WBC-Net: A white blood cell segmentation network based on UNet++ and ResNet

Lu, Yan; Qin, Xuejun; Fan, Haoyi; Lai, Taotao; Li, Zuoyong

doi:10.1016/j.asoc.2020.107006

Cited by 73 publications

(33 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, IoU increased by 0.62%, dice score by 0.07% and accuracy by 0.35%. As per the results in Table 2, Lu et al [15] segmented WBCs using UNet++ and ResNet34, and it outperformed our suggested model in terms of IoU score. Hence, the same model was used to cross-verify the results on our dataset too.…”

Section: Ablation Studysupporting

confidence: 68%

See 1 more Smart Citation

LeukoSegmenter: A Double Encoder-decoder Based Network for Leukocyte Segmentation From Blood Smear Images

Dhalla

Mittal

Gupta

2021

Preprint

View full text Add to dashboard Cite

Segmentation of blood cells is a prerequisite step in automated morphological analysis of blood smear images, cell count determination and diagnosis of various diseases such as leukemia. It is extremely challenging due to different sizes, shapes, morphological characteristics and overlapping of blood cells. Due to its complicated nature, it is generally performed as a sequence of steps. However, sequential segmentation results in restricted accuracy due to cascading of errors that creep during each stage. On the contrary, pixel-wise segmentation of blood cells is a single step task and gives promising results. In this paper, we propose LeukoSegmenter, a double encoder-decoder for precise pixel-wise segmentation of leukocytes from blood smear images. It uses pre-trained ResNet18 based encoders and U-Net based decoders. Feature maps obtained from the first network are utilised as attention maps. These are used as input in conjunction with the original 3-channel image to obtain final mask from the second network. This mechanism allows the latter encoder-decoder pair to focus explicitly on leukocytes and ignore other blood cells and debris, thus improving the segmentation accuracy. Experiments on ALL-IDB1 dataset show that the proposed LeukoSegmenter achieves intersection-over-union score of 94.6827% and Dice score of 97.1987% which is superior than that of state-of-the-art methods.

show abstract

Section: Ablation Studysupporting

confidence: 68%

“…Thus, UNet prevents loss of any information and is specifically designed for medical images. Lu et al [15] used a combination of UNet++, a variant of UNet with multi-skip connections, and ResNet50 to segment WBCs from the background using four types of datasets. The mean IoU value obtained for all the datasets is above 90%.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

LeukoSegmenter: A Double Encoder-decoder Based Network for Leukocyte Segmentation From Blood Smear Images

Dhalla

Mittal

Gupta

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the presence of dyeing impurities and cytoplasm with low image contrast makes the microscopical differences between WBC more challenging to distinguish [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

WBC-AMNet: Automatic classification of WBC images using deep feature fusion network based on focalized attention mechanism

Wang

Xiao

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

The recognition and classification of White Blood Cell (WBC) play a remarkable role in blood-related diseases (i.e., leukemia, infections) diagnosis. For the highly similar morphology of different WBC subtypes, it is too confused to classify the WBC effectively and accurately for visual observation of blood cell smears. This paper proposes a Deep Convolutional Neural Network (DCNN) with feature fusion strategies, named WBC-AMNet, for automatically classifying WBC subtypes based on focalized attention mechanism. To obtain more localized attention of CNN, the fusion features of the first and the last convolutional layer are extracted by focalized attention mechanism combining Squeeze-and-Excitation (SE) and Gather-Excite (GE) modules. The new method performs successfully in classifying monocytes, neutrophils, lymphocytes, and eosinophils on the complex background with an overall accuracy of 95.66%, better than that of general CNNs. The multi-classification accuracy of WBC-AMNet with the background segmentation is over 98% in all cases. In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to visualize the attention heatmaps of different feature maps.

show abstract

“…However, the traditional detection models usually have low efficiency for MAs detection, owing to MAs are relatively small circular structure in FFA image. Some models based on neural network did not achieve better detection for MAs, such as GoogleNet [7] and ResNet [8], only learn higher-level features from the features of the upper layer forward, and then give up the features of the lower layer after abstracting them. These neural networks do not make full use of the characteristic information of the context, which led to the problem of false detection for small target.…”

Section: Introductionmentioning

confidence: 99%

An Automatic Detection Model of Microaneurysms Based on Improved FC-Densenet

Wang¹,

Yao²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a common eye disease, which leads cause of blindness all around the world. Microaneurysms (MAs) is one of the early symptoms of DR. Accurate and effective MAs detection and segmentation is an important step for the diagnosis and treatment of DR. In this paper, we propose an automatic model for detection of MAs in fluorescein fundus angiography (FFA) images. The model mainly consists of two steps. The first step is pre-processing of FFA images, where the quality of FFA images is improved by Histogram Stretching and Gaussian Filtering algorithm. The second step is to detect MAs regions, where the MAs regions are detected by improved FC-DenseNet. We compare the proposed model with traditional FC-DenseNet model and other previously published models. The experimental result shows that our proposed model has the highest scores on evaluation metrics of pixel accuracy (PA), mean pixel accuracy (MPA), precision (Pre), recall (Re), F1-score (F1) and mean intersection over union (MIoU), which are 99.97%, 94.19%, 88.40%, 89.70%, 88.98% and 90.14%, respectively. The result suggests that the performance of our proposed model is closer to the ground truth of MAs detection. Our proposed model would be helpful for ophthalmologists to find the symptoms more quickly and to take better treatment measures in the screening process of diabetic retinopathy.

show abstract

WBC-Net: A white blood cell segmentation network based on UNet++ and ResNet

Cited by 73 publications

References 30 publications

LeukoSegmenter: A Double Encoder-decoder Based Network for Leukocyte Segmentation From Blood Smear Images

LeukoSegmenter: A Double Encoder-decoder Based Network for Leukocyte Segmentation From Blood Smear Images

WBC-AMNet: Automatic classification of WBC images using deep feature fusion network based on focalized attention mechanism

An Automatic Detection Model of Microaneurysms Based on Improved FC-Densenet

Contact Info

Product

Resources

About