首页|Center for Physical Sciences and Technology Reports Findings inThyroid Nodules (Machine learning-based diagnostics of capsularinvasion in thyroid nodules with wide-field second harmonic generationmicroscopy)
Center for Physical Sciences and Technology Reports Findings inThyroid Nodules (Machine learning-based diagnostics of capsularinvasion in thyroid nodules with wide-field second harmonic generationmicroscopy)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – New research on Thyroid Diseases and C onditions - Thyroid Nodules is the subjectof a report. According to news origin ating from Vilnius, Lithuania, by NewsRx correspondents, researchstated, “Papil lary thyroid carcinoma (PTC) is one of the most common, well-differentiated carc inomasof the thyroid gland. PTC nodules are often surrounded by a collagen caps ule that prevents the spread ofcancer cells.”Our news journalists obtained a quote from the research from Center for Physical Sciences and Technology,“However, as the malignant tumor progresses, the integ rity of this protective barrier is compromised,and cancer cells invade the surr oundings. The detection of capsular invasion is, therefore, crucial for thediag nosis and the choice of treatment and the development of new approaches aimed at the increase ofdiagnostic performance are of great importance. In the present study, we exploited the wide-field secondharmonic generation (SHG) microscopy i n combination with texture analysis and unsupervised machinelearning (ML) to ex plore the possibility of quantitative characterization of collagen structure in the capsuleand designation of different capsule areas as either intact, disrupt ed by invasion, or apt to invasion.Two-step k-means clustering showed that the collagen capsules in all analyzed tissue sections were highlyheterogeneous and exhibited distinct segments described by characteristic ML parameter sets. The l atterallowed a structural interpretation of the collagen fibers at the sites of overt invasion as fragmented andcurled fibers with rarely formed distributed n etworks. Clustering analysis also distinguished areas in thePTC capsule that we re not categorized as invasion sites by the initial histopathological analysis b ut couldbe recognized as prospective micro-invasions after additional inspectio n. The characteristic features ofsuspicious and invasive sites identified by th e proposed unsupervised ML approach can become a reliablecomplement to existing methods for diagnosing encapsulated PTC, increase the reliability of diagnosis,simplify decision making, and prevent human-related diagnostic errors.”
VilniusLithuaniaEuropeCancerColl agenCyborgsDiagnosticsand ScreeningEmerging TechnologiesEndocrine Gland NeoplasmsExtracellular Matrix ProteinsHealth and MedicineMachine LearningOncologyPapillary Thyroid CarcinomaThyroid Diseases andConditionsThyroi d NeoplasmsThyroid Nodules
NETL
NSTL
