TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

Hu, Chuan-Shen; Lawson, Austin; Chen, Jung‐Sheng; Chung, Yu-Min; Smyth, Clifford; Yang, Shih-Min

doi:10.3390/math9222924

Cited by 9 publications

(6 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the ResBlock layer, the previous data is moved to the new one. ResNet101 is one of the deepest residual neural network techniques suggested for ImageNet, with 101 layers when viewed from an architectural standpoint [15], [16].…”

Section: Resnet101mentioning

confidence: 99%

An effective study on the diagnosis of colon cancer with the developed local binary pattern method

Gül

2024

Preprint

View full text Add to dashboard Cite

According to a recent study, 1 million people died from colon cancer and approximately 2 million from lung cancer. Regardless of the type of cancer, identifying the tumor area is extremely important. The pathology method is the most trustworthy technique for locating the tumor. Nucleus detection and classification studies were performed on images obtained with the pathology method. The principal objective of this study is to ascertain the presence of the tumor and acquire insights into its behavior. There could be some complications while the pathology procedure is performed. On the other hand, it is also important that the samples obtained are examined correctly by experts. Within the scope of the study, the local binary pattern method was used as a highly effective method among image enhancement methods. Colon cancer was diagnosed with two valuable local binary pattern (LBP) methods derived from the local binary pattern (LBP) method. During the diagnosis procedure, the developed LBP methods were first evaluated with machine learning and some transfer learning (TL) methods. Within the scope of the study, the LC25000 dataset was used to analyze colon cancer histopathological images. The performance values for step LBP method analysis were, respectively, accuracy (96.87%), kappa (93.74%), precision (96.9%), recall (96.9%), F1 score (96.9%), and ROC (99.4%). The results obtained with the developed cross-over LBP method were, respectively, accuracy (94.57%), kappa (90.91%), precision (94.9%), recall (94.9%), F1 score (94.9%), and ROC (98.8%).

show abstract

Section: Resnet101mentioning

confidence: 99%

An effective study on the diagnosis of colon cancer with the developed local binary pattern method

Gül

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In [40], Hu et al developed a TopoResNet that integrates topological information into the residual neural network architecture. They applied TopoResNet to a skin lesion classification problem.…”

Section: Related Workmentioning

confidence: 99%

“…The Dice coefficient (DC) is employed for validating the segmentation of the medical volume-oriented data. This is an overlapping index that calculates the magnitude of overlapping between actual result and achieved results in the context of task-related binary segmentation [40]. For the actual and achieved mask, the DC is expressed by following Equation (6):…”

Section: Evaluation Criteriamentioning

confidence: 99%

See 2 more Smart Citations

Ensemble of 2D Residual Neural Networks Integrated with Atrous Spatial Pyramid Pooling Module for Myocardium Segmentation of Left Ventricle Cardiac MRI

et al. 2022

View full text Add to dashboard Cite

Cardiac disease diagnosis and identification is problematic mostly by inaccurate segmentation of the cardiac left ventricle (LV). Besides, LV segmentation is challenging since it involves complex and variable cardiac structures in terms of components and the intricacy of time-based crescendos. In addition, full segmentation and quantification of the LV myocardium border is even more challenging because of different shapes and sizes of the myocardium border zone. The foremost purpose of this research is to design a precise automatic segmentation technique employing deep learning models for the myocardium border using cardiac magnetic resonance imaging (MRI). The ASPP module (Atrous Spatial Pyramid Pooling) was integrated with a proposed 2D-residual neural network for segmentation of the myocardium border using a cardiac MRI dataset. Further, the ensemble technique based on a majority voting ensemble method was used to blend the results of recent deep learning models on different set of hyperparameters. The proposed model produced an 85.43% dice score on validation samples and 98.23% on training samples and provided excellent performance compared to recent deep learning models. The myocardium border was successfully segmented across diverse subject slices with different shapes, sizes and contrast using the proposed deep learning ensemble models. The proposed model can be employed for automatic detection and segmentation of the myocardium border for precise quantification of reflow, myocardial infarction, myocarditis, and h cardiomyopathy (HCM) for clinical applications.

show abstract

Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis

Maurya,

Stanley,

Lama

et al. 2024

J Digit Imaging. Inform. med.

View full text Add to dashboard Cite

A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.

show abstract

TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

Cited by 9 publications

References 49 publications

An effective study on the diagnosis of colon cancer with the developed local binary pattern method

An effective study on the diagnosis of colon cancer with the developed local binary pattern method

Ensemble of 2D Residual Neural Networks Integrated with Atrous Spatial Pyramid Pooling Module for Myocardium Segmentation of Left Ventricle Cardiac MRI

Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis

Contact Info

Product

Resources

About