Bone Tumor Segmentation on Bone Scans Using Context Information and Random Forests

Chu, Gregory H.; Lo, Pechin; Ramakrishna, Bharath; Kim, Hee Jin; Morris, Derrick; Goldin, Jonathan G.; Brown, Matthew S.

doi:10.1007/978-3-319-10404-1_75

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques generally do not incorporate spatial information unless it is included in the feature space derivation. Examples of classification and clustering methods used to segment tumors include Random Forest (RF) [ 2 , 87 , 103 ], Support Vector Machines (SVM) [ 51 , 55 , 63 , 103 , 109 ], fuzzy clustering [ 101 ], Decision Tree (DT) [ 63 , 67 ], K-nearest neighbors (KNN) [ 67 ], K-means [ 73 ], parallelepiped classification [ 38 ], and Fuzzy C-Mean (FCM) [ 69 ].…”

Section: Discussionmentioning

confidence: 99%

“…Two studies derived useful information regarding the classification process and the ground truth values. Chu et al [ 2 ] developed an RF classifier to segment tumors on bone scans using intensity and context features aimed at addressing areas prone to false positives and found that context features played a critical role. Furthermore, their study performed well in areas where tumors and high-intensity non-tumors were in close proximity, which could be due to the restrictiveness of a rule-based approach compared to a learning-based approach.…”

Section: Discussionmentioning

confidence: 99%

“…The median survival rate of patients suffering from bone lesions metastasized from breast, prostate, and renal cancer ranges between 12 and 33 months, while survival is critically low for patients with primary lung cancer along with bone metastasis, ranging from 9.5% to 12% with one-year survival [ 1 ]. The level of bone metastasis is strongly linked with shorter survival rates [ 2 ]. Generally, these patients are treated with palliative chemotherapy and radiotherapy in clinical practice [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Systematic Review of Tumor Segmentation Strategies for Bone Metastases

Paranavithana

Stirling

Ros

et al. 2023

Cancers

View full text Add to dashboard Cite

Purpose: To investigate the segmentation approaches for bone metastases in differentiating benign from malignant bone lesions and characterizing malignant bone lesions. Method: The literature search was conducted in Scopus, PubMed, IEEE and MedLine, and Web of Science electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 77 original articles, 24 review articles, and 1 comparison paper published between January 2010 and March 2022 were included in the review. Results: The results showed that most studies used neural network-based approaches (58.44%) and CT-based imaging (50.65%) out of 77 original articles. However, the review highlights the lack of a gold standard for tumor boundaries and the need for manual correction of the segmentation output, which largely explains the absence of clinical translation studies. Moreover, only 19 studies (24.67%) specifically mentioned the feasibility of their proposed methods for use in clinical practice. Conclusion: Development of tumor segmentation techniques that combine anatomical information and metabolic activities is encouraging despite not having an optimal tumor segmentation method for all applications or can compensate for all the difficulties built into data limitations.

show abstract