A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA

Abstract

Detection of dysmorphic cells in peripheral blood (PB) smears is essential in diagnostic screening of hematological diseases. Myelodysplastic syndromes (MDS) are hematopoietic neoplasms characterized by dysplastic and ineffective hematopoiesis, which diagnosis is mainly based on morphological findings of PB and bone marrow. We developed an automated diagnostic support system of MDS by combining an automated blood cell image-recognition system using a deep learning system (DLS) powered by convolutional neural networks (CNNs) with a decision-making system using extreme gradient boosting (XGBoost). The DLS of blood cell image-recognition has been trained using datasets consisting of 695,030 blood cell images taken from 3,261 PB smears including hematopoietic malignancies. The DLS simultaneously classified 17 blood cell types and 97 morphological features of such cells with >93.5% sensitivity and >96.0% specificity. The automated MDS diagnostic system successfully differentiated MDS from aplastic anemia (AA) with high accuracy; 96.2% of sensitivity and 100% of specificity (AUC 0.990). This is the first CNN-based automated initial diagnostic system for MDS using PB smears, which is applicable to develop new automated diagnostic systems for various hematological disorders.

Artificial intelligence–based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients

“…This compliments other novel AI strategies aimed at utilizing mutational and peripheral blood data for more accurate MPN diagnosis, 30 along with improved interpretation of peripheral blood/bone marrow smear preparations. [31][32][33][34] Secondly, a comprehensive and easily interpreted summary of the megakaryocytic population will enable the pathologist to concentrate on the "higher-level" process of integrating the broader pathological features with the clinical and laboratory findings. Thirdly, this approach is ideally suited for more accurate assessment of sequential specimens from patients undergoing treatment and/or repeated investigation, in whom quantitative morphological correlates of disease response are currently unavailable.…”

Automated diagnostic support system with deep learning algorithms for distinction of Philadelphia chromosome-negative myeloproliferative neoplasms using peripheral blood specimen

“…Image analyses. To perform analyses of the cell images, we employed the CNN-based automatic imagerecognition system that we recently developed 10 . Briefly, the deep learning system (DLS) was trained using a .…”

“…SHAP values close to 1 denote high likelihood, whereas those close to -1 denote less likelihood. https://doi.org/10.1038/s41598-021-82826-9www.nature.com/scientificreports/ total of 695,030 normal and abnormal cell images, and we could accurately classify 17 cell subtypes and detect 97 abnormal morphological features10 . The neural network was composed of two modules: the first module consisting of series of neural networks layers such as 2 dimensional Separative convolutional neural-network (CNN) based "image extractor" module, and the second module consisting of the layers connected to the output module.…”

“…In order to reduce the workload and inter-and intra-personal inconsistency, we previously developed an automated image analysis system using deep convolutional neural networks (CNNs) based-image analysis algorithms using a total of 695,030 normal and abnormal blood cells. Using the system, we could differentiate myelodysplastic syndrome (MDS) and aplastic anemia with high accuracy compared to human diagnoses 8 .…”

Automatic quantification of lymphocyte vacuolization in peripheral blood smears of patients with Batten's disease (CLN3 disease)

“…Machine learning methods like convolutional neural networks (CNNs) have proven to be quite successful in detecting image features and could potentially be utilized to automate (aspects of) PB analyses. Indeed, CNNs have been used to differentiate between leukocytes, 3 and to detect myelodysplastic syndromes in PBSs 4 . In this study, we present an automated pipeline based on CNNs that enabled us to successfully detect and quantify lymphocyte vacuolization as observed in PBSs of CLN3 disease patients.…”