| 1. |
- Brandl, Miriam B, et al.
(author)
-
Application of Fuzzy c-Means and Joint-Feature-Clustering to Detect Redundancies of Image-Features in Drug Combinations Studies of Breast Cancer
- 2011
-
In: AIP Conference Proceedings. - : AIP. - 0094-243X.
-
Conference paper (peer-reviewed)abstract
- The high dimensionality of image‐based dataset can be a drawback for classification accuracy. In this study, we propose the application of fuzzy c‐means clustering, cluster validity indices and the notation of a joint‐feature‐clustering matrix to find redundancies of image‐features. The introduced matrix indicates how frequently features are grouped in a mutual cluster. The resulting information can be used to find data‐derived feature prototypes with a common biological meaning, reduce data storage as well as computation times and improve the classification accuracy
|
|
| 2. |
- Cirillo, Marco Domenico, et al.
(author)
-
Improving burn depth assessment for pediatric scalds by AI based on semantic segmentation of polarized light photography images
- 2021
-
In: Burns. - : Elsevier. - 0305-4179 .- 1879-1409. ; 47:7, s. 1586-1593
-
Journal article (peer-reviewed)abstract
- This paper illustrates the efficacy of an artificial intelligence (AI) (a convolutional neural network, based on the U-Net), for the burn-depth assessment using semantic segmentation of polarized high-performance light camera images of burn wounds. The proposed method is evaluated for paediatric scald injuries to differentiate four burn wound depths: superficial partial-thickness (healing in 0–7 days), superficial to intermediate partial-thickness (healing in 8–13 days), intermediate to deep partial-thickness (healing in 14–20 days), deep partial-thickness (healing after 21 days) and full-thickness burns, based on observed healing time.In total 100 burn images were acquired. Seventeen images contained all 4 burn depths and were used to train the network. Leave-one-out cross-validation reports were generated and an accuracy and dice coefficient average of almost 97% was then obtained. After that, the remaining 83 burn-wound images were evaluated using the different network during the cross-validation, achieving an accuracy and dice coefficient, both on average 92%.This technique offers an interesting new automated alternative for clinical decision support to assess and localize burn-depths in 2D digital images. Further training and improvement of the underlying algorithm by e.g., more images, seems feasible and thus promising for the future.
|
|
| 3. |
- Cirillo, Marco Domenico, et al.
(author)
-
Tensor Decomposition for Colour Image Segmentation of Burn Wounds
- 2019
-
In: Scientific Reports. - : NATURE PUBLISHING GROUP. - 2045-2322. ; 9
-
Journal article (peer-reviewed)abstract
- Research in burns has been a continuing demand over the past few decades, and important advancements are still needed to facilitate more effective patient stabilization and reduce mortality rate. Burn wound assessment, which is an important task for surgical management, largely depends on the accuracy of burn area and burn depth estimates. Automated quantification of these burn parameters plays an essential role for reducing these estimate errors conventionally carried out by clinicians. The task for automated burn area calculation is known as image segmentation. In this paper, a new segmentation method for burn wound images is proposed. The proposed methods utilizes a method of tensor decomposition of colour images, based on which effective texture features can be extracted for classification. Experimental results showed that the proposed method outperforms other methods not only in terms of segmentation accuracy but also computational speed.
|
|
| 4. |
- Cirillo, Marco Domenico, et al.
(author)
-
Time-Independent Prediction of Burn Depth using Deep Convolutional Neural Networks
- 2019
-
In: Journal of Burn Care & Research. - : Oxford University Press. - 1559-047X .- 1559-0488. ; 40:6, s. 857-863
-
Journal article (peer-reviewed)abstract
- We present in this paper the application of deep convolutional neural networks, which are a state-of-the-art artificial intelligence (AI) approach in machine learning, for automated time-independent prediction of burn depth. Colour images of four types of burn depth injured in first few days, including normal skin and background, acquired by a TiVi camera were trained and tested with four pre-trained deep convolutional neural networks: VGG-16, GoogleNet, ResNet-50, and ResNet-101. In the end, the best 10-fold cross-validation results obtained from ResNet- 101 with an average, minimum, and maximum accuracy are 81.66%, 72.06% and 88.06%, respectively; and the average accuracy, sensitivity and specificity for the four different types of burn depth are 90.54%, 74.35% and 94.25%, respectively. The accuracy was compared to the clinical diagnosis obtained after the wound had healed. Hence, application of AI is very promising for prediction of burn depth and therefore can be a useful tool to help in guiding clinical decision and initial treatment of burn wounds.
|
|
| 5. |
- Jin, Qiangguo, et al.
(author)
-
DUNet : A deformable network for retinal vessel segmentation
- 2019
-
In: Knowledge-Based Systems. - : Elsevier. - 0950-7051 .- 1872-7409. ; 178, s. 149-162
-
Journal article (peer-reviewed)abstract
- Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels’ local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired by the recently introduced deformable convolutional networks, we integrate the deformable convolution into the proposed network. The DUNet, with upsampling operators to increase the output resolution, is designed to extract context information and enable precise localization by combining low-level features with high-level ones. Furthermore, DUNet captures the retinal vessels at various shapes and scales by adaptively adjusting the receptive fields according to vessels’ scales and shapes. Public datasets: DRIVE, STARE, CHASE_DB1 and HRF are used to test our models. Detailed comparisons between the proposed network and the deformable neural network, U-Net are provided in our study. Results show that more detailed vessels can be extracted by DUNet and it exhibits state-of-the-art performance for retinal vessel segmentation with a global accuracy of 0.9566/0.9641/0.9610/0.9651 and AUC of 0.9802/0.9832/0.9804/0.9831 on DRIVE, STARE, CHASE_DB1 and HRF respectively. Moreover, to show the generalization ability of the DUNet, we use another two retinal vessel data sets, i.e., WIDE and SYNTHE, to qualitatively and quantitatively analyze and compare with other methods. Extensive cross-training evaluations are used to further assess the extendibility of DUNet. The proposed method has the potential to be applied to the early diagnosis of diseases.
|
|
| 6. |
- Pham, Tuan, et al.
(author)
-
Automated VSS-based Burn Scar Assessment using Combined Texture and Color Features of Digital Images in Error-Correcting Output Coding
- 2017
-
In: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 7
-
Journal article (peer-reviewed)abstract
- Assessment of burn scars is an important study in both medical research and clinical settings because it can help determine response to burn treatment and plan optimal surgical procedures. Scar rating has been performed using both subjective observations and objective measuring devices. However, there is still a lack of consensus with respect to the accuracy, reproducibility, and feasibility of the current methods. Computerized scar assessment appears to have potential for meeting such requirements but has been rarely found in literature. In this paper an image analysis and pattern classifcation approach for automating burn scar rating based on the Vancouver Scar Scale (VSS) was developed. Using the image data of pediatric patients, a rating accuracy of 85% was obtained, while 92% and 98% were achieved for the tolerances of one VSS score and two VSS scores, respectively. The experimental results suggest that the proposed approach is very promising as a tool for clinical burn scar assessment that is reproducible and cost-efective.
|
|
| 7. |
|
|
| 8. |
- Pham, Tuan D
(author)
-
Brain lesion detection in MRI with fuzzy and geostatistical models
- 2010
-
Conference paper (peer-reviewed)abstract
- Automated image detection of white matter changes of the brain is essentially helpful in providing a quantitative measure for studying the association of white matter lesions with other types of biomedical data. Such study allows the possibility of several medical hypothesis validations which lead to therapeutic treatment and prevention. This paper presents a new clustering-based segmentation approach for detecting white matter changes in magnetic resonance imaging with particular reference to cognitive decline in the elderly. The proposed method is formulated using the principles of fuzzy c-means algorithm and geostatistics.
|
|
| 9. |
- Pham, Tuan D.
(author)
-
Entropy rates of physiological aging on microscopy
- 2016
-
In: Proceedings of 2016 IEEE Symposium Series on Computational Intelligence. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781509042401 - 9781509042418
-
Conference paper (peer-reviewed)abstract
- This paper presents a method for computing entropy rates of images by modeling a stationary Markov chain constructed from a weighted graph. The proposed method was applied to the quantification of the complex behavior of the growing rates of physiological aging of Caenorhabditis elegans (C. elegans) on microscopic images, which has been considered as one of the most challenging problems in the search for metrics that can be used for identifying differences among stages in high- throughput and high-content images of physiological aging.
|
|
| 10. |
- Pham, Tuan D
(author)
-
Medical image restoration using multiple-point geostatistics
- 2010
-
In: 2010 3rd International Conference on Biomedical Engineering and Informatics (BMEI 2010). - : IEEE. - 9781424464951 ; , s. 371-374
-
Conference paper (other academic/artistic)abstract
- Noise inherently exists in medical and biological images as any imaging device, by a finite exposure time, is subject to stochastic noise from the random arrival events of photons. The purpose of image restoration is to bring back as much as possible the original image from its degraded state. This paper presents a spatial multiple-point statistical approach for restoration of medical image degradation.
|
|
