Quantitative bone scan lesion area as an early surrogate outcome measure indicative of overall survival in metastatic prostate cancer

Pretreatment visceral metastases in castration resistant metastatic prostate cancer: role in prediction versus actual site of disease progression

BACKGROUND

To evaluate the anatomic site(s) of initial disease progression in patients with castration resistant metastatic prostate cancer (mCRPC) in the presence or absence of pre-treatment visceral metastases while on systemic therapy.

METHODS

This is a retrospective cohort study of mCRPC patients who have baseline and at least one follow up bone scan and CT chest, abdomen and pelvis (CAP). Disease progression was determined by RECIST and/or ≥ 30% increase in automated bone scan lesion area score. Kaplan-Meier plot was used to estimate the median progression free survival and log-rank tests were used to compare anatomic sites.

RESULTS

Of 203 patients, 61 (30%) had pre-treatment visceral metastases. Patients with baseline visceral disease were 1.5 times more likely to develop disease progression (HR = 1.53; 95% CI, 1.03-2.26). Disease progression was a result of worsening bone scan disease (42% (16/38)) versus visceral (32% (12/38)) or lymph node disease (3% (1/38)) by CT or a combination thereof (23% (9/38)). Median time to progression (TTP) did not differ by anatomic location of initial progression (p = 0.86). Development of new lesions occurred in 50% of those visceral patients with soft tissue only progression and was associated with a significantly longer TTP (3.1 months (2.8-4.3 months) than those with worsening of pre-existing lesions (1.8 months (1.6-2.7 months); p = 0.04.

CONCLUSIONS

Patients with pre-treatment visceral metastases in mCRPC are more likely to experience disease progression of bone disease with the initial anatomic site of progression similar to those without baseline visceral involvement.

Bone radiomics reproducibility: a three-centered study on the impacts of image contrast, edge enhancement, and latitude variations

This study aims to measure the reproducibility of radiomics features in ankle bone radiography over changes in post-processing parameters including contrast, edge enhancement and latitude. Lateral ankle bone radiographies for sixty patients were obtained from three digital radiology centers. All images were acquired by same image acquisition settings. A two-dimensional region of interest was drawn in any image and 93 features from 6 feature sets including first and second order were extracted. The coefficient of variation (COV) and intraclass correlation coefficient (ICC) were calculated to assess feature reproducibility for each center and among all centers in three scenarios: Adams (Nat Rev Endocrinol 9(1):28, 2013) ten different contrast Brown et al. (J Med Imaging 5(1):011017, 2018) ten different edge enhancement and Hirvasniemi et al. (Osteoarthr Cartilage 27(6):906-914, 2019)  ten different image latitude parameters. Based on ICC analysis, it is observed that 46-100-44% of Histogram, 54-72-42% of GLCM, 43-76-36% of GLDM, 60-90-17% of GLRLM, 33-19-21% of GLSZM and 13-20-0% of NGTDM radiomics features had 90% < ICC < 100% over changes in contrast-edge enhancement-latitude changes respectively. Based on COV, GLRLM was only feature set that 100% of their features had COV ≤ 5% over changes in contrast and edge enhancement. The results presented here, indicating that radiomics features extracted are vulnerable over changes in contrast, edge enhancement and latitude. The most reproducible features that introduced in this study could be used for further clinical decision making.

Deep Learning for the Automatic Diagnosis and Analysis of Bone Metastasis on Bone Scintigrams

OBJECTIVE

To develop an approach for automatically analyzing bone metastases (BMs) on bone scintigrams based on deep learning technology.

METHODS

This research included a bone scan classification model, a regional segmentation model, an assessment model for tumor burden and a diagnostic report generation model. Two hundred eighty patients with BMs and 341 patients with non-BMs were involved. Eighty percent of cases were randomly extracted from two groups as training set. Remaining cases were as testing set. A deep residual convolutional neural network with different structures was used to determine whether metastatic bone lesions existed, regions of lesions were automatically segmented. Bone scan tumor burden index (BSTBI) was calculated; finally, diagnostic report could be automatically generated. The sensitivity, specificity and accuracy of classification model were compared with three physicians with different clinical experience. The Dice coefficient evaluated the effect of segmentation model and compared to the result of nnU-Net model. The correlation between BSTBI and blood alkaline phosphatase (ALP) level was analyzed to verify the efficiency of BSTBI. The performance of report generation model was evaluated by the accuracy of interpretation of report.

RESULTS

In testing set, the sensitivity, specificity and accuracy of classification model were 92.59%, 85.51% and 88.62%, respectively. The accuracy showed no statistical difference with moderately and experienced physicians and obviously outperformed the inexperienced. The Dice coefficient of BMs area was 0.7387 in segmentation stage. Based on the whole model frame, our segmentation model outperformed the nnU-Net. BSTBI value changed as the BMs changed. There was a positive correlation between BSTBI and ALP level. The accuracy of report generation model was 78.05%.

CONCLUSION

Deep learning based on automatic analysis frameworks for BMs can accurately identify BMs, preliminarily realize a fully automatic analysis process from raw data to report generation. BSTBI can be used as a quantitative evaluation indicator to assess the effect of therapy on BMs in different patients or in the same patient before and after treatment.

Decreased enrollment in breast cancer trials by histologic subtype: does invasive lobular carcinoma resist RECIST?

Enrollment in metastatic breast cancer trials usually requires measurable lesions, but patients with invasive lobular carcinoma (ILC) tend to form diffuse disease. We found that the proportion of patients with metastatic ILC enrolled in clinical trials at our institution was significantly lower than that of patients with invasive ductal carcinoma (IDC). Possible links between requiring measurable disease and decreased enrollment of ILC patients require further study to ensure equitable trial access.

Extraction of metastasis hotspots in a whole-body bone scintigram based on bilateral asymmetry

PURPOSE

A hotspot of bone metastatic lesion in a whole-body bone scintigram is often observed as left-right asymmetry. The purpose of this study is to present a network to evaluate bilateral difference of a whole-body bone scintigram, and to subsequently integrate it with our previous network that extracts the hotspot from a pair of anterior and posterior images.

METHODS

Input of the proposed network is a pair of scintigrams that are the original one and the flipped version with respect to body axis. The paired scintigrams are processed by a butterfly-type network (BtrflyNet). Subsequently, the output of the network is combined with the output of another BtrflyNet for a pair of anterior and posterior scintigrams by employing a convolutional layer optimized using training images.

RESULTS

We evaluated the performance of the combined networks, which comprised two BtrflyNets followed by a convolutional layer for integration, in terms of accuracy of hotspot extraction using 1330 bone scintigrams of 665 patients with prostate cancer. A threefold cross-validation experiment showed that the number of false positive regions was reduced from 4.30 to 2.13 for anterior and 4.71 to 2.62 for posterior scintigrams on average compared with our previous model.

CONCLUSIONS

This study presented a network for hotspot extraction of bone metastatic lesion that evaluates bilateral difference of a whole-body bone scintigram. When combining the network with the previous network that extracts the hotspot from a pair of anterior and posterior scintigrams, the false positives were reduced by nearly half compared to our previous model.

Underutilisation of nuclear medicine scans at a regional hospital in Nigeria: need for implementation research

Background

Nuclear medicine needs better integration into the Nigerian health system. To understand the relevant public health initiatives that will be required, this study assessed the pattern of nuclear medicine imaging services at the first nuclear medicine centre in Nigeria from January 2010 to December 2018.

Methods

The data of consecutive nuclear medicine (NM) scans performed between 1st January 2010 and 31st December 2018 at the NM department in a tertiary hospital in Nigeria were extracted from patient records and analysed using SAS version 9.4 (SAS Institute, Cary, NC). The National Cancer Institute’s Joinpoint software and QCIS (QGIS project) were used to estimate imaging trends and geographical spread of patients.

Results

An average of 486 scans per year was performed during the study period. Patients travelled from 32 of Nigeria’s 36 states, and the majority (65%) travelled more than 100 km to obtain NM scans. Bone scans accounted for 88.1% of the studies. The remainder were renal scintigraphy (7.3%), thyroid scans (2.5%), whole-body iodine scans (1.7%) and others (0.4%).

Conclusions

NM in Nigeria appears underutilised. Furthermore, the studies to characterise the access gaps and implementation needs will contribute to the design of practical strategies to strengthen NM services in Nigeria.

Automated measurement of bone scan index from a whole-body bone scintigram

Purpose

We propose a deep learning-based image interpretation system for skeleton segmentation and extraction of hot spots of bone metastatic lesion from a whole-body bone scintigram followed by automated measurement of a bone scan index (BSI), which will be clinically useful.

Methods

The proposed system employs butterfly-type networks (BtrflyNets) for skeleton segmentation and extraction of hot spots of bone metastatic lesions, in which a pair of anterior and posterior images are processed simultaneously. BSI is then measured using the segmented bones and extracted hot spots. To further improve the networks, deep supervision (DSV) and residual learning technologies were introduced.

Results

We evaluated the performance of the proposed system using 246 bone scintigrams of prostate cancer in terms of accuracy of skeleton segmentation, hot spot extraction, and BSI measurement, as well as computational cost. In a threefold cross-validation experiment, the best performance was achieved by BtrflyNet with DSV for skeleton segmentation and BtrflyNet with residual blocks. The cross-correlation between the measured and true BSI was 0.9337, and the computational time for a case was 112.0 s.

Conclusion

We proposed a deep learning-based BSI measurement system for a whole-body bone scintigram and proved its effectiveness by threefold cross-validation study using 246 whole-body bone scintigrams. The automatically measured BSI and computational time for a case are deemed clinically acceptable and reliable.