Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images
Abstract Background Melanoma is the most dangerous and aggressive form among skin cancers, exhibiting a high mortality rate worldwide. Biopsy and histopathological analysis are standard procedures for skin cancer detection and prevention in clinical settings. A significant step in the diagnosis proc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-05-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-022-00829-y |
| _version_ | 1811258697300574208 |
|---|---|
| author | Ranpreet Kaur Hamid GholamHosseini Roopak Sinha Maria Lindén |
| author_facet | Ranpreet Kaur Hamid GholamHosseini Roopak Sinha Maria Lindén |
| author_sort | Ranpreet Kaur |
| collection | DOAJ |
| description | Abstract Background Melanoma is the most dangerous and aggressive form among skin cancers, exhibiting a high mortality rate worldwide. Biopsy and histopathological analysis are standard procedures for skin cancer detection and prevention in clinical settings. A significant step in the diagnosis process is the deep understanding of the patterns, size, color, and structure of lesions based on images obtained through dermatoscopes for the infected area. However, the manual segmentation of the lesion region is time-consuming because the lesion evolves and changes its shape over time, making its prediction challenging. Moreover, it is challenging to predict melanoma at the initial stage as it closely resembles other skin cancer types that are not malignant as melanoma; thus, automatic segmentation techniques are required to design a computer-aided system for accurate and timely detection. Methods As deep learning approaches have gained significant attention in recent years due to their remarkable performance, therefore, in this work, we proposed a novel design of a convolutional neural network (CNN) framework based on atrous convolutions for automatic lesion segmentation. This architecture is built based on the concept of atrous/dilated convolutions which are effective for semantic segmentation. A deep neural network is designed from scratch employing several building blocks consisting of convolutional, batch normalization, leakyReLU layer, and fine-tuned hyperparameters contributing altogether towards higher performance. Conclusion The network was tested on three benchmark datasets provided by International Skin Imaging Collaboration (ISIC), i.e., ISIC 2016, ISIC 2017, and ISIC 2018. The experimental results showed that the proposed network achieved an average Jaccard index of 90.4% on ISIC 2016, 81.8% on ISIC 2017, and 89.1% on ISIC 2018 datasets, respectively which is recorded as higher than the top three winners of the ISIC challenge and other state-of-the-art methods. Also, the model successfully extracts lesions from the whole image in one pass in less time, requiring no pre-processing step. The conclusions yielded that network is accurate in performing lesion segmentation on adopted datasets. |
| first_indexed | 2024-04-12T18:18:28Z |
| format | Article |
| id | doaj.art-13188c8c9bb84f209cbfff8019883040 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-04-12T18:18:28Z |
| publishDate | 2022-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-13188c8c9bb84f209cbfff80198830402022-12-22T03:21:32ZengBMCBMC Medical Imaging1471-23422022-05-0122111310.1186/s12880-022-00829-yAutomatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer imagesRanpreet Kaur0Hamid GholamHosseini1Roopak Sinha2Maria Lindén3School of Engineering, Computer, and Mathematical Sciences, Auckland University of TechnologySchool of Engineering, Computer, and Mathematical Sciences, Auckland University of TechnologySchool of Engineering, Computer, and Mathematical Sciences, Auckland University of TechnologySchool of Innovation Design and Engineering, Mälardalen UniversityAbstract Background Melanoma is the most dangerous and aggressive form among skin cancers, exhibiting a high mortality rate worldwide. Biopsy and histopathological analysis are standard procedures for skin cancer detection and prevention in clinical settings. A significant step in the diagnosis process is the deep understanding of the patterns, size, color, and structure of lesions based on images obtained through dermatoscopes for the infected area. However, the manual segmentation of the lesion region is time-consuming because the lesion evolves and changes its shape over time, making its prediction challenging. Moreover, it is challenging to predict melanoma at the initial stage as it closely resembles other skin cancer types that are not malignant as melanoma; thus, automatic segmentation techniques are required to design a computer-aided system for accurate and timely detection. Methods As deep learning approaches have gained significant attention in recent years due to their remarkable performance, therefore, in this work, we proposed a novel design of a convolutional neural network (CNN) framework based on atrous convolutions for automatic lesion segmentation. This architecture is built based on the concept of atrous/dilated convolutions which are effective for semantic segmentation. A deep neural network is designed from scratch employing several building blocks consisting of convolutional, batch normalization, leakyReLU layer, and fine-tuned hyperparameters contributing altogether towards higher performance. Conclusion The network was tested on three benchmark datasets provided by International Skin Imaging Collaboration (ISIC), i.e., ISIC 2016, ISIC 2017, and ISIC 2018. The experimental results showed that the proposed network achieved an average Jaccard index of 90.4% on ISIC 2016, 81.8% on ISIC 2017, and 89.1% on ISIC 2018 datasets, respectively which is recorded as higher than the top three winners of the ISIC challenge and other state-of-the-art methods. Also, the model successfully extracts lesions from the whole image in one pass in less time, requiring no pre-processing step. The conclusions yielded that network is accurate in performing lesion segmentation on adopted datasets.https://doi.org/10.1186/s12880-022-00829-ySkin cancerLesion segmentationCNNDeep learning |
| spellingShingle | Ranpreet Kaur Hamid GholamHosseini Roopak Sinha Maria Lindén Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images BMC Medical Imaging Skin cancer Lesion segmentation CNN Deep learning |
| title | Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images |
| title_full | Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images |
| title_fullStr | Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images |
| title_full_unstemmed | Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images |
| title_short | Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images |
| title_sort | automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images |
| topic | Skin cancer Lesion segmentation CNN Deep learning |
| url | https://doi.org/10.1186/s12880-022-00829-y |
| work_keys_str_mv | AT ranpreetkaur automaticlesionsegmentationusingatrousconvolutionaldeepneuralnetworksindermoscopicskincancerimages AT hamidgholamhosseini automaticlesionsegmentationusingatrousconvolutionaldeepneuralnetworksindermoscopicskincancerimages AT roopaksinha automaticlesionsegmentationusingatrousconvolutionaldeepneuralnetworksindermoscopicskincancerimages AT marialinden automaticlesionsegmentationusingatrousconvolutionaldeepneuralnetworksindermoscopicskincancerimages |