DE-Ada*: A novel model for breast mass classification using cross-modal pathological semantic mining and organic integration of multi-feature fusions

Zhang, Hongbin; Wu, Renbiao; Yuan, Tian; Jiang, Ziliang; Huang, Song; Wu, Jinpeng; Jin, Hua; Niu, Zheng-Yu; Ji, Donghong

doi:10.1016/j.ins.2020.05.080

Cited by 45 publications

(32 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed finegrained feature selection idea is effective. Fourth, the RCA model obtains a suboptimal Acc (87.07%), which is close to the DE-Ada * model [46] (87.93%). From the AUC perspective, the RCA model (93%) beats the DE-Ada * model and approaches Shen's single model [26] (95%).…”

Section: B Performance Comparisons With State-of-the-art Modelsmentioning

confidence: 64%

“…(4) State-of-the-art breast cancer recognition models were used for direct comparisons: Shen's model [26], Dhungel's model [28], and Zhang's DE-Ada * model [46].…”

Section: ) Benchmark Modelsmentioning

confidence: 99%

“…A CAD system should be evaluated comprehensively from diverse perspectives. Hence, similar to the state-of-the-art studies [46] - [50], several specific methods were used to evaluate the model. The two most important evaluation metrics include accuracy (Acc) and area under the receiver operating characteristic curve (AUC).…”

Section: ) Evaluation Metricsmentioning

confidence: 99%

“…A higher Spe means that the corresponding FPR is low, and the probability of diagnosis is higher. Moreover, a Kiviatdiagram-based evaluation metric [46] was used to evaluate the overall performance of each recognition model more comprehensively. The Acc, Sen, Spe, and AUC values of each model are plotted in the Kiviat diagram.…”

Section: Tpmentioning

confidence: 99%

See 3 more Smart Citations

Effective Breast Cancer Recognition Based on Fine-Grained Feature Selection

Yuan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Section: B Performance Comparisons With State-of-the-art Modelsmentioning

confidence: 64%

“…(4) State-of-the-art breast cancer recognition models were used for direct comparisons: Shen's model [26], Dhungel's model [28], and Zhang's DE-Ada * model [46].…”

Section: ) Benchmark Modelsmentioning

confidence: 99%

Section: ) Evaluation Metricsmentioning

confidence: 99%

Section: Tpmentioning

confidence: 99%

See 2 more Smart Citations

Effective Breast Cancer Recognition Based on Fine-Grained Feature Selection

Yuan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

“…As it uses kernel function which maps the feature space into new domain that can easily separate between classes of a dataset. Therefore, it is commonly used with the huge dimension of DL features extracted from CNNs Jadoon et al, 2017;Zhang et al, 2020;Das et al, 2020;Xue et al, 2016;Leng et al, 2016;Wu et al, 2018;Sampaio et al, 2011) achieving outperforming results. Also, as you can see in Table 1, that SVM is the commonly used in the literature It can be observed that articles that used SVM achieved the highest performance as Khan et al (2020b) which achieved an accuracy of 99.13%, (Khan et al, 2020a) achieving an accuracy of 98.4%, obtaining an accuracy of 95%, (Billah, Waheed & Rahman, 2017) achieving an accuracy of 98.65%…”

Section: Classification Stepmentioning

confidence: 99%

GASTRO-CADx: a three stages framework for diagnosing gastrointestinal diseases

Attallah¹,

Sharkas²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Gastrointestinal (GI) diseases are common illnesses that affect the GI tract. Diagnosing these GI diseases is quite expensive, complicated, and challenging. A computer-aided diagnosis (CADx) system based on deep learning (DL) techniques could considerably lower the examination cost processes and increase the speed and quality of diagnosis. Therefore, this article proposes a CADx system called Gastro-CADx to classify several GI diseases using DL techniques. Gastro-CADx involves three progressive stages. Initially, four different CNNs are used as feature extractors to extract spatial features. Most of the related work based on DL approaches extracted spatial features only. However, in the following phase of Gastro-CADx, features extracted in the first stage are applied to the discrete wavelet transform (DWT) and the discrete cosine transform (DCT). DCT and DWT are used to extract temporal-frequency and spatial-frequency features. Additionally, a feature reduction procedure is performed in this stage. Finally, in the third stage of the Gastro-CADx, several combinations of features are fused in a concatenated manner to inspect the effect of feature combination on the output results of the CADx and select the best-fused feature set. Two datasets referred to as Dataset I and II are utilized to evaluate the performance of Gastro-CADx. Results indicated that Gastro-CADx has achieved an accuracy of 97.3% and 99.7% for Dataset I and II respectively. The results were compared with recent related works. The comparison showed that the proposed approach is capable of classifying GI diseases with higher accuracy compared to other work. Thus, it can be used to reduce medical complications, death-rates, in addition to the cost of treatment. It can also help gastroenterologists in producing more accurate diagnosis while lowering inspection time.

show abstract

Breast lesion classification using features fusion and selection of ensemble ResNet method

Kilicarslan¹,

Koç

Özyurt

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Medical Imaging with Deep Learning has recently become the most prominent topic in the scientific world. Significant results have been obtained in the classification of medical images using deep learning methods, and there has been an increase in studies on malignant types. The main reason for choosing breast cancer is that breast cancer is one of the critical malignant types that increase the death rate in women. In this study, 1236 ultrasound images were collected from Elazig Fethi Sekin City Hospital, and three different ResNet CNN architectures were used for feature extraction. Data were trained with an SVM classifier. In addition, the three ResNet architectures were combined, and novel fused ResNet architecture was used in this study. In addition, these features were used with three different feature selection techniques, MR‐MR, NCA, and Relieff. These results are 89.3% obtained from ALL‐ResNet architecture and the feature selected with NCA in normal and lesion classification. Normal, malignant, and benign classification best accuracy is 84.9% with ALL‐ResNet NCA. Experimental studies show that MR‐MR, NCA, and Relieff feature selection algorithms reduce features and give more results that are successful. This indicates that the proposed method is more successful than classical deep learning methods.

show abstract

DE-Ada*: A novel model for breast mass classification using cross-modal pathological semantic mining and organic integration of multi-feature fusions

Cited by 45 publications

References 26 publications

Effective Breast Cancer Recognition Based on Fine-Grained Feature Selection

Effective Breast Cancer Recognition Based on Fine-Grained Feature Selection

GASTRO-CADx: a three stages framework for diagnosing gastrointestinal diseases

Breast lesion classification using features fusion and selection of ensemble ResNet method

Contact Info

Product

Resources

About