Deep learning detects acute myeloid leukemia and predicts NPM1 mutation status from bone marrow smears.
Ontology highlight
ABSTRACT:
SUBMITTER: Eckardt JN
PROVIDER: S-EPMC8727290 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:AbstractThe detection of genetic aberrations is crucial for early therapy decisions in acute myeloid leukemia (AML) and recommended for all patients. Because genetic testing is expensive and time consuming, a need remains for cost-effective, fast, and broadly accessible tests to predict these aberrations in this aggressive malignancy. Here, we developed a novel fully automated end-to-end deep learning pipeline to predict genetic aberrations directly from single-cell images from scans of conventionally stained bone marrow smears already on the day of diagnosis. We used this pipeline to compile a multiterabyte data set of >2 000 000 single-cell images from diagnostic samples of 408 patients with AML. These images were then used to train convolutional neural networks for the prediction of various therapy-relevant genetic alterations. Moreover, we created a temporal test cohort data set of >444 000 single-cell images from further 71 patients with AML. We show that the models from our pipeline can significantly predict these subgroups with high areas under the curve of the receiver operating characteristic. Potential genotype-phenotype links were visualized with 2 different strategies. Our pipeline holds the potential to be used as a fast and inexpensive automated tool to screen patients with AML for therapy-relevant genetic aberrations directly from routine, conventionally stained bone marrow smears already on the day of diagnosis. It also creates a foundation to develop similar approaches for other bone marrow disorders in the future.
| S-EPMC10787267 | biostudies-literature
Project description:BackgroundAcute promyelocytic leukemia (APL) is considered a hematologic emergency due to high risk of bleeding and fatal hemorrhages being a major cause of death. Despite lower death rates reported from clinical trials, patient registry data suggest an early death rate of 20%, especially for elderly and frail patients. Therefore, reliable diagnosis is required as treatment with differentiation-inducing agents leads to cure in the majority of patients. However, diagnosis commonly relies on cytomorphology and genetic confirmation of the pathognomonic t(15;17). Yet, the latter is more time consuming and in some regions unavailable.MethodsIn recent years, deep learning (DL) has been evaluated for medical image recognition showing outstanding capabilities in analyzing large amounts of image data and provides reliable classification results. We developed a multi-stage DL platform that automatically reads images of bone marrow smears, accurately segments cells, and subsequently predicts APL using image data only. We retrospectively identified 51 APL patients from previous multicenter trials and compared them to 1048 non-APL acute myeloid leukemia (AML) patients and 236 healthy bone marrow donor samples, respectively.ResultsOur DL platform segments bone marrow cells with a mean average precision and a mean average recall of both 0.97. Further, it achieves high accuracy in detecting APL by distinguishing between APL and non-APL AML as well as APL and healthy donors with an area under the receiver operating characteristic of 0.8575 and 0.9585, respectively, using visual image data only.ConclusionsOur study underlines not only the feasibility of DL to detect distinct morphologies that accompany a cytogenetic aberration like t(15;17) in APL, but also shows the capability of DL to abstract information from a small medical data set, i. e. 51 APL patients, and infer correct predictions. This demonstrates the suitability of DL to assist in the diagnosis of rare cancer entities. As our DL platform predicts APL from bone marrow smear images alone, this may be used to diagnose APL in regions were molecular or cytogenetic subtyping is not routinely available and raise attention to suspected cases of APL for expert evaluation.
| S-EPMC8864866 | biostudies-literature
Project description:Acute myeloid leukemia (AML) is a deadly hematological malignancy. Cellular morphology detection of bone marrow smears based on the French-American-British (FAB) classification system remains an essential criterion in the diagnosis of hematological malignancies. However, the diagnosis and discrimination of distinct FAB subtypes of AML obtained from bone marrow smear images are tedious and time-consuming. In addition, there is considerable variation within and among pathologists, particularly in rural areas, where pathologists may not have relevant expertise. Here, we established a comprehensive database encompassing 8245 bone marrow smear images from 651 patients based on a retrospective dual-center study between 2010 and 2021 for the purpose of training and testing. Furthermore, we developed AMLnet, a deep-learning pipeline based on bone marrow smear images, that can discriminate not only between AML patients and healthy individuals but also accurately identify various AML subtypes. AMLnet achieved an AUC of 0.885 at the image level and 0.921 at the patient level in distinguishing nine AML subtypes on the test dataset. Furthermore, AMLnet outperformed junior human experts and was comparable to senior experts on the test dataset at the patient level. Finally, we provided an interactive demo website to visualize the saliency maps and the results of AMLnet for aiding pathologists' diagnosis. Collectively, AMLnet has the potential to serve as a fast prescreening and decision support tool for cytomorphological pathologists, especially in areas where pathologists are overburdened by medical demands as well as in rural areas where medical resources are scarce.
| S-EPMC10031907 | biostudies-literature
Project description:Murine models of myeloid neoplasia show how leukemia infiltration alters the hematopoietic stem cell (HSC) niche to reinforce malignancy at the expense of healthy hematopoiesis. However, little is known about the bone marrow architecture in humans and its impact on clinical outcome. Here, we dissect the bone marrow niche in patients with acute myeloid leukemia (AML) at first diagnosis. We combined immunohistochemical stainings with global gene expression analyses from these AML patients and correlated them with clinical features. Mesenchymal stem and progenitor cells (MSPCs) lost quiescence and significantly expanded in the bone marrow of AML patients. Strikingly, their HSC- and niche-regulating capacities were impaired with significant inhibition of osteogenesis and bone formation in a cell contact-dependent manner through inhibition of cytoplasmic β-catenin. Assessment of bone metabolism by quantifying peripheral blood osteocalcin levels revealed 30% lower expression in AML patients at first diagnosis than in non-leukemic donors. Furthermore, patients with osteocalcin levels ≤11 ng/mL showed inferior overall survival with a 1-year survival rate of 38.7% whereas patients with higher osteocalcin levels reached a survival rate of 66.8%. These novel insights into the human AML bone marrow microenvironment help translate findings from preclinical models and detect new targets which might pave the way for niche-targeted therapies in AML patients.
| S-EPMC7594397 | biostudies-literature
Project description:Gene abnormalities, including mutations and fusions, are important determinants in the molecular diagnosis of myeloid neoplasms. The use of bone marrow (BM) smears as a source of DNA and RNA for next-generation sequencing (NGS) enables molecular diagnosis to be done with small amounts of bone marrow and is especially useful for patients without stocked cells, DNA or RNA. The present study aimed to analyze the quality of DNA and RNA derived from smear samples and the utility of NGS for diagnosing myeloid neoplasms. Targeted DNA sequencing using paired BM cells and smears yielded sequencing data of adequate quality for variant calling. The detected variants were analyzed using the bioinformatics approach to detect mutations reliably and increase sensitivity. Noise deriving from variants with extremely low variant allele frequency (VAF) was detected in smear sample data and removed by filtering. Consequently, various driver gene mutations were detected across a wide range of allele frequencies in patients with myeloid neoplasms. Moreover, targeted RNA sequencing successfully detected fusion genes using smear-derived, very low-quality RNA, even in a patient with a normal karyotype. These findings demonstrated that smear samples can be used for clinical molecular diagnosis with adequate noise-reduction methods even if the DNA and RNA quality is inferior.
| S-EPMC8301613 | biostudies-literature
Project description:The genetic heterogeneity of acute myeloid leukemia (AML) and the variable responses of individual patients to therapy suggest that different AML genotypes may influence the bone marrow (BM) microenvironment in different ways. We performed gene expression profiling of bone marrow mesenchymal stromal cells (BM-MSC) isolated from normal C57BL/6 mice or mice inoculated with syngeneic murine leukemia cells carrying different human AML genotypes, developed in mice with Trp53 wild-type or nullgenetic backgrounds. We identified a set of genes whose expression in BM-MSC was modulated by all four AML genotypes tested. In addition, there were sets of differentially-expressed genes in AML-exposed BM-MSC that were unique to the particular AML genotype or Trp53 status. Our findings support the hypothesis that leukemia cells alter the transcriptome of surrounding BM stromal cells, in both common and genotype-specific ways. These changes are likely to be advantageous to AML cells, affecting disease progression and response to chemotherapy, and suggest opportunities for stroma-targeting therapy, including those based on AML genotype.
| S-EPMC5663521 | biostudies-literature
Project description:In addition to their roles in different biological processes, microRNAs in the tumor microenvironment appear to be potential diagnostic and prognostic biomarkers for various malignant diseases, including acute myeloid leukemia (AML). To date, no screening of circulating miRNAs has been carried out in the bone marrow compartment of AML. Accordingly, we investigated the circulating miRNA profile in AML bone marrow at diagnosis (AMLD) and first complete remission post treatment (AMLPT) in comparison to healthy donors (HD). Circulating miRNAs were isolated from AML bone marrow aspirations, and a low-density TaqMan miRNA array was performed to identify deregulated miRNAs followed by quantitative RT-PCR to validate the results. Bioinformatic analysis was conducted to evaluate the diagnostic and prognostic accuracy of the highly and significantly identified deregulated miRNA(s) as potential candidate biomarker(s). We found several deregulated miRNAs between the AMLD vs. HD vs. AMLPT groups, which were involved in tumor progression and immune suppression pathways. We also identified significant diagnostic and prognostic signatures with the ability to predict AML patient treatment response. This study provides a possible role of enriched circulating bone marrow miRNAs in the initiation and progression of AML and highlights new markers for prognosis and treatment monitoring.
| S-EPMC7583041 | biostudies-literature
Project description:Bone marrow (BM) is a highly complex tissue that provides important regulatory signals to orchestrate hematopoiesis. Resident and transient cells occupy and interact with some well characterized niches to produce molecular and cellular mechanisms that interfere with differentiation, migration, survival, and proliferation in this microenvironment. The acute myeloid leukemia (AML), the most common and severe hematological neoplasm in adults, arises and develop in the BM. The osteoblastic, vascular, and reticular niches provide surface co-receptors, soluble factors, cytokines, and chemokines that mediate important functions on hematopoietic cells and leukemic blasts. There are some evidences of how AML modify the architecture and function of these three BM niches, but it has been still unclear how essential those modifications are to maintain AML development. Basic studies and clinical trials have been suggesting that disturbing specific cells and molecules into the BM niches might be able to impair leukemia competencies. Either through niche-specific molecule inhibition alone or in combination with more traditional drugs, the bone marrow microenvironment is currently considered the potential target for new strategies to treat AML patients. This review describes the cellular and molecular constitution of the BM niches under healthy and AML conditions, presenting this anatomical compartment by a new perspective: as a prospective target for current and next generation therapies.
| S-EPMC8639599 | biostudies-literature
Project description:Despite the advances in intensive chemotherapy regimens and targeted therapies, overall survival (OS) of acute myeloid leukemia (AML) remains unfavorable due to inevitable chemotherapy resistance and high relapse rate, which mainly caused by the persistence existence of leukemia stem cells (LSCs). Bone marrow microenvironment (BMM), the home of hematopoiesis, has been considered to play a crucial role in both hematopoiesis and leukemogenesis. When interrupted by the AML cells, a malignant BMM formed and thus provided a refuge for LSCs and protecting them from the cytotoxic effects of chemotherapy. In this review, we summarized the alterations in the bidirectional interplay between hematopoietic cells and BMM in the normal/AML hematopoietic environment, and pointed out the key role of these alterations in pathogenesis and chemotherapy resistance of AML. Finally, we focused on the current potential BMM-targeted strategies together with future prospects and challenges. Accordingly, while further research is necessary to elucidate the underlying mechanisms behind LSC-BMM interaction, targeting the interaction is perceived as a potential therapeutic strategy to eradicate LSCs and ultimately improve the outcome of AML.
| S-EPMC8272391 | biostudies-literature
Project description:Label-free proteomics on AML cells from mice (C1498), compared to mononuclear cells isolated from long bones of C57BL/6J mice.
2024-06-02 | PXD042672 | JPOST Repository