Automatic detection and characterization of quantitative phase images of thalassemic red blood cells using a mask region-based convolutional neural network

Lin, Yang-Hsien; Liao, Ken Ying-Kai; Sung, Kung-Bin

doi:10.1117/1.jbo.25.11.116502

Cited by 22 publications

(10 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Doan et al 38 trained a deep learning model to classify unlabeled images of stored RBCs into seven morpho-types with 76.7% accuracy, which was comparable to 82.5% agreement in manual classification by experts. Other studies trained deep learning models to identify RBCs from patients with malaria, [39][40][41][42][43][44] sickle cell disease, [45][46][47][48][49][50] and thalassemia, [51][52][53] based on visually identifiable changes in RBC morphology. Our application of machine learning in RBC deformability measurement deviates from these previous efforts because cellular features corresponding to deformability are beyond human perception.…”

Section: Discussionmentioning

confidence: 99%

“…36,37 In fact, deep learning methods have been developed to assess changes in RBC morphology during cold storage, 38 malaria, [39][40][41][42][43][44] sickle cell disease, [45][46][47][48][49][50] and thalassemia. [51][52][53] However, RBC morphology varies over the life cycle of the cell and this variability may obscure efforts to infer deformability from cell morphology. Furthermore, no specific morphological features can be directly attributed to predictable changes in RBC deformability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Image Classification of Red Blood Cell Deformability

Lamoureux

Islamzada

Wiens

et al. 2021

Preprint

View full text Add to dashboard Cite

Red blood cells (RBCs) must be highly deformable to transit through the microvasculature to deliver oxygen to tissues. The loss of RBC deformability resulting from pathology, natural aging, or storage in blood bags can impede the proper function of these cells. A variety of methods have been developed to measure RBC deformability, but these methods require specialized equipment, long measurement time, and highly skilled personnel. To address this challenge, we investigated whether a machine learning approach could be applied to determine donor RBC deformability using single cell microscope images. We used the microfluidic ratchet device to sort RBCs based on deformability. Sorted cells are then imaged and used to train a deep learning model to classify RBCs based on deformability. This model correctly predicted deformability of individual RBCs with 84 ± 11% accuracy averaged across ten donors. Using this model to score the deformability of RBC samples were accurate to within 4.4 ± 2.5% of the value obtained using the microfluidic ratchet device. While machine learning methods are frequently developed to automate human image analysis, our study is remarkable in showing that deep learning of single cell microscopy images could be used to measure RBC deformability, a property not normally measurable by imaging. Measuring RBC deformability by imaging is also desirable because it can be performed rapidly using a standard microscopy system, potentially enabling RBC deformability studies to be performed as part of routine clinical assessments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Learning Image Classification of Red Blood Cell Deformability

Lamoureux

Islamzada

Wiens

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…They divided RBCs into nine categories and achieved an accuracy of 98.5%. Lin et al ( 28 ) used FPN-ResNet-101 and Mask RCNN to classify two types of RBCs (hRBCs and tRBCs) in quantitative phase images, with an accuracy of 97%.…”

Section: Introductionmentioning

confidence: 99%

Red Blood Cell Classification Based on Attention Residual Feature Pyramid Network

et al. 2021

View full text Add to dashboard Cite

Clinically, red blood cell abnormalities are closely related to tumor diseases, red blood cell diseases, internal medicine, and other diseases. Red blood cell classification is the key to detecting red blood cell abnormalities. Traditional red blood cell classification is done manually by doctors, which requires a lot of manpower produces subjective results. This paper proposes an Attention-based Residual Feature Pyramid Network (ARFPN) to classify 14 types of red blood cells to assist the diagnosis of related diseases. The model performs classification directly on the entire red blood cell image. Meanwhile, a spatial attention mechanism and channel attention mechanism are combined with residual units to improve the expression of category-related features and achieve accurate extraction of features. Besides, the RoI align method is used to reduce the loss of spatial symmetry and improve classification accuracy. Five hundred and eighty eight red blood cell images are used to train and verify the effectiveness of the proposed method. The Channel Attention Residual Feature Pyramid Network (C-ARFPN) model achieves an mAP of 86%; the Channel and Spatial Attention Residual Feature Pyramid Network (CS-ARFPN) model achieves an mAP of 86.9%. The experimental results indicate that our method can classify more red blood cell types and better adapt to the needs of doctors, thus reducing the doctor's time and improving the diagnosis efficiency.

show abstract

“…Furthermore, specific deep learning approaches have also been proposed for complex cell analysis of QPI data. Mask region-based convolution neural (Mask R-CNN [15]) network was used in two recent papers [16] [17]. A U-Net architecture [9] was also applied to QPI images, for instance, Yi et al [18] applied U-Net to red blood cell segmentation directly on hologram images to avoid the image reconstruction part.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Pretraining for Transferable Quantitative Phase Image Cell Segmentation

Vičar

Chmelík

Jakubíček

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, U-Net-based method for robust adherent cell segmentation for quantitative phase microscopy image is designed and optimised. We designed and evaluated four specific post-processing pipelines. To increase the transferability to different cell types, non-deep learning transfer with adjustable parameters is used in the post-processing step. Additionally, we proposed a self-supervised pretraining technique using nonlabelled data, which is trained to reconstruct multiple image distortions and improved the segmentation performance by from 0.67 to 0.70 of Object-wise Intersection over Union. Moreover, we publish a new dataset of manually labelled images suitable for this task together with the unlabelled data for self-supervised pretraining.

show abstract

Automatic detection and characterization of quantitative phase images of thalassemic red blood cells using a mask region-based convolutional neural network

Cited by 22 publications

References 59 publications

Deep Learning Image Classification of Red Blood Cell Deformability

Deep Learning Image Classification of Red Blood Cell Deformability

Red Blood Cell Classification Based on Attention Residual Feature Pyramid Network

Self-Supervised Pretraining for Transferable Quantitative Phase Image Cell Segmentation

Contact Info

Product

Resources

About