Goto

Collaborating Authors

Fully Automated Wound Tissue Segmentation Using Deep Learning on Mobile Devices: Cohort Study

#artificialintelligence

Background: Composition of tissue types within a wound is a useful indicator of its healing progression. Tissue composition is clinically used in wound healing tools (eg, Bates-Jensen Wound Assessment Tool) to assess risk and recommend treatment. However, wound tissue identification and the estimation of their relative composition is highly subjective. Consequently, incorrect assessments could be reported, leading to downstream impacts including inappropriate dressing selection, failure to identify wounds at risk of not healing, or failure to make appropriate referrals to specialists. Objective: This study aimed to measure inter- and intrarater variability in manual tissue segmentation and quantification among a cohort of wound care clinicians and determine if an objective assessment of tissue types (ie, size and amount) can be achieved using deep neural networks. Methods: A data set of 58 anonymized wound images of various types of chronic wounds from Swift Medical’s Wound Database was used to conduct the inter- and intrarater agreement study. The data set was split into 3 subsets with 50% overlap between subsets to measure intrarater agreement. In this study, 4 different tissue types (epithelial, granulation, slough, and eschar) within the wound bed were independently labeled by the 5 wound clinicians at 1-week intervals using a browser-based image annotation tool. In addition, 2 deep convolutional neural network architectures were developed for wound segmentation and tissue segmentation and were used in sequence in the workflow. These models were trained using 465,187 and 17,000 image-label pairs, respectively. This is the largest and most diverse reported data set used for training deep learning models for wound and wound tissue segmentation. The resulting models offer robust performance in diverse imaging conditions, are unbiased toward skin tones, and could execute in near real time on mobile devices. Results: A poor to moderate interrater agreement in identifying tissue types in chronic wound images was reported. A very poor Krippendorff α value of .014 for interrater variability when identifying epithelization was observed, whereas granulation was most consistently identified by the clinicians. The intrarater intraclass correlation (3,1), however, indicates that raters were relatively consistent when labeling the same image multiple times over a period. Our deep learning models achieved a mean intersection over union of 0.8644 and 0.7192 for wound and tissue segmentation, respectively. A cohort of wound clinicians, by consensus, rated 91% (53/58) of the tissue segmentation results to be between fair and good in terms of tissue identification and segmentation quality. Conclusions: The interrater agreement study validates that clinicians exhibit considerable variability when identifying and visually estimating wound tissue proportion. The proposed deep learning technique provides objective tissue identification and measurements to assist clinicians in documenting the wound more accurately and could have a significant impact on wound care when deployed at scale.


Injectable seaweed bandages can prevent fatal battleground wounds

ZDNet

A team of scientists has taken inspiration from seaweed to create a new hydrogel able to stop excessive blood loss. According to scientists from the Inspired Nanomaterials and Tissue Engineering Laboratory at Texas A&M University, the new gel is an injectable bandage which can wrap around wounds with severe tissue disruption in order to combat wounds which could otherwise lead to death. In a paper published in Acta Biomaterialia, Dr. Akhilesh K. Gaharwar, assistant professor in the Department of Biomedical Engineering at Texas A&M University and one of the authors of the paper, said that there is an "unmet need" when it comes to wounds in which blood may hemorrhage. Shrapnel-based wounds on the battlefield, for example, are difficult to treat on the ground and high volumes of blood can be lost from jagged wounds. As such, bandages which could stem the flow of blood effectively without causing further damage may save lives.


The Future of Medicine: 3D Printers Can Already Create Human Body Parts

#artificialintelligence

In recent years, updates in 3D printing technologies have allowed medical researchers to print things that were not possible to make using the previous version of this technology, including food, medicine, and even body parts. In 2018, doctors from the Ontario Veterinary College 3D printed a custom titanium plate for a dog that had lost part of its skull after cancer surgery. "By performing these procedures in our animal patients, we can provide valuable information that can be used to show the value and safety of these implants for humans", said veterinary surgical oncologist Michelle Oblak at the time. "These implants are the next big leap in personalized medicine that allows for every element of an individual's medical care to be specifically tailored to their particular needs." However, instead of depositing materials such as plastic or ceramic, they deposit layers of biomaterial, including living cells, to build complex structures like blood vessels or skin tissue.


Digital health helping cancer diagnosis - Pharmaphorum

#artificialintelligence

The FDA has been championing digital health of late with wide-ranging guidance that derives from the 21st Century Cures Act. This legislation acknowledges the potential that digital health has to make a difference in patient care, potentially leading to more precise therapies. Several developments this week show that the regulator is right to be excited about its potential. Some of the most exciting advances have come in the field of cancer – medical devices firm Angle has produced a new analysis showing that its liquid biopsy device Parsortix could be used instead of conventional tissue biopsies. Parsortix works by monitoring a patient's bloodstream for circulating cancer cells and the University of Southern California research adds to the body of evidence showing that liquid biopsies could replace invasive and unpleasant tissue biopsies in the future.


'Cellular programming' could enable soldiers to heal own wounds

Daily Mail - Science & tech

It may sound like a super power of the comic book character Wolverine, but the US Air Force is developing a way for future warfighters to heal their wounds in an instance. Working with the University of Michigan, the teams is exploring cellular reprogramming to treat wounds, burns and other injuries on the battle five times faster than what occurs naturally with the human body. The process of cell programming modifies its genome using proteins, called transcription factors, which stop different genes'to regulate activities such as cell division and growth, and cell migration and organization.' The transcription factors could be administered through a'spray-on' bandage where they would be applied directly to wounds, which could convert exposed muscle cells into surface skin cells that cover the wound so it heals faster. Dr. Indika Rajapakse, associate professor of computational medicine and bioinformatics, and of mathematics, at the University of Michigan, is using a live cell imaging microscope for the project.