Computer Aided Classification of Neuroblastoma Histological Images Using Scale Invariant Feature Transform with Feature Encoding

Gheisari, Soheila; Catchpoole, Daniel; Charlton, Amanda; Melegh, Zsombor; Gradhand, Elise; Kennedy, Paul J.

doi:10.3390/diagnostics8030056

Cited by 11 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From a medical perspective, more accurate results would be desirable to increase confidence and improve the chances of computer-based systems being used to assist experts. Furthermore, [5][6][7] also identified that there was a high degree of misclassification between poorly-differentiated and differentiating neuroblastoma classes. From a biological perspective, these misclassifications are significant as they can result in patients being overtreated or undertreated.…”

Section: Introductionmentioning

confidence: 95%

“…This paper aims to improve the previous work performed by S. Gheisari et al [5][6][7], where neuroblastoma images were successfully classified into five categories. The dataset used for this work is the same as used in [5][6][7] which was gathered from The Tumour Bank at Kids Research at The Children's Hospital at Westmead. Through the exploration of previously used feature extraction methods and existing data optimisation techniques, this study aims to improve the overall accuracy metrics achieved in previous neuroblastoma research.…”

Section: Introductionmentioning

confidence: 99%

“…There is a lack of significant exploration of the use of machine learning techniques in for classification of Nuroblastoma types. One of the recent work was done by S. Gheisari et al [5][6][7] who classified neuroblastoma histopathological images into five categories which were: undifferentiated neuroblastoma, ganglioneuroblastoma, ganglioneuroma, poorly-differentiated neuroblastoma, and differentiating neuroblastoma. A range of low level and high-level feature extraction techniques were used in previous research to achieve accuracy of around 84%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Neuroblastoma Histopathological Images Using Machine Learning

Panta

Khushi

Naseem

et al. 2020

Neural Information Processing

Self Cite

View full text Add to dashboard Cite

Neuroblastoma is the most common cancer in young children accounting for over 15 % of deaths in children due to cancer. Identification of the class of neuroblastoma is dependent on histopathological classification performed by pathologists which are considered the gold standard. However, due to the heterogeneous nature of neuroblast tumours, the human eye can miss critical visual features in histopathology. Hence, the use of computer-based models can assist pathologists in classification through mathematical analysis. There is no publicly available dataset containing neuroblastoma histopathological images. So, this study uses dataset gathered from The Tumour Bank at Kids Research at The Children's Hospital at Westmead, which has been used in previous research. Previous work on this dataset has shown maximum accuracy of 84%. One main issue that previous research fails to address is the class imbalance problem that exists in the dataset as one class represents over 50% of the samples. This study explores a range of feature extraction and data undersampling and over-sampling techniques to improve classification accuracy. Using these methods, this study was able to achieve accuracy of over 90% in the dataset. Moreover, significant improvements observed in this study were in the minority classes where previous work failed to achieve high level of classification accuracy. In doing so, this study shows importance of effective management of available data for any application of machine learning.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Neuroblastoma Histopathological Images Using Machine Learning

Panta

Khushi

Naseem

et al. 2020

Neural Information Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…SIFT, SURF, and ORB are the most well-known methods in this category. Gheisari et al [40] proposed the combination of SIFT with a feature encoding algorithm to extract highly discriminative features from neuroblastoma histology images, and applied an SVM classifier to classify the images into five subtypes. In [41], medical image classification based on the PLSA-BOW model using SIFT features was proposed.…”

Section: Related Work a Image Retrieval And Classificationmentioning

confidence: 99%

Heterogeneity-Aware Local Binary Patterns for Retrieval of Histopathology Images

et al. 2019

View full text Add to dashboard Cite

Histopathology images exhibit considerable variability, which can make diagnosis prone to uncertainty and errors. Using retrieval systems to locate similar images when a query image is given can assist pathologists in making more reliable decisions when diagnosing, based on accurately diagnosed past cases. Local binary patterns (LBP) have been successfully used as image descriptors for different applications. However, using LBP on histopathology images is still under investigation from different perspectives. The immense texture variability of these images and the lack of labeled training data are among the challenges that must be addressed. In this paper, we propose a new extension of LBP that is explicitly aware of the heterogeneity of local texture patterns through heterogeneity-based weighting. We use both homogeneity and the second moment (variance) of local neighborhoods to extend LBP histograms with heterogeneity information so that they better capture the polymorphism in histopathology images. We applied all concepts at multiple scales and investigated the extensions through both separated and concatenated extended histograms. We applied the proposed method on three publicly available datasets, namely, KimiaPath24, invasive ductal carcinoma (IDC), and BreakHis. The experimental results revealed that our features could retrieve and classify images with the highest accuracy. For KimiaPath24, we achieved 96.4% surpassing both LBP (91.0%) and deep features from VGG network (79.5%). For IDC, we reached the highest F1 measure (0.7665). Only for BreakHis, the proposed method was slightly less accurate than a customized convolutional neural network with rule fusion.INDEX TERMS Content based image retrieval (CBIR), whole slide image (WSI) processing, heterogeneity mask, local binary pattern (LBP).

show abstract

“…The LBP combined with minimum redundancy maximum relevance feature selection was employed to recognize Parkinson's disease [9] and classify tumors from mammograms [10]. The SIFT features were used to realize the classification of neuroblastoma histological images [11]. The HOG features were utilized for risk estimation of breast cancer development [12].…”

Section: Introductionmentioning

confidence: 99%

Medical Image Classification Using a Light-Weighted Hybrid Neural Network Based on PCANet and DenseNet

et al. 2020

View full text Add to dashboard Cite

Medical image classification plays an important role in disease diagnosis since it can provide important reference information for doctors. The supervised convolutional neural networks (CNNs) such as DenseNet provide the versatile and effective method for medical image classification tasks, but they require large amounts of data with labels and involve complex and time-consuming training process. The unsupervised CNNs such as principal component analysis network (PCANet) need no labels for training but cannot provide desirable classification accuracy. To realize the accurate medical image classification in the case of a small training dataset, we have proposed a light-weighted hybrid neural network which consists of a modified PCANet cascaded with a simplified DenseNet. The modified PCANet has two stages, in which the network produces the effective feature maps at each stage by convoluting inputs with various learned kernels. The following simplified DenseNet with a small number of weights will take all feature maps produced by the PCANet as inputs and employ the dense shortcut connections to realize accurate medical image classification. To appreciate the performance of the proposed method, some experiments have been done on mammography and osteosarcoma histology images. Experimental results show that the proposed hybrid neural network is easy to train and it outperforms such popular CNN models as PCANet, ResNet and DenseNet in terms of classification accuracy, sensitivity and specificity. INDEX TERMS Medical image classification, hybrid neural network, PCANet, DenseNet.

show abstract

Computer Aided Classification of Neuroblastoma Histological Images Using Scale Invariant Feature Transform with Feature Encoding

Cited by 11 publications

References 19 publications

Classification of Neuroblastoma Histopathological Images Using Machine Learning

Classification of Neuroblastoma Histopathological Images Using Machine Learning

Heterogeneity-Aware Local Binary Patterns for Retrieval of Histopathology Images

Medical Image Classification Using a Light-Weighted Hybrid Neural Network Based on PCANet and DenseNet

Contact Info

Product

Resources

About