PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification

Chen, Kanghao; Lei, Weixian; Hu, Ping; Zhao, Shu; Zheng, Wei‐Shi; Wang, Ruixuan

doi:10.1109/jbhi.2023.3240136

Cited by 15 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The table shows the competitiveness of the proposed model when compared to other models proposed by other researchers in recent years. The proposed hybrid CNN-DenseNet model provided an accuracy of 95.7% compared to Harangi (2018) , which had an accuracy of 79% and 80%, ( Shahin, Kamal & Elattar, 2018 ), which had an accuracy of 89%, ( Hameed, Shabut & Hossain, 2018 ), which had an accuracy of 91%, and ( Maron et al, 2020 ; Chen et al, 2023 ), which had accuracies of 95% and 94%, respectively. As a result, this model may be efficiently utilized to automate the detection of illnesses such as melanocytic nevi, melanoma, benign keratosis-like lesions, BCC, actinic keratoses, vascular lesions, and dermatofibroma.…”

Section: Overall Assessment and Discussionmentioning

confidence: 99%

“…Compared to the research by Chen et al (2023) on “PCCT: Progressive class-center triplet loss for imbalanced medical image classification,” our approach stands out in its architectural design and focus. While both studies aim to address classification challenges in medical image analysis, our work presents a distinctive hybridized CNN-DenseNet model.…”

Section: Related Workmentioning

confidence: 99%

“…While both studies aim to address classification challenges in medical image analysis, our work presents a distinctive hybridized CNN-DenseNet model. Unlike the progressive class-center triplet loss utilized by Chen et al (2023) , our model amalgamates the strengths of the CNN and DenseNet architectures, leveraging both traditional and pretrained models. This hybridization allows for a more comprehensive feature extraction and enhanced gradient flow, leading to heightened accuracy in dermatological classification.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model

De,

Mishra,

Chang

2024

PeerJ Computer Science

View full text Add to dashboard Cite

This research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integrating a hybrid CNN-DenseNet model, this study aimed to overcome the complexities of differentiating various skin diseases and automating the diagnostic process effectively. Our methodology involved rigorous data preprocessing, exploratory data analysis, normalization, and label encoding. Techniques such as model hybridization, batch normalization and data fitting were employed to optimize the model architecture and data fitting. Initial iterations of our convolutional neural network (CNN) model achieved an accuracy of 76.22% on the test data and 75.69% on the validation data. Recognizing the need for improvement, the model was hybridized with DenseNet architecture and ResNet architecture was implemented for feature extraction and then further trained on the HAM10000 and PAD-UFES-20 datasets. Overall, our efforts resulted in a hybrid model that demonstrated an impressive accuracy of 95.7% on the HAM10000 dataset and 91.07% on the PAD-UFES-20 dataset. In comparison to recently published works, our model stands out because of its potential to effectively diagnose skin diseases such as melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma, all of which rival the diagnostic accuracy of real-world clinical specialists but also offer customization potential for more nuanced clinical uses.

show abstract

Section: Overall Assessment and Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model

De,

Mishra,

Chang

2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Given the similarity between triplet loss and AUC optimization, several studies have used DML as a viable solution for class imbalance [33], [34]. To train a network and optimize AUC simultaneously, they use triplet loss as the primary loss function.…”

Section: Deep-metric Learningmentioning

confidence: 99%

“…Accordingly, several studies have employed triplet losses to optimize the AUC metric or have used the AUC metric instead of the triplet loss. This strategy has been proved in the literature to be successful in a variety of classification problems with class-imbalanced data [33], [34]. Triplet (x + a , x + i , x − j ) consists of an anchor point x + a , a positive sample x + i (sample of the same class as the anchor point), and a negative sample x − j (sample of a class different from the anchor point).…”

Section: A Theoretical Foundationmentioning

confidence: 99%

Learning From Imbalanced Data Using Triplet Adversarial Samples

Yun

Lee

2023

IEEE Access

View full text Add to dashboard Cite

The imbalance of classes in real-world datasets poses a major challenge in machine learning and classification, and traditional synthetic data generation methods often fail to address this problem effectively. A major limitation of these methods is that they tend to separate the process of generating synthetic samples from the training process, resulting in synthetic data that lack the necessary informative characteristics for proper model training. We present a new synthetic data generation method that addresses this issue by combining adversarial sample generation with a triplet loss method. This approach focuses on increasing the diversity in the minority class while preserving the integrity of the decision boundary. Furthermore, we show that reducing triplet loss is equivalent to maximizing the area under the receiver operating characteristic curve under specific conditions, providing a theoretical basis for the effectiveness of our method. In addition, we present a model training approach to further improve the generalization of the model to small classes by providing a diverse set of synthetic samples optimized using our proposed loss function. We evaluated our method on several imbalanced benchmark tasks and compared it to state-of-theart techniques, demonstrating that our method can deliver even better performance, making it an effective solution to the class imbalance problem.

show abstract

Engineering Nanoplatforms for Theranostics of Atherosclerotic Plaques

Liu,

Jiang,

Yang

et al. 2024

Adv Healthcare Materials

View full text Add to dashboard Cite

Atherosclerotic plaque formation is considered the primary pathological mechanism underlying atherosclerotic cardiovascular diseases, leading to severe cardiovascular events such as stroke, acute coronary syndromes, and even sudden cardiac death. Early detection and timely intervention of plaques are challenging due to the lack of typical symptoms in the initial stages. Therefore, precise early detection and intervention play a crucial role in risk stratification of atherosclerotic plaques and achieving favorable post‐interventional outcomes. The continuously advancing nanoplatforms have demonstrated numerous advantages including high signal‐to‐noise ratio, enhanced bioavailability, and specific targeting capabilities for imaging agents and therapeutic drugs, enabling effective visualization and management of atherosclerotic plaques. Motivated by these superior properties, we comprehensively summarize various noninvasive imaging modalities for early recognition of plaques in the preliminary stage of atherosclerosis. Additionally, we propose several therapeutic strategies to enhance the efficacy of treating atherosclerotic plaques. Finally, we discuss existing challenges and promising prospects for accelerating clinical translation of nanoplatform‐based molecular imaging and therapy for atherosclerotic plaques. In conclusion, this review provides an insightful perspective on the diagnosis and therapy of atherosclerotic plaques.This article is protected by copyright. All rights reserved

show abstract

PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification

Cited by 15 publications

References 28 publications

An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model

An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model

Learning From Imbalanced Data Using Triplet Adversarial Samples

Engineering Nanoplatforms for Theranostics of Atherosclerotic Plaques

Contact Info

Product

Resources

About