Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET
نویسندگان
چکیده
Abstract Background Positron emission tomography (PET) is routinely used for cancer staging and treatment follow-up. Metabolic active tumor volume (MATV) as well total MATV (TMATV—including primary tumor, lymph nodes metastasis) and/or lesion glycolysis derived from PET images have been identified prognostic factor or the evaluation of efficacy in patients. To this end, a segmentation approach with high precision repeatability important. However, implementation repeatable accurate algorithm remains an ongoing challenge. Methods In study, we compare two semi-automatic artificial intelligence (AI)-based methods conventional approaches terms repeatability. One based on textural feature (TF) designed tumors metastasis. Moreover, convolutional neural network (CNN) trained. The algorithms are trained, validated tested using lung dataset. accuracy both compared Jaccard coefficient (JC). Additionally, externally fully independent test–retest those majority vote (MV2, MV3) approaches, 41%SUV MAX , SUV > 4 (SUV4). Repeatability assessed coefficients (TRT%) intraclass correlation (ICC). An ICC 0.9 was regarded representing excellent Results segmentations reference good (JC median TF: 0.7, CNN: 0.73). Both outperformed most other (TRT% mean: 13.0%, 13.9%, MV2: 14.1%, MV3: 28.1%, : SUV4: 18.1%) (TF: 0.98, 0.97, 0.99, 0.73, 0.81, 0.68). Conclusion AI-based study provided better than approaches. lead to metastasis therefore candidates segmentation.
منابع مشابه
Automatic Segmentation of the Gross Tumor Volume in Prostate Carcinoma Using Fuzzy Clustering in Gallium-68 PSMA PET/CT Scan
Introduction: Modern radiotherapy (RT) techniques allow a highly precise deposition of the radiation dose in tumor. So, high conformal tumor doses can be reached while sparing critical organs at risk. Materials and Methods: This study was conducted in three phases. In the first phase; Fourteen patients with primary or recurrent prostate cancer receive Gallium-...
متن کاملSemi-automatic Segmentation of MRI Brain Tumor
Segmentation of images holds an important position in the area of image processing. It becomes more important while typically dealing with medical images where presurgery and post surgery decisions are required for the purpose of initiating and speeding up the recovery process. Computer aided detection of abnormal growth of tissues is primarily motivated by the necessity of achieving maximum po...
متن کاملAutomatic classification of hyperactive children: comparing multiple artificial intelligence approaches.
Automatic classification of different behavioral disorders with many similarities (e.g. in symptoms) by using an automated approach will help psychiatrists to concentrate on correct disorder and its treatment as soon as possible, to avoid wasting time on diagnosis, and to increase the accuracy of diagnosis. In this study, we tried to differentiate and classify (diagnose) 306 children with many ...
متن کاملArtificial intelligence-based approaches for multi-station modelling of dissolve oxygen in river
ABSTRACT: In this study, adaptive neuro-fuzzy inference system, and feed forward neural network as two artificial intelligence-based models along with conventional multiple linear regression model were used to predict the multi-station modelling of dissolve oxygen concentration at the downstream of Mathura City in India. The data used are dissolved oxygen, pH, biological oxygen demand and water...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: EJNMMI research
سال: 2021
ISSN: ['2191-219X']
DOI: https://doi.org/10.1186/s13550-020-00744-9