Bioimage classification with subcategory discriminant transform of high dimensional visual descriptors

Song, Yang; Cai, Weidong; Huang, Heng; Feng, Dagan; Wang, Yue; Chen, Mei

doi:10.1186/s12859-016-1318-9

Cited by 20 publications

(12 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM was used as classifier and it obtained 95.5% accuracy. Song et al [8] proposed a method to extract high-dimensional descriptor and subcategory discriminant transform (SDT) was used to enhance discriminative power of descriptors, which achieved the accuracy of 96.8%. Meng et al [7] proposed a framework based on the Collateral Representative Subspace Projection Modeling (CRSPM) supervised classification model for histology image classification.…”

Section: Comparison and Discussionmentioning

confidence: 99%

“…However, its weighting scheme was performed in a class level and majority voting was still used for image label acquisition, which might lead to losing a part of local information. Song et al [8] proposed a method to extract high-dimensional multimodal descriptor, and subcategory discriminant transform (SDT) was used to enhance discriminative power of descriptors. This approach extracted sufficient image information and achieved decent results, but it used deep learning method just for comparison purpose instead of benefitting from making use of the full power of deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NHL Pathological Image Classification Based on Hierarchical Local Information and GoogLeNet-Based Representations

Bai

Jiang

et al. 2019

BioMed Research International

View full text Add to dashboard Cite

Background. Accurate classification for different non-Hodgkin lymphomas (NHL) is one of the main challenges in clinical pathological diagnosis due to its intrinsic complexity. Therefore, this paper proposes an effective classification model for three types of NHL pathological images, including mantle cell lymphoma (MCL), follicular lymphoma (FL), and chronic lymphocytic leukemia (CLL). Methods. There are three main parts with respect to our model. First, NHL pathological images stained by hematoxylin and eosin (H&E) are transferred into blue ratio (BR) and Lab spaces, respectively. Then specific patch-level textural and statistical features are extracted from BR images and color features are obtained from Lab images both using a hierarchical way, yielding a set of hand-crafted representations corresponding to different image spaces. A random forest classifier is subsequently trained for patch-level classification. Second, H&E images are cropped and fed into a pretrained google inception net (GoogLeNet) for learning high-level representations and a softmax classifier is used for patch-level classification. Finally, three image-level classification strategies based on patch-level results are discussed including a novel method for calculating the weighted sum of patch results. Different classification results are fused at both feature 1 and image levels to obtain a more satisfactory result. Results. The proposed model is evaluated on a public IICBU Malignant Lymphoma Dataset and achieves an improved overall accuracy of 0.991 and area under the receiver operating characteristic curve of 0.998. Conclusion. The experimentations demonstrate the significantly increased classification performance of the proposed model, indicating that it is a suitable classification approach for NHL pathological images.

show abstract

Section: Comparison and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

NHL Pathological Image Classification Based on Hierarchical Local Information and GoogLeNet-Based Representations

Bai

Jiang

et al. 2019

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…Despite our method presenting an accuracy rate smaller than that obtained by Refs. [2,[12][13][14], the differences were not significant when analyzed by the Friedman test (P f ¼ 0:05), with all pairwise comparisons (Conover), and the Kruskal-Wallis test (P k ¼ 0:9746), considering all pairwise comparisons (Dwass-Steel-Chritchlow-Fligner). In these tests the significance level was of 0.05.…”

Section: Unsegmentedmentioning

confidence: 93%

“…After applying the chi-squared attribute selection, the size of the feature vector was reduced from 12,625 to 50. The authors in Song et al [13] proposed a method based on visual descriptors to extract features from grayscale images, including a NHL dataset. The features were extracted separately and each one went on to make up a different set that was given as input to a specific classification stage.…”

Section: Introductionmentioning

confidence: 99%

Features based on the percolation theory for quantification of non-Hodgkin lymphomas

Roberto

Neves

Nascimento

et al. 2017

Computers in Biology and Medicine

View full text Add to dashboard Cite

Non-Hodgkin lymphomas are a health problem that affects over 70,000 people per year in the United States alone. The early diagnosis and the identification of this lymphoma are essential for an effective treatment. The classification of non-Hodgkin lymphomas is a task that continues to rank as one of the main challenges faced by hematologists, pathologists, as well as in the producing of computer vision methods due to its inherent complexity. In this paper, we present a new method to quantify and classify tissue samples of non-Hodgkin lymphomas based on the percolation theory. The method consists of associating multiscale and multidimensional approaches in order to divide the image into smaller regions and then verifying color similarity between pixels. A cluster labeling algorithm was applied to each region of interest to obtain the values for the number of clusters, occurrence of percolation and coverage ratio of the largest cluster. The method was tested on different classifiers aiming to differentiate three different groups of non-Hodgkin lymphomas. The obtained results (AUC rates between 0.940 and 0.993) were compared to those provided by methods consolidated in the Literature, which indicates that the percolation theory is a suitable approach for identifying these three classes of non-Hodgkin lymphomas, those being: mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia.

show abstract

“…In Nascimento et al [16] an investigation was also made into the classification of these lesions with descriptors based on the stationary wavelet transform. In addition authors also presented approaches for quantifying and extracting features from the histological images of the lymphoma image dataset [17,18] . In these works, the authors did not employ the detection stage for nuclei before the feature extraction stage.…”

Section: Introductionmentioning

confidence: 99%

Lymphoma images analysis using morphological and non-morphological descriptors for classification

Nascimento

Martins²,

Tosta

et al. 2018

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia are the principle subtypes of the non-Hodgkin lymphomas. The diversity of clinical presentations and the histopathological features have made diagnosis of such lymphomas a complex task for specialists. Computer aided diagnosis systems employ computational vision and image processing techniques, which contribute toward the detection, diagnosis and prognosis of digitised images of histological samples. Studies aimed at improving the understanding of morphological and non-morphological features for classification of lymphoma remain a challenge in this area. This work presents a new approach for the classification of information extracted from morphological and non-morphological features of nuclei of lymphoma images. We extracted data of the RGB model of the image and employed contrast limited adaptive histogram equalisation and 2D order-statistics filter methods to enhance the contrast and remove noise. The regions of interest were identified by the global thresholding method. The flood-fill and watershed techniques were used to remove the small false positive regions. The area, extent, perimeter, convex area, solidity, eccentricity, equivalent diameter, minor axis and major axis measurements were computed for the regions detected in the nuclei. In the feature selection stage, we applied the ANOVA, Ansari-Bradley and Wilcoxon rank sum methods. Finally, we employed the polynomial, support vector machine, random forest and decision tree classifiers in order to evaluate the performance of the proposed approach. The non-morphological features achieved higher AUC and AC values for all cases: the obtained rates were between 95% and 100%. These results are relevant, especially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed approach is useful as an automated protocol for the diagnosis of lymphoma histological tissue.

show abstract

Bioimage classification with subcategory discriminant transform of high dimensional visual descriptors

Cited by 20 publications

References 52 publications

NHL Pathological Image Classification Based on Hierarchical Local Information and GoogLeNet-Based Representations

NHL Pathological Image Classification Based on Hierarchical Local Information and GoogLeNet-Based Representations

Features based on the percolation theory for quantification of non-Hodgkin lymphomas

Lymphoma images analysis using morphological and non-morphological descriptors for classification

Contact Info

Product

Resources

About