Research on Soil Pore Segmentation of CT Images Based on MMLFR-UNet Hybrid Network

Guardado en:
Detalles Bibliográficos
Publicado en:Agronomy vol. 15, no. 5 (2025), p. 1170
Autor principal: Qin Changfeng
Otros Autores: Zhang, Jie, Duan, Yu, Li, Chenyang, Dong Shanzhi, Mu, Feng, Chi Chengquan, Han, Ying
Publicado:
MDPI AG
Materias:
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3211846980
003 UK-CbPIL
022 |a 2073-4395 
024 7 |a 10.3390/agronomy15051170  |2 doi 
035 |a 3211846980 
045 2 |b d20250101  |b d20251231 
084 |a 231332  |2 nlm 
100 1 |a Qin Changfeng  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
245 1 |a Research on Soil Pore Segmentation of CT Images Based on MMLFR-UNet Hybrid Network 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Accurate segmentation of soil pore structure is crucial for studying soil water migration, nutrient cycling, and gas exchange. However, the low-contrast and high-noise CT images in complex soil environments cause the traditional segmentation methods to have obvious deficiencies in accuracy and robustness. This paper proposes a hybrid model combining a Multi-Modal Low-Frequency Reconstruction algorithm (MMLFR) and UNet (MMLFR-UNet). MMLFR enhances the key feature expression by extracting the image low-frequency signals and suppressing the noise interference through the multi-scale spectral decomposition, whereas UNet excels in the segmentation detail restoration and complexity boundary processing by virtue of its coding-decoding structure and the hopping connection mechanism. In this paper, an undisturbed soil column was collected in Hainan Province, China, which was classified as Ferralsols (FAO/UNESCO), and CT scans were utilized to acquire high-resolution images and generate high-quality datasets suitable for deep learning through preprocessing operations such as fixed-layer sampling, cropping, and enhancement. The results show that MMLFR-UNet outperforms UNet and traditional methods (e.g., Otsu and Fuzzy C-Means (FCM)) in terms of Intersection over Union (IoU), Dice Similarity Coefficients (DSC), Pixel Accuracy (PA), and boundary similarity. Notably, this model exhibits exceptional robustness and precision in segmentation tasks involving complex pore structures and low-contrast images. 
651 4 |a Hainan Island 
653 |a Image resolution 
653 |a Decoding 
653 |a Segmentation 
653 |a Task complexity 
653 |a Soil water 
653 |a Gas exchange 
653 |a Image processing 
653 |a Soil environment 
653 |a Deep learning 
653 |a Accuracy 
653 |a Soil sciences 
653 |a Moisture content 
653 |a Image reconstruction 
653 |a Fourier transforms 
653 |a Computed tomography 
653 |a Image segmentation 
653 |a Permeability 
653 |a Nutrient cycles 
653 |a Soil columns 
653 |a Algorithms 
653 |a Image acquisition 
653 |a Image quality 
653 |a Robustness (mathematics) 
653 |a Morphology 
700 1 |a Zhang, Jie  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
700 1 |a Duan, Yu  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
700 1 |a Li, Chenyang  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
700 1 |a Dong Shanzhi  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
700 1 |a Mu, Feng  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
700 1 |a Chi Chengquan  |u School of Information Science and Technology, Hainan Normal University, Haikou 571158, China; qcf1428@gmail.com (C.Q.); z15882515884@gmail.com (J.Z.); lhua7430@gmail.com (Y.D.); lcy5653@163.com (C.L.); dongshanzhi204730@gmail.com (S.D.); mf17339680919@163.com (F.M.) 
700 1 |a Han, Ying  |u College of Geography and Environmental Science, Hainan Normal University, Haikou 571158, China 
773 0 |t Agronomy  |g vol. 15, no. 5 (2025), p. 1170 
786 0 |d ProQuest  |t Agriculture Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3211846980/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3211846980/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3211846980/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch