Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313463660> ?p ?o ?g. }
Showing items 1 to 46 of
46
with 100 items per page.
- W4313463660 endingPage "113" @default.
- W4313463660 startingPage "95" @default.
- W4313463660 abstract "The second leading cause of cancer-related fatalities worldwide is liver tumor disorders, and its global incidence rate has been increasing, in contrast to other cancers' static or falling rates. Almost all highly malignant cancers are caused by hepatocellular carcinoma (HCC) and might result in a serious worldwide health issue. Early identification and diagnosis of HCC can help patients get treatment quicker and have a greater chance of surviving. Blood tests, imaging, and biopsies are traditionally used to diagnose liver cancer. Through MRI imagery, staging tests can be used to identify the extent and location of cancer. The proposed research uses CT imaging to segment liver cancers. The liver lesions in abdominal CT images are segmented using automatic segmentation techniques. The hybrid U-Net model is employed with using the Deep ResNet34 model architecture. Hyper parameters and epoch scores are utilized to determine the model's accuracy. Finally, the CT scans are employed to train the proposed model to segment multiple liver tumors and the performance is analyzed with the average losses and dice score. This will serve as the foundation for developing an automated liver tumor diagnosis system for clinicians with increased accuracy, reducing the risk of manual mistakes during diagnosis." @default.
- W4313463660 created "2023-01-06" @default.
- W4313463660 creator A5047199772 @default.
- W4313463660 creator A5065391306 @default.
- W4313463660 creator A5066947968 @default.
- W4313463660 creator A5085755790 @default.
- W4313463660 date "2023-01-03" @default.
- W4313463660 modified "2023-09-23" @default.
- W4313463660 title "Liver Tumor Segmentation Using Deep Learning Neural Networks" @default.
- W4313463660 doi "https://doi.org/10.1201/9781003277002-8" @default.
- W4313463660 hasPublicationYear "2023" @default.
- W4313463660 type Work @default.
- W4313463660 citedByCount "0" @default.
- W4313463660 crossrefType "book-chapter" @default.
- W4313463660 hasAuthorship W4313463660A5047199772 @default.
- W4313463660 hasAuthorship W4313463660A5065391306 @default.
- W4313463660 hasAuthorship W4313463660A5066947968 @default.
- W4313463660 hasAuthorship W4313463660A5085755790 @default.
- W4313463660 hasConcept C108583219 @default.
- W4313463660 hasConcept C154945302 @default.
- W4313463660 hasConcept C41008148 @default.
- W4313463660 hasConcept C50644808 @default.
- W4313463660 hasConcept C89600930 @default.
- W4313463660 hasConceptScore W4313463660C108583219 @default.
- W4313463660 hasConceptScore W4313463660C154945302 @default.
- W4313463660 hasConceptScore W4313463660C41008148 @default.
- W4313463660 hasConceptScore W4313463660C50644808 @default.
- W4313463660 hasConceptScore W4313463660C89600930 @default.
- W4313463660 hasLocation W43134636601 @default.
- W4313463660 hasOpenAccess W4313463660 @default.
- W4313463660 hasPrimaryLocation W43134636601 @default.
- W4313463660 hasRelatedWork W2790662084 @default.
- W4313463660 hasRelatedWork W2948658236 @default.
- W4313463660 hasRelatedWork W2960184797 @default.
- W4313463660 hasRelatedWork W4200477060 @default.
- W4313463660 hasRelatedWork W4220708658 @default.
- W4313463660 hasRelatedWork W4220855245 @default.
- W4313463660 hasRelatedWork W4243168368 @default.
- W4313463660 hasRelatedWork W4285827401 @default.
- W4313463660 hasRelatedWork W4293211451 @default.
- W4313463660 hasRelatedWork W4295036012 @default.
- W4313463660 isParatext "false" @default.
- W4313463660 isRetracted "false" @default.
- W4313463660 workType "book-chapter" @default.