Search

Conventional radiomics in nuclear medicine involve hand-crafted and computer-assisted regions of interest. Recent developments in artificial intelligence (AI) have seen the emergence of AI-augmented segmentation and extraction of lower order traditional radiomic features. Deep learning (DL) affords the opportunity to extract abstract radiomic features directly from input tensors (images) without the need for segmentation. These fourth-order, high dimensional radiomics produce deep radiomics and are well suited to the data density associated with the molecular nature of hybrid imaging. Molecular radiomics and deep molecular radiomics provide insights beyond images and quantitation typical of semantic reporting. While the application of molecular radiomics using hand-crafted and computer-generated features is integrated into decision-making in nuclear medicine, the acceptance of deep molecular radiomics is less universal. This manuscript aims to provide an understanding of the language and principles associated with radiomics and deep radiomics in nuclear medicine.

Social and health care equity and justice should be prioritized by the mantra of medicine, first do no harm. Despite highly motivated national and global health strategies, there remains significant health care inequity. Intrinsic and extrinsic factors, including a number of biases, are key drivers of ongoing health inequity including equity of access and opportunity for nuclear medicine and radiology services. There is a substantial gap in the global practice of nuclear medicine in particular, but also radiology, between developed health economies and those considered developing or undeveloped. At a local level, even in developed health economies, there can be a significant disparity between health services, including medical imaging, between communities based on socioeconomic, cultural or geographic differences. Artificial intelligence (AI) has the potential to either widen the health inequity divide or substantially reduce it. Distributed generally, AI technology could be used to overcome geographic boundaries to health care, thus bringing general and specialist care into underserved communities. However, should AI technology be limited to localities already enjoying ample healthcare access and direct access to health infrastructure, like radiology and nuclear medicine, it could then accentuate the gap. There are a number of challenges across the AI pipeline that need careful attention to ensure beneficence over maleficence. Fully realized, AI augmented health care could be crafted as an integral part of the broader strategy convergence on local, national and global health equity. The applications of AI in nuclear medicine and radiology could emerge as a powerful tool in social and health equity.

Purpose:The prognosis of metastatic osteosarcoma continues to be poor. We hypothesized that alpha-emitting, bone-targeting radium 223 dichloride (223RaCl2) can be safely administered to patients with osteosarcoma and that early signals of response or resistance can be assessed by quantitative and qualitative correlative imaging studies and biomarkers.Patients and Methods:A 3+3 phase I, dose-escalation trial of 223RaCl2 (50, 75, and 100 kBq/kg) was designed in patients with recurrent/metastatic osteosarcoma aged ≥15 years. Objective measurements included changes in standardized uptake values of positron emission tomography (PET; 18FDG and/or NaF-18) and single-photon emission CT/CT (99mTc-MDP) as well as alkaline phosphatase and bone turnover markers at baseline, midstudy, and the end of the study.Results:Among 18 patients enrolled (including 15 males) aged 15–71 years, tumor locations included spine (n = 12, 67%), pelvis (n = 10, 56%), ribs (n = 9, 50%), extremity (n = 7, 39%), and skull (n = 2, 11%). Patients received 1–6 cycles of 223RaCl2; cumulative doses were 6.84-57.81 MBq. NaF PET revealed more sites of metastases than did FDG PET. One patient showed a metabolic response on FDG PET and NaF PET. Four patients had mixed responses, and one patient had a response in a brain metastasis. Bronchopulmonary hemorrhage from Grade 3 thrombocytopenia (N = 1) was a DLT. The median overall survival time was 25 weeks.Conclusions:The first evaluation of the safety and efficacy of an alpha particle in high-risk osteosarcoma shows that the recommended phase II dose for 223RaCl2 in osteosarcoma is 100 kBq/kg monthly (twice the dose approved for prostate cancer), with minimal hematologic toxicity, setting the stage for combination therapies.

Supplementary file: Previous therapies, Overall survival S1 : Prior therapies of patients with osteosarcoma enrolled on the Radium 223 trial. Supplementary Table S2: Adverse events in patients with osteosarcoma enrolled on the Radium 223 trial. Supplementary Figure 1: Overall survival of patients with osteosarcoma enrolled on the Radium 223 trial. Supplementary Figure 2: Correlation of % change in RECIST with relative change in LDH. Table 3: Table 1. Ra-223 dichloride Dose Escalation scheme (N=3/cohort)

Artificial intelligence (AI) in radiology is transforming medical image analysis. While applications in triaging for priority reporting and radiomic feature analysis have been widely reported, perhaps the most important applications lie in noise reduction, image optimization following dose reduction strategies, image reconstruction direct from projection data and generation of pseudo-CT for attenuation correction. There are common beneficial applications, and potential risks, between human radiology and veterinary radiology. Artificial intelligence may see recrafting of some responsibilities but offers AI augmentation of human driven systems. The redundancy afforded by human augmentation of AI and AI autonomy are not on the horizon, but rather are already here.

Radiomics refers to the process of extracting useful imaging features from radiological data. Conventional radiomics like standard uptake value, intensity histograms, or phase images involve hand-crafted (manual) or automated regions of interest (computer generated), however, artificial intelligence (AI) segmentation (AI-augmented radiomics) has recently emerged. Radiomic feature extraction extends image insights beyond simply data quantitation and provides additional insights to aid semantic reporting. Deeper layers of a convolutional neural network produce more abstract radiomic features that are referred to as deep radiomics. The application of radiomics in veterinary radiology is already firmly entrenched using hand-crafted and automated computer-generated radiomic features in X-ray, nuclear medicine, CT, ultrasound, and MRI. There is an opportunity for veterinary radiology to capitalize on advances in AI, machine learning, and deep learning to enrich imaging interpretation using deep radiomic feature extraction. This manuscript aims to provide a general understanding of radiomics and deep radiomics, and to arm readers with the vernacular to progress discussion and development of deep radiomics in veterinary imaging.

Objective To determine whether an interim 18F-fluoride positron-emission tomography/computed tomography (PET/CT) study performed after the third cycle of radium-223 dichloride (223RaCl2) therapy is able to identify patients that will not respond to treatment. Materials and Methods We retrospectively reviewed 34 histologically confirmed cases of hormone-refractory prostate cancer with bone metastasis in patients submitted to 223RaCl2 therapy. All of the patients underwent baseline and interim 18F-fluoride PET/CT studies. The interim study was performed immediately prior to the fourth cycle of 223RaCl2. The skeletal tumor burden-expressed as the total lesion fluoride uptake above a maximum standardized uptake value of 10 (TLF10)-was calculated for the baseline and the interim studies. The percent change in TLF10 between the baseline and interim studies (%TFL10) was calculated as follows: %TFL10 = interim TLF10 - baseline TLF10 / baseline TLF10. End points were overall survival, progression-free survival, and skeletal-related events. Results The mean age of the patients was 72.4 ± 10.2 years (range, 43.3-88.8 years). The %TLF10 was not able to predict overall survival (p = 0.6320; hazard ratio [HR] = 0.753; 95% confidence interval [CI]: 0.236-2.401), progression-free survival (p = 0.5908; HR = 1.248; 95% CI: 0.557-2.797) nor time to a bone event (p = 0.5114; HR = 1.588; 95% CI: 0.399-6.312). Conclusion The skeletal tumor burden on an interim 18F-fluoride PET/CT, performed after three cycles of 223RaCl2, is not able to predict overall survival, progression-free survival, or time to bone event, and should not be performed to monitor response at this time.

Osteosarcoma is a cancer characterized by formation of bone by malignant cells. Routine bone scan imaging with Tc-99m-MDP is done at diagnosis to evaluate primary tumor uptake and check for bone metastases. At time of relapse the Tc-99m-MDP bone scan also provides a specific means to assess formation of bone by malignant osteosarcoma cells and the potential for bone-seeking radiopharmaceuticals to deliver radioactivity directly into osteoblastic osteosarcoma lesions. This chapter will review and compare a bone-seeking radiopharmaceutical that emits beta-particles, samarium-153-EDTMP, with an alpha-particle emitter, radium-223. The charged alpha particles from radium-223 have far more mass and energy than beta particles (electrons) from Sm-153-EDTMP. Because radium-223 has less marrow toxicity and more radiobiological effectiveness, especially if inside the bone forming cancer cell than samarium-153-EDTMP, radium-223 may have greater potential to become widely used against osteosarcoma as a targeted therapy. Radium-223 also has more potential to be used with chemotherapy against osteosarcoma and bone metastases. Because osteosarcoma makes bone and radium-223 acts like calcium, this radiopharmaceutical could possibly become a new targeted means to achieve safe and effective reduction of tumor burden as well as facilitate better surgery and/or radiotherapy for difficult to resect large, or metastatic tumors.

The NCCN Clinical Practice Guidelines in Oncology for Colon Cancer begin with the clinical presentation of the patient to the primary care physician or gastroenterologist and address diagnosis, pathologic staging, surgical management, perioperative treatment, patient surveillance, management of recurrent and metastatic disease, and survivorship. The NCCN Colon Cancer Panel meets annually to review comments from reviewers within their institutions and to reevaluate and update their recommendations. In addition, the panel has interim conferences as new data necessitate. These NCCN Guidelines Insights summarize the NCCN Colon Cancer Panel's discussions regarding the treatment of localized disease for the 2013 update of the guidelines.

Several investigators have shown that noise equivalent count rate (NECR) is linearly proportional to the square of image signal-to-noise ratio (SNR) when PET images are reconstructed using filtered back-projection. However, to our knowledge, none have shown a similar relationship in fully 3D ordered-subset expectation maximization (OSEM) reconstruction. This paper has two aims. The first is to investigate the NECR-SNR relationship for 3D-OSEM reconstruction using phantom studies while the second aim is to evaluate the NECR-SNR relationship using patient data.An anthropomorphic phantom was scanned on a GE Discovery-STE (DSTE) PET∕CT scanner in 3D mode with an initial activity concentration of 66.34 kBq∕cc. PET data were acquired over the lower chest∕upper abdomen region in dynamic mode. The experiment was repeated with the same activity concentration on a GE Discovery-RX (DRX) scanner. Care was taken to place the phantom at identical positions in both scanners. PET data were then reconstructed using 3D Reprojection (3D-RP) and 3D-OSEM with different reconstruction parameters and the NECR and SNR for each frame∕image were calculated. SNR(2) was then plotted versus the NECR for each scanner, reconstruction method and parameters. In addition, 40 clinical PET∕CT studies from the two scanners (20 patients∕scanner) were evaluated retrospectively. The patient studies from each scanner were further divided into two subgroups of body mass indices (BMI). Each PET study was acquired in 3D mode and reconstructed using both 3D-OSEM and 3D-RP. The NECR and SNR of the bed position covering the patient liver were calculated for each patient and averaged for each subgroup. Comparisons of the NECR and SNR between scanner types and BMIs were performed using a t-test and a p value less than 0.05 was considered significant.Phantom results showed that SNR(2) versus NECR was linear for 3D-RP reconstruction across all activity concentration on both scanners, as expected. However, when 3D-OSEM was used, this relationship was nonlinear at activity concentrations beyond the peak NECR on both scanners. On the other hand, the plot of SNR(2) versus trues count rate was linear for 3D-OSEM across all activity concentrations on both scanners independent of reconstruction parameters used. In addition, for activity concentrations30kBq∕cc, phantom results showed a higher SNR (by 12 ± 10%; p0.05) and NECR for the DRX scanner compared to DSTE for 3D-RP reconstruction. However, for 3D-OSEM reconstruction, these two scanners had similar SNRs (different by 2% ± 9%; p0.05), despite having different NECRs. Patient studies showed a statistically significant difference in NECR as well as the SNR for 3D-RP reconstruction between the two scanners. However, no statistically significant difference was found for 3D-OSEM. A statistically significant difference in both NECR and SNR were found between the different BMI subgroups for both 3D-RP and 3D-OSEM reconstructions.For the scanners and reconstruction algorithm used in this study, our results suggest that the image SNR cannot be predicted by the NEC when using 3D-OSEM reconstruction particularly for those clinical applications requiring high activity concentration. Instead, our results suggest that image SNR varies with activity concentration and is dominated by the 3D-OSEM reconstruction algorithm and its associated parameters, while not being affected by the scanner type for the range of activity concentrations usually found in the clinic.