Computer-assisted liver graft steatosis assessment via learning-based texture analysis
| العنوان: | Computer-assisted liver graft steatosis assessment via learning-based texture analysis |
|---|---|
| المؤلفون: | Michela Ruperti, François Cauchy, Nicolas Poté, Manuela Cesaretti, Federica Dondero, Olivier Soubrane, Elena De Momi, Alberto Diaspro, Ailton Sepulveda, Ilaria Patrini, Leonardo S. Mattos, Sara Moccia |
| المصدر: | International Journal of Computer Assisted Radiology and Surgery. 13:1357-1367 |
| بيانات النشر: | Springer Science and Business Media LLC, 2018. |
| سنة النشر: | 2018 |
| مصطلحات موضوعية: | Surgical data science, Computer science, Local binary patterns, Biomedical Engineering, Color, Health Informatics, Pattern Recognition, Automated, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Liver, Machine learning, Texture analysis, Transplantation, 0302 clinical medicine, Nuclear Medicine and Imaging, Histogram, Image Interpretation, Computer-Assisted, Humans, Radiology, Nuclear Medicine and imaging, Sensitivity (control systems), business.industry, Image (category theory), Surgery, Radiology, Nuclear Medicine and Imaging, 1707, Computer Science Applications1707 Computer Vision and Pattern Recognition, Computer Graphics and Computer-Aided Design, Pattern recognition, General Medicine, Gold standard (test), Liver Transplantation, Computer Science Applications, Fatty Liver, Feature (computer vision), RGB color model, 030211 gastroenterology & hepatology, Computer Vision and Pattern Recognition, Artificial intelligence, Radiology, business, Algorithms |
| الوصف: | Fast and accurate graft hepatic steatosis (HS) assessment is of primary importance for lowering liver dysfunction risks after transplantation. Histopathological analysis of biopsied liver is the gold standard for assessing HS, despite being invasive and time consuming. Due to the short time availability between liver procurement and transplantation, surgeons perform HS assessment through clinical evaluation (medical history, blood tests) and liver texture visual analysis. Despite visual analysis being recognized as challenging in the clinical literature, few efforts have been invested to develop computer-assisted solutions for HS assessment. The objective of this paper is to investigate the automatic analysis of liver texture with machine learning algorithms to automate the HS assessment process and offer support for the surgeon decision process. Forty RGB images of forty different donors were analyzed. The images were captured with an RGB smartphone camera in the operating room (OR). Twenty images refer to livers that were accepted and 20 to discarded livers. Fifteen randomly selected liver patches were extracted from each image. Patch size was $$100\times 100$$ . This way, a balanced dataset of 600 patches was obtained. Intensity-based features (INT), histogram of local binary pattern ( $$H_{{\mathrm{LBP}}_{riu2}}$$ ), and gray-level co-occurrence matrix ( $$F_{\mathrm{GLCM}}$$ ) were investigated. Blood-sample features (Blo) were included in the analysis, too. Supervised and semisupervised learning approaches were investigated for feature classification. The leave-one-patient-out cross-validation was performed to estimate the classification performance. With the best-performing feature set ( $$H_{{\mathrm{LBP}}_{riu2}}+\hbox {INT}+\hbox {Blo}$$ ) and semisupervised learning, the achieved classification sensitivity, specificity, and accuracy were 95, 81, and 88%, respectively. This research represents the first attempt to use machine learning and automatic texture analysis of RGB images from ubiquitous smartphone cameras for the task of graft HS assessment. The results suggest that is a promising strategy to develop a fully automatic solution to assist surgeons in HS assessment inside the OR. |
| تدمد: | 1861-6429 1861-6410 |
| DOI: | 10.1007/s11548-018-1787-6 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::121974aa5c6fb497561d16116fd58bae https://doi.org/10.1007/s11548-018-1787-6 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....121974aa5c6fb497561d16116fd58bae |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 18616429 18616410 |
|---|---|
| DOI: | 10.1007/s11548-018-1787-6 |