The predictive value of morphological findings in early diagnosis of acute myeloid leukemia with recurrent cytogenetic abnormalities

Jaković, Ljubomir; Bogdanović, Andrija; Djordjević, Vesna; Denčić‐Fekete, Marija; Kraguljac-Kurtovic, Nada; Knezevic, Vesna; Tos̆ić, Nataša; Pavlović, Sonja; Terzić, Tatjana

doi:10.1016/j.leukres.2018.10.017

Cited by 7 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is necessary to determine whether AML patients can be relieved following chemotherapy to estimate the treatment strategy and prognosis as soon as possible. The traditional diagnosis of CR and relapsed disease in AML relies mainly on routine blood, bone marrow smear count, and cytomorphology [5] . According to recent studies, minimal residual disease (MRD) in AML has a signi cant independent predictive value on the recurrence rate and survival of AML patients [6] .…”

Section: Introductionmentioning

confidence: 99%

Cytokine levels in patients with non-M3 myeloid leukemia are key indicators of how well the disease responds to chemotherapy

Hu,

Ling,

Yang

et al. 2023

Clin Exp Med

View full text Add to dashboard Cite

Acute myeloid leukemia (AML) is a malignant hematological neoplastic disease. Autocrine or paracrine cytokines released by leukemic cells regulate the proliferation of AML cells. It is uncertain whether cytokines can indicate whether patients with AML are in remission with chemotherapy. The goal of this study was to evaluate the levels of Th1/Th2/Th17 cytokines in AML patients before and after chemotherapy to determine whether the cytokine levels could predict disease remission after chemotherapy. It was found that the levels of IL-5, IL-6, IL-8, IL-10, TNF-α, TNF-β, IL-17F, and IL-22 were signi cantly increased at the time of AML diagnosis in patients who achieved remission after two chemotherapy treatments (P < 0.05). After chemotherapy, the cytokine levels were reduced in patients with remission, while the levels of IL-6 and IL-8 were raised in patients without remission (P < 0.05). A comparison of cytokine levels before and after chemotherapy in patients who achieved remission showed areas under the curve (AUCs) of 0.69 for both IL-6 and IL-8. In addition, a comparison of the remission and non-remission groups after chemotherapy showed an AUC of 0.77 for IL-6. We then calculated the cut-off value using receiver operating characteristic (ROC) curves. Values of IL-6 < 9.99 and IL-8 < 8.46 at the time of diagnosis were predictive of chemotherapy success and remission, while IL-6 >14.89 at diagnosis suggested that chemotherapy would not be successful and remission would not be achieved. In conclusion, IL-6 levels were found to be predictive of the likelihood of remission.

show abstract

Section: Introductionmentioning

confidence: 99%

Cytokine levels in patients with non-M3 myeloid leukemia are key indicators of how well the disease responds to chemotherapy

Hu,

Ling,

Yang

et al. 2023

Clin Exp Med

View full text Add to dashboard Cite

show abstract

“…Despite the wide use of immunological, cytogenetic, and molecular tests, the morphologic analysis of bone marrow smears is still an important initial step for leukemia diagnosis ( 2 , 3 ), as it is an economical and relatively convenient method. Morphologists analyses the characteristics of blood cells, such as shape, size, and granularity to define the cell types by using a light microscope, and then, they make diagnoses according to the guidelines.…”

Section: Introductionmentioning

confidence: 99%

Development and Evaluation of a Leukemia Diagnosis System Using Deep Learning in Real Clinical Scenarios

Zhou

et al. 2021

Front. Pediatr.

View full text Add to dashboard Cite

Leukemia is the most common malignancy affecting children. The morphologic analysis of bone marrow smears is an important initial step for diagnosis. Recent publications demonstrated that artificial intelligence is able to classify blood cells but a long way from clinical use. A total of 1,732 bone marrow images were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated and an end-to-end leukemia diagnosis system was developed by using raw images without pre-processing. The system creatively imitated the workflow of a hematologist by detecting and excluding uncountable and crushed cells, then classifying and counting the remain cells to make a diagnosis. The performance of the CNN in classifying WBCs achieved an accuracy of 82.93%, precision of 86.07% and F1 score of 82.02%. And the performance in diagnosing acute lymphoid leukemia achieved an accuracy of 89%, sensitivity of 86% and specificity of 95%. The system also performs well at detecting the bone marrow metastasis of lymphoma and neuroblastoma, achieving an average accuracy of 82.93%. This is the first study which included a wider variety of cell types in leukemia diagnosis, and achieved a relatively high performance in real clinical scenarios.

show abstract

“…According to the morphology screening guidelines for APL proposed by FAB, the microscopic examination should be implemented manually by well-trained hematopathologists, which are scarce in most primary hospitals [ 8 ]. Besides, objective bias is difficult to avoid in manual work, which may lead to missed diagnosis and misdiagnosis.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model

et al. 2021

View full text Add to dashboard Cite

Timely microscopy screening of peripheral blood smears is essential for the diagnosis of acute promyelocytic leukemia (APL) due to the occurrence of early death (ED) before or during the initial therapy. Screening manually is time-consuming and tedious, and may lead to missed diagnosis or misdiagnosis because of subjective bias. To address these problems, we develop a three-step pipeline to help in the early diagnosis of APL from peripheral blood smears. The entire pipeline consists of leukocytes focusing, cell classification and diagnostic opinions. As the key component of the pipeline, a compact classification model based on attention embedded convolutional neural network blocks is proposed to distinguish promyelocytes from normal leukocytes. The compact classification model is validated on both the combination of two public datasets, APL-Cytomorphology_LMU and APL-Cytomorphology_JHH, as well as the clinical dataset, to yield a precision of 96.53% and 99.20%, respectively. The results indicate that our model outperforms the other evaluated popular classification models owing to its better accuracy and smaller size. Furthermore, the entire pipeline is validated on realistic patient data. The proposed method promises to act as an assistant tool for APL diagnosis.

show abstract

The predictive value of morphological findings in early diagnosis of acute myeloid leukemia with recurrent cytogenetic abnormalities

Cited by 7 publications

References 31 publications

Cytokine levels in patients with non-M3 myeloid leukemia are key indicators of how well the disease responds to chemotherapy

Cytokine levels in patients with non-M3 myeloid leukemia are key indicators of how well the disease responds to chemotherapy

Development and Evaluation of a Leukemia Diagnosis System Using Deep Learning in Real Clinical Scenarios

An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model

Contact Info

Product

Resources

About