scholarly journals Integrated information and measurement system for the diagnosis of acute leukemia and minimal residual disease based on computer microscopy, flow laser cytofluorimetry and artificial intelligence

2021 ◽  
Vol 2058 (1) ◽  
pp. 012033
Author(s):  
V G Nikitayev ◽  
A N Pronichev ◽  
N N Tupitsin ◽  
V Yu Selchuk ◽  
V V Dmitrieva ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Bone Marrow ◽  
Acute Leukemia ◽  
Minimal Residual Disease ◽  
Measurement System ◽  
Bone Marrow Cells ◽  
Residual Disease ◽  
Computer Microscopy ◽  
Minimal Residual ◽  
Integrated Information

Abstract The article considers a new integrated information and measurement system for the diagnosis of acute leukemia and minimal residual disease based on computer microscopy and flow laser cytometry. The system is based on combining the results of computer microscopy in the analysis of bone marrow preparations and the results of flow laser cytofluorimetry. A special feature of the system is the use of artificial intelligence technologies in the recognition of images of bone marrow cells in the computer microscopy subsystem. The work was the result of joint work of the Department of Computer Medical Systems of the National Research Nuclear University "MEPhI" and the Laboratory of Hematopoietic Immunology of the National Medical Research Center of Oncology named after N. N. Blokhin.

METHODS OF MULTICLASSICATION OF BONE MARROW CELLS FOR THE DIAGNOSIS OF ACUTE LEUKEMIA AND MINIMAL RESIDUAL DISEASE (ON THE MATERIALS OF THE LABORATORY OF HEMATOPOIESIS OF N. N. BLOKHIN NATIONAL MEDICAL RESEARCH CENTER OF ONCOLOGY)

2020 ◽  
pp. 155-158
Author(s):  
Валентина Викторовна Дмитриева ◽  
Николай Николаевич Тупицын ◽  
Евгений Валерьевич Поляков ◽  
Софья Сергеевна Денисюк
Keyword(s):  
Bone Marrow ◽  
Acute Leukemia ◽  
Medical Research ◽  
Bone Marrow Cells ◽  
Residual Disease ◽  
Binary Classification ◽  
National Medical ◽  
Cell Class ◽  
Minimal Residual ◽  
Marrow Cells

Применение методов и средств цифровой обработки изображений при распознавании типов клеток крови и костного мозга для повышения качества диагностики острых лейкозов является актуальной научно-технической задачей, отвечающей стратегии развития технологий искусственного интеллекта в медицине. В работе предложен подход к мультиклассификации клеток костного мозга при диагностике острых лейкозов и минимальной остаточной болезни. Для проведения экспериментальных исследований сформирована выборка из 3284 изображений клеток, представленных Лабораторией гемопоэза Национального медицинского исследовательского центра онкологии им. Н.Н. Блохина. Предложенный подход к мультиклассификации клеток костного мозга основан на бинарной модели классификации для каждого из исследуемых классов относительно остальных. В рассматриваемой работе бинарная классификация выполняется методом опорных векторов. Метод мультиклассификации был программно реализован с применением интерпретатора Python 3.6.9. Входными данными программы служат файлы формата *.csv с таблицами морфологических, цветовых, текстурных признаков для каждой из клеток используемой выборки. В выборке представлено девять типов клеток костного мозга. Выходными данными программы мультиклассификации являются значения точности классификации на тестовой выборке, которые отражают совпадение прогнозируемого класса клетки с фактическим (верифицированным) классом клетки. “Эксперимент показал следующие результаты: точность мультиклассификации рассматриваемых типов клеток в среднем составила: 87% на тестовом наборе, 88% на обучающем наборе данных. Проведенное исследование является предварительным. В дальнейшем планируется увеличить число классов клеток, объем выборок различных типов клеток и с уточнением результатов мультиклассификации The use of methods and means of digital image processing in the recognition of types of blood cells and bone marrow to improve the quality of diagnosis of acute leukemia is an urgent scientific and technical task that meets the strategy for the development of artificial intelligence technologies in medicine. The paper proposes an approach to the multiclassification of bone marrow cells in the diagnosis of acute leukemia and minimal residual disease. For experimental studies, a sample of 3284 images of cells was formed, submitted by the Hematopoiesis Laboratory of the National Medical Research Center of Oncology named after V.I. N.N. Blokhin. The proposed approach to the multiclassification of bone marrow cells is based on a binary classification model for each of the studied classes relative to the others. In the work under consideration, binary classification is performed by the support vector machine. The multiclassification method was implemented programmatically using the Python 3.6.9 interpreter. The input data of the program are * .csv files with tables of morphological, color, texture features for each of the cells of the sample used. The sample contains nine types of bone marrow cells. The output data of the multiclassification program are the classification accuracy values on the test sample, which reflect the coincidence of the predicted cell class with the actual (verified) cell class. “The experiment showed the following results: the accuracy of multiclassification of the considered types of cells on average was: 87% on the test set, 88% on the training data set. This study is preliminary. In the future, it is planned to increase the number of classes of cells, the volume of samples of various types of cells and with the refinement of the results of multiclassification

Minimal residual disease in acute lymphoblastic leukemia detected by immune selection and gene rearrangement analysis.

1989 ◽  
Vol 7 (3) ◽  
pp. 338-343 ◽  
Author(s):  
M Bregni ◽  
S Siena ◽  
A Neri ◽  
R Bassan ◽  
T Barbui ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Acute Lymphoblastic Leukemia ◽  
Minimal Residual Disease ◽  
Gene Rearrangement ◽  
Bone Marrow Cells ◽  
Residual Disease ◽  
Lymphoblastic Leukemia ◽  
Immune Selection ◽  
Gene Rearrangement Analysis ◽  
Minimal Residual

We have developed an assay for the detection of malignant residual cells in the bone marrow from patients with B- or T-lineage acute lymphoblastic leukemia (ALL) in clinical remission. This assay involves an immune selection step followed by immunoglobulin or T-cell receptor gene rearrangement analysis and allows the detection of one contaminating tumor cell out of 1,000 normal bone marrow cells. We have examined the bone marrow of 11 patients with adult ALL in remission over a 24-month period. Five patients relapsed in the bone marrow and one in the CNS. The assay allowed the detection of minimal residual disease in four of five patients that subsequently relapsed in the bone marrow, 1.5 to 9 months before the relapse became morphologically and clinically manifest. Residual disease was not found in the bone marrow from patients in continuous remission and from the single patient who relapsed in the CNS. We conclude that the ability of the assay described here to detect minimal residual disease with high specificity can provide information for further understanding of the biology of ALL and hopefully for the clinical management of patients with this disease.

Minimal Residual Disease Quantification in Ovarian Tissue Collected in Patients in Complete Remission of Acute Leukemia

Blood ◽  
2020 ◽  
Author(s):  
Florian Chevillon ◽  
Emmanuelle Clappier ◽  
Chloe Arfeuille ◽  
Jean-Michel Cayuela ◽  
Jean-Hugues Dalle ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Complete Remission ◽  
Acute Leukemia ◽  
Minimal Residual Disease ◽  
Residual Disease ◽  
Ovarian Tissue ◽  
Ovarian Tissue Cryopreservation ◽  
Hematopoietic Stem ◽  
Leukemic Infiltration ◽  
Minimal Residual

Ovarian tissue cryopreservation (OTC) is offered to women treated for acute leukemia to preserve their fertility before hematopoietic stem cell transplantation. The risk of leukemic infiltration in ovarian samples harvested before administration of chemotherapy limits ovarian tissue transplantations. We assessed the minimal residual disease (MRD) by sensitive quantitative polymerase chain reaction in cryopreserved ovarian cortex and medulla samples harvested from 30 patients in complete remission of acute leukemia, including 60 % with negative bone marrow MRD at the time of OTC. Ovarian MRD was undetectable in 21 patients (70%), detectable below 10-4 in 8 patients (27%) and between 10-3 and 10-4 in 1 patient (3%). Twenty patients (67%) had concordant MRD between bone marrow and ovarian samples. Interestingly 4 patients had positive MRD in ovarian samples while undetectable in bone marrow. Our results underline the importance of reaching the best control of the disease with undetectable or low MRD levels before OTC to minimize the risk of ovarian leukemic infiltration. The discordant results between ovarian samples and bone marrow require to test the more ovarian samples available before considering ovarian tissue transplantation.

scholarly journals Bone marrow cells recognition methods in the diagnosis of minimal residual disease

2020 ◽  
Vol 169 ◽  
pp. 353-358 ◽  
Author(s):  
Valentin Nikitaev ◽  
Alexander Pronichev ◽  
Evgeney Polyakov ◽  
Olga Chernysheva ◽  
Irina Serebryakova ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Minimal Residual Disease ◽  
Bone Marrow Cells ◽  
Residual Disease ◽  
Minimal Residual ◽  
Marrow Cells

Unusual Immunophenotypes in the Bone Marrow of Infants with Acute Leukemia: Minimal Residual Disease or ATRA-Mediated Regeneration?.

Blood ◽  
2007 ◽  
Vol 110 (11) ◽  
pp. 4260-4260
Author(s):  
Alexander Popov ◽  
Tatiana Verzhbitskaya ◽  
Grigory Tsaur ◽  
Egor Shorikov ◽  
Leonid Saveliev ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Flow Cytometry ◽  
Minimal Residual Disease ◽  
Bone Marrow Cells ◽  
Residual Disease ◽  
Multicolor Flow Cytometry ◽  
Acute Leukemias ◽  
Short Period ◽  
Minimal Residual ◽  
Marrow Cells

Abstract Minimal Residual Disease (MRD) monitoring is essential to predict early outcome and further optimize treatment, especially when new approaches to therapy are used. A promising new treatment is the combination of chemotherapy with all trans-retinoic acid (ATRA) for infant acute leukemias. ATRA-mediated maturation of bone marrow cells can lead to the appearance of unusual undifferentiated cells with new immunological characteristics. We investigated the immunophenotypic features of bone marrow cells in infant acute leukemias treated with traditional chemotherapy combined with ATRA. From May 2006 to July 2007, we performed initial and consecutive multicolor flow cytometry assays of bone marrow samples from 4 infants with primary ALL or AML (except M3) treated at our institution. Patient I had BII-ALL, co-expressing CD15, but the majority of his blast cells were CD10(-). Conventional cytogenetics revealed t(4;11) and MLL/AF4 was detected. Early after ATRA administration, we detected MPO(+)TdT(+)-cells and subsequently, CD19, CD10, CD34, CD99 positive cells were found. Moreover, those cells occupied the “blast region” (SSC(low)CD45(dim)) and were seen as an autonomous population on the FSC/SSC dot plot. There was no correlation with the number of CD19(+)MPO(+)-cells and either MRD, measured by multicolor flow cytometry, or the level of the fusion gene transcript performed by the quantitative real-time polymerase chain reaction. In patient II with primary AML-M2, the cells with the same phenotype were also detected after several ATRA courses. Patient III, with primary biphenotypic leukemia, demonstrated total clearance of tumor blasts after the beginning of ATRA treatment with the later appearance of two cells populations: one similar to the phenotype previously described in patients I and II, but additionally expressing CD79a. The second cell population was positive for the cortical thymocytes markers CD7, CD5, CD2, CD4, CD8 and CD1a. This phenotype was observed shortly after ATRA initiation and disappeared with further chemotherapy. Patient IV with primary AML-M7 was switched to BII-ALL after the 3rd ATRA course. Simultaneously, a minor population of biphenotypic cells was observed and later comprised 2 groups: TdT(−)CD99(−)CD45(bright) and TdT(+)CD99(+)CD45(dim) cells. We infer from this observation that the biphenotypic cells had matured. Cortical thymocytes were also detected in this patient for a short period. In all 4 patients we observed an equal distribution of biphenotypic cells on dot plots despite the differences in the primary leukemia phenotypes. This raises the question of a tumor versus an ATRA-mediated origin of the biphenotypic cells that requires further investigation in the patients treated with ATRA. Moreover, we conclude that a more extensive and specific panel of monoclonal antibodies is also required for the full immunophenotypic characterization of infant leukemia.

Flow Cytometric Immunophenotyping for Minimal Residual Disease Analysis in Multiple Myeloma

Blood ◽  
2008 ◽  
Vol 112 (11) ◽  
pp. 2711-2711
Author(s):  
Ritu Gupta ◽  
Archana Bhaskar ◽  
Paresh Jain ◽  
Atul Sharma ◽  
Lalit Kumar
Keyword(s):  
Bone Marrow ◽  
Minimal Residual Disease ◽  
Bone Marrow Aspirate ◽  
Plasma Cells ◽  
Bone Marrow Cells ◽  
Residual Disease ◽  
Protein Electrophoresis ◽  
Tumor Load ◽  
Total Bone Marrow ◽  
Minimal Residual

Abstract Recent studies using multi-parametric flow cytometry (MFC) have shown frequent immunophenotypic aberrations of plasma cells (PCs) and their utility in minimal residual disease (MRD) detection in multiple myeloma (MM). Presence of normal PCs and hemodilution of the bone marrow aspirate are important considerations in MRD assessment by MFC. The purpose of present study was to characterize PCs in MM to determine the incidence of aberrant antigen expression on myeloma PCs and its role in estimation of minimal residual disease. A total of 108 patients of MM were evaluated to study the immunophenotype of PCs and 37 patients for estimation of MRD using pre-titrated volumes of the following monoclonal antibodies: CD19 FITC, CD20 FITC, CD45 FITC, CD117 PE, CD56 PE, CD38 PE-Cy5.5, CD138 APC (BD Biosciences, San Jose, CA, USA), CD52 PE, Kappa (κ) FITC and Lambda (λ) PE (Serotec). CD38 and CD138 were added to all the tubes for specific identification of PCs. 2ml of bone marrow aspirate was collected from all the subjects as per the guidelines of the institute ethics committee, processed for immunophenotyping studies using standard whole blood lysis technique and analyzed with 4-color flow cytometry. At least two antigens were aberrantly expressed in all and three in 92.6% of MM with CD19 being most frequent followed by CD56, CD45, CD52, CD117 and CD20. Using aberrant immunophenotype for identification of neoplastic PCs, MRD by MFC was detectable in all the patients of MM with ≤5% PC on bone marrow smears. The neoplastic PCs as percentage of total bone marrow cells could not differentiate protein electrophoresis (PE) + from PE− samples (Figure 1A). Assuming that in a hemodiluted bone marrow aspirate both the neoplastic and normal PCs would be proportionately reduced and normal PCs would outnumber the neoplastic clone after successful therapy; when we analyzed the tumor load i.e. the neoplastic PC as percentage of total PCs, a cut-off of 50% neoplastic PCs of total PCs could differentiate PE + samples from PE− ones (Figure 1B). To conclude, MRD detection by aberrant antigen expression is useful and evaluation of tumor load i.e. neoplastic PCs as percentage of total PC may help in better assessment of response to therapy and circumvent the problem of hemodilution in MFC based MRD assays in MM. Figure 1: Tumor load i.e. neoplastic plasma cells (NPCs) as % of total PCs (A) & of total bone marrow cells (B) in samples evaluated for minimal residual disease. The NPCs constituted ≤50% of the total PCs in protein electrophoresis (PE) & immunofixation negative samples and >60% of the total PCs in PE+ samples (B). Arrow indicates two cases which were PE- but positive on immunofixation and had relatively low numbers of neoplastic PCs (B) <> Figure 1:. Tumor load i.e. neoplastic plasma cells (NPCs) as % of total PCs (A) & of total bone marrow cells (B) in samples evaluated for minimal residual disease. The NPCs constituted ≤50% of the total PCs in protein electrophoresis (PE) & immunofixation negative samples and >60% of the total PCs in PE+ samples (B). Arrow indicates two cases which were PE- but positive on immunofixation and had relatively low numbers of neoplastic PCs (B) <>

Intensive minimal residual disease monitoring to drive early intervention after allogeneic hematopoietic stem cell transplant for pediatric acute leukemia.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e18531-e18531
Author(s):  
Thomas Pincez ◽  
Raoul Santiago ◽  
Henrique Bittencourt ◽  
Isabelle Louis ◽  
Pierre Teira ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Stem Cell ◽  
Acute Leukemia ◽  
Minimal Residual Disease ◽  
Therapeutic Intervention ◽  
Residual Disease ◽  
Cell Transplant ◽  
Rt Pcr ◽  
The Impact ◽  
Minimal Residual

e18531 Background: Relapse of acute leukemia (AL) remains the main cause of death after allogeneic stem cell transplantation (HSCT) in children. Minimal residual disease (MRD) allows to detect leukemia cells in the bone marrow at low level. The impact of post-HSCT MRD monitoring to detect early leukemia recurrence, to guide therapeutic intervention, and to prevent overt relapse is unknown. We report our experience of systematic MRD monitoring after pediatric HSCT. Methods: All patients who underwent HSCT from January 2012 to December 2017 for an AL had bone marrow MRD performed for 2 years (months 1, 2, 3, 5, 7, 9, 12, 15, 18, 21 and 24). MRD was assessed by flow-cytometry (FC) and, when a molecular alteration was present, by nested RT-PCR. Results: Seventy-one HSCT were performed for AL of myeloid (n=38), lymphoid (n=31) or mixed (n=2) lineage in 59 patients at a median (range) age of 6.5 (0.7-18.4) years. Nine cases did not engraft or had a refractory disease at month+1 evaluation. In all other cases (n=62) MRD was monitored using FC (n=58) and/or RT-PCR (n=34). Thirty-three cases had a MRD detection and/or an overt relapse (≥5% blasts). In 23/33 cases (70%), MRD was detected without simultaneous overt relapse. In the 10 others, an overt relapse occurred without prior MRD detection. Among the cases monitored with RT-PCR, only one relapse occurred without a prior MRD detection. The follow-up protocol was not respected in this particular case. On early MRD detection, 20/23 cases underwent therapeutic intervention, the most frequent being the discontinuation of immunosuppressive drugs (n=13), with subsequent undetectable MRD in 6. Other interventions included chemotherapy (n=8), donor lymphocyte infusion (n=6) and/or interferon ± interleukine 2 (n=3), leading to an undetectable MRD in 3 cases. Overall after first MRD detection, 9/23 (39%) cases never experienced a subsequent overt relapse. Conclusions: Intensified MRD monitoring detected 70% of leukemia recurrences before overt relapse. Therapeutic intervention were taken in most of the cases and 39% never experienced overt leukemia relapse. More efficient immunotherapies may improve the impact of preemptive interventions.

scholarly journals Established Standards of Minimal Residual Disease Detected By Multiparametric Flow Cytometry in Acute Leukemia

Blood ◽  
2014 ◽  
Vol 124 (21) ◽  
pp. 5262-5262
Author(s):  
Hui Jing ◽  
Fen Huang ◽  
Zhengshan Yi ◽  
Zhongxin Zheng ◽  
Xiaolei Wei ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Flow Cytometry ◽  
Acute Leukemia ◽  
Minimal Residual Disease ◽  
Residual Disease ◽  
Remission Induction ◽  
Test Results ◽  
Color Flow ◽  
Multiparametric Flow Cytometry ◽  
Minimal Residual

Abstract Purpose To establish a method for detecting minimal residual disease (MRD) by eight color flow cytometry which is stable, repeatable and accurate quantitation. Method According to the ratio of 10%, 1%, 0.1%, 0.01% and 0.001%,to analyze sensitivity of the method by successively mixing the cell lines (Kasumi, KG-1a) and primary acute leukemic bone marrow cell were mixed with normal bone marrow cells. In order to ensure the specificity of the test results, we increased antibody number to eight color combinations of antibodies to adjust fluorescence compensation value after labeling antibody separately in each channel. To verify the feasibility of standardization, standardized test were in 25 bone marrow samples of acute leukemia. Result In standard conditions of detection and sensitivity of 10-5could be detected by eight color flow cytometry. In our study there were 25 cases of acute leukemia, including 14 patients with acute myeloid leukemia and 11 patients with acute B-lymphoblastic leukemia. 23 of 25 cases were detected specific leukemia associated immunophenotypes (LAIP) at diagnosis. 20 patients could be detected the original LAIP, and LAIP of 3 patients changed after remission induction therapy. To analyze the relationship between the clinical data and MRD level, the result showed that the type of LAIP had significant influence on level of MRD. After remission the level of MRD in patients who expressed cross lineage and non-synchronous antigens at diagnosis was significantly higher than those who did not express (P=0.003, P=0.006). Conclusion We established the standardized conditions of minimal residual disease detected by multiparametric flow cytometry to ensure the accuracy and specificity of the test results. It has important significance to confirm that manifestations of LAIP were consistent with the outcome in patients with acute leukemia. Disclosures No relevant conflicts of interest to declare.

Sign in / Sign up

Export Citation Format

Share Document