Diagnostic efficacy of PET/CT in bone tumors

Incidence and survival outcomes of patients with high-grade appendicular bone sarcoma and isolated regional lymph node metastasis: A national cohort database study

BACKGROUND

While distant metastases in primary bone sarcomas have been extensively studied, the impact of isolated regional lymph node (LN) metastasis on survival remains unknown. In patients with primary bone sarcomas, we sought to assess the prevalence of isolated regional LN metastasis and the survival of this population.

METHODS

A total of 6651 patients with histologically-confirmed high-grade osteosarcoma, Ewing sarcoma, or chondrosarcoma were retrieved from the SEER database. We defined four subgroups for our analysis: localized disease (N0 M0), isolated regional LN metastasis (N1 M0), isolated distant metastasis (N0 M1), and combined regional LN and distant metastasis (N1 M1). Disease-specific survival (DSS) was assessed using the Kaplan-Meier method.

RESULTS

Prevalence of isolated regional LN metastasis (N1 M0) was highest in Ewing sarcoma (27/1097; 3.3 %), followed by chondrosarcoma (18/1702; 1.4 %) and osteosarcoma (26/3740; 0.9 %). In all three histologies, patients with isolated regional LN metastasis had a worse 2-year, 5-year, and 10-year DSS than those with localized disease. Chondrosarcoma patients with isolated regional LN (N1 M0) metastasis had a significantly higher DSS in comparison to those with only distant metastasis (N0 M1) at the 5- and 10-year marks; for osteosarcoma and Ewing sarcoma, only a pattern towards higher survival was seen. Risk factors for presenting isolated regional LN metastasis included tumor location in lower-limb (OR = 2.01) or pelvis (OR = 2.49), diagnosis of Ewing sarcoma (OR = 2.98), and tumor >10 cm (OR = 1.96).

CONCLUSIONS

Isolated regional LN metastases in primary bone sarcomas is an infrequent presentation associated with worse survival than localized disease.

LEVEL OF EVIDENCE

III.

A comparative analysis of CNN-based deep learning architectures for early diagnosis of bone cancer using CT images

Bone cancer is a rare in which cells in the bone grow out of control, resulting in destroying the normal bone tissue. A benign type of bone cancer is harmless and does not spread to other body parts, whereas a malignant type can spread to other body parts and might be harmful. According to Cancer Research UK (2021), the survival rate for patients with bone cancer is 40% and early detection can increase the chances of survival by providing treatment at the initial stages. Prior detection of these lumps or masses can reduce the risk of death and treat bone cancer early. The goal of this current study is to utilize image processing techniques and deep learning-based Convolution neural network (CNN) to classify normal and cancerous bone images. Medical image processing techniques, like pre-processing (e.g., median filter), K-means clustering segmentation, and, canny edge detection were used to detect the cancer region in Computer Tomography (CT) images for parosteal osteosarcoma, enchondroma and osteochondroma types of bone cancer. After segmentation, the normal and cancerous affected images were classified using various existing CNN-based models. The results revealed that AlexNet model showed a better performance with a training accuracy of 98%, validation accuracy of 98%, and testing accuracy of 100%.