Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings
Colon polyps, small clump of cells on the lining of the colon, can lead to colorectal cancer (CRC), one of the leading types of cancer globally. Hence, early detection of these polyps automatically is crucial in the prevention of CRC. The deep learning models proposed for the detection and segmentat...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/8/6/169 |
| _version_ | 1797485818208583680 |
|---|---|
| author | Ranit Karmakar Saeid Nooshabadi |
| author_facet | Ranit Karmakar Saeid Nooshabadi |
| author_sort | Ranit Karmakar |
| collection | DOAJ |
| description | Colon polyps, small clump of cells on the lining of the colon, can lead to colorectal cancer (CRC), one of the leading types of cancer globally. Hence, early detection of these polyps automatically is crucial in the prevention of CRC. The deep learning models proposed for the detection and segmentation of colorectal polyps are resource-consuming. This paper proposes a lightweight deep learning model for colorectal polyp segmentation that achieved state-of-the-art accuracy while significantly reducing the model size and complexity. The proposed deep learning autoencoder model employs a set of state-of-the-art architectural blocks and optimization objective functions to achieve the desired efficiency. The model is trained and tested on five publicly available colorectal polyp segmentation datasets (CVC-ClinicDB, CVC-ColonDB, EndoScene, Kvasir, and ETIS). We also performed ablation testing on the model to test various aspects of the autoencoder architecture. We performed the model evaluation by using most of the common image-segmentation metrics. The backbone model achieved a DICE score of 0.935 on the Kvasir dataset and 0.945 on the CVC-ClinicDB dataset, improving the accuracy by 4.12% and 5.12%, respectively, over the current state-of-the-art network, while using 88 times fewer parameters, 40 times less storage space, and being computationally 17 times more efficient. Our ablation study showed that the addition of ConvSkip in the autoencoder slightly improves the model’s performance but it was not significant (<i>p</i>-value = 0.815). |
| first_indexed | 2024-03-09T23:24:20Z |
| format | Article |
| id | doaj.art-4e365538eedf4d91b707848072968336 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-09T23:24:20Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-4e365538eedf4d91b7078480729683362023-11-23T17:20:39ZengMDPI AGJournal of Imaging2313-433X2022-06-018616910.3390/jimaging8060169Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource SettingsRanit Karmakar0Saeid Nooshabadi1Electrical and Computer Engineering, Michigan Technological University, Houghton, MI 49931, USAElectrical and Computer Engineering, Michigan Technological University, Houghton, MI 49931, USAColon polyps, small clump of cells on the lining of the colon, can lead to colorectal cancer (CRC), one of the leading types of cancer globally. Hence, early detection of these polyps automatically is crucial in the prevention of CRC. The deep learning models proposed for the detection and segmentation of colorectal polyps are resource-consuming. This paper proposes a lightweight deep learning model for colorectal polyp segmentation that achieved state-of-the-art accuracy while significantly reducing the model size and complexity. The proposed deep learning autoencoder model employs a set of state-of-the-art architectural blocks and optimization objective functions to achieve the desired efficiency. The model is trained and tested on five publicly available colorectal polyp segmentation datasets (CVC-ClinicDB, CVC-ColonDB, EndoScene, Kvasir, and ETIS). We also performed ablation testing on the model to test various aspects of the autoencoder architecture. We performed the model evaluation by using most of the common image-segmentation metrics. The backbone model achieved a DICE score of 0.935 on the Kvasir dataset and 0.945 on the CVC-ClinicDB dataset, improving the accuracy by 4.12% and 5.12%, respectively, over the current state-of-the-art network, while using 88 times fewer parameters, 40 times less storage space, and being computationally 17 times more efficient. Our ablation study showed that the addition of ConvSkip in the autoencoder slightly improves the model’s performance but it was not significant (<i>p</i>-value = 0.815).https://www.mdpi.com/2313-433X/8/6/169colorectal cancerpolyp segmentationdeep learning |
| spellingShingle | Ranit Karmakar Saeid Nooshabadi Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings Journal of Imaging colorectal cancer polyp segmentation deep learning |
| title | Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings |
| title_full | Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings |
| title_fullStr | Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings |
| title_full_unstemmed | Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings |
| title_short | Mobile-PolypNet: Lightweight Colon Polyp Segmentation Network for Low-Resource Settings |
| title_sort | mobile polypnet lightweight colon polyp segmentation network for low resource settings |
| topic | colorectal cancer polyp segmentation deep learning |
| url | https://www.mdpi.com/2313-433X/8/6/169 |
| work_keys_str_mv | AT ranitkarmakar mobilepolypnetlightweightcolonpolypsegmentationnetworkforlowresourcesettings AT saeidnooshabadi mobilepolypnetlightweightcolonpolypsegmentationnetworkforlowresourcesettings |