Selection and monitoring of patients with metastatic castration-resistant prostate cancer for treatment with radium-223

Deep bone oncology Diagnostics: Computed tomography based Machine learning for detection of bone tumors from breast cancer metastasis

Purpose

The objective of this study is to develop a novel diagnostic tool using deep learning and radiomics to distinguish bone tumors on CT images as metastases from breast cancer. By providing a more accurate and reliable method for identifying metastatic bone tumors, this approach aims to significantly improve clinical decision-making and patient management in the context of breast cancer.

Methods

This study utilized CT images of bone tumors from 178 patients, including 78 cases of breast cancer bone metastases and 100 cases of non-breast cancer bone metastases. The dataset was processed using the Medical Image Segmentation via Self-distilling TransUNet (MISSU) model for automated segmentation. Radiomics features were extracted from the segmented tumor regions using the Pyradiomics library, capturing various aspects of tumor phenotype. Feature selection was conducted using LASSO regression to identify the most predictive features. The model's performance was evaluated using ten-fold cross-validation, with metrics including accuracy, sensitivity, specificity, and the Dice similarity coefficient.

Results

The developed radiomics model using the SVM algorithm achieved high discriminatory power, with an AUC of 0.936 on the training set and 0.953 on the test set. The model's performance metrics demonstrated strong accuracy, sensitivity, and specificity. Specifically, the accuracy was 0.864 for the training set and 0.853 for the test set. Sensitivity values were 0.838 and 0.789 for the training and test sets, respectively, while specificity values were 0.896 and 0.933 for the training and test sets, respectively. These results indicate that the SVM model effectively distinguishes between bone metastases originating from breast cancer and other origins. Additionally, the average Dice similarity coefficient for the automated segmentation was 0.915, demonstrating a high level of agreement with manual segmentations.

Conclusion

This study demonstrates the potential of combining CT-based radiomics and deep learning for the accurate detection of bone metastases from breast cancer. The high-performance metrics indicate that this approach can significantly enhance diagnostic accuracy, aiding in early detection and improving patient outcomes. Future research should focus on validating these findings on larger datasets, integrating the model into clinical workflows, and exploring its use in personalized treatment planning.

Nuclear medicine imaging for bone metastases assessment: what else besides bone scintigraphy in the era of personalized medicine?

Accurate detection and reliable assessment of therapeutic responses in bone metastases are imperative for guiding treatment decisions, preserving quality of life, and ultimately enhancing overall survival. Nuclear imaging has historically played a pivotal role in this realm, offering a diverse range of radiotracers and imaging modalities. While the conventional bone scan using 99mTc marked bisphosphonates has remained widely utilized, its diagnostic performance is hindered by certain limitations. Positron emission tomography, particularly when coupled with computed tomography, provides improved spatial resolution and diagnostic performance with various pathology-specific radiotracers. This review aims to evaluate the performance of different nuclear imaging modalities in clinical practice for detecting and monitoring the therapeutic responses in bone metastases of diverse origins, addressing their limitations and implications for image interpretation.

Radiopharmaceuticals for Bone Metastases

As a single organ distributed diffusely throughout the body, bones represent both a unique challenge and unique opportunity for the treatment of symptomatic metastatic disease. While the multifocality of bone metastases often prevents effective complete treatment with focal radiotherapy, the similar pathophysiology of these diffuse sites of disease opens the door to targeted systemic therapy. The relatively rapid dose fall-off from beta- or alpha-emitting particles, if correctly and reliably targeted to osseous metastases, might reduce tumor burden and enhance pain control or improve survival. Radioisotopes have thus been studied keenly with the first generation of primarily beta-emitting radioisotopes, strontium-89 and samarium-153, which reached early FDA approval based on successful endpoints of pain control. More recently, an alpha-emitting therapy, radium-223, has demonstrated a successful endpoint of improved overall survival in patients with a burden of symptomatic, metastatic castrate-resistant prostate cancer (mCRPC) confined to the bones. With this discovery, an additional survival-improving tool beyond systemic and hormonal agents was added to the treatment arsenal for mCRPC for suitable candidates. With an improved understanding of the optimization of hormonal and systemic therapies in the context of mCRPC, there is lingering uncertainty regarding the safety and efficacy of combinatorial use of alpha and beta-emitting therapies with the current generation of systemic agents. In this narrative review, we will highlight the current understanding of the relative utility and clinical paradigms involving alpha- and beta-emitting radioisotopes. We discuss fundamental mechanisms for antineoplastic activity, initial clinical trials validating their use, the use of concurrent antiresorptive therapies to provide bone protection, and ongoing clinical trials targeted at best utilization of these agents in the broader context of mCRPC treatment.

Radium-223 as an Approved Modality for Treatment of Bone Metastases

Radium-223 dichloride (²²³Ra) is an α-emitter radionuclide approved for treatment of osteoblastic metastases in castrate-resistant prostate cancer (mCRPC) patients. ²²³Ra increases overall survival, improves bone pain, increases the median time to the first skeletal-related event, reduces the use of external beam radiation therapy for bone pain palliation, reduces the rates of spinal cord compression, and hospitalization. ²²³Ra therapy has minimal side effects; the most common hematological side effects are anemia, thrombocytopenia and neutropenia while the nonhematological side effects that may occur are bone pain flare, nausea, fatigue, and diarrhea. Alongside ²²³Ra therapy there are currently a variety of first-line therapeutic options available to treat mCRPC patients and much debate regarding the appropriate treatment algorithm for these patients and the possible combination of therapies among the ones available. In this article, we review the rationale behind ²²³Ra therapy as well as ²²³Ra mechanisms of action, biodistribution and dosimetry, optimal timing possibilities to initiate ²²³Ra in contrast to other treatments available, the association of ²²³Ra with other therapies and the means of evaluating patients in order to properly deliver to ²²³Ra therapy. Furthermore, we will discuss ²²³Ra dose administration possibilities, patient and dose preparation and the challenges of treatment response evaluation during and after ²²³Ra.

Ra-223 Treatment for Bone Metastases in Castrate-Resistant Prostate Cancer: Practical Management Issues for Patient Selection

Bone metastases are common in men with metastatic castrate-resistant prostate cancer (mCRPC), occurring in 30% of patients within 2 years of castrate resistance and in >90% of patients over the disease course. There are 6 US Food and Drug Administration-approved therapies for mCRPC with demonstrated survival benefit. Of these, only radium-223 (Ra-223) specifically targets bone metastases, delays development of skeletal-related events, and improves survival. This review discusses key data from the ALSYMPCA trial, which contributed to the approval of Ra-223. Data from other trials are highlighted to provide further insight into which patients might benefit from Ra-223. Special patient populations are described, as well as other considerations for the administration of Ra-223. Finally, ongoing trials of Ra-223 combined with other therapies for mCRPC are discussed. These include combining Ra-223 with sipuleucel-T or immunooncology agents, to enhance immune responses, and trials in mildly symptomatic or asymptomatic patients. To date, the optimal timing, sequence, and combinations of Ra-223 with other agents are yet to be determined. The goals of this review are to provide insight into practical aspects of patient selection for Ra-223 treatment and to discuss key therapeutic strategies using the 6 approved mCRPC agents in patients with bone metastases. Results from ongoing trials should help guide the practitioner in using Ra-223 in patients with mCRPC.

Radium-223 treatment in castration resistant bone metastatic prostate cancer. Should be the primary tumor always treated?

INTRODUCTION

Radium-223 (223Ra) improves symptoms and survival in patients with bone metastatic castration-resistant prostate cancer (mCRPC).

STUDY AIM

To evaluate the impact of a previous radical prostatectomy (RP) on the outcome of 223Ra therapy in mCRPC patients. The primary prostate tumor left untreated could progress during 223Ra treatment.

MATERIALS AND METHODS

mCRPC symptomatic patients treated with 223Ra were enrolled. Luteinizing Hormone-Releasing Hormone analogue was maintained. No other anticancer therapy was given. 223Ra was administered i.v. at the dose of 55 kBq/kg every 4 weeks for 6 cycles. Patients were stratified according to previous RP or not. Hematological toxicity was monitored. Statistical analysis of 223Ra discontinuations, progressions, and deaths were performed.

RESULTS

Forty-four patients were enrolled, 16 (36.4%) previously received RP, 5 (11.3%) prostate radiotherapy and 23 (52.3%) maintained the primary prostate tumor after local treatment. All patients presented only bone metastases, 24 patients (54.5%) had more than 20. Twenty-six (59.1%) patients were treated after first or second line systemic chemotherapy. Treatment interruptions occurred in 14 patients (50%) with prostate and in 4 (25%) without (P = 0.04). After a median follow-up of 18 months (6-30 months), 15 (53.6%), and 7 (43.7%) progressions (P = 0.34) and 13 and 1 (6.2%) deaths (P = 0.04) occurred in patients with and without prostate respectively.

CONCLUSION

The presence of the primary prostate tumor seems to play a detrimental role in mCRPC patients undergoing 223Ra treatment in absence of other concomitant anticancer therapy. On the other hand a previous RP might play a protective role.