Metastatic bone disease: Have we improved after a decade of guidelines?

Automatic identification of suspicious bone metastatic lesions in bone scintigraphy using convolutional neural network

Background

We aimed to construct an artificial intelligence (AI) guided identification of suspicious bone metastatic lesions from the whole-body bone scintigraphy (WBS) images by convolutional neural networks (CNNs).

Methods

We retrospectively collected the ^99mTc-MDP WBS images with confirmed bone lesions from 3352 patients with malignancy. 14,972 bone lesions were delineated manually by physicians and annotated as benign and malignant. The lesion-based differentiating performance of the proposed network was evaluated by fivefold cross validation, and compared with the other three popular CNN architectures for medical imaging. The average sensitivity, specificity, accuracy and the area under receiver operating characteristic curve (AUC) were calculated. To delve the outcomes of this study, we conducted subgroup analyses, including lesion burden number and tumor type for the classifying ability of the CNN.

Results

In the fivefold cross validation, our proposed network reached the best average accuracy (81.23%) in identifying suspicious bone lesions compared with InceptionV3 (80.61%), VGG16 (81.13%) and DenseNet169 (76.71%). Additionally, the CNN model's lesion-based average sensitivity and specificity were 81.30% and 81.14%, respectively. Based on the lesion burden numbers of each image, the area under the receiver operating characteristic curve (AUC) was 0.847 in the few group (lesion number n ≤ 3), 0.838 in the medium group (n = 4–6), and 0.862 in the extensive group (n > 6). For the three major primary tumor types, the CNN-based lesion identifying AUC value was 0.870 for lung cancer, 0.900 for prostate cancer, and 0.899 for breast cancer.

Conclusion

The CNN model suggests potential in identifying suspicious benign and malignant bone lesions from whole-body bone scintigraphic images.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-021-00662-9.

Bone biopsy results in patients with a history of malignancy: a case series of 378 patients

OBJECTIVE

The value of a bone biopsy in patients who present with a bone lesion and past medical history of malignancy is uncertain. The objective of this study was to evaluate the outcome of bone biopsies in patients with a history of a malignancy undergoing bone biopsy of a lesion in a regional bone tumour unit. Secondary outcomes include the assessment of survival in the different outcome groups.

MATERIALS AND METHODS

This was a retrospective study of patients, with a previous malignancy and suspicious bone lesions, who underwent bone biopsy for final diagnosis between March 2010 and September 2019. Results of the biopsy were summarized into 3 groups: confirmed original malignancy, confirmed benign diagnosis, and confirmed new malignancy. Survival analysis of each group was also undertaken.

RESULTS

A total of 378 patients met the inclusion criteria (mean age 64 years, 216 females (57%)). In 250 cases (66%), the original malignancy was confirmed on the bone biopsy; in 128 cases, an alternative diagnosis was confirmed (benign diagnosis in 69 (18%)), and 59 had a new malignancy (16%). Survival was significantly greater for those in whom a benign diagnosis was confirmed (logrank test p = 0.0100).

CONCLUSION

This study shows that for patients presenting with a suspicious bone lesion, together with a history of malignancy, in a third of cases, the bone biopsy will confirm an alternative diagnosis of a benign lesion or a new malignancy. Survival of these patients will vary significantly depending on the biopsy outcome.

Double-plate compound osteosynthesis for pathological fractures of the proximal femur: high survivorship and low complication rate

INTRODUCTION

Management of pathological fractures of the proximal femur is often challenging. Compound double-plate osteosynthesis has been specifically developed for surgical treatment of these pathological fractures. To our knowledge, this study represents the largest series to date of double-plate compound osteosynthesis with the longest follow-up.

MATERIALS AND METHODS

Using our institutional digital database, we identified 61 procedures in 53 patients at the proximal femur. Patients were divided into two groups. A 'primary' group with all cases in which a double-plate compound osteosynthesis was performed as initial procedure (n = 46) and a 'revision' group with all cases in which a double-plate compound osteosynthesis was performed as revision procedure after failed previous attempts of internal fixation (n = 15). (1) The survivorship of the hip was calculated using the Kaplan-Meier survivorship analysis. (2) Complications were graded using Sink's classification. (3) The functional outcome was quantified with the Merle d'Aubigné and Postel score. (4) Risk factors were identified based on a multivariate Cox-regression analysis.

RESULTS

The cumulative Kaplan-Meier survivorship of the primary group was 96% at 6 months, 90% at 1 year, 5 years and thereafter and 83% at 6 months, 74% at 1 year, 53% at 2 years for the 'revision' group (p = 0.0008). According to the classification of Sink et al., the rate of grade III and IV complications was significantly lower in the primary group (p < 0.0001). The mean Merle d'Aubigné score was 14 ± 7 at 0-3 months, 13 ± 3 at 3-6 months, 15 ± 3 at 6-12 months and 15 ± 4 thereafter (p = 0.54). The only multivariate negative predictor was previous surgery with a hazard ratio of 9.2 (p < 0.006).

CONCLUSION

Double-plate compound osteosynthesis is a valuable treatment option for pathological fractures in proximal femur with good functional results.

Extent of Surgery Does Not Influence 30-Day Mortality in Surgery for Metastatic Bone Disease: An Observational Study of a Historical Cohort

Estimating patient survival has hitherto been the main focus when treating metastatic bone disease (MBD) in the appendicular skeleton. This has been done in an attempt to allocate the patient to a surgical procedure that outlives them. No questions have been addressed as to whether the extent of the surgery and thus the surgical trauma reduces survival in this patient group. We wanted to evaluate if perioperative parameters such as blood loss, extent of bone resection, and duration of surgery were risk factors for 30-day mortality in patients having surgery due to MBD in the appendicular skeleton. We retrospectively identified 270 consecutive patients who underwent joint replacement surgery or intercalary spacing for skeletal metastases in the appendicular skeleton from January 1, 2003 to December 31, 2013. We collected intraoperative (duration of surgery, extent of bone resection, and blood loss), demographic (age, gender, American Society of Anesthesiologist score [ASA score], and Karnofsky score), and disease-specific (primary cancer) variables. An association with 30-day mortality was addressed using univariate and multivariable analyses and calculation of odds ratio (OR). All patients were included in the analysis. ASA score 3 + 4 (OR 4.16 [95% confidence interval, CI, 1.80-10.85], P = 0.002) and Karnofsky performance status below 70 (OR 7.34 [95% CI 3.16-19.20], P < 0.001) were associated with increased 30-day mortality in univariate analysis. This did not change in multivariable analysis. No parameters describing the extent of the surgical trauma were found to be associated with 30-day mortality. The 30-day mortality in patients undergoing surgery for MBD is highly dependent on the general health status of the patients as measured by the ASA score and the Karnofsky performance status. The extent of surgery, measured as duration of surgery, blood loss, and degree of bone resection were not associated with 30-day mortality.

The radiological evaluation of the hip joint after prosthetic arthroplasty of the proximal femur in patients with a tumour using a bipolar femoral head

Excision of the proximal femur for tumour with prosthetic reconstruction using a bipolar femoral head places a considerable load on the unreplaced acetabulum.

We retrospectively reviewed the changes which occur around the affected hip joint by evaluating the post-operative radiographs of 65 consecutive patients who underwent proximal prosthetic arthroplasty of the femur, and in whom an acetabular component had not been used. There were 37 men and 28 women with a mean age of 57.3 years (17 to 93). Radiological assessment included the extent of degenerative change in the acetabulum, heterotopic ossification, and protrusio acetabuli.

The mean follow-up was 9.1 years (2 to 11.8). Degenerative changes in the acetabulum were seen in three patients (4.6%), Brooker grade 1 or 2 heterotopic ossification in 17 (26%) and protrusion of the prosthetic head in nine (13.8%).

A total of eight patients (12.3%) needed a revision. Five were revised to the same type of prosthesis and three (4.6%) were converted to a total hip arthroplasty.

We conclude that radiological evidence of degenerative change, heterotopic ossification and protrusion occur in a few patients who undergo prosthetic arthroplasty of the proximal femur for tumour. The limited extent of these changes and the lack of associated symptoms do not justify the routine arthroplasty of the acetabulum in these patients.

Cite this article: Bone Joint J 2015;97-B:1704–9