Currently, kinetic analyses using dynamic positron emission tomography (PET) experience very limited use despite their potential for improving quantitative accuracy in several clinical and research applications. For targeted volume applications, such as radiation treatment planning, treatment monitoring, and cerebral metabolic studies, the key to implementation of these methods is the determination of an arterial input function, which can include time-consuming analysis of blood samples for metabolite correction. Targeted kinetic applications would become practical for the clinic if blood sampling and metabolite correction could be avoided. To this end, we developed a novel method (Patlak-P) of generating parametric maps that is identical to Patlak K(i) (within a global scalar multiple) but does not require the determination of the arterial input function or metabolite correction. In this initial study, we show that Patlak-P (a) mimics Patlak K(i) images in terms of visual assessment and target-to-background (TB) ratios of regions of elevated uptake, (b) has higher visual contrast and (generally) better image quality than SUV, and (c) may have an important role in improving radiotherapy planning, therapy monitoring, and neurometabolism studies.

We report the case of a 17-year-old girl with keratitis, ichthyosis, and deafness (KID) syndrome. As a complication of her KID syndrome she developed squamous cell carcinoma at the left index finger. Additional clinical features were multiple soft tissue lesions over the scalp mimicking metastatic disease on 18F-FDG PET/CT. To our knowledge, this is the first case report about the uptake pattern of KID syndrome associated skin lesions on whole body PET/CT with 18F-FDG.

Purpose

Simultaneous positron emission tomography-magnetic resonance imaging (PET-MRI) is an emerging technology providing both anatomical and functional images without increasing the scan time. Compared to the traditional PET/computed tomography imaging, it also exposes the patient to significantly less radiation and provides better anatomical images as MRI provides superior soft tissue characterization. Using PET-MRI, we aim to study interactions between cartilage composition and bone function simultaneously, in knee osteoarthritis (OA).

Procedures

In this article, bone turnover and remodeling was studied using [¹⁸F]-sodium fluoride (NaF) PET data. Quantitative MR-derived T_1ρ relaxation times characterized the biochemical cartilage degeneration. Sixteen participants with early signs of OA of the knee received intravenous injections of [¹⁸F]-NaF at the onset of PET-MR image acquisition. Regions of interest were identified, and kinetic analysis of dynamic PET data provided the rate of uptake ( K_i) and the normalized uptake (standardized uptake value) of [¹⁸F]-NaF in the bone. Morphological MR images and quantitative voxel-based T_1ρ maps of cartilage were obtained using an atlas-based registration technique to segment cartilage automatically. Voxel-by-voxel statistical parameter mapping was used to investigate the relationship between bone and cartilage.

Results

Increases in cartilage T_1ρ, indicating degenerative changes, were associated with increased turnover in the adjoining bone but reduced turnover in the nonadjoining compartments. Associations between pain and increased bone uptake were seen in the absence of morphological lesions in cartilage, but the relationship was reversed in the presence of incident cartilage lesions.

Conclusion

This study shows significant cartilage and bone interactions in OA of the knee joint using simultaneous [¹⁸F]-NaF PET-MR, the first in human study. These observations highlight the complex biomechanical and biochemical interactions in the whole knee joint in OA, which potentially could help assess therapeutic targets in treating OA.

To develop a method for calculating rates of testing for breast cancer recurrence in patients who have already undergone initial treatment for breast cancer, we calculated rates in a cohort of Medicare breast cancer patients and an age-matched noncancer cohort. We first used only tests with claims including diagnosis codes indicating invasive breast cancer and then used all tests regardless of diagnosis code. For each method, we calculated testing rates in the breast cancer cohort above the background rate in the noncancer population. The two methods provided similar estimates of testing prevalence and frequency, with exception of prevalence of CT.

Our objective was to develop deep learning models with chest radiograph data to predict healthcare costs and classify top-50% spenders. 21,872 frontal chest radiographs were retrospectively collected from 19,524 patients with at least 1-year spending data. Among the patients, 11,003 patients had 3 years of cost data, and 1678 patients had 5 years of cost data. Model performances were measured with area under the receiver operating characteristic curve (ROC-AUC) for classification of top-50% spenders and Spearman ρ for prediction of healthcare cost. The best model predicting 1-year (N = 21,872) expenditure achieved ROC-AUC of 0.806 [95% CI 0.793-0.819] for top-50% spender classification and ρ of 0.561 [0.536-0.586] for regression. Similarly, for predicting 3-year (N = 12,395) expenditure, ROC-AUC of 0.771 [0.750-0.794] and ρ of 0.524 [0.489-0.559]; for predicting 5-year (N = 1779) expenditure ROC-AUC of 0.729 [0.667-0.729] and ρ of 0.424 [0.324-0.529]. Our deep learning model demonstrated the feasibility of predicting health care expenditure as well as classifying top 50% healthcare spenders at 1, 3, and 5 year(s), implying the feasibility of combining deep learning with information-rich imaging data to uncover hidden associations that may allude to physicians. Such a model can be a starting point of making an accurate budget in reimbursement models in healthcare industries.

Purpose

Transforming growth factor β (TGFβ) promotes cell survival by endorsing DNA damage repair and mediates an immunosuppressive tumor microenvironment. Thus, TGFβ activation in response to radiation therapy is potentially targetable because it opposes therapeutic control. Strategies to assess this potential in the clinic are needed.

Methods and materials

We evaluated positron emission tomography (PET) to image ⁸⁹Zr -fresolimumab, a humanized TGFβ neutralizing monoclonal antibody, as a means to detect TGFβ activation in intracranial tumor models. Pathway activity of TGFβ was validated by immunodetection of phosphorylated SMAD2 and the TGFβ target, tenascin. The contribution of TGFβ to radiation response was assessed by Kaplan-Meier survival analysis of mice bearing intracranial murine tumor models GL261 and SB28 glioblastoma and brain-adapted 4T1 breast cancer (4T1-BrA) treated with TGFβ neutralizing monoclonal antibody, 1D11, and/or focal radiation (10 Gy).

Results

⁸⁹Zr-fresolimumab PET imaging detected engineered, physiological, and radiation-induced TGFβ activation, which was confirmed by immunostaining of biological markers. GL261 glioblastoma tumors had a greater PET signal compared with similar-sized SB28 glioblastoma tumors, whereas the widespread PET signal of 4T1-BrA intracranial tumors was consistent with their highly dispersed histologic distribution. Survival of mice bearing intracranial tumors treated with 1D11 neutralizing antibody alone was similar to that of mice treated with control antibody, whereas 1D11 improved survival when given in combination with focal radiation. The extent of survival benefit of a combination of radiation and 1D11 was associated with the degree of TGFβ activity detected by PET.

Conclusions

This study demonstrates that ⁸⁹Zr-fresolimumab PET imaging detects radiation-induced TGFβ activation in tumors. Functional imaging indicated a range of TGFβ activity in intracranial tumors, but TGFβ blockade provided survival benefit only in the context of radiation treatment. This study provides further evidence that radiation-induced TGFβ activity opposes therapeutic response to radiation.

Metabolic imaging of the primary breast tumor with ¹⁸F-fluorodeoxyglucose ([¹⁸F]FDG) PET may assist in predicting treatment response in the neoadjuvant chemotherapy (NAC) setting. Dedicated breast PET (dbPET) is a high-resolution imaging modality with demonstrated ability in highlighting intratumoral heterogeneity and identifying small lesions in the breast volume. In this study, we characterized similarities and differences in the uptake of [¹⁸F]FDG in dbPET compared to whole-body PET (wbPET) in a cohort of ten patients with biopsy-confirmed, locally advanced breast cancer at the pre-treatment timepoint. Patients received bilateral dbPET and wbPET following administration of 186 MBq and 307 MBq [¹⁸F]FDG on separate days, respectively. [¹⁸F]FDG uptake measurements and 20 radiomic features based on morphology, tumor intensity, and texture were calculated and compared. There was a fivefold increase in SUL_peak for dbPET (median difference (95% CI): 4.0 mL^-1 (1.8-6.4 mL^-1), p = 0.006). Additionally, spatial heterogeneity features showed statistically significant differences between dbPET and wbPET. The higher [¹⁸F]FDG uptake in dbPET highlighted the dynamic range of this breast-specific imaging modality. Combining with the higher spatial resolution, dbPET may be able to detect treatment response in the primary tumor during NAC, and future studies with larger cohorts are warranted.

Breast cancer is a leading cause of cancer death among women in the USA. Screening mammography is effective in reducing mortality, but has a high rate of unnecessary recalls and biopsies. While deep learning can be applied to mammography, large-scale labeled datasets, which are difficult to obtain, are required. We aim to remove many barriers of dataset development by automatically harvesting data from existing clinical records using a hybrid framework combining traditional NLP and IBM Watson. An expert reviewer manually annotated 3521 breast pathology reports with one of four outcomes: left positive, right positive, bilateral positive, negative. Traditional NLP techniques using seven different machine learning classifiers were compared to IBM Watson's automated natural language classifier. Techniques were evaluated using precision, recall, and F-measure. Logistic regression outperformed all other traditional machine learning classifiers and was used for subsequent comparisons. Both traditional NLP and Watson's NLC performed well for cases under 1024 characters with weighted average F-measures above 0.96 across all classes. Performance of traditional NLP was lower for cases over 1024 characters with an F-measure of 0.83. We demonstrate a hybrid framework using traditional NLP techniques combined with IBM Watson to annotate over 10,000 breast pathology reports for development of a large-scale database to be used for deep learning in mammography. Our work shows that traditional NLP and IBM Watson perform extremely well for cases under 1024 characters and can accelerate the rate of data annotation.

Radiomics is an emerging technology for imaging biomarker discovery and disease-specific personalized treatment management. This paper aims to determine the benefit of using multi-modality radiomics data from PET and MR images in the characterization breast cancer phenotype and prognosis. Eighty-four features were extracted from PET and MR images of 113 breast cancer patients. Unsupervised clustering based on PET and MRI radiomic features created three subgroups. These derived subgroups were statistically significantly associated with tumor grade (p = 2.0 × 10^-6), tumor overall stage (p = 0.037), breast cancer subtypes (p = 0.0085), and disease recurrence status (p = 0.0053). The PET-derived first-order statistics and gray level co-occurrence matrix (GLCM) textural features were discriminative of breast cancer tumor grade, which was confirmed by the results of L2-regularization logistic regression (with repeated nested cross-validation) with an estimated area under the receiver operating characteristic curve (AUC) of 0.76 (95% confidence interval (CI) = [0.62, 0.83]). The results of ElasticNet logistic regression indicated that PET and MR radiomics distinguished recurrence-free survival, with a mean AUC of 0.75 (95% CI = [0.62, 0.88]) and 0.68 (95% CI = [0.58, 0.81]) for 1 and 2 years, respectively. The MRI-derived GLCM inverse difference moment normalized (IDMN) and the PET-derived GLCM cluster prominence were among the key features in the predictive models for recurrence-free survival. In conclusion, radiomic features from PET and MR images could be helpful in deciphering breast cancer phenotypes and may have potential as imaging biomarkers for prediction of breast cancer recurrence-free survival.

Dedicated breast positron emission tomography (dbPET) is an emerging technology with high sensitivity and spatial resolution that enables detection of sub-centimeter lesions and depiction of intratumoral heterogeneity. In this study, we report our initial experience with dbPET using [F-18]fluoroestradiol (FES) in assessing ER+ primary breast cancers. Six patients with >90% ER+ and HER2- breast cancers were imaged with dbPET and breast MRI. Two patients had ILC, three had IDC, and one had an unknown primary tumor. One ILC patient was treated with letrozole, and another patient with IDC was treated with neoadjuvant chemotherapy without endocrine treatment. In this small cohort, we observed FES uptake in ER+ primary breast tumors with specificity to ER demonstrated in a case with tamoxifen blockade. FES uptake in ILC had a diffused pattern compared to the distinct circumscribed pattern in IDC. In evaluating treatment response, the reduction of SUV_max was observed with residual disease in an ILC patient treated with letrozole, and an IDC patient treated with chemotherapy. Future study is critical to understand the change in FES SUV_max after endocrine therapy and to consider other tracer uptake metrics with SUV_max to describe ER-rich breast cancer. Limitations include variations of FES uptake in different ER+ breast cancer diseases and exclusion of posterior tissues and axillary regions. However, FES-dbPET has a high potential for clinical utility, especially in measuring response to neoadjuvant endocrine treatment. Further development to improve the field of view and studies with a larger cohort of ER+ breast cancer patients are warranted.