Friday, September 29, 2023

High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system – Scientific Reports

Highly accurate classification of BM nucleated cells by Morphogo system

The high-resolution digital images of BM nucleated cells from the ROI were acquired using the Morphogo system. These cell images were categorized into 25 categories (Fig. 3). Cell classification results predicted by the Morphogo system and annotated by pathologists were shown in a confusion matrix (Fig. 2). The dataset consisted of 385,207 single-cell images. The row displayed cell classification results from the Morphogo system, and the column showed results from pathologists’ proofreading. The dark blue pane located diagonally illustrated the number of nucleated cells classified by the Morphogo system which were entirely consistent with pathologists’ proofreading. The white pane represented cells that were classified as different types by the Morphogo system and pathologists proofreading. Cell numbers shown in light blue panes represented cells that were easily confused either between different maturing stages within the same lineage or between morphologically related cell types, so their misclassification was considered tolerable.

Figure 3

Sample images of BM cells classified by Morphogo.

To evaluate the cell classification performance of the Morphogo system under different pathological conditions, the Morphogo system was applied to patient cases with more than 14 types of hematological diseases. The evaluation indicators were calculated for each disease condition and are shown in Table 3. The sensitivity in the classification of BM nucleated cells by the Morphogo system was an average value of 80.95%. The Morphogo system exhibited a sensitivity of more than 95% in the identification of 9 categories of BM nucleated cells. For specificity, the test sample yielded an average of 99.48% for all classes of BM nucleated cells. The value of PPV varied greatly in different classes of BM nucleated cells, ranging from 30.45% to 99.69%, with an average value of 76.49%. The Morphogo system showed a more than 95% PPV value among Neutrophilic metamyelocytes, Band neutrophils, Segmented neutrophils, Intermediate erythroblasts, Monocytes, and others. The average value of the NPV was more than 99%, ranging from 95.43 to 100.00%. And the NPVs of eosinophilic metamyelocyte, band eosinophil, and plasmablast ahead of the other cells have a value of 100.00%. The Morphogo system performed a high accuracy in the classification of BM nucleated cells by 95.55–99.98%, with an average value of 99.01%. Therefore, the results of our study showed that the Morphogo system had high sensitivity, specificity, PPV, NPV, and accuracy in the classification and counting of BM nucleated cells.

Table 3 Performance of Morphogo system to classify BM nucleated cells.

Morphogo system was in substantial agreement with pathologists’ proofreading in the identification of BM nucleated cells

To better understand the agreement of BM nucleated cells between the Morphogo system and pathologists proofreading, we performed the correlation analysis and consistency analysis between the Morphogo system and pathologists proofreading in the classification and counting of BM nucleated cells. The results were shown in Fig. 4. Morphogo system showed positive correlation between pathologists and Morphogo system in the classification of myeloblast (r = 0.6009, Fig. 4A), promyelocyte (r = 0.8008, Fig. 4B), neutrophilic myelocyte (r = 0.8912, Fig. 4C), neutrophilic metamyelocyte (r = 0.8954, Fig. 4D), band neutrophil (r = 0.9923, Fig. 4E), segmented neutrophil (r = 0.9982, Fig. 4F), eosinophilic myelocyte (r = 0.8039, Fig. 4G), eosinophilic metamyelocyte (r = 0.8691, Fig. 4H), band eosinophil (r = 0.8134, Fig. 4I), segmented eosinophil (r = 0.9878, Fig. 4J), basophil (r = 0.9204, Fig. 4K), proerythroblast (r = 0.6903, Fig. 4L), early erythroblast (r = 0.8878, Fig. 4M), intermediate erythroblast (r = 0.9817, Fig. 4N), late erythroblast (r = 0.9930, Fig. 4O), lymphoblast (r = 0.7923, Fig. 4P), prolymphocyte (r = 0.7724, Fig. 4Q), mature lymphocyte (r = 0.7785, Fig. 4R), monoblast (r = 0.7071, Fig. 4S), promonocyte (r = 0.2038, Fig. 4T), monocyte (r = 0.9489, Fig. 4U), plasmablast (r = 0.9985, Fig. 4V), immature plasma cell (r = 0.5702, Fig. 4W), plasma cell (r = 0.9963, Fig. 4X) and others (r = 0.9695, Fig. 4Y), the P values of these 25 classes of BM nucleated cells were less than 0.001.

Figure 4
figure 4

The correlation analysis of Morphogo pre-classification and pathologists’ proofreading. (A)–(Y) shows the scatter plot of linear regression lines of the percentage of BM cells after paired counting of BM smears in 508 patients.

It was shown that the cell classification results of the Morphogo system were in general agreement with that of pathologists proofreading in the identification of BM nucleated cells, as evidenced by kappa value (0.461–0.987), except for promonocytes (Table 4). The Morphogo system exhibited almost perfect agreement with pathologists’ proofreading in the classification of neutrophilic metamyelocyte, band neutrophil, segmented neutrophil, eosinophilic myelocyte, eosinophilic metamyelocyte, band eosinophil, segmented eosinophil, basophil, early erythroblast, intermediate erythroblast, late erythroblast, mature lymphocyte, monocyte, plasmablast, plasma cell, and others, with the kappa value of more than 0.813. However, the classification of myeloblast, promyelocyte, lymphoblast, prolymphocyte, monoblast, and immature plasma showed only moderate agreement between the Morphogo system and pathologists’ proofreading, with Kappa value from 0.461 to 0.566. Overall, correlation and consistency results collectively supported that the Morphogo system maintained a substantial agreement with pathologists’ proofreading in identifying BM nucleated cells.

Table 4 Evaluation of the consistency between Morphogo pre-classification and pathologists’ proofreading of BM cells using the Cohen kappa coefficient.

The Morphogo system has high application value in the diagnosis of hematological diseases

To further verify the application value of the Morphogo system in the diagnosis of hematological diseases, the diagnoses made based on the Morphogo system were compared to the pathologists proofreading. The evaluation was made for each sample group (G1–G5) in terms of intraclass correlation coefficient (ICC) and 95% CI. As shown in Table 5, except for the progenitors, ICC between the two different methods was high for granulocytes, erythrocytes, lymphocytes, monocytes, and plasma cells in the G1, G2, G3, and G5 groups (ICC ≥ 0.818, P < 0.01), and slightly lower for G4. Based on these results, the diagnosis results of the Morphogo system for most hematological diseases should be correct.

Table 5 Correlation analysis between Morphogo and manual proofreading among 5 groups (ICC and 95% CI).

The Morphogo system automatically records the time it takes to scan BM smears and identify BM cells

Morphogo system can complete automatic scanning continuously, and efficiently, with a success rate of 99.4%. The average time of a single slide scan is 7:46 (min), and most of the slide scanning time is concentrated in 5–9 min. The Morphogo system takes 7.46 ± 0.002 min/sheet to identify and count BM cells (Table 6). These results suggest that the Morphogo system can assist in the artificial diagnosis of hematologic diseases, which greatly saves time.

Table 6 The time required for Morphogo to scan a digital BM slide and count 600 nucleated cells.

Source link

Related Articles

Leave a Reply

Stay Connected

- Advertisement -spot_img

Latest Articles

%d bloggers like this: