Automatic Skin Lesion Segmentation and Melanoma Detection: Transfer Learning Approach with U-Net and DCNN-SVM

Nazi, Zabir Al; Abir, Tasnim Azad

doi:10.1007/978-981-13-7564-4_32

Cited by 45 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This technique improves the melanoma segmentation accuracy but suffering from high computational cost. Al Nazi and Abir (2020) presented an approach for automated detection and localization of melanoma lesions from input samples. After performing the preprocessing step, a deep CNN model was applied to compute the image features, which were later utilized to train the SVM classifier to classify the melanoma moles.…”

Section: Related Workmentioning

confidence: 99%

Skin cancer detection from dermoscopic images using deep learning and fuzzy k‐means clustering

Nawaz

Mehmood

Nazir

et al. 2021

Microscopy Res & Technique

174

View full text Add to dashboard Cite

Melanoma skin cancer is the most life-threatening and fatal disease among the family of skin cancer diseases. Modern technological developments and research methodologies made it possible to detect and identify this kind of skin cancer more effectively; however, the automated localization and segmentation of skin lesion at earlier stages is still a challenging task due to the low contrast between melanoma moles and skin portion and a higher level of color similarity between melanoma-affected and -nonaffected areas. In this paper, we present a fully automated method for segmenting the skin melanoma at its earliest stage by employing a deep-learningbased approach, namely faster region-based convolutional neural networks (RCNN) along with fuzzy k-means clustering (FKM). Several clinical images are utilized to test the presented method so that it may help the dermatologist in diagnosing this lifethreatening disease at its earliest stage. The presented method first preprocesses the dataset images to remove the noise and illumination problems and enhance the visual information before applying the faster-RCNN to obtain the feature vector of fixed length. After that, FKM has been employed to segment the melanoma-affected portion of skin with variable size and boundaries. The performance of the presented method is evaluated on the three standard datasets, namely ISBI-2016, ISIC-2017, and PH2, and the results show that the presented method outperforms the state-ofthe-art approaches. The presented method attains an average accuracy of 95.40, 93.1, and 95.6% on the ISIC-2016, ISIC-2017, and PH2 datasets, respectively, which is showing its robustness to skin lesion recognition and segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

Skin cancer detection from dermoscopic images using deep learning and fuzzy k‐means clustering

Nawaz

Mehmood

Nazir

et al. 2021

Microscopy Res & Technique

174

View full text Add to dashboard Cite

show abstract

“…In recent years, the proliferation and advent of deep learning through convolutional neural networks (CNNs) have captivated interest in various fields such as object detection [ 22 ], agriculture [ 23 ], and natural language processing [ 24 ] with prominent results. Particularly, the deep learning models have been adopted in many medical image analysis applications, namely physiotherapy [ 25 ], eye disease detection [ 26 ], and skin lesion segmentation [ 27 ]. This adoption is driven by the ability of deep learning in discovering multiple levels of discriminative features by automatically learn the high-level abstractions of the image data to avoid any feature engineering process.…”

Section: Computerized Bone Age Assessmentmentioning

confidence: 99%

Intelligent Bone Age Assessment: An Automated System to Detect a Bone Growth Problem Using Convolutional Neural Networks with Attention Mechanism

et al. 2021

View full text Add to dashboard Cite

Skeletal bone age assessment using X-ray images is a standard clinical procedure to detect any anomaly in bone growth among kids and babies. The assessed bone age indicates the actual level of growth, whereby a large discrepancy between the assessed and chronological age might point to a growth disorder. Hence, skeletal bone age assessment is used to screen the possibility of growth abnormalities, genetic problems, and endocrine disorders. Usually, the manual screening is assessed through X-ray images of the non-dominant hand using the Greulich–Pyle (GP) or Tanner–Whitehouse (TW) approach. The GP uses a standard hand atlas, which will be the reference point to predict the bone age of a patient, while the TW uses a scoring mechanism to assess the bone age using several regions of interest information. However, both approaches are heavily dependent on individual domain knowledge and expertise, which is prone to high bias in inter and intra-observer results. Hence, an automated bone age assessment system, which is referred to as Attention-Xception Network (AXNet) is proposed to automatically predict the bone age accurately. The proposed AXNet consists of two parts, which are image normalization and bone age regression modules. The image normalization module will transform each X-ray image into a standardized form so that the regressor network can be trained using better input images. This module will first extract the hand region from the background, which is then rotated to an upright position using the angle calculated from the four key-points of interest. Then, the masked and rotated hand image will be aligned such that it will be positioned in the middle of the image. Both of the masked and rotated images will be obtained through existing state-of-the-art deep learning methods. The last module will then predict the bone age through the Attention-Xception network that incorporates multiple layers of spatial-attention mechanism to emphasize the important features for more accurate bone age prediction. From the experimental results, the proposed AXNet achieves the lowest mean absolute error and mean squared error of 7.699 months and 108.869 months2, respectively. Therefore, the proposed AXNet has demonstrated its potential for practical clinical use with an error of less than one year to assist the experts or radiologists in evaluating the bone age objectively.

show abstract

“…Em [Nazi and Abir 2020], foi utilizada uma rede convolucional U-Net para segmentar imagens, obtendo uma média 0,87 com o Dice. A base de dados utilizada foi a ISIC 2018.…”

Section: Trabalhos Relacionadosunclassified

“…As métricas utilizadas para a avaliação do acerto na segmentação foram: Dice, acurácia (ACC), Jaccard (JAC), kappa (KPA) [Cohen 1968] eárea sobre a curva ROC (AUC) [van Erkel and Pattynama 1998]. Para calcular essas métricasé utilizada a matriz de confusão [Provost and Kohavi 1998] na geração dos valores: Falso Negativo (FN), Falso Positivo (FP), Verdadeiro Positivo (VP) e Verdadeiro Negativo (VN). Assim as métricas são definidos como:…”

Section: Validaçãounclassified

Segmentação de Lesões de Pele Utilizando Algoritmos de Aprendizagem Profunda

Souza¹,

Lelis²,

Silva³

2020

Anais Principais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2020)

View full text Add to dashboard Cite

Dentre os cânceres de pele, o melanoma o mais grave e mais frequente no Brasil. Além disso, sua incidência está aumentando cada vez mais pelo mundo, assim mostrando a importância dos sistemas de detecção do câncer através de imagens médicas para a obtenção de um diagnóstico mais rápido. Uma das etapas é a segmentação, que trata do isolamento da região lesionada. Nesta pesquisa realizou-se a aplicação das técnicas de pós-processamento limiar de Otsu, fechamento de regiões e remoção de pequenas regiões para melhorar o resultado com algoritmos baseados em aprendizagem profunda U-Net. Com a utilização das bases PH2 e ISIC 2018, foram obtidos 0,9482 e 0,7729 de valores de Dice, respectivamente.

show abstract

Automatic Skin Lesion Segmentation and Melanoma Detection: Transfer Learning Approach with U-Net and DCNN-SVM

Cited by 45 publications

References 19 publications

Skin cancer detection from dermoscopic images using deep learning and fuzzy k‐means clustering

Skin cancer detection from dermoscopic images using deep learning and fuzzy k‐means clustering

Intelligent Bone Age Assessment: An Automated System to Detect a Bone Growth Problem Using Convolutional Neural Networks with Attention Mechanism

Segmentação de Lesões de Pele Utilizando Algoritmos de Aprendizagem Profunda

Contact Info

Product

Resources

About