FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367175082> ?p ?o ?g. }

• W4367175082 endingPage "4233" @default.
• W4367175082 startingPage "4220" @default.
• W4367175082 abstract "Background Cancer prognosis before and after treatment is key for patient management and decision making. Handcrafted imaging biomarkers—radiomics—have shown potential in predicting prognosis. Purpose However, given the recent progress in deep learning, it is timely and relevant to pose the question: could deep learning based 3D imaging features be used as imaging biomarkers and outperform radiomics? Methods Effectiveness, reproducibility in test/retest, across modalities, and correlation of deep features with clinical features such as tumor volume and TNM staging were tested in this study. Radiomics was introduced as the reference image biomarker. For deep feature extraction, we transformed the CT scans into videos, and we adopted the pre-trained Inflated 3D ConvNet (I3D) video classification network as the architecture. We used four datasets—LUNG 1 (n = 422), LUNG 4 (n = 106), OPC (n = 605), and H&N 1 (n = 89)—with 1270 samples from different centers and cancer types—lung and head and neck cancer—to test deep features’ predictiveness and two additional datasets to assess the reproducibility of deep features. Results Support Vector Machine–Recursive Feature Elimination (SVM–RFE) selected top 100 deep features achieved a concordance index (CI) of 0.67 in survival prediction in LUNG 1, 0.87 in LUNG 4, 0.76 in OPC, and 0.87 in H&N 1, while SVM-RFE selected top 100 radiomics achieved CIs of 0.64, 0.77, 0.73, and 0.74, respectively, all statistically significant differences (p < 0.01, Wilcoxon's test). Most selected deep features are not correlated with tumor volume and TNM staging. However, full radiomics features show higher reproducibility than full deep features in a test/retest setting (0.89 vs. 0.62, concordance correlation coefficient). Conclusion The results show that deep features can outperform radiomics while providing different views for tumor prognosis compared to tumor volume and TNM staging. However, deep features suffer from lower reproducibility than radiomic features and lack the interpretability of the latter." @default.
• W4367175082 created "2023-04-28" @default.
• W4367175082 creator A5004688031 @default.
• W4367175082 creator A5013513157 @default.
• W4367175082 creator A5018386036 @default.
• W4367175082 creator A5058533373 @default.
• W4367175082 date "2023-04-27" @default.
• W4367175082 modified "2023-09-27" @default.
• W4367175082 title "Using 3D deep features from CT scans for cancer prognosis based on a video classification model: A multi‐dataset feasibility study" @default.
• W4367175082 cites W1901129140 @default.
• W4367175082 cites W1971933336 @default.
• W4367175082 cites W2003652177 @default.
• W4367175082 cites W2041387425 @default.
• W4367175082 cites W2068854404 @default.
• W4367175082 cites W2083927153 @default.
• W4367175082 cites W2084139018 @default.
• W4367175082 cites W2100495367 @default.
• W4367175082 cites W2108598243 @default.
• W4367175082 cites W2114588884 @default.
• W4367175082 cites W2126903025 @default.
• W4367175082 cites W2128625986 @default.
• W4367175082 cites W2130448611 @default.
• W4367175082 cites W2136916987 @default.
• W4367175082 cites W2143426320 @default.
• W4367175082 cites W2147800946 @default.
• W4367175082 cites W2158497151 @default.
• W4367175082 cites W2194775991 @default.
• W4367175082 cites W2295107390 @default.
• W4367175082 cites W2295124130 @default.
• W4367175082 cites W2313339984 @default.
• W4367175082 cites W2342045095 @default.
• W4367175082 cites W2478868884 @default.
• W4367175082 cites W2515969222 @default.
• W4367175082 cites W2558300345 @default.
• W4367175082 cites W2600642189 @default.
• W4367175082 cites W2607444182 @default.
• W4367175082 cites W2746726611 @default.
• W4367175082 cites W2751538714 @default.
• W4367175082 cites W2760796828 @default.
• W4367175082 cites W2767128594 @default.
• W4367175082 cites W2776581140 @default.
• W4367175082 cites W2801894005 @default.
• W4367175082 cites W2899425762 @default.
• W4367175082 cites W2954017268 @default.
• W4367175082 cites W2962785568 @default.
• W4367175082 cites W2963524571 @default.
• W4367175082 cites W2963881378 @default.
• W4367175082 cites W2964166134 @default.
• W4367175082 cites W2964350391 @default.
• W4367175082 cites W2965512201 @default.
• W4367175082 cites W2997189273 @default.
• W4367175082 cites W2998449599 @default.
• W4367175082 cites W2998789541 @default.
• W4367175082 cites W3017737365 @default.
• W4367175082 cites W3020996329 @default.
• W4367175082 cites W3041133507 @default.
• W4367175082 cites W3047057232 @default.
• W4367175082 cites W3088102655 @default.
• W4367175082 cites W3096019617 @default.
• W4367175082 cites W3108241103 @default.
• W4367175082 cites W3126990165 @default.
• W4367175082 cites W3134475970 @default.
• W4367175082 cites W3138950012 @default.
• W4367175082 cites W3181327235 @default.
• W4367175082 cites W3188344035 @default.
• W4367175082 cites W3197181177 @default.
• W4367175082 cites W3205211994 @default.
• W4367175082 cites W3205825199 @default.
• W4367175082 cites W4212862206 @default.
• W4367175082 cites W4214612132 @default.
• W4367175082 cites W4229043294 @default.
• W4367175082 cites W4230373391 @default.
• W4367175082 cites W4288535810 @default.
• W4367175082 cites W4317473799 @default.
• W4367175082 cites W597221494 @default.
• W4367175082 doi "https://doi.org/10.1002/mp.16430" @default.
• W4367175082 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37102270" @default.
• W4367175082 hasPublicationYear "2023" @default.
• W4367175082 type Work @default.
• W4367175082 citedByCount "0" @default.
• W4367175082 crossrefType "journal-article" @default.
• W4367175082 hasAuthorship W4367175082A5004688031 @default.
• W4367175082 hasAuthorship W4367175082A5013513157 @default.
• W4367175082 hasAuthorship W4367175082A5018386036 @default.
• W4367175082 hasAuthorship W4367175082A5058533373 @default.
• W4367175082 hasBestOaLocation W43671750821 @default.
• W4367175082 hasConcept C105795698 @default.
• W4367175082 hasConcept C108583219 @default.
• W4367175082 hasConcept C121608353 @default.
• W4367175082 hasConcept C12267149 @default.
• W4367175082 hasConcept C126322002 @default.
• W4367175082 hasConcept C126838900 @default.
• W4367175082 hasConcept C12868164 @default.
• W4367175082 hasConcept C138885662 @default.
• W4367175082 hasConcept C142724271 @default.
• W4367175082 hasConcept C143409427 @default.
• W4367175082 hasConcept C153180895 @default.
• W4367175082 hasConcept C154945302 @default.

• next