Image based cellular contractile force evaluation with small-world network inspired CNN: SW-UNet

Li, Honghan; Matsunaga, Daiki; Matsui, Tsubasa S.; Aosaki, Hiroki; Deguchi, Shinji

doi:10.1016/j.bbrc.2020.04.134

Cited by 9 publications

(15 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on our previous studies (16, 19, 22–24), we prepared the substrate that can reversibly generate wrinkles upon application of cellular forces. Firstly, a circular cover glass is treated with oxygen plasma (SEDE-GE, Meiwafosis) to hydrophilize the surface and is desiccated after fluorescent micro-beads (0.2 μ m in diameter, carboxylate yellow-green fluorescent beads; Invitrogen) in water solution are distributed on the surface.…”

Section: Methodsmentioning

confidence: 99%

“…We use a new method SW-UNet (19), which is a CNN based on U-Net (35) to extract wrinkle patterns from the microscope image as shown in Fig. 1(b).…”

Section: Methodsmentioning

confidence: 99%

“…Second, the wrinkle positions are extracted from the microscope images as shown in Fig. 1(b) by using our SW-UNet (small world U-Net) (19), which is a convolutional neural network (CNN) that reflects the concept of the small world networks (25, 26). Third, the machine learning system utilizing GAN (27) is trained to understand a way to convert the microscope image, or the extracted wrinkle image, to the cellular force distributions as shown in Fig.…”

Section: Full Picture Of the Systemmentioning

confidence: 99%

“…As shown in Fig. 1(a), the cellular contractile forces are obtained using the traction force microscopy (TFM) (13), and cells generate wrinkles because the surface of PDMS layer is harden by the plasma irradiation (9,12,(14)(15)(16). Second, the wrinkle positions are extracted from the microscope images as shown in Fig.…”

Section: Overviewmentioning

confidence: 99%

“…We previously developed a wrinkle assay, a modified version of the method originally reported by Harris and colleagues (13, 14), in which the silicone substrates are spatially treated with uniform oxygen plasma to allow them to buckle upon the forces exerted by cells (15–17). As the individual wrinkles are lengthened with the increase in the forces (18), the wrinkle length, detected for example by a machine learning approach (19), can be used as a measure of the relative change in the force caused by perturbations such as specific gene mutations. While this technology is promising in that these experiments are performed easily to potentially enable a high-throughput analysis on the force-related pathways, the interpretation of the wrinkle length was not necessarily straightforward in terms of quantitatively measuring the magnitude and direction of traction forces.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Wrinkle force microscopy: a new machine learning based approach to predict cell mechanics from images

Li¹,

Matsunaga²,

Matsui³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a new machine learning system that can predict the cellular force distributions from the microscope images. The full process can be divided into three steps. First, we culture the cells on a special substrate and measure both the cellular contractile force and the substrate wrinkles simultaneously. The cellular contractile forces are obtained using the traction force microscopy (TFM), while cells generate wrinkles thanks to our original plasma-irradiated substrates. Second, the wrinkle positions are extracted from the microscope images by using SW-UNet. Third, we train the machine learning system with GAN (generative adversarial network) by using sets of corresponding two images, the force distributions and the input images (raw microscope images or extracted wrinkle images), as the training data. The network understands the way to convert the input images to the force distributions from the training. After sufficient training, the network can be utilized to predict the cellular forces just from the input images. Comparing with the TFM experiment (test data), our system has 33-35% errors in the force magnitude prediction and angle errors 19-20 o in the force direction. The system would be a powerful tool to evaluate the cellular forces efficiently because the forces can be predicted just by observing the cells, which is a way simpler method compared to the TFM experiment. We believe that our machine learning based system will be an useful method for other cellular assay applicants and researches in the future.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We use a new method SW-UNet (19), which is a CNN based on U-Net (35) to extract wrinkle patterns from the microscope image as shown in Fig. 1(b).…”

Section: Methodsmentioning

confidence: 99%

Section: Full Picture Of the Systemmentioning

confidence: 99%

Section: Overviewmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Wrinkle force microscopy: a new machine learning based approach to predict cell mechanics from images

Li¹,

Matsunaga²,

Matsui³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

LSW‐Net: Lightweight Deep Neural Network Based on Small‐World properties for Spine MR Image Segmentation

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundSegmenting spinal tissues from MR images is important for automatic image analysis. Deep neural network‐based segmentation methods are efficient, yet have high computational costs.PurposeTo design a lightweight model based on small‐world properties (LSW‐Net) to segment spinal MR images, suitable for low‐computing‐power embedded devices.Study TypeRetrospective.PopulationA total of 386 subjects (2948 images) from two independent sources. Dataset I: 214 subjects/779 images, all for disk degeneration screening, 147 had disk degeneration, 52 had herniated disc. Dataset II: 172 subjects/2169 images, 142 patients with vertebral degeneration, 163 patients with disc degeneration. 70% images in each dataset for training, 20% for validation, and 10% for testing.Field Strength/SequenceT1‐ and T2‐weighted turbo spin echo sequences at 3 T.AssessmentSegmentation performance of LSW‐Net was compared with four mainstream (including U‐net and U‐net++) and five lightweight models using five radiologists' manual segmentations (vertebrae, disks, spinal fluid) as reference standard. LSW‐Net was also deployed on NVIDIA Jetson nano to compare the pixels number in segmented vertebrae and disks.Statistical TestsAll models were evaluated with accuracy, precision, Dice similarity coefficient (DSC), and area under the receiver operating characteristic (AUC). Pixel numbers segmented by LSW‐Net on the embedded device were compared with manual segmentation using paired t‐tests, with P < 0.05 indicating significance.ResultsLSW‐Net had 98.5% fewer parameters than U‐net but achieved similar accuracy in both datasets (dataset I: DSC 0.84 vs. 0.87, AUC 0.92 vs. 0.94; dataset II: DSC 0.82 vs. 0.82, AUC 0.88 vs. 0.88). LSW‐Net showed no significant differences in pixel numbers for vertebrae (dataset I: 5893.49 vs. 5752.61, P = 0.21; dataset II: 5073.42 vs. 5137.12, P = 0.56) and disks (dataset I: 1513.07 vs. 1535.69, P = 0.42; dataset II: 1049.74 vs. 1087.88, P = 0.24) segmentation on an embedded device compared to manual segmentation.Data ConclusionProposed LSW‐Net achieves high accuracy with fewer parameters than U‐net and can be deployed on embedded device, facilitating wider application.Evidence Level2.Technical Efficacy1.

show abstract

Anomaly detection model of mammography using YOLOv4-based histogram

Kim

Chung

Park

2021

Pers Ubiquit Comput

View full text Add to dashboard Cite

Image based cellular contractile force evaluation with small-world network inspired CNN: SW-UNet

Cited by 9 publications

References 25 publications

Wrinkle force microscopy: a new machine learning based approach to predict cell mechanics from images

Wrinkle force microscopy: a new machine learning based approach to predict cell mechanics from images

LSW‐Net: Lightweight Deep Neural Network Based on Small‐World properties for Spine MR Image Segmentation

Anomaly detection model of mammography using YOLOv4-based histogram

Contact Info

Product

Resources

About