Datasets for training and validating a deep learning-based system to detect microfossil fish teeth from slide images

Mimura, Kazuhide; Nakamura, Kozo

doi:10.1016/j.dib.2023.108940

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The VGG Image Annotator 46 generated a dataset using a coco‐like style. It is a straightforward method of manually annotating coco‐formatted images, videos, and audio files.…”

Section: Methodsmentioning

confidence: 99%

Segmentation and classification of skin lesions using hybrid deep learning method in the Internet of Medical Things

Akram,

Rashid,

Jaffar

et al. 2023

Skin Research and Technology

View full text Add to dashboard Cite

IntroductionParticularly within the Internet of Medical Things (IoMT) context, skin lesion analysis is critical for precise diagnosis. To improve the accuracy and efficiency of skin lesion analysis, CAD systems play a crucial role. To segment and classify skin lesions from dermoscopy images, this study focuses on using hybrid deep learning techniques.MethodThis research uses a hybrid deep learning model that combines two cutting‐edge approaches: Mask Region‐based Convolutional Neural Network (MRCNN) for semantic segmentation and ResNet50 for lesion detection. To pinpoint the precise location of a skin lesion, the MRCNN is used for border delineation. We amass a huge, annotated collection of dermoscopy images for thorough model training. The hybrid deep learning model to capture subtle representations of the images is trained from start to finish using this dataset.ResultsThe experimental results using dermoscopy images show that the suggested hybrid method outperforms the current state‐of‐the‐art methods. The model's capacity to segment lesions into distinct groups is demonstrated by a segmentation accuracy measurement of 95.49 percent. In addition, the classification of skin lesions shows great accuracy and dependability, which is a notable advancement over traditional methods. The model is put through its paces on the ISIC 2020 Challenge dataset, scoring a perfect 96.75% accuracy. Compared to current best practices in IoMT, segmentation and classification models perform exceptionally well.ConclusionIn conclusion, this paper's hybrid deep learning strategy is highly effective in skin lesion segmentation and classification. The results show that the model has the potential to improve diagnostic accuracy in the setting of IoMT, and it outperforms the current gold standards. The excellent results obtained on the ISIC 2020 Challenge dataset further confirm the viability and superiority of the suggested methodology for skin lesion analysis.

show abstract

“…The VGG Image Annotator 46 generated a dataset using a coco‐like style. It is a straightforward method of manually annotating coco‐formatted images, videos, and audio files.…”

Section: Methodsmentioning

confidence: 99%

Segmentation and classification of skin lesions using hybrid deep learning method in the Internet of Medical Things

Akram,

Rashid,

Jaffar

et al. 2023

Skin Research and Technology

View full text Add to dashboard Cite

show abstract

“…The dataset itself is an important component because it has a significant impact on model performance. A good dataset is a dataset that is diverse, balanced, unbiased, does not contain errors and is also large [12]. The dataset must have labels.…”

Section: Datasetmentioning

confidence: 99%

Skin Cancer Detection Approach Using Convolutional Neural Network Artificial Intelligence

Hayat

2024

IJIIS Int. J. Informatics Inf. Syst.

View full text Add to dashboard Cite

Skin cancer is a type of cancer that can cause death, where skin cancer is included in the 15 common cancers that occur in Indonesia. The number of skin cancer sufferers was around 6,170 cases of non-melanoma skin cancer and 1,392 cases of melanoma skin cancer in 2018 in Indonesia. Therefore, research related to skin cancer classification is increasing. This is done as an initial step in detecting whether a lesion can be said to be cancerous or not. The deep learning approach has certainly shown promising results in carrying out classification, so this research proposes a deep learning-based method used for skin cancer classification. The proposed approach involves Convolutional Neural Networks with the ISIC 2017 dataset. The models used for skin cancer classification are InceptionV3, EfficientNetB0, ResNet50, MobileNetV2, and NASNetMobile. The highest accuracy of the single model produced reached 69.3% using the MobileNetV2 model. An ensemble model combining the five models was also tested and produced the highest accuracy compared to other single models with an accuracy result of 80.6%.

show abstract

Artificial intelligence in paleontology

Yu,

Qin,

Watanabe

et al. 2024

Earth-Science Reviews

View full text Add to dashboard Cite

Datasets for training and validating a deep learning-based system to detect microfossil fish teeth from slide images

Cited by 4 publications

References 10 publications

Segmentation and classification of skin lesions using hybrid deep learning method in the Internet of Medical Things

Segmentation and classification of skin lesions using hybrid deep learning method in the Internet of Medical Things

Skin Cancer Detection Approach Using Convolutional Neural Network Artificial Intelligence

Artificial intelligence in paleontology

Contact Info

Product

Resources

About