Skip to main content
Top
Published in:

Open Access 01-12-2022 | Melanoma | Research

Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images

Authors: Ranpreet Kaur, Hamid GholamHosseini, Roopak Sinha, Maria Lindén

Published in: BMC Medical Imaging | Issue 1/2022

Login to get access

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.
Literature
1.
go back to reference Elwood JM, Jopson J. Melanoma and sun exposure: An overview of published studies. Int J Cancer. 1997;73(2):198–203.CrossRef Elwood JM, Jopson J. Melanoma and sun exposure: An overview of published studies. Int J Cancer. 1997;73(2):198–203.CrossRef
2.
go back to reference Bogo F, Peruch F, Fortina A, Peserico E, Celebi M, Mendonca T, Marques J. Where’s the lesion? Variability in human and automated segmentation of dermoscopy images of melanocytic skin lesions. Boca Raton: CRC Press; 2015.CrossRef Bogo F, Peruch F, Fortina A, Peserico E, Celebi M, Mendonca T, Marques J. Where’s the lesion? Variability in human and automated segmentation of dermoscopy images of melanocytic skin lesions. Boca Raton: CRC Press; 2015.CrossRef
3.
go back to reference Schadendorf D, van Akkooi AC, Berking C, Griewank KG, Gutzmer R, Hauschild A, Stang A, Roesch A, Ugurel S. Melanoma. Lancet. 2018;392(10151):971–84.CrossRef Schadendorf D, van Akkooi AC, Berking C, Griewank KG, Gutzmer R, Hauschild A, Stang A, Roesch A, Ugurel S. Melanoma. Lancet. 2018;392(10151):971–84.CrossRef
6.
go back to reference Ruiz ES, Morgan FC, Zigler CM, Besaw RJ, Schmults CD. Analysis of national skin cancer expenditures in the United States medicare population, 2013. J Am Acad Dermatol. 2019;80(1):275–8.CrossRef Ruiz ES, Morgan FC, Zigler CM, Besaw RJ, Schmults CD. Analysis of national skin cancer expenditures in the United States medicare population, 2013. J Am Acad Dermatol. 2019;80(1):275–8.CrossRef
7.
go back to reference Guy GP Jr, Machlin SR, Ekwueme DU, Yabroff KR. Prevalence and costs of skin cancer treatment in the US, 2002–2006 and 2007–2011. Am J Prev Med. 2015;48(2):183–7.CrossRef Guy GP Jr, Machlin SR, Ekwueme DU, Yabroff KR. Prevalence and costs of skin cancer treatment in the US, 2002–2006 and 2007–2011. Am J Prev Med. 2015;48(2):183–7.CrossRef
8.
go back to reference Rigel DS, Friedman RJ, Kopf AW, Polsky D. ABCDE: an evolving concept in the early detection of melanoma. Arch Dermatol. 2005;141(8):1032–4.CrossRef Rigel DS, Friedman RJ, Kopf AW, Polsky D. ABCDE: an evolving concept in the early detection of melanoma. Arch Dermatol. 2005;141(8):1032–4.CrossRef
9.
go back to reference Chen L-C, Papandreou G, Schroff F, Adam H. Rethinking atrous convolution for semantic image segmentation. 2017. arXiv preprint. arXiv:1706.05587. Chen L-C, Papandreou G, Schroff F, Adam H. Rethinking atrous convolution for semantic image segmentation. 2017. arXiv preprint. arXiv:​1706.​05587.
10.
go back to reference Gutman D, Codella N.C, Celebi E, Helba B, Marchetti M, Mishra N, Halpern A. Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). 2016. arXiv preprint. arXiv:1605.01397. Gutman D, Codella N.C, Celebi E, Helba B, Marchetti M, Mishra N, Halpern A. Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). 2016. arXiv preprint. arXiv:​1605.​01397.
11.
go back to reference Codella NC, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza SW, Kalloo A, Liopyris K, Mishra N, Kittler H, et al. Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISIC), hosted by the international skin imaging collaboration (ISIC). In: IEEE 15th international symposium on biomedical imaging (ISBI 2018). IEEE; 2018. p. 168–172. Codella NC, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza SW, Kalloo A, Liopyris K, Mishra N, Kittler H, et al. Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISIC), hosted by the international skin imaging collaboration (ISIC). In: IEEE 15th international symposium on biomedical imaging (ISBI 2018). IEEE; 2018. p. 168–172.
12.
go back to reference Codella N, Rotemberg V, Tschandl P, Celebi ME, Dusza S, Gutman D, Helba B, Kalloo A, Liopyris K, Marchetti M, et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). 2019. arXiv preprint. arXiv:1902.03368. Codella N, Rotemberg V, Tschandl P, Celebi ME, Dusza S, Gutman D, Helba B, Kalloo A, Liopyris K, Marchetti M, et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). 2019. arXiv preprint. arXiv:​1902.​03368.
13.
go back to reference Tschandl P, Rosendahl C, Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data. 2018;5: 180161.CrossRef Tschandl P, Rosendahl C, Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data. 2018;5: 180161.CrossRef
14.
go back to reference Lee I, Du X, Anthony B. Hair segmentation using adaptive threshold from edge and branch length measures. Comput Biol Med. 2017;89:314–24.CrossRef Lee I, Du X, Anthony B. Hair segmentation using adaptive threshold from edge and branch length measures. Comput Biol Med. 2017;89:314–24.CrossRef
15.
go back to reference Garnavi R, Aldeen M, Celebi ME, Varigos G, Finch S. Border detection in dermoscopy images using hybrid thresholding on optimized color channels. Comput Med Imaging Graph. 2011;35(2):105–15.CrossRef Garnavi R, Aldeen M, Celebi ME, Varigos G, Finch S. Border detection in dermoscopy images using hybrid thresholding on optimized color channels. Comput Med Imaging Graph. 2011;35(2):105–15.CrossRef
16.
go back to reference Aitnouri E, Ouali M. Performance evaluation of clustering techniques for image segmentation. Comput Sci J Mold. 2010;54(3):271–302. Aitnouri E, Ouali M. Performance evaluation of clustering techniques for image segmentation. Comput Sci J Mold. 2010;54(3):271–302.
17.
go back to reference Vasconcelos FFX, Medeiros AG, Peixoto SA, Reboucas Filho PP. Automatic skin lesions segmentation based on a new morphological approach via geodesic active contour. Cogn Syst Res. 2019;55:44–59.CrossRef Vasconcelos FFX, Medeiros AG, Peixoto SA, Reboucas Filho PP. Automatic skin lesions segmentation based on a new morphological approach via geodesic active contour. Cogn Syst Res. 2019;55:44–59.CrossRef
18.
go back to reference Moghaddam MJ, Soltanian-Zadeh H. Medical image segmentation using artificial neural networks. Artif Neural Netw Methodol Adv Biomed Appl. 2011;6:121–38. Moghaddam MJ, Soltanian-Zadeh H. Medical image segmentation using artificial neural networks. Artif Neural Netw Methodol Adv Biomed Appl. 2011;6:121–38.
19.
go back to reference Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 3431–3440. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 3431–3440.
20.
21.
go back to reference Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39(12):2481–95.CrossRef Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39(12):2481–95.CrossRef
22.
go back to reference Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer; 2015. p. 234–241. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer; 2015. p. 234–241.
23.
go back to reference Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell. 2017;40(4):834–48.CrossRef Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell. 2017;40(4):834–48.CrossRef
24.
go back to reference Kawahara J, BenTaieb A, Hamarneh G. Deep features to classify skin lesions. In: IEEE 13th international symposium on biomedical imaging (ISBI). IEEE; 2016. p. 1397–1400. Kawahara J, BenTaieb A, Hamarneh G. Deep features to classify skin lesions. In: IEEE 13th international symposium on biomedical imaging (ISBI). IEEE; 2016. p. 1397–1400.
25.
go back to reference Bi L, Kim J, Ahn E, Kumar A, Feng D, Fulham M. Step-wise integration of deep class-specific learning for dermoscopic image segmentation. Pattern Recogn. 2019;85:78–89.CrossRef Bi L, Kim J, Ahn E, Kumar A, Feng D, Fulham M. Step-wise integration of deep class-specific learning for dermoscopic image segmentation. Pattern Recogn. 2019;85:78–89.CrossRef
26.
go back to reference Yu L, Chen H, Dou Q, Qin J, Heng P-A. Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging. 2016;36(4):994–1004.CrossRef Yu L, Chen H, Dou Q, Qin J, Heng P-A. Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging. 2016;36(4):994–1004.CrossRef
27.
go back to reference Al-Masni MA, Al-Antari MA, Choi M-T, Han S-M, Kim T-S. Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Comput Methods Programs Biomed. 2018;162:221–31.CrossRef Al-Masni MA, Al-Antari MA, Choi M-T, Han S-M, Kim T-S. Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Comput Methods Programs Biomed. 2018;162:221–31.CrossRef
28.
go back to reference Bi L, Kim J, Ahn E, Kumar A, Fulham M, Feng D. Dermoscopic image segmentation via multistage fully convolutional networks. IEEE Trans Biomed Eng. 2017;64(9):2065–74.CrossRef Bi L, Kim J, Ahn E, Kumar A, Fulham M, Feng D. Dermoscopic image segmentation via multistage fully convolutional networks. IEEE Trans Biomed Eng. 2017;64(9):2065–74.CrossRef
29.
go back to reference Hasan MK, Elahi MTE, Alam MA, Jawad MT. DermoExpert: skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation. medRxiv. 2021. Hasan MK, Elahi MTE, Alam MA, Jawad MT. DermoExpert: skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation. medRxiv. 2021.
30.
go back to reference Pour MP, Seker H. Transform domain representation-driven convolutional neural networks for skin lesion segmentation. Expert Syst Appl. 2020;144: 113129.CrossRef Pour MP, Seker H. Transform domain representation-driven convolutional neural networks for skin lesion segmentation. Expert Syst Appl. 2020;144: 113129.CrossRef
31.
go back to reference Vesal S, Ravikumar N, Maier A. SkinNet: a deep learning framework for skin lesion segmentation. In: IEEE nuclear science symposium and medical imaging conference proceedings (NSS/MIC). IEEE; 2018. p. 1–3. Vesal S, Ravikumar N, Maier A. SkinNet: a deep learning framework for skin lesion segmentation. In: IEEE nuclear science symposium and medical imaging conference proceedings (NSS/MIC). IEEE; 2018. p. 1–3.
32.
go back to reference Yuan Y, Chao M, Lo Y-C. Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging. 2017;36(9):1876–86.CrossRef Yuan Y, Chao M, Lo Y-C. Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging. 2017;36(9):1876–86.CrossRef
33.
go back to reference Liu L, Tsui YY, Mandal M. Skin lesion segmentation using deep learning with auxiliary task. J Imaging. 2021;7(4):67.CrossRef Liu L, Tsui YY, Mandal M. Skin lesion segmentation using deep learning with auxiliary task. J Imaging. 2021;7(4):67.CrossRef
34.
go back to reference Bishop CM. Pattern recognition and machine learning. New York: Springer; 2006. Bishop CM. Pattern recognition and machine learning. New York: Springer; 2006.
35.
go back to reference Mendonça T, Ferreira PM, Marques JS, Marcal AR, Rozeira J. \({PH}^{2}\)-A dermoscopic image database for research and benchmarking. In: 35th Annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE; 2013. p. 5437–5440. Mendonça T, Ferreira PM, Marques JS, Marcal AR, Rozeira J. \({PH}^{2}\)-A dermoscopic image database for research and benchmarking. In: 35th Annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE; 2013. p. 5437–5440.
37.
38.
go back to reference Qian C, Liu T, Jiang H, Wang Z, Wang P, Guan M, Sun B. A detection and segmentation architecture for skin lesion segmentation on dermoscopy images. 2018. arXiv preprint. arXiv:1809.03917. Qian C, Liu T, Jiang H, Wang Z, Wang P, Guan M, Sun B. A detection and segmentation architecture for skin lesion segmentation on dermoscopy images. 2018. arXiv preprint. arXiv:​1809.​03917.
39.
go back to reference Berseth M. ISIC 2017-skin lesion analysis towards melanoma detection. CoRR. abs/1703.00523. 2017. Berseth M. ISIC 2017-skin lesion analysis towards melanoma detection. CoRR. abs/1703.00523. 2017.
42.
go back to reference Bi L, Kim J, Ahn E, Feng D. Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. 2017. arXiv preprint. arXiv:1703.04197. Bi L, Kim J, Ahn E, Feng D. Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. 2017. arXiv preprint. arXiv:​1703.​04197.
43.
go back to reference Ji Y, Li X, Zhang G, Lin D, Chen H. Automatic skin lesion segmentation by feature aggregation convolutional neural network. Technical report. 2018. Ji Y, Li X, Zhang G, Lin D, Chen H. Automatic skin lesion segmentation by feature aggregation convolutional neural network. Technical report. 2018.
44.
go back to reference Huang L, Zhao Y-G, Yang T-J. Skin lesion segmentation using object scale-oriented fully convolutional neural networks. Signal Image Video Process. 2019;13(3):431–8.CrossRef Huang L, Zhao Y-G, Yang T-J. Skin lesion segmentation using object scale-oriented fully convolutional neural networks. Signal Image Video Process. 2019;13(3):431–8.CrossRef
45.
go back to reference Menegola A, Tavares J, Fornaciali M, Li L.T, Avila S, Valle E. Recod titans at ISIC challenge 2017. 2017. arXiv preprint. arXiv:1703.04819. Menegola A, Tavares J, Fornaciali M, Li L.T, Avila S, Valle E. Recod titans at ISIC challenge 2017. 2017. arXiv preprint. arXiv:​1703.​04819.
47.
go back to reference Xie F, Yang J, Liu J, Jiang Z, Zheng Y, Wang Y. Skin lesion segmentation using high-resolution convolutional neural network. Comput Methods Programs Biomed. 2020;186: 105241.CrossRef Xie F, Yang J, Liu J, Jiang Z, Zheng Y, Wang Y. Skin lesion segmentation using high-resolution convolutional neural network. Comput Methods Programs Biomed. 2020;186: 105241.CrossRef
48.
go back to reference Zafar K, Gilani SO, Waris A, Ahmed A, Jamil M, Khan MN, Sohail Kashif A. Skin lesion segmentation from dermoscopic images using convolutional neural network. Sensors. 2020;20(6):1601.CrossRef Zafar K, Gilani SO, Waris A, Ahmed A, Jamil M, Khan MN, Sohail Kashif A. Skin lesion segmentation from dermoscopic images using convolutional neural network. Sensors. 2020;20(6):1601.CrossRef
49.
go back to reference Ali R, Hardie RC, De Silva MS, Kebede TM. Skin lesion segmentation and classification for ISIC 2018 by combining deep CNN and handcrafted features. 2019. arXiv preprint arXiv:1908.05730. Ali R, Hardie RC, De Silva MS, Kebede TM. Skin lesion segmentation and classification for ISIC 2018 by combining deep CNN and handcrafted features. 2019. arXiv preprint arXiv:​1908.​05730.
50.
go back to reference Lei B, Xia Z, Jiang F, Jiang X, Ge Z, Xu Y, Qin J, Chen S, Wang T, Wang S. Skin lesion segmentation via generative adversarial networks with dual discriminators. Med Image Anal. 2020;64: 101716.CrossRef Lei B, Xia Z, Jiang F, Jiang X, Ge Z, Xu Y, Qin J, Chen S, Wang T, Wang S. Skin lesion segmentation via generative adversarial networks with dual discriminators. Med Image Anal. 2020;64: 101716.CrossRef
51.
go back to reference Ashraf H, Waris A, Ghafoor MF, Gilani SO, Niazi IK. Melanoma segmentation using deep learning with test-time augmentations and conditional random fields. Sci Rep. 2022;12(1):1–16.CrossRef Ashraf H, Waris A, Ghafoor MF, Gilani SO, Niazi IK. Melanoma segmentation using deep learning with test-time augmentations and conditional random fields. Sci Rep. 2022;12(1):1–16.CrossRef
52.
go back to reference Chu T, Li X, Vo H.V, Summers R.M, Sizikova E. Improving weakly supervised lesion segmentation using multi-task learning. In: Medical imaging with deep learning. PMLR; 2021. p. 60–73. Chu T, Li X, Vo H.V, Summers R.M, Sizikova E. Improving weakly supervised lesion segmentation using multi-task learning. In: Medical imaging with deep learning. PMLR; 2021. p. 60–73.
53.
go back to reference Tong X, Wei J, Sun B, Su S, Zuo Z, Wu P. ASCU-Net: attention gate, spatial and channel attention U-Net for skin lesion segmentation. Diagnostics. 2021;11(3):501.CrossRef Tong X, Wei J, Sun B, Su S, Zuo Z, Wu P. ASCU-Net: attention gate, spatial and channel attention U-Net for skin lesion segmentation. Diagnostics. 2021;11(3):501.CrossRef
Metadata
Title
Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images
Authors
Ranpreet Kaur
Hamid GholamHosseini
Roopak Sinha
Maria Lindén
Publication date
01-12-2022
Publisher
BioMed Central
Published in
BMC Medical Imaging / Issue 1/2022
Electronic ISSN: 1471-2342
DOI
https://doi.org/10.1186/s12880-022-00829-y

Other articles of this Issue 1/2022

BMC Medical Imaging 1/2022 Go to the issue