Classification of skin cancer images by applying simple evolving connectionist system

Al-Khowarizmi, Al-Khowarizmi; Suherman, Suherman

doi:10.11591/ijai.v10.i2.pp421-429

Cited by 5 publications

(2 citation statements)

References 24 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rustam et al [10] applied regression logistics and random forest for pancreatic cancer detection and have found random forest to perform better. Al-Khowarizmi and Suherman [11] applied a simple evolving connectionist system (SECoS) on a balanced cancer dataset, whilst Dabeer et al [12] applied CNN for breast cancer detection using histopathology images from a biopsy. Pratiwi et al [13] ensembled three architectures: inception V3, inception ResNet V2, and DenseNet 201, with the ensembled model showing sensitivity of 90%, specificity of 97%, precision of 82%, and recall of 85%.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning for cancer diagnosis in histopathological images

Aneja

Abas

et al. 2022

IJ-AI

View full text Add to dashboard Cite

Transfer learning allows us to exploit knowledge gained from one task to assist in solving another but relevant task. In modern computer vision research, the question is which architecture performs better for a given dataset. In this paper, we compare the performance of 14 pre-trained ImageNet models on the histopathologic cancer detection dataset, where each model has been configured as naive model, feature extractor model, or fine-tuned model. Densenet161 has been shown to have high precision whilst Resnet101 has a high recall. A high precision model is suitable to be used when follow-up examination cost is high, whilst low precision but a high recall/sensitivity model can be used when the cost of follow-up examination is low. Results also show that transfer learning helps to converge a model faster.

show abstract

Section: Introductionmentioning

confidence: 99%

Transfer learning for cancer diagnosis in histopathological images

Aneja

Abas

et al. 2022

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Many computer applications help people to obtain more services with less effort and impressive results [5]. Classification has become one of the major focuses of computer science [6].…”

Section: Introductionmentioning

confidence: 99%

Automated multi-class skin cancer classification through concatenated deep learning models

Bedeir

Mahmoud

Zayed

2022

IJ-AI

View full text Add to dashboard Cite

Skin cancer is the most annoying type of cancer diagnosis according to its fast spread to various body areas, so it was necessary to establish computer-assisted diagnostic support systems. State-of-the-art classifiers based on convolutional neural networks (CNNs) are used to classify images of skin cancer. This paper tries to get the most accurate model to classify and detect skin cancer types from seven different classes using deep learning techniques; ResNet-50, VGG-16, and the merged model of these two techniques through the concatenate function. The performance of the proposed model was evaluated through a set of experiments on the HAM10000 database. The proposed system has succeeded in achieving a recognition accuracy of up to 94.14%.

show abstract