首页|IRCCS Regina Elena National Cancer Institute Reports Findings in Chondrosarcoma (X-rays radiomics-based machine learning classification of atypical cartilaginou s tumour and high-grade chondrosarcoma of long bones)
IRCCS Regina Elena National Cancer Institute Reports Findings in Chondrosarcoma (X-rays radiomics-based machine learning classification of atypical cartilaginou s tumour and high-grade chondrosarcoma of long bones)
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 Daily News Daily News-New research on Oncology - Chondrosarc oma is the subject of a report. According to news originating from Rome, Italy, by NewsRx correspondents, research stated, "Atypical cartilaginous tumour (ACT) and high-grade chondrosarcoma (CS) of long bones are respectively managed with a ctive surveillance or curettage and wide resection. Our aim was to determine dia gnostic performance of X-rays radiomics-based machine learning for classificatio n of ACT and high-grade CS of long bones." Financial support for this research came from Associazione Italiana per la Ricer ca sul Cancro. Our news journalists obtained a quote from the research from IRCCS Regina Elena National Cancer Institute, "This retrospective, IRB-approved study included 150 patients with surgically treated and histology-proven lesions at two tertiary bo ne sarcoma centres. At centre 1, the dataset was split into training (n = 71 ACT , n = 24 high-grade CS) and internal test (n = 19 ACT, n = 6 high-grade CS) coho rts, respectively, based on the date of surgery. At centre 2, the dataset consti tuted the external test cohort (n = 12 ACT, n = 18 high-grade CS). Manual segmen tation was performed on frontal view X-rays, using MRI or CT for preliminary ide ntification of lesion margins. After image pre-processing, radiomic features wer e extracted. Dimensionality reduction included stability, coefficient of variati on, and mutual information analyses. In the training cohort, after class balanci ng, a machine learning classifier (Support Vector Machine) was automatically tun ed using nested 10-fold cross-validation. Then, it was tested on both the test c ohorts and compared to two musculoskeletal radiologists' performance using McNem ar's test. Five radiomic features (3 morphology, 2 texture) passed dimensionalit y reduction. After tuning on the training cohort (AUC = 0.75), the classifier ha d 80%, 83%, 79% and 80%, 89 %, 67% accuracy, sensitivity, and specificity in the internal (temporally independent) and external (geographically independent) test cohorts, respectively, with no difference compared to the radiologists (p 0.617 )."
RomeItalyEuropeBone ResearchCanc erChondrosarcomaCyborgsDimensionality ReductionEmerging TechnologiesHe alth and MedicineMachine LearningOncology
NETL
NSTL
