RESUMO
BACKGROUND: Myelodysplastic/myeloproliferative neoplasms (MDS/MPN) comprise several rare hematologic malignancies with shared concomitant dysplastic and proliferative clinicopathologic features of bone marrow failure and propensity of acute leukemic transformation, and have significant impact on patient quality of life. The only approved disease-modifying therapies for any of the MDS/MPN are DNA methyltransferase inhibitors (DNMTi) for patients with dysplastic CMML, and still, outcomes are generally poor, making this an important area of unmet clinical need. Due to both the rarity and the heterogeneous nature of MDS/MPN, they have been challenging to study in dedicated prospective studies. Thus, refining first-line treatment strategies has been difficult, and optimal salvage treatments following DNMTi failure have also not been rigorously studied. ABNL-MARRO (A Basket study of Novel therapy for untreated MDS/MPN and Relapsed/Refractory Overlap Syndromes) is an international cooperation that leverages the expertise of the MDS/MPN International Working Group (IWG) and provides the framework for collaborative studies to advance treatment of MDS/MPN and to explore clinical and pathologic markers of disease severity, prognosis, and treatment response. METHODS: ABNL MARRO 001 (AM-001) is an open label, randomly allocated phase 1/2 study that will test novel treatment combinations in MDS/MPNs, beginning with the novel targeted agent itacitinib, a selective JAK1 inhibitor, combined with ASTX727, a fixed dose oral combination of the DNMTi decitabine and the cytidine deaminase inhibitor cedazuridine to improve decitabine bioavailability. DISCUSSION: Beyond the primary objectives of the study to evaluate the safety and efficacy of novel treatment combinations in MDS/MPN, the study will (i) Establish the ABNL MARRO infrastructure for future prospective studies, (ii) Forge innovative scientific research that will improve our understanding of pathogenetic mechanisms of disease, and (iii) Inform the clinical application of diagnostic criteria, risk stratification and prognostication tools, as well as response assessments in this heterogeneous patient population. TRIAL REGISTRATION: This trial was registered with ClinicalTrials.gov on August 19, 2019 (Registration No. NCT04061421).
Assuntos
Doenças Mieloproliferativas-Mielodisplásicas , Qualidade de Vida , Acetonitrilas , Citidina Desaminase , DNA/uso terapêutico , Decitabina/uso terapêutico , Humanos , Metiltransferases , Estudos Prospectivos , Pirazóis , Pirimidinas , Pirróis , SíndromeRESUMO
BACKGROUND: Aggressive large B-cell lymphomas (LBCLs) are curable, but previous studies have shown inferior outcomes in minorities. Nurse navigation programs can improve patient outcomes by providing patient support. This study presents the outcomes of White and minority patients with aggressive LBCL at an institution with an active nurse navigation program. METHODS: The authors prospectively collected baseline characteristics, treatment regimens, and outcome data for patients with aggressive LBCL. Navigation encounters were characterized as low or high intensity. Overall survival (OS) and progression-free survival (PFS) were calculated with Kaplan-Meier methods. Baseline characteristics were compared with Fisher exact tests. RESULTS: Two hundred four consecutive patients (47 minority patients and 157 White patients) were included. Results were presented as minorities versus Whites. There were no differences in prognostic scores (Revised International Prognostic Index score of 3-5, 43% vs 47%; P = .50), frontline chemotherapy (98% vs 96%; P = .68), or the incidence of relapsed/refractory disease (40% vs 38%; P = .74). For relapsed/refractory LBCL, similar proportions of patients underwent hematopoietic stem cell transplantation (32% vs 29%; P > .99) or chimeric antigen receptor T-cell therapy (16% vs 19%; P > .99). Enrollment in clinical trials was comparable (17% vs 14%; P = .64). More than 85% received nurse navigation, but minorities had higher intensity navigation encounters (42% vs 21%; P = .01). The 2-year OS rates were 81% and 76% for minorities and Whites, respectively (P = .27); the 2-year PFS rates were 62% and 65%, respectively (P = .78). CONCLUSIONS: This study shows similar survival between Whites and minorities with aggressive LBCL, which was likely due to equal access to guideline-concordant therapy. Minorities received higher intensity navigation encounters, which may have helped them to overcome socioeconomic disadvantages.
Assuntos
Transplante de Células-Tronco Hematopoéticas , Linfoma Difuso de Grandes Células B , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapêutico , Acessibilidade aos Serviços de Saúde , Humanos , Imunoterapia Adotiva , Linfoma Difuso de Grandes Células B/terapia , Intervalo Livre de Progressão , Estudos RetrospectivosAssuntos
Adenina/análogos & derivados , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapêutico , Perna (Membro)/patologia , Lenalidomida/uso terapêutico , Linfoma Difuso de Grandes Células B/tratamento farmacológico , Piperidinas/uso terapêutico , Rituximab/uso terapêutico , Adenina/farmacologia , Adenina/uso terapêutico , Idoso , Protocolos de Quimioterapia Combinada Antineoplásica/farmacologia , Humanos , Lenalidomida/farmacologia , Masculino , Pessoa de Meia-Idade , Piperidinas/farmacologia , Rituximab/farmacologiaRESUMO
Multiple myeloma (MM) infiltrates bone marrow and causes anemia by disrupting erythropoiesis, but the effects of marrow infiltration on anemia are difficult to quantify. Marrow biopsies of newly diagnosed MM patients were analyzed before and after four 28-day cycles of non-erythrotoxic remission induction chemotherapy. Complete blood cell counts and serum paraprotein concentrations were measured at diagnosis and before each chemotherapy cycle. At diagnosis, marrow area infiltrated by myeloma correlated negatively with hemoglobin, erythrocytes, and marrow erythroid cells. After successful chemotherapy, patients with less than 30% myeloma infiltration at diagnosis had no change in these parameters, whereas patients with more than 30% myeloma infiltration at diagnosis increased all three parameters. Clinical data were used to develop mathematical models of the effects of myeloma infiltration on the marrow niches of terminal erythropoiesis, the erythroblastic islands (EBIs). A hybrid discrete-continuous model of erythropoiesis based on EBI structure/function was extended to sections of marrow containing multiple EBIs. In the model, myeloma cells can kill erythroid cells by physically destroying EBIs and by producing proapoptotic cytokines. Following chemotherapy, changes in serum paraproteins as measures of myeloma cells and changes in erythrocyte numbers as measures of marrow erythroid cells allowed modeling of myeloma cell death and erythroid cell recovery, respectively. Simulations of marrow infiltration by myeloma and treatment with non-erythrotoxic chemotherapy demonstrate that myeloma-mediated destruction and subsequent reestablishment of EBIs and expansion of erythroid cell populations in EBIs following chemotherapy provide explanations for anemia development and its therapy-mediated recovery in MM patients.
Assuntos
Anemia/etiologia , Anemia/fisiopatologia , Medula Óssea/patologia , Eritropoese , Mieloma Múltiplo/complicações , Mieloma Múltiplo/patologia , Adulto , Idoso , Anemia/diagnóstico , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapêutico , Biomarcadores , Medula Óssea/fisiopatologia , Bortezomib/administração & dosagem , Dexametasona/administração & dosagem , Índices de Eritrócitos , Células Eritroides/patologia , Eritropoese/efeitos dos fármacos , Feminino , Humanos , Lenalidomida , Masculino , Pessoa de Meia-Idade , Modelos Teóricos , Mieloma Múltiplo/tratamento farmacológico , Talidomida/administração & dosagem , Talidomida/análogos & derivados , Resultado do TratamentoRESUMO
The revised International Prognostic Index (R-IPI) is an important prognostic tool in diffuse large B cell lymphoma (DLBCL); however, outcomes can vary markedly within R-IPI groups, and additional prognostic markers are needed. We conducted a prospective observational study to evaluate the circulating immature myeloid (IM) cell subsets and cytokine profiles of 31 patients with newly diagnosed DLBCL before and after chemoimmunotherapy. Among circulating IM cells, myeloid-derived suppressor cells (MDSCs) were the predominant cell type (73.8% ± 26%). At baseline, circulating monocytic MDSCs (M-MDSCs) and polymorphonuclear MDSCs (PMN-MDSCs) were predominantly mutually exclusive. Patients with DLBCL clustered into three distinct immunotypes according to MDSC levels and subtype predominance: M-MDSChigh, PMN-MDSChigh, and MDSClow. The M-MDSChigh immunotype was associated with the germinal center B cell-like (GCB) subtype and elevated serum IL-8 and MIP-1α levels. PMN-MDSChigh was associated with the non-GCB subtype and elevated IL-8, MCP-1, IP-10, TNFα, and IL-1Ra levels. Standard chemoimmunotherapy partially reduced M-MDSC distribution across the MDSClow and M-MDSChigh groups. By contrast, among the MDSClow and PMN-MDSChigh groups, PMN-MDSCs persisted after treatment. Two high-risk patients with non-GCB DLBCL and MDSClow immunotype experienced early disease recurrence within 12 months of treatment completion. This study demonstrates that distinct types of MDSCs are associated with subtypes of DLBCL. MDSC levels are dynamic and may be associated with disease status. Persistence of PMN-MDSCs among high-risk patients with DLBCL may be associated with early relapse.
Assuntos
Linfoma Difuso de Grandes Células B , Células Supressoras Mieloides , Humanos , Células Supressoras Mieloides/imunologia , Células Supressoras Mieloides/patologia , Células Supressoras Mieloides/metabolismo , Linfoma Difuso de Grandes Células B/diagnóstico , Linfoma Difuso de Grandes Células B/terapia , Linfoma Difuso de Grandes Células B/tratamento farmacológico , Linfoma Difuso de Grandes Células B/patologia , Linfoma Difuso de Grandes Células B/imunologia , Linfoma Difuso de Grandes Células B/sangue , Feminino , Masculino , Pessoa de Meia-Idade , Idoso , Prognóstico , Inflamação/patologia , Adulto , Estudos Prospectivos , Idoso de 80 Anos ou mais , Citocinas/sangue , Imunoterapia , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapêuticoRESUMO
ABSTRACT: Chimeric antigen receptor (CAR) T-cell (CAR-T) immunotherapy is an effective therapy for relapsed/refractory B-cell non-Hodgkin lymphoma (r/r B-NHL). However, data are limited on the impact of the convergence of race and social determinants of health on outcomes for patients treated with CAR-T therapy. We examined the impact of interactions between race and insurance type on health care use and outcomes in patients treated with CAR-T therapy for aggressive B-NHL. Adult patients with r/r B-NHL treated with CD19 CAR-Ts were identified between 2015 and 2021 across 13 US academic centers. Insurance type, demographic, and clinical data were collected and analyzed. In total, 466 adult patients were included in our analysis. Median follow-up after CAR-T therapy was 12.7 months. Median progression-free survival (mPFS) was longer for Caucasians (11.5 months) than for African Americans (3.5 months; hazard ratio [HR], 1.56 [1.03-2.4]; P = .04) or Asians (2.7 months; HR, 1.7 [1.02-2.67]; P = .04). Differences in median overall survival (mOS) were not significant. For Medicare (n = 206) vs Medicaid (n = 33) vs private insurance (n = 219) vs self-pay (n = 7): mPFS was 15.9 vs 4.2 vs 6.0 vs 0.9 months (P < .001), respectively; and mOS was 31.2 vs 12.8 vs 21.5 vs 3.2 months (P < .001), respectively. Our multicenter retrospective analysis showed that race and insurance status can affect outcomes for patients treated with CAR-T therapy.
Assuntos
Imunoterapia Adotiva , Determinantes Sociais da Saúde , Humanos , Masculino , Feminino , Pessoa de Meia-Idade , Adulto , Linfoma de Células B/terapia , Linfoma de Células B/mortalidade , Resultado do Tratamento , Idoso , Estados Unidos , Estudos Retrospectivos , Grupos RaciaisRESUMO
PURPOSE: Patients with chronic lymphocytic leukemia (CLL) treated with ibrutinib are at risk of developing cardiovascular side effects (CVSE). The molecular determinants of CVSEs have not been fully elucidated. We interrogated genetic polymorphisms in the Bruton tyrosine kinase (BTK) signaling pathway for their association with ibrutinib-related CVSEs. EXPERIMENTAL DESIGN: We conducted a retrospective/prospective observational pharmacogenetic study of 50 patients with newly diagnosed or relapsed CLL who received ibrutinib at a starting daily dose of 420 mg for at least 6 months. CVSEs, primarily atrial fibrillation and hypertension, occurred in 10 patients (20%), of whom 4 discontinued therapy. DNA was isolated from buccal swabs of all 50 patients and genotyped for 40 SNPs in GATA4, SGK1, KCNQ1, KCNA4, NPPA, and SCN5A using a customized next-generation sequencing panel. Univariate and multivariate logistic regression analysis were performed to determine genetic and clinical factors associated with the incidence of ibrutinib-related CVSEs. RESULTS: GATA4 rs804280 AA (P = 0.043), KCNQ1 rs163182 GG (P = 0.036), and KCNQ1 rs2237895 AA (P = 0.023) genotypes were univariately associated with ibrutinib-related CVSEs. On the basis of multivariate analysis, a high genetic risk score, defined as the presence of at least two of these genotypes, was associated with 11.5-fold increased odds of CVSEs (P = 0.019; 95% confidence interval, 1.79-119.73). CONCLUSIONS: Our findings suggest possible genetic determinants of ibrutinib-related CVSEs in CLL. If replicated in a larger study, pretreatment pharmacogenetic testing for GATA4 and KCNQ1 polymorphisms may be a useful clinical tool for personalizing treatment selection for CLL and/or instituting early risk mitigation strategies.
Assuntos
Leucemia Linfocítica Crônica de Células B , Humanos , Leucemia Linfocítica Crônica de Células B/tratamento farmacológico , Leucemia Linfocítica Crônica de Células B/genética , Estudos Retrospectivos , Canal de Potássio KCNQ1 , Piperidinas/uso terapêutico , Inibidores de Proteínas Quinases/uso terapêuticoRESUMO
Most patients receiving chimeric antigen receptor T-cell therapy (CAR-T) for aggressive B-cell non-Hodgkin lymphoma (B-NHL) do not experience a durable remission. Several novel agents are approved to treat relapsed, refractory aggressive B-NHL; however, it remains unclear how to sequence these therapies pre- and post-CAR-T. We conducted a multicenter retrospective analysis to describe peri-CAR-T practice patterns and survival predictors for patients receiving CD19-directed CAR-T. Patients (n = 514) from 13 centers treated with CAR-T for B-NHL between 2015-2021 were included in the study. Survival curves were constructed using Kaplan-Meier method. Multivariate Cox regression analysis was used to determine the impact of the variables on survival outcomes. For all patients receiving CAR-T, a greater number of lines of therapy pre-CAR-T apheresis and bridging therapy were predictive of inferior progression-free survival (PFS) and overall survival (OS). The median PFS and OS from the time of CAR-T cell infusion were 7.6 and 25.6 months, respectively. From the time of progression post-CAR-T, the median OS was 5.5 months. The median PFS of treatments administered in the first-line post-CAR-T failure was 2.8 months. Patients with refractory disease on day 30 had inferior OS and were less likely to receive subsequent treatment(s) than other patients with CAR-T failure. Allogeneic hematopoietic cell transplantation for selected patients at any time following CAR-T failure led to durable responses in over half of patients at 1 year. These data provide a benchmark for future clinical trials in patients with post-CAR-T cell progression, which remains an unmet clinical need.
Assuntos
Linfoma de Células B , Receptores de Antígenos Quiméricos , Humanos , Receptores de Antígenos Quiméricos/uso terapêutico , Estudos Retrospectivos , Imunoterapia Adotiva/métodos , Intervalo Livre de ProgressãoRESUMO
PURPOSE: Treatment options are limited beyond JAK inhibitors for patients with primary myelofibrosis (MF) or secondary MF. Preclinical studies have revealed that PI3Kδ inhibition cooperates with ruxolitinib, a JAK1/2 inhibitor, to reduce proliferation and induce apoptosis of JAK2V617F-mutant cell lines. PATIENTS AND METHODS: In a phase I dose-escalation and -expansion study, we evaluated the safety and efficacy of a selective PI3Kδ inhibitor, umbralisib, in combination with ruxolitinib in patients with MF who had a suboptimal response or lost response to ruxolitinib. Enrolled subjects were required to be on a stable dose of ruxolitinib for ≥8 weeks and continue that MTD at study enrollment. The recommended dose of umbralisib in combination with ruxolitinib was determined using a modified 3+3 dose-escalation design. Safety, pharmacokinetics, and efficacy outcomes were evaluated, and spleen size was measured with a novel automated digital atlas. RESULTS: Thirty-seven patients with MF (median age, 67 years) with prior exposure to ruxolitinib were enrolled. A total of 2 patients treated with 800 mg umbralisib experienced reversible grade 3 asymptomatic pancreatic enzyme elevation, but no dose-limiting toxicities were seen at lower umbralisib doses. Two patients (5%) achieved a durable complete response, and 12 patients (32%) met the International Working Group-Myeloproliferative Neoplasms Research and Treatment response criteria of clinical improvement. With a median follow-up of 50.3 months for censored patients, overall survival was greater than 70% after 3 years of follow-up. CONCLUSIONS: Adding umbralisib to ruxolitinib in patients was well tolerated and may resensitize patients with MF to ruxolitinib without unacceptable rates of adverse events seen with earlier generation PI3Kδ inhibitors. Randomized trials testing umbralisib in the treatment of MF should be pursued.
Assuntos
Inibidores de Janus Quinases , Mielofibrose Primária , Humanos , Idoso , Mielofibrose Primária/tratamento farmacológico , Mielofibrose Primária/metabolismo , Fosfatidilinositol 3-Quinases , Pirimidinas/uso terapêutico , Nitrilas/uso terapêutico , Inibidores de Janus Quinases/uso terapêuticoRESUMO
Ibrutinib is effective in the treatment of relapsed/refractory (R/R) marginal zone lymphoma (MZL) with an overall response rate (ORR) of 48%. However, factors associated with response (or lack thereof) to ibrutinib in R/R MZL in clinical practice are largely unknown. To answer this question, we performed a multicenter (25 US centers) cohort study and divided the study population into three groups: "ibrutinib responders"-patients who achieved complete or partial response (CR/PR) to ibrutinib; "stable disease (SD)"; and "primary progressors (PP)"-patients with progression of disease as their best response to ibrutinib. One hundred and nineteen patients met the eligibility criteria with 58%/17% ORR/CR, 29% with SD, and 13% with PP. The median PFS and OS were 29 and 71.4 months, respectively, with no difference in PFS or OS based on the ibrutinib line of therapy or type of therapy before ibrutinib. Patients with complex cytogenetics had an inferior PFS (HR = 3.08, 95% CI 1.23-7.67, p = 0.02), while those with both complex cytogenetics (HR = 3.00, 95% CI 1.03-8.68, p = 0.04) and PP (HR = 13.94, 95% CI 5.17-37.62, p < 0.001) had inferior OS. Only primary refractory disease to first-line therapy predicted a higher probability of PP to ibrutinib (RR = 3.77, 95% CI 1.15-12.33, p = 0.03). In this largest study to date evaluating outcomes of R/R MZL treated with ibrutinib, we show that patients with primary refractory disease and those with PP on ibrutinib are very high-risk subsets and need to be prioritized for experimental therapies.
Assuntos
Linfoma de Zona Marginal Tipo Células B , Adenina/análogos & derivados , Estudos de Coortes , Humanos , Linfoma de Zona Marginal Tipo Células B/tratamento farmacológico , Linfoma de Zona Marginal Tipo Células B/patologia , Recidiva Local de Neoplasia/tratamento farmacológico , Piperidinas , Pirazóis/uso terapêutico , Pirimidinas/uso terapêutico , Resultado do TratamentoRESUMO
Collectively, hematological malignancies account for the fourth most common malignancy. Myeloma and lymphoma are the most common types of hematological malignancies. Unfortunately, the management of refractory myeloma and lymphoma remains challenging. The discovery of new immunological therapies, namely chimeric antigen receptors T cells (CAR-T), outlined unprecedented B cell malignancies results. In this context, the CAR-T-based approach has led to the proliferation of many clinical studies. In this review, we will deal with the CAR-T structure, and we will summarize the primary clinical studies assessing the risks and benefits of CAR-T cell therapy. We will also deal with the adverse events and management of cytokine release syndromes/immune effector cell-associated neurotoxicity syndrome (ICANS). Subsequently, we will review potential future improvements to overcome refractoriness and improve expansion while decreasing CAR-T's off-target effects. The advances in the CAR-T platform represent a step forward with promising unlimited future possibilities that made it a paradigm-shifting for the management of B cell malignancies.
RESUMO
Chronic myelomonocytic leukemia (CMML) is a myelodysplastic syndrome/myeloproliferative neoplasm overlap syndrome characterized by monocytic proliferation in the presence of dysplastic bone marrow changes, inflammatory symptoms, and propensity for transformation to acute myeloid leukemia (AML), with a poor prognosis and limited treatment options. Unlike the α and ß isoforms, the phosphatidylinositol-3-kinase (PI3K)-δ signaling protein is predominantly expressed by hematopoietic cells and therefore has garnered interest as a potential target for the treatment of lymphomas and leukemias. We revealed a pattern of increased PIK3CD:PIK3CA ratio in monocytic M5 AML patients and cell lines, and this ratio correlated with responsiveness to pharmacological PI3K-δ inhibition in vitro. Because CMML is a disease defined by monocytic clonal proliferation, we tested the PI3K-δ inhibitor umbralisib as a single agent and in combination with the JAK1/2 inhibitor ruxolitinib, in CMML. Our ex vivo experiments with primary CMML patient samples revealed synergistic inhibition of viability and clonogenicity with this combination. Phospho-specific flow cytometry revealed that dual inhibition had the unique ability to decrease STAT5, ERK, AKT, and S6 phosphorylation simultaneously, which offers a mechanistic hypothesis for the enhanced efficacy of the combination treatment. These preclinical data indicate promising activity by co-inhibition of PI3K-δ and JAK1/2 and support the use of ruxolitinibâ¯+â¯umbralisib combination therapy in CMML under active clinical investigation.
Assuntos
Classe I de Fosfatidilinositol 3-Quinases/antagonistas & inibidores , Compostos Heterocíclicos de 4 ou mais Anéis/farmacologia , Leucemia Mielomonocítica Crônica/tratamento farmacológico , Inibidores de Fosfoinositídeo-3 Quinase/farmacologia , Pirazóis/farmacologia , Linhagem Celular Tumoral , Sobrevivência Celular/efeitos dos fármacos , Classe I de Fosfatidilinositol 3-Quinases/metabolismo , Sinergismo Farmacológico , Humanos , Leucemia Mielomonocítica Crônica/enzimologia , Terapia de Alvo Molecular , Nitrilas , PirimidinasRESUMO
Splenomegaly segmentation on computed tomography (CT) abdomen anatomical scans is essential for identifying spleen biomarkers and has applications for quantitative assessment in patients with liver and spleen disease. Deep convolutional neural network automated segmentation has shown promising performance for splenomegaly segmentation. However, manual labeling of abdominal structures is resource intensive, so the labeled abdominal imaging data are rare resources despite their essential role in algorithm training. Hence, the number of annotated labels (e.g., spleen only) are typically limited with a single study. However, with the development of data sharing techniques, more and more publicly available labeled cohorts are available from different resources. A key new challenging is to co-learn from the multi-source data, even with different numbers of labeled abdominal organs in each study. Thus, it is appealing to design a co-learning strategy to train a deep network from heterogeneously labeled scans. In this paper, we propose a new deep convolutional neural network (DCNN) based method that integrates heterogeneous multi-resource labeled cohorts for splenomegaly segmentation. To enable the proposed approach, a novel loss function is introduced based on the Dice similarity coefficient to adaptively learn multi-organ information from different resources. Three cohorts were employed in our experiments, the first cohort (98 CT scans) has only splenomegaly labels, while the second training cohort (100 CT scans) has 15 distinct anatomical labels with normal spleens. A separate, independent cohort consisting of 19 splenomegaly CT scans with labeled spleen was used as testing cohort. The proposed method achieved the highest median Dice similarity coefficient value (0.94), which is superior (p-value<0.01 against each other method) to the baselines of multi-atlas segmentation (0.86), SS-Net segmentation with only spleen labels (0.90) and U-Net segmentation with multi-organ training (0.91). Our approach for adapting the loss function and training structure is not specific to the abdominal context and may be beneficial in other situations where datasets with varied label sets are available.
RESUMO
Delineation of Computed Tomography (CT) abdominal anatomical structure, specifically spleen segmentation, is useful for not only measuring tissue volume and biomarkers but also for monitoring interventions. Recently, segmentation algorithms using deep learning have been widely used to reduce time humans spend to label CT data. However, the computerized segmentation has two major difficulties: managing intermediate results (e.g., resampled scans, 2D sliced image for deep learning), and setting up the system environments and packages for autonomous execution. To overcome these issues, we propose an automated pipeline for the abdominal spleen segmentation. This pipeline provides an end-to-end synthesized process that allows users to avoid installing any packages and to deal with the intermediate results locally. The pipeline has three major stages: pre-processing of input data, segmentation of spleen using deep learning, 3D reconstruction with the generated labels by matching the segmentation results with the original image dimensions, which can then be used later and for display or demonstration. Given the same volume scan, the approach described here takes about 50â¯s on average whereas the manual segmentation takes about 30â¯min on the average. Even if it includes all subsidiary processes such as preprocessing and necessary setups, the whole pipeline process requires on the average 20â¯min from beginning to end.
Assuntos
Aprendizado Profundo , Imageamento Tridimensional/métodos , Baço/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Algoritmos , Humanos , Fatores de TempoRESUMO
The findings of splenomegaly, abnormal enlargement of the spleen, is a non-invasive clinical biomarker for liver and spleen diseases. Automated segmentation methods are essential to efficiently quantify splenomegaly from clinically acquired abdominal magnetic resonance imaging (MRI) scans. However, the task is challenging due to: 1) large anatomical and spatial variations of splenomegaly; 2) large inter- and intra-scan intensity variations on multi-modal MRI; and 3) limited numbers of labeled splenomegaly scans. In this paper, we propose the Splenomegaly Segmentation Network (SS-Net) to introduce the deep convolutional neural network (DCNN) approaches in multi-modal MRI splenomegaly segmentation. Large convolutional kernel layers were used to address the spatial and anatomical variations, while the conditional generative adversarial networks were employed to leverage the segmentation performance of SS-Net in an end-to-end manner. A clinically acquired cohort containing both T1-weighted (T1w) and T2-weighted (T2w) MRI splenomegaly scans was used to train and evaluate the performance of multi-atlas segmentation (MAS), 2D DCNN networks, and a 3-D DCNN network. From the experimental results, the DCNN methods achieved superior performance to the state-of-the-art MAS method. The proposed SS-Net method has achieved the highest median and mean Dice scores among the investigated baseline DCNN methods.
Assuntos
Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Redes Neurais de Computação , Esplenomegalia/diagnóstico por imagem , Humanos , Imageamento Tridimensional/métodos , Baço/diagnóstico por imagemAssuntos
Antígenos CD19 , Imunoterapia Adotiva , Humanos , Antígenos CD19/imunologia , Imunoterapia Adotiva/métodos , Imunoterapia Adotiva/efeitos adversos , Masculino , Feminino , Segunda Neoplasia Primária/etiologia , Segunda Neoplasia Primária/terapia , Adulto , Receptores de Antígenos Quiméricos , Pessoa de Meia-Idade , Neoplasias/terapia , Neoplasias/imunologiaRESUMO
A key limitation of deep convolutional neural networks (DCNN) based image segmentation methods is the lack of generalizability. Manually traced training images are typically required when segmenting organs in a new imaging modality or from distinct disease cohort. The manual efforts can be alleviated if the manually traced images in one imaging modality (e.g., MRI) are able to train a segmentation network for another imaging modality (e.g., CT). In this paper, we propose an end-to-end synthetic segmentation network (SynSeg-Net) to train a segmentation network for a target imaging modality without having manual labels. SynSeg-Net is trained by using (1) unpaired intensity images from source and target modalities, and (2) manual labels only from source modality. SynSeg-Net is enabled by the recent advances of cycle generative adversarial networks (CycleGAN) and DCNN. We evaluate the performance of the SynSeg-Net on two experiments: (1) MRI to CT splenomegaly synthetic segmentation for abdominal images, and (2) CT to MRI total intracranial volume synthetic segmentation (TICV) for brain images. The proposed end-to-end approach achieved superior performance to two stage methods. Moreover, the SynSeg-Net achieved comparable performance to the traditional segmentation network using target modality labels in certain scenarios. The source code of SynSeg-Net is publicly available 2.