ABSTRACT
Rare antinuclear antibody (ANA) pattern recognition has been a widely applied technology for routine ANA screening in clinical laboratories. In recent years, the application of deep learning methods in recognizing ANA patterns has witnessed remarkable advancements. However, the majority of studies in this field have primarily focused on the classification of the most common ANA patterns, while another subset has concentrated on the detection of mitotic metaphase cells. To date, no prior research has been specifically dedicated to the identification of rare ANA patterns. In the present paper, we introduce a novel attention-based enhancement framework, which was designed for the recognition of rare ANA patterns in ANA-indirect immunofluorescence images. More specifically, we selected the algorithm with the best performance as our target detection network by conducting comparative experiments. We then further developed and enhanced the chosen algorithm through a series of optimizations. Then, attention mechanism was introduced to facilitate neural networks in expediting the learning process, extracting more essential and distinctive features for the target features that belong to the specific patterns. The proposed approach has helped to obtained high precision rate of 86.40%, 82.75% recall, 84.24% F1 score and 84.64% mean average precision for a 9-category rare ANA pattern detection task on our dataset. Finally, we evaluated the potential of the model as medical technologist assistant and observed that the technologist's performance improved after referring to the results of the model prediction. These promising results highlighted its potential as an efficient and reliable tool to assist medical technologists in their clinical practice.
Subject(s)
Algorithms , Antibodies, Antinuclear , Fluorescent Antibody Technique, Indirect/methodsABSTRACT
@# Objective: To investigate the effect of down-regulation of miR-221 on cell proliferation and apoptosis of chronic myeloid leukemia (CML) K562 cells and its related regulatory mechanism. Methods: K562 cells were divided into control group, miRNAnegative control (miR-NC) group, miR-221 inhibitor group, miR-221 inhibitor+ negative control siRNA(NC siRNA) group and miR-221 inhibitor+SOCS3 siRNA group. The cells in the control group received no additional treatment. Cells in miR-NC group and miR-221 inhibitor group were transfected with miR-NC and miR-221 inhibitor, respectively. Cells in miR-221 inhibitor+NC siRNA group and miR-221 inhibitor+SOCS3 siRNA group were transfected with NC siRNA and SOCS3 siRNA, respectively, on the basis of successful transfection with miR-221 inhibitor. The transfection efficiency of miR-221 inhibitor was identified by qPCR. Cell viability in each group was measured by CCK-8 assay. Apoptosis in each group was detected by Annexin V-FITC/PI staining using a flow cytometry. The protein expressions of SOCS3, p-JAK1, p-JAK2, p-STAT3 and survivin in each group were detected by WB. Results: Compared with the control group, miR-221 expression was significantly down-regulated in miR-221 inhibitor group (P<0.01), cell viability was significantly reduced at 48 and 72 h after transfection (P<0.05 or P<0.01), the number of apoptotic cells was significantly increased (P< 0.01), the expression of SOCS3 was significantly increased (P<0.01) and the expression levels of p-JAK1, p-JAK2, p-STAT3 and survivin were significantly reduced (all P<0.01). Compared with miR-221 inhibitor group, cell viability was significantly increased at 24, 48 and 72 h after transfection (P<0.05 or P<0.01), the number of apoptotic cells was significantly decreased (P<0.01) and the expression levels of p-JAK1, p-JAK2, p-STAT3 and survivin were significantly increased in miR-221 inhibitor+SOCS3 siRNA group (all P< 0.01). Conclusion: Down-regulation of miR-221 inhibits proliferation and promotes apoptosis of K562 cells, the mechanism of which may be related with up-regulating SOCS3 expression to suppress JAK-STAT3 signaling pathway.
