Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs

Nemoto, Takafumi; Futakami, Natsumi; Kunieda, Etsuo; Yagi, Masamichi; Takeda, Atsuya; Akiba, Takeshi; Mutu, Eride; Shigematsu, Naoyuki

doi:10.1007/s12194-021-00630-6

Cited by 29 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, because the code contains only random cropping and side-to-side flipping, we expect that additional data augmentation by simply replicating input images will improve performance. 20 Additionally, by changing the dataset files in the cloud, the U-Net framework based on pix2pix can be applied to other ocular imaging domains and other tasks.…”

Section: Discussionmentioning

confidence: 99%

“…A previous study described that the performance of U-Net stabilized after training more than 200 radiographic images and data augmentation provided an additional gain in segmentation performance. 20 The exploration of further data or augmentation techniques may be required in future work. Second, only three ophthalmologists performed annotations using polygons or free-hand drawing.…”

Section: Discussionmentioning

confidence: 99%

“…Considering the workload of manual segmentation and the proper number of training images provided by previous studies using U-Net or conditional GANs, 11 , 18 , 19 a dataset with more than 100 cases was considered sufficient to train the U-Net segmentation model. 20 Finally, the total dataset included fundus photographs and a segmentation image dataset from 194 eyes with CSC from medical centers and publicly accessible datasets. Additionally, we collected 93 fundus photographs of healthy eyes from the same sources to build a classification model to discriminate between CSCs and normal retinas.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Simple Code Implementation for Deep Learning–Based Segmentation to Evaluate Central Serous Chorioretinopathy in Fundus Photography

Yoo

Kim

Jeong

et al. 2022

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Purpose Central serous chorioretinopathy (CSC) is a retinal disease that frequently shows resolution and recurrence with serous detachment of the neurosensory retina. Here, we present a deep learning analysis of subretinal fluid (SRF) lesion segmentation in fundus photographs to evaluate CSC. Methods We collected 194 fundus photographs of SRF lesions from the patients with CSC. Three graders manually annotated of the entire SRF area in the retinal images. The dataset was randomly separated into training (90%) and validation (10%) datasets. We used the U-Net segmentation model based on conditional generative adversarial networks (pix2pix) to detect the SRF lesions. The algorithms were trained and validated using Google Colaboratory. Researchers did not need prior knowledge of coding skills or computing resources to implement this code. Results The validation results showed that the Jaccard index and Dice coefficient scores were 0.619 and 0.763, respectively. In most cases, the segmentation results overlapped with most of the reference areas in the annotated images. However, cases with exceptional SRFs were not accurate in terms of prediction. Using Colaboratory, the proposed segmentation task ran easily in a web-based environment without setup or personal computing resources. Conclusions The results suggest that the deep learning model based on U-Net from the pix2pix algorithm is suitable for the automatic segmentation of SRF lesions to evaluate CSC. Translational Relevance Our code implementation has the potential to facilitate ophthalmology research; in particular, deep learning–based segmentation can assist in the development of pathological lesion detection solutions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Simple Code Implementation for Deep Learning–Based Segmentation to Evaluate Central Serous Chorioretinopathy in Fundus Photography

Yoo

Kim

Jeong

et al. 2022

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…To predict the Dice scores of the three deep learning models with a large training set, we evaluated two regression models for learning curves using Eqs. ( 5 ) 29 and ( 6 ) 28 . We used the Akaike information criterion corrected for a finite number of samples (AIC c ) in Eq.…”

Section: Experimental Methodsmentioning

confidence: 99%

“…There has been no previous head-to-head comparison as a function of the number of training samples. Second, we evaluated the number of training samples required for such methods, including regression analyses for learning curves 28 , 29 . Third, we tested for the best approach to improve segmentation, using a GPU with a large amount of RAM (48 GB).…”

Section: Introductionmentioning

confidence: 99%

Deep learning multi-organ segmentation for whole mouse cryo-images including a comparison of 2D and 3D deep networks

Liu

Gargesha

Scott

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Cryo-imaging provided 3D whole-mouse microscopic color anatomy and fluorescence images that enables biotechnology applications (e.g., stem cells and metastatic cancer). In this report, we compared three methods of organ segmentation: 2D U-Net with 2D-slices and 3D U-Net with either 3D-whole-mouse or 3D-patches. We evaluated the brain, thymus, lung, heart, liver, stomach, spleen, left and right kidney, and bladder. Training with 63 mice, 2D-slices had the best performance, with median Dice scores of > 0.9 and median Hausdorff distances of < 1.2 mm in eightfold cross validation for all organs, except bladder, which is a problem organ due to variable filling and poor contrast. Results were comparable to those for a second analyst on the same data. Regression analyses were performed to fit learning curves, which showed that 2D-slices can succeed with fewer samples. Review and editing of 2D-slices segmentation results reduced human operator time from ~ 2-h to ~ 25-min, with reduced inter-observer variability. As demonstrations, we used organ segmentation to evaluate size changes in liver disease and to quantify the distribution of therapeutic mesenchymal stem cells in organs. With a 48-GB GPU, we determined that extra GPU RAM improved the performance of 3D deep learning because we could train at a higher resolution.

show abstract

Hyperparameter selection for dataset‐constrained semantic segmentation: Practical machine learning optimization

Boyd,

Brown,

Kleinig

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose/aimThis paper provides a pedagogical example for systematic machine learning optimization in small dataset image segmentation, emphasizing hyperparameter selections. A simple process is presented for medical physicists to examine hyperparameter optimization. This is also applied to a case‐study, demonstrating the benefit of the method.Materials and methodsAn unrestricted public Computed Tomography (CT) dataset, with binary organ segmentation, was used to develop a multiclass segmentation model. To start the optimization process, a preliminary manual search of hyperparameters was conducted and from there a grid search identified the most influential result metrics. A total of 658 different models were trained in 2100 h, using 13 160 effective patients. The quantity of results was analyzed using random forest regression, identifying relative hyperparameter impact.ResultsMetric implied segmentation quality (accuracy 96.8%, precision 95.1%) and visual inspection were found to be mismatched. In this work batch normalization was most important, but performance varied with hyperparameters and metrics selected. Targeted grid‐search optimization and random forest analysis of relative hyperparameter importance, was an easily implementable sensitivity analysis approach.ConclusionThe proposed optimization method gives a systematic and quantitative approach to something intuitively understood, that hyperparameters change model performance. Even just grid search optimization with random forest analysis presented here can be informative within hardware and data quality/availability limitations, adding confidence to model validity and minimize decision‐making risks. By providing a guided methodology, this work helps medical physicists to improve their model optimization, irrespective of specific challenges posed by datasets and model design.

show abstract

Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs

Cited by 29 publications

References 26 publications

Simple Code Implementation for Deep Learning–Based Segmentation to Evaluate Central Serous Chorioretinopathy in Fundus Photography

Simple Code Implementation for Deep Learning–Based Segmentation to Evaluate Central Serous Chorioretinopathy in Fundus Photography

Deep learning multi-organ segmentation for whole mouse cryo-images including a comparison of 2D and 3D deep networks

Hyperparameter selection for dataset‐constrained semantic segmentation: Practical machine learning optimization

Contact Info

Product

Resources

About