Automatic 3D cell segmentation of fruit parenchyma tissue from X-ray micro CT images using deep learning

被引:2
作者
Van Doorselaer, Leen [1 ]
Verboven, Pieter [1 ]
Nicolai, Bart [1 ,2 ]
机构
[1] Katholieke Univ Leuven, Biosyst Dept, Mechatron Biostat & Sensors MeBioS, Leuven, Belgium
[2] Flanders Ctr Postharvest Biol, Leuven, Belgium
关键词
Plant microstructure; Fruit physiology; X-ray micro-computed tomography; Contrast-enhanced imaging; Image processing; Artificial intelligence; Instance segmentation; CONTROLLED-ATMOSPHERE STORAGE; BROWNING DISORDER; GAS-EXCHANGE; MODEL;
D O I
10.1186/s13007-024-01137-y
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
BackgroundHigh quality 3D information of the microscopic plant tissue morphology-the spatial organization of cells and intercellular spaces in tissues-helps in understanding physiological processes in a wide variety of plants and tissues. X-ray micro-CT is a valuable tool that is becoming increasingly available in plant research to obtain 3D microstructural information of the intercellular pore space and individual pore sizes and shapes of tissues. However, individual cell morphology is difficult to retrieve from micro-CT as cells cannot be segmented properly due to negligible density differences at cell-to-cell interfaces. To address this, deep learning-based models were trained and tested to segment individual cells using X-ray micro-CT images of parenchyma tissue samples from apple and pear fruit with different cell and porosity characteristics.ResultsThe best segmentation model achieved an Aggregated Jaccard Index (AJI) of 0.86 and 0.73 for apple and pear tissue, respectively, which is an improvement over the current benchmark method that achieved AJIs of 0.73 and 0.67. Furthermore, the neural network was able to detect other plant tissue structures such as vascular bundles and stone cell clusters (brachysclereids), of which the latter were shown to strongly influence the spatial organization of pear cells. Based on the AJIs, apple tissue was found to be easier to segment, as the porosity and specific surface area of the pore space are higher and lower, respectively, compared to pear tissue. Moreover, samples with lower pore network connectivity, proved very difficult to segment.ConclusionsThe proposed method can be used to automatically quantify 3D cell morphology of plant tissue from micro-CT instead of opting for laborious manual annotations or less accurate segmentation approaches. In case fruit tissue porosity or pore network connectivity is too low or the specific surface area of the pore space too high, native X-ray micro-CT is unable to provide proper marker points of cell outlines, and one should rely on more elaborate contrast-enhancing scan protocols.
引用
收藏
页数:19
相关论文
共 51 条
[21]   3D pore structure analysis of intact 'Braeburn' apples using X-ray micro-CT [J].
Janssen, Siem ;
Verboven, Pieter ;
Nugraha, Bayu ;
Wang, Zi ;
Boone, Matthieu ;
Josipovic, Ivan ;
Nicolai, Bart M. .
POSTHARVEST BIOLOGY AND TECHNOLOGY, 2020, 159
[22]   Benchmarking of deep learning algorithms for 3D instance segmentation of confocal image datasets [J].
Kar, Anuradha ;
Petit, Manuel ;
Refahi, Yassin ;
Cerutti, Guillaume ;
Godin, Christophe ;
Traas, Jan .
PLOS COMPUTATIONAL BIOLOGY, 2022, 18 (04)
[23]  
Kassambara A., 2023, rstatix: Pipe-Friendly Framework for Basic Statistical Tests.
[24]   mdatools - R package for chemometrics [J].
Kucheryayskiy, Sergey .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2020, 198
[25]   A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology [J].
Kumar, Neeraj ;
Verma, Ruchika ;
Sharma, Sanuj ;
Bhargava, Surabhi ;
Vahadane, Abhishek ;
Sethi, Amit .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (07) :1550-1560
[26]   Antioxidant treatment alters metabolism associated with internal browning in 'Braeburn' apples during controlled atmosphere storage [J].
Lee, Jinwook ;
Mattheis, James P. ;
Rudell, David R. .
POSTHARVEST BIOLOGY AND TECHNOLOGY, 2012, 68 :32-42
[27]   Cell density and airspace patterning in the leaf can be manipulated to increase leaf photosynthetic capacity [J].
Lehmeier, Christoph ;
Pajor, Radoslaw ;
Lundgren, Marjorie R. ;
Mathers, Andrew ;
Sloan, Jen ;
Bauch, Marion ;
Mitchell, Alice ;
Bellasio, Chandra ;
Green, Adam ;
Bouyer, Daniel ;
Schnittger, Arp ;
Sturrock, Craig ;
Osborne, Colin P. ;
Rolfe, Stephen ;
Mooney, Sacha ;
Fleming, Andrew J. .
PLANT JOURNAL, 2017, 92 (06) :981-994
[28]   Size does matter - susceptibility of apple for grey mould is affected by cell size [J].
Naets, M. ;
Wang, Z. ;
Verboven, P. ;
Nicolai, B. ;
Keulemans, W. ;
Geeraerd, A. .
PLANT PATHOLOGY, 2020, 69 (01) :60-67
[29]   Gas exchange model using heterogeneous diffusivity to study internal browning in 'Conference' pear [J].
Nugraha, Bayu ;
Verboven, Pieter ;
Verlinden, Bert E. ;
Verreydt, Celine ;
Boone, Matthieu ;
Josipovic, Ivan ;
Nicolai, Bart M. .
POSTHARVEST BIOLOGY AND TECHNOLOGY, 2022, 191
[30]   Oxygen diffusivity mapping of fruit and vegetables based on X-ray CT [J].
Nugraha, Bayu ;
Verboven, Pieter ;
Janssen, Siem ;
Hertog, Maarten L. A. T. M. ;
Boone, Matthieu ;
Josipovic, Ivan ;
Nicolai, Bart M. .
JOURNAL OF FOOD ENGINEERING, 2021, 306