Segmenting skin ulcers and measuring the wound area using deep convolutional networks

Chino, Daniel Yoshinobu Takada; Scabora, Lucas C.; Cazzolato, Mirela T.; Jorge, Ana Elisa Serafim; Traina-Jr, Caetano; Traina, Agma J. M.

doi:10.1016/j.cmpb.2020.105376

Cited by 55 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 1 gives a summary of the contributions in the field of pressure injuries segmentation and measurement. Some of the related works were able to measure the segmentation area of the wound using real-world units [ 28 , 29 , 30 ]. However, bypassing the 3D information of the wounds results in biased values.…”

Section: Related Workmentioning

confidence: 99%

Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning

Zahia

Garcia‐Zapirain

Elmaghraby

2020

Sensors

View full text Add to dashboard Cite

Pressure injuries represent a major concern in many nations. These wounds result from prolonged pressure on the skin, which mainly occur among elderly and disabled patients. If retrieving quantitative information using invasive methods is the most used method, it causes significant pain and discomfort to the patients and may also increase the risk of infections. Hence, developing non-intrusive methods for the assessment of pressure injuries would represent a highly useful tool for caregivers and a relief for patients. Traditional methods rely on findings retrieved solely from 2D images. Thus, bypassing the 3D information deriving from the deep and irregular shape of this type of wounds leads to biased measurements. In this paper, we propose an end-to-end system which uses a single 2D image and a 3D mesh of the pressure injury, acquired using the Structure Sensor, and outputs all the necessary findings such as: external segmentation of the wound as well as its real-world measurements (depth, area, volume, major axis and minor axis). More specifically, a first block composed of a Mask RCNN model uses the 2D image to output the segmentation of the external boundaries of the wound. Then, a second block matches the 2D and 3D views to segment the wound in the 3D mesh using the segmentation output and generates the aforementioned real-world measurements. Experimental results showed that the proposed framework can not only output refined segmentation with 87% precision, but also retrieves reliable measurements, which can be used for medical assessment and healing evaluation of pressure injuries.

show abstract

Section: Related Workmentioning

confidence: 99%

Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning

Zahia

Garcia‐Zapirain

Elmaghraby

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…3). This kind of wound/skin boundary segmentation is common among computational wound segmentation works [19][20][21][22][23]. Given our automatically generated cropped wound dataset (see "Detection" Section for details) we used the open-source software Labelme [26] to draw polygons around the wound edge for all the images in our dataset.…”

Section: Manual Measurement (Periphery)mentioning

confidence: 99%

“…Furthermore, combining image segmentation, least-squares conformal mapping, and structure from motion, 3D transformation is utilized in [22] to measure wound area on a human body surface. Moreover, using deep learning-based techniques, the automatic skin ulcer region assessment (ASURA) framework was introduced in [23].…”

Section: Introductionmentioning

confidence: 99%

Automatic wound detection and size estimation using deep learning algorithms

Carrión

Jafari

Bagood³

et al. 2020

Preprint

View full text Add to dashboard Cite

Evaluating and tracking wound size is a fundamental metric for the wound assessment process. Good location and size estimates can enable proper diagnosis and effective treatment. Traditionally, laboratory wound healing studies include a collection of images at uniform time intervals exhibiting the wounded area and the healing process in the test animal, often a mouse. These images are then manually observed to determine key metrics—such as wound size progress—relevant to the study. However, this task is a time-consuming and laborious process. In addition, defining the wound edge could be subjective and can vary from one individual to another even among experts. Furthermore, as our understanding of the healing process grows, so does our need to efficiently and accurately track these key factors for high throughput (e.g., over large-scale and longterm experiments). Thus, in this study, we develop a deep learning-based image analysis pipeline that aims to intake non-uniform wound images and extract relevant information such as the location of interest, wound only image crops, and wound periphery size over-time metrics. Our work focuses on images of wounded laboratory mice that are used widely for translationally relevant wound studies. We compare results to that of expert measurements and demonstrate preservation of information relevant to predicting wound closure despite variability from machine-to-expert and even expert-to-expert. The proposed system resulted in high fidelity results on unseen data with minimal human intervention.Author summaryKnowledge of the wound size changes over-time allows us to observe important insights such as rate of closure, time to closure, and expansion events, which are key indicators for predicting healing status. To better perform wound measurements it is essential to utilize a technique that returns accurate and consistent results every time. Over the last years, collecting wound images is becoming easier and more popular as digital cameras and smartphones are more accessible. Commonly, scientists/clinicians trace the wound in these images manually to observe changes in the wound, which is normally a slow and labor-intensive process and also requires a trained eye. The clinical goal is to more efficiently and effectively treat wounds by employing easy to use and precise wound measurement techniques. Therefore, the objective should be devising automatic and precise wound measurement tools to be used for wound assessment. To this end, we leveraged a combination of various state-of-the-art computer vision and machine learning-based methods for developing a versatile and automatic wound assessment tool. We applied this tool to analyze the images of wound inflicted lab mice and showed that our developed tool automated the overall wound measurement process, therefore, resulting in high fidelity results without significant human intervention. Furthermore, we compared results to two expert measurements. We found variability in measurement even across experts further validating the need for a consistent approach. However, qualitative behavior, which is most important for predicting wound closure, is preserved.

show abstract

“…Finally, Section 6.5 show our final thoughts on the skin ulcer segmentation problem. This Chapter is based on the work submitted to the Journal of Computer Methods and Programs in Biomedicine (CHINO et al, 2019).…”

Section: Chaptermentioning

confidence: 99%

Managing feature extraction, mining and retrieval of complex data: applications in emergency situations and medicine

Chino¹

View full text Add to dashboard Cite

The size and complexity of the data generated by social media and medical images has increased in a fast pace. Unlike traditional data, images cannot be dealt with in its original domain, leading to rising challenges in knowledge discovery tasks. The image analysis can aid on several decision making tasks. Crowdsourcing images such as social media images can be used to increase the speed of authorities to take action in emergency situations. Images taken from the medical domain can support on daily activities of physicians to diagnose their patients. Content-Based Image Retrieval (CBIR) systems are built to retrieve similar images, being an important step for the knowledge discovery. However, in some image domains, only parts of the image are relevant to the problem. This PhD research is based on the following hypothesis: the integration of image segmentation methods with local feature CBIR system improves the precision of the retrieved images. We evaluate our proposals in two images domain: fire detection on urban emergency situations and chronic skin ulcer images. The main contributions of this PhD research can be divided in four parts. First, we propose BoWFire to detect and segment fire in emergency situations. We explore the combination of color and texture features through superpixels to detect fire in still images. Then, we explore the use of superpixels to extract local features with BoSS. BoSS is a Bag-of-Visual-Words (BoVW) approach based on visual signatures. To integrate segmentation methods with CBIR, we propose ICARUS, a skin ulcer image retrieval framework. ICARUS integrate segmentations methods based on superpixels with BoVW. We also propose ASURA, a deep learning segmentation method for skin ulcer lesions. Besides segmenting skin ulcer lesions, ASURA is able to estimate the area of the lesion in real-world units by analyzing real-world objects present in the images. Our experiments show that our proposals achieved a better precision while retrieving the most similar images in comparison with the existing approaches.

show abstract

Segmenting skin ulcers and measuring the wound area using deep convolutional networks

Cited by 55 publications

References 13 publications

Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning

Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning

Automatic wound detection and size estimation using deep learning algorithms

Managing feature extraction, mining and retrieval of complex data: applications in emergency situations and medicine

Contact Info

Product

Resources

About