Leukemia is a fatal disease of white blood cells which affects the blood and bone marrow in human body. We deployed deep convolutional neural network for automated detection of acute lymphoblastic leukemia and classification of its subtypes into 4 classes, that is, L1, L2, L3, and Normal which were mostly neglected in previous literature. In contrary to the training from scratch, we deployed pretrained AlexNet which was fine-tuned on our data set. Last layers of the pretrained network were replaced with new layers which can classify the input images into 4 classes. To reduce overtraining, data augmentation technique was used. We also compared the data sets with different color models to check the performance over different color images. For acute lymphoblastic leukemia detection, we achieved a sensitivity of 100%, specificity of 98.11%, and accuracy of 99.50%; and for acute lymphoblastic leukemia subtype classification the sensitivity was 96.74%, specificity was 99.03%, and accuracy was 96.06%. Unlike the standard methods, our proposed method was able to achieve high accuracy without any need of microscopic image segmentation.

https://journals.sagepub.com/doi/pdf/10.1177/1533033818802789

Acute Lymphoblastic Leukemia Detection and Classification of Its Subtypes Using Pretrained Deep Convolutional Neural Networks.

The detection and classification of white blood cells (WBCs, also known as Leukocytes) is a hot issue because of its important applications in disease diagnosis. Nowadays the morphological analysis of blood cells is operated manually by skilled operators, which results in some drawbacks such as slowness of the analysis, a non-standard accuracy, and the dependence on the operator’s skills. Although there have been many papers studying the detection of WBCs or classification of WBCs independently, few papers consider them together. This paper proposes an automatic detection and classification system for WBCs from peripheral blood images. It firstly proposes an algorithm to detect WBCs from the microscope images based on the simple relation of colors R, B and morphological operation. Then a granularity feature (pairwise rotation invariant co-occurrence local binary pattern, PRICoLBP feature) and SVM are applied to classify eosinophil and basophil from other WBCs firstly. Lastly, convolution neural networks are used to extract features in high level from WBCs automatically, and a random forest is applied to these features to recognize the other three kinds of WBCs: neutrophil, monocyte and lymphocyte. Some detection experiments on Cellavison database and ALL-IDB database show that our proposed detection method has better effect almost than iterative threshold method with less cost time, and some classification experiments show that our proposed classification method has better accuracy almost than some other methods.

Automatic detection and classification of leukocytes using convolutional neural networks

Computer assisted classification framework for prediction of acute lymphoblastic and acute myeloblastic leukemia

Mutual Information based hybrid model and deep learning for Acute Lymphocytic Leukemia detection in single cell blood smear images.

Acute lymphoblastic leukemia segmentation using local pixel information

We propose a dual-threshold method based on a strategic combination of RGB and HSV color space for white blood cell (WBC) segmentation. The proposed method consists of three main parts: preprocessing, threshold segmentation, and postprocessing. In the preprocessing part, we get two images for further processing: one contrast-stretched gray image and one H component image from transformed HSV color space. In the threshold segmentation part, a dual-threshold method is proposed for improving the conventional single-threshold approaches and a golden section search method is used for determining the optimal thresholds. For the postprocessing part, mathematical morphology and median filtering are utilized to denoise and remove incomplete WBCs. The proposed method was tested in segmenting the lymphoblasts on a public Acute Lymphoblastic Leukemia (ALL) image dataset. The results show that the performance of the proposed method is better than single-threshold approach independently performed in RGB and HSV color space and the overall single WBC segmentation accuracy reaches 97.85%, showing a good prospect in subsequent lymphoblast classification and ALL diagnosis.

/pdf/segmentation-of-white-blood-cell-from-acute-lymphoblastic-19z1tkb4f5.pdf

Segmentation of White Blood Cell from Acute Lymphoblastic Leukemia Images Using Dual-Threshold Method

The utility model relates to a virtual display helmet capable of being controlled by eyes. The virtual display helmet capable of being controlled by eyes comprises a virtual reality display helmet, a handle sensor and an eye control unit. The virtual reality display helmet is provided with a detachable image display unit. The handle sensor is used for controlling position movement and a displacement distance of a view point in a panoramic map displayed in the image display unit. A user can tourist in a virtual way at home by using the virtual display helmet capable of being controlled by eyes.

Virtual display helmet capable of being controlled by eyes

The invention relates to an identification method and a prompting system for depth of a vein blood vessel. The identification method and the prompting system solve the problem that judgment of the depth of the blood vessel cannot be carried out in the prior art. The identification method and the prompting system have the advantages that a mapping relationship between the image mode and the depth of the blood vessel is established by a machine learning regression module in machine visual learning according to the image of the vein blood vessel, so the depth of the blood vessel is automatically identified on the basis of images; the information of the depth of the blood vessel is prompted by voice and projection, and a medical staff can position the blood vessel, and can also determine the depth of the blood vessel, so the needle entry angle is accurately controlled, the success rate of vein puncturing is improved, and the pain of a patient due to the vein puncturing is reduced.

Identification method and prompting system for depth of vein blood vessel

The utility model relates to an audio -visual player of wear -type 3D based on aspect sensor. Including the virtual demonstration helmet, still including setting up the dismantled image display unit and speech control unit on the virtual demonstration helmet, the image display unit includes display screen, aspect sensor and is used for receiving speech control unit signals's receiver, the speech control unit includes pronunciation receiving element, is used for to judge the speech recognition unit and the signal transmitter of pronunciation order, the signal control display screen of image display unit through receiving the transmission of speech control unit signal transmitter opening and closing, the image display unit passes through the receiver with the speech control unit and is connected with signal transmitter. The utility model provides a convenient to use can at will adjust the audio -visual player of the wear -type 3D who watches the picture.

Cao Yihui

Papers

Segmentation of White Blood Cell from Acute Lymphoblastic Leukemia Images Using Dual-Threshold Method

Virtual display helmet capable of being controlled by eyes

Identification method and prompting system for depth of vein blood vessel

Audio -visual player of wear -type 3D based on aspect sensor