysers able to recognise these abnormal cells. This study aims to develop a machine learning approach to predict the diagnosis of acute leukaemia using peripheral blood (PB) images. METHODS: A set of 442 smears was analysed from 206 patients. It was split into a training set with 75% of these smears and a testing set with the remaining 25%. Colour clustering and mathematical morphology were used to segment cell images, which allowed the extraction of 2,867 geometric, colour and texture features. Several classification techniques were studied to obtain the most accurate classification method. Afterwards, the classifier was assessed with the images of the testing set. The final strategy was to predict the patient's diagnosis using the PB smear, and the final assessment was done with the cell images of the smears of the testing set. RESULTS: The highest classification accuracy was achieved with the selection of 700 features with linear discriminant analysis. The overall classification accuracy for the six groups of cell types was 85.8%, while the overall classification accuracy for individual smears was 94% as compared with the true confirmed diagnosis. CONCLUSIONS: The proposed method achieves a high diagnostic precision in the recognition of different types of blast cells among other mononuclear cells circulating in blood. It is the first encouraging step towards the idea of being a diagnostic support tool in the future.
Asunto(s)
Interpretación de Imagen Asistida por Computador/métodos , Leucemia/patología , Leucocitos/patología , Aprendizaje Automático , Reconocimiento de Normas Patrones Automatizadas/métodos , Coloración y Etiquetado/métodos , Enfermedad Aguda , Recolección de Muestras de Sangre , Linaje de la Célula , Diagnóstico Diferencial , Humanos , Leucemia/sangre , Leucemia/clasificación , Valor Predictivo de las Pruebas , Reproducibilidad de los ResultadosRESUMEN
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.