A deep network designed for segmentation and classification of leukemia using fusion of the transfer learning models

Saleem, Saba; Amin, Javeria; Sharif, Muhammad; Anjum, Muhammad Almas; Iqbal, Muhammad Junaid; Wang, Shuihua

doi:10.1007/s40747-021-00473-z

Cited by 55 publications

(24 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [10] have learnt vehicle feature representations by perceiving attention from multi-perspectives of the vehicle. Many vehicle ReID models use additional annotations to obtain more robust features, and image segmentation [13,14] is one effective approach. For example, Meng et al [11] have introduced a parsing network to parse a vehicle into four different views.…”

Section: Introductionmentioning

confidence: 99%

Joint metric learning of local and global features for vehicle re-identification

Shen

Sun

Wang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Vehicle re-identification (ReID) means to identify the target vehicle in large-scale surveillance videos captured by multiple cameras, where robust and distinctive visual features of vehicles are critical to the performance. Recently, the researchers have approached the problem with attention based models. However, most of these models use strongly-supervised methods, which rely on expensive extra labels, e.g., keypoints(vehicle wheels , logo and lamps) and attributes(e.g., color and type). Therefore, we propose a joint metric learning approach to solve the problem. We present an end-to-end Partition and Fusion Multi-branch Network (PFMN), a novel approach to effectively learn discriminative features without any annotations or additional attributes. For hard samples, which means different vehicles with similar appearance or the same vehicle with different appearances, a novel variant of hard sampling triplet loss is proposed. Based on extensive experiments, we have proved the effectiveness of our proposed method. On the challenging public data sets VeRi-776 and VehicleID, our model outperforms most state-of-the-art algorithms on mAP and rank-1. Especially on mINP, which measures the cost of model retrieval hard samples, we can achieve a significant improvement.

show abstract

Section: Introductionmentioning

confidence: 99%

Joint metric learning of local and global features for vehicle re-identification

Shen

Sun

Wang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Table 4 compares the optimal proposed ALL detection CNN with recent leukemia diagnosis CAD systems in terms of the used methodology, use of optimization, used dataset, and classification accuracy. The proposed CNN records higher classification accuracy than the non-optimized models in [ 8 , 22 ] and the Naïve Bayes classifier in [ 44 ]. It records an equal classification accuracy as the Decision Tree classifier of [ 44 ].…”

Section: Resultsmentioning

confidence: 99%

“…The proposed CNN records higher classification accuracy than the non-optimized models in [ 8 , 22 ] and the Naïve Bayes classifier in [ 44 ]. It records an equal classification accuracy as the Decision Tree classifier of [ 44 ]. However, our Bayesian-based optimized CNN outperforms all optimized deep learning-based leukemia detectors in [ 53 , 54 , 55 , 56 ].…”

Section: Resultsmentioning

confidence: 99%

“…Pretrained CNNs have the capability to classify images efficiently through transfer learning. Transfer learning enables the classification of a specific dataset by fine-tuning the final layers of the pretrained CNN [ 44 , 45 ]. Shafique et al [ 46 ] created a technique for automatically diagnosing ALL and its three subtypes (L1, L2, and L3) using blood smear images.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

BO-ALLCNN: Bayesian-Based Optimized CNN for Acute Lymphoblastic Leukemia Detection in Microscopic Blood Smear Images

Atteia

Alhussan

2022

Sensors

View full text Add to dashboard Cite

Acute lymphoblastic leukemia (ALL) is a deadly cancer characterized by aberrant accumulation of immature lymphocytes in the blood or bone marrow. Effective treatment of ALL is strongly associated with the early diagnosis of the disease. Current practice for initial ALL diagnosis is performed through manual evaluation of stained blood smear microscopy images, which is a time-consuming and error-prone process. Deep learning-based human-centric biomedical diagnosis has recently emerged as a powerful tool for assisting physicians in making medical decisions. Therefore, numerous computer-aided diagnostic systems have been developed to autonomously identify ALL in blood images. In this study, a new Bayesian-based optimized convolutional neural network (CNN) is introduced for the detection of ALL in microscopic smear images. To promote classification performance, the architecture of the proposed CNN and its hyperparameters are customized to input data through the Bayesian optimization approach. The Bayesian optimization technique adopts an informed iterative procedure to search the hyperparameter space for the optimal set of network hyperparameters that minimizes an objective error function. The proposed CNN is trained and validated using a hybrid dataset which is formed by integrating two public ALL datasets. Data augmentation has been adopted to further supplement the hybrid image set to boost classification performance. The Bayesian search-derived optimal CNN model recorded an improved performance of image-based ALL classification on test set. The findings of this study reveal the superiority of the proposed Bayesian-optimized CNN over other optimized deep learning ALL classification models.

show abstract

“…In the study by Sell et al, the images were processed using three components of two-color spaces, CMYK and HSV, to produce new images for determining the most important features through principal component analysis to obtain WBC nuclei [16]. Saba et al introduced the deep learning (SDL) approach to leukocyte segmentation and classification in the pre-processing and segmentation steps and conducted optimization using a generative adversarial network through its normalization, followed by deep feature extraction with the DarkNet-53 and ShuffleNet models [17]. Pouria et al enhanced images to reduce the brightness when converting from RGB to HSV, and then applied fuzzy c-means to segment the cores and separate them from the rest of the image (the watershed transform method separates the link between the cores and the background and then extracts the most important geometric and statistical features) [18].…”

Section: Related Workmentioning

confidence: 99%

Multi-Method Diagnosis of Blood Microscopic Sample for Early Detection of Acute Lymphoblastic Leukemia Based on Deep Learning and Hybrid Techniques

Abunadi

Senan

2022

Sensors

View full text Add to dashboard Cite

Leukemia is one of the most dangerous types of malignancies affecting the bone marrow or blood in all age groups, both in children and adults. The most dangerous and deadly type of leukemia is acute lymphoblastic leukemia (ALL). It is diagnosed by hematologists and experts in blood and bone marrow samples using a high-quality microscope with a magnifying lens. Manual diagnosis, however, is considered slow and is limited by the differing opinions of experts and other factors. Thus, this work aimed to develop diagnostic systems for two Acute Lymphoblastic Leukemia Image Databases (ALL_IDB1 and ALL_IDB2) for the early detection of leukemia. All images were optimized before being introduced to the systems by two overlapping filters: the average and Laplacian filters. This study consists of three proposed systems as follows: the first consists of the artificial neural network (ANN), feed forward neural network (FFNN), and support vector machine (SVM), all of which are based on hybrid features extracted using Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM) and Fuzzy Color Histogram (FCH) methods. Both ANN and FFNN reached an accuracy of 100%, while SVM reached an accuracy of 98.11%. The second proposed system consists of the convolutional neural network (CNN) models: AlexNet, GoogleNet, and ResNet-18, based on the transfer learning method, in which deep feature maps were extracted and classified with high accuracy. All the models obtained promising results for the early detection of leukemia in both datasets, with an accuracy of 100% for the AlexNet, GoogleNet, and ResNet-18 models. The third proposed system consists of hybrid CNN–SVM technologies, consisting of two blocks: CNN models for extracting feature maps and the SVM algorithm for classifying feature maps. All the hybrid systems achieved promising results, with AlexNet + SVM achieving 100% accuracy, Goog-LeNet + SVM achieving 98.1% accuracy, and ResNet-18 + SVM achieving 100% accuracy.

show abstract

A deep network designed for segmentation and classification of leukemia using fusion of the transfer learning models

Cited by 55 publications

References 67 publications

Joint metric learning of local and global features for vehicle re-identification

Joint metric learning of local and global features for vehicle re-identification

BO-ALLCNN: Bayesian-Based Optimized CNN for Acute Lymphoblastic Leukemia Detection in Microscopic Blood Smear Images

Multi-Method Diagnosis of Blood Microscopic Sample for Early Detection of Acute Lymphoblastic Leukemia Based on Deep Learning and Hybrid Techniques

Contact Info

Product

Resources

About