Deep learning approach to peripheral leukocyte recognition

Abstract

Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once . To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.

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.…”

Obtaining Deep Learning Models for Automatic Classification of Leukocytes

“…Other architectures are one-stage and fully integrate detection and classification: e.g., You Only Look Once (YOLO) , YOLOv2 , YOLOv3 and Single Shot Multibox Detector (SSD) (Liu et al, 2020). Wang et al used SSD and YOLOv3 models for the detection and classification of leukocytes, reaching a mean average precision of 93% (Wang et al, 2019). This value is noteworthy since this work shows the classification of eleven types of leukocytes, while most works use the five base leukocytes.…”

Artificial Intelligence and Digital Microscopy Applications in Diagnostic Hematopathology

“…Moreover, the precision of detection was better for the blasts and mature white blood cells compared to the immature types, the accuracies being 97%, almost 100%, and 87%, respectively. In terms of inference time, YOLOv3 achieved outstanding outcomes, as the inference time was 14 ms per image compared to 53 ms per image for the SSD pipeline [30].…”