Analyzing Microscopic Images of Peripheral Blood Smear Using Deep Learning

Mundhra, Dheeraj; Cheluvaraju, Bharath; Rampure, Jaiprasad; Dastidar, Tathagato Rai

doi:10.1007/978-3-319-67558-9_21

Cited by 24 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equivocal diagnosis with use of SR is demonstrated using a commercially available artificial intelligence (AI) digital pathology system 2 [13] for inferring with the Sigtuple WBC Dataset with its results presented in Table 2. This justifies role of T 1(·) and T 2(·) in restoring texture of diagnostic importance beyond what can be achieved using simple interpolation on learning a SRNet without rVTT adversarial framework.…”

Section: Experiments Results and Discussionmentioning

confidence: 99%

Learning A Deep Convolution Network with Turing Test Adversaries for Microscopy Image Super Resolution

Tom

Sharma²,

Mundhra³

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

Self Cite

View full text Add to dashboard Cite

Adversarially trained deep neural networks have significantly improved performance of single image super resolution, by hallucinating photorealistic local textures, thereby greatly reducing the perception difference between a real high resolution image and its super resolved (SR) counterpart. However, application to medical imaging requires preservation of diagnostically relevant features while refraining from introducing any diagnostically confusing artifacts. We propose using a deep convolutional super resolution network (SRNet) trained for (i) minimising reconstruction loss between the real and SR images, and (ii) maximally confusing learned relativistic visual Turing test (rVTT) networks to discriminate between (a) pair of real and SR images (T1) and (b) pair of patches in real and SR selected from region of interest (T2). The adversarial loss of T1 and T2 while backpropagated through SRNet helps it learn to reconstruct pathorealism in the regions of interest such as white blood cells (WBC) in peripheral blood smears or epithelial cells in histopathology of cancerous biopsy tissues, which are experimentally demonstrated here. Experiments performed for measuring signal distortion loss using peak signal to noise ratio (pSNR) and structural similarity (SSIM) with variation of SR scale factors, impact of rVTT adversarial losses, and impact on reporting using SR on a commercially available artificial intelligence (AI) digital pathology system substantiate our claims.

show abstract

Section: Experiments Results and Discussionmentioning

confidence: 99%

Learning A Deep Convolution Network with Turing Test Adversaries for Microscopy Image Super Resolution

Tom

Sharma²,

Mundhra³

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, the complexity of preparing a balanced dataset of blood smears comes from its natural structure; each blood smear contains hundreds of blood cells from different types, which are naturally distributed in an imbalanced manner. In [3], the authors demonstrated that RBCs occurred approximately seven times more than WBCs in the training set. This challenge implies that traditional augmentation techniques might not help as it will only amplify the imbalance issue.…”

Section: Motivationmentioning

confidence: 99%

“…The target of PBS analysis is to classify the categories in the blood cell subtypes column. This has been automated in the literature either by one step approaches [7] or multi-step pipelines [8]. Hence, in this study both approaches will be taken into consideration, and two sets of annotations will be automatically composed during image constructions:…”

Section: Motivationmentioning

confidence: 99%

Synthetic Blood Smears Generation Using Locality Sensitive Hashing and Deep Neural Networks

Al-qudah

Suen

2020

IEEE Access

View full text Add to dashboard Cite

Peripheral Blood Smear (PBS) analysis is a vital routine test carried out by hematologists to assess some aspects of humans' health status. PBS analysis is prone to human errors and utilizing computerbased analysis can greatly enhance this process in terms of accuracy and cost. Recent approaches in learning algorithms, such as deep learning, are data hungry, but due to the scarcity of labeled medical images, researchers had to find viable alternative solutions to increase the size of available datasets. Synthetic datasets provide a promising solution to data scarcity, however, the complexity of blood smears' natural structure adds an extra layer of challenge to its synthesizing process. In this work, we propose a methodology that utilizes Locality Sensitive Hashing (LSH) to create a novel balanced dataset of 2500 synthetic blood smears. This dataset, which was automatically annotated during the generation phase, will be made public for research purposes and covers 17 essential categories of blood cells. We proved the effectiveness of the proposed dataset by utilizing it for training a deep neural network, this model got a very high accuracy score of 98.72% when tested with the well known ALL-IDB dataset. The dataset also got the approval of 5 experienced hematologists to meet the general standards of making thin blood smears .

show abstract

“…When real data are not sufficient, it is possible to generate augmented data by data augmentation techniques such as reflection, translation, rotation, etc. Using DNNs for image segmentation in computed topography (CT) [1,2], magnetic resonance (MR) [3][4][5] or X-ray [6,7] images has become standard, while promising results are being obtained with DL in microscopy [8][9][10][11][12][13] and electron microscopy [14][15][16][17][18]. Furthermore, DNNs are successfully implemented for nucleus segmentation [19][20][21][22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Mathematical Modelling of Ground Truth Image for 3D Microscopic Objects Using Cascade of Convolutional Neural Networks Optimized with Parameters’ Combinations Generators

et al. 2020

View full text Add to dashboard Cite

Mathematical modelling to compute ground truth from 3D images is an area of research that can strongly benefit from machine learning methods. Deep neural networks (DNNs) are state-of-the-art methods design for solving these kinds of difficulties. Convolutional neural networks (CNNs), as one class of DNNs, can overcome special requirements of quantitative analysis especially when image segmentation is needed. This article presents a system that uses a cascade of CNNs with symmetric blocks of layers in chain, dedicated to 3D image segmentation from microscopic images of 3D nuclei. The system is designed through eight experiments that differ in following aspects: number of training slices and 3D samples for training, usage of pre-trained CNNs and number of slices and 3D samples for validation. CNNs parameters are optimized using linear, brute force, and random combinatorics, followed by voter and median operations. Data augmentation techniques such as reflection, translation and rotation are used in order to produce sufficient training set for CNNs. Optimal CNN parameters are reached by defining 11 standard and two proposed metrics. Finally, benchmarking demonstrates that CNNs improve segmentation accuracy, reliability and increased annotation accuracy, confirming the relevance of CNNs to generate high-throughput mathematical ground truth 3D images.

show abstract

Analyzing Microscopic Images of Peripheral Blood Smear Using Deep Learning

Cited by 24 publications

References 8 publications

Learning A Deep Convolution Network with Turing Test Adversaries for Microscopy Image Super Resolution

Learning A Deep Convolution Network with Turing Test Adversaries for Microscopy Image Super Resolution

Synthetic Blood Smears Generation Using Locality Sensitive Hashing and Deep Neural Networks

Mathematical Modelling of Ground Truth Image for 3D Microscopic Objects Using Cascade of Convolutional Neural Networks Optimized with Parameters’ Combinations Generators

Contact Info

Product

Resources

About