Combining Multistaged Filters and Modified Segmentation Network for Improving Lung Nodules Classification.

Advancements in computational technology have led to a shift towards automated detection processes in lung cancer screening, particularly through nodule segmentation techniques. These techniques employ thresholding to distinguish between soft and firm tissues, including cancerous nodules. The challenge of accurately detecting nodules close to critical lung structures such as blood vessels, bronchi, and the pleura highlights the necessity for more sophisticated methods to enhance diagnostic accuracy. This paper proposed combined processing filters for data preparation before using one of the modified Convolutional Neural Networks (CNN) as the classifier. With refined filters, the nodule targets are solid, semi-solid, and ground glass, ranging from low-stage cancer (cancer screening data) to high-stage cancer. Furthermore, two additional works were added to address juxta-pleural nodules while the pre-processing end and classification are done in a 3-dimensional domain in opposition to the usual image classification. The accuracy output indicates that even using a simple Segmentation Network if modified correctly, can improve the classification result compared to the other eight models. The proposed sequence total accuracy reached 99.7%, with 99.71% cancer class accuracy and 99.82% non-cancer accuracy, much higher than any previous research, which can improve the detection efforts of the radiologist.

Women in leadership matters: Achieving diversity in radiology residency recruitment.

RATIONALE AND OBJECTIVES: To assess whether academic radiology departments and residency programs with efforts toward supporting and augmenting Diversity, Equity, and Inclusion (DEI) are associated with a higher proportion of residents from diverse backgrounds. MATERIALS AND METHODS: Program Directors within the Radiology Residency Education Research Alliance were surveyed to gather information about program characteristics, incorporation of diversity in resident recruitment, the sponsoring department's commitment to efforts at expanding diversity, and a summary of their current and past residents, staff and faculty members (academic years 2020 and 2023) with respect to a list of diversity characteristics. RESULTS: Survey response rate was 51 %. Sixty-three percent (15/24) of participating programs have departmental committees dedicated to DEI work; 46 % (11/24) of programs' departments have a Vice Chair for DEI. Sixty percent (15/24) of programs use their social media accounts to advertise their DEI programming efforts. Ninety-six percent (23/24) of programs participating in the survey use diversity factors to select candidates for their program. Women Leadership was associated with above-median diversity of residents and faculty. CONCLUSION: This study of radiology residency programs encourages a more prominent role for women in leadership positions within academic radiology departments to drive diversity and inclusion efforts.

Magnitude and persistence of higher estrus-associated temperatures in beef heifers and suckled cows.

Higher estrus-associated temperatures (HEAT) are a hallmark feature in sexually active females. The overarching aim of this study was to characterize the variability, magnitude, and persistence of HEAT in heifers and suckled beef cows as well as identify associated factors when occurring during thermoneutral conditions at the onset of the spring breeding season. In both heifers and cows, estrus was induced using a 7-d controlled internal drug release (CIDR)-PGF2α protocol. Vaginal temperature after prostaglandin F2α administration was recorded every 5 min using a Thermochron iButton affixed to a blank CIDR (containing no progesterone). Estrus was defined as when a heifer first stood to be mounted or when a cow had an Estrotect patch score of 3 or 4. Level of HEAT varied among individual animals. When comparing common HEAT variables using a mixed model with date nested within a year, maximum HEAT (39.9 ±â€…0.1 and 40.0 ±â€…0.1 °C) and duration (15.5 ±â€…0.8 and 15.4 ±â€…0.7) were similar in heifers and cows, respectively. However, the magnitude and persistence of HEAT differed. Total area under the HEAT curve was 117.1 ±â€…13.5 and 158.7 ±â€…12.3 for heifers vs cows, respectively (P = 0.0571). Further, 42.9% of heifers and 49% of cows had maximum HEAT ≥ 40 °C which persisted up to 6.5 and 10 h, respectively. When ambient conditions were predominantly thermoneutral, temperature humidity index had minimal impact on HEAT (mixed model, repeated measures over time). Toward identifying associated factors with different aspects of HEAT using best fit hierarchical linear regression models, baseline vaginal temperature and baseline duration were the most highly associated independent variables. Follicle size, estradiol and progesterone levels, and other available animal-related variables (e.g., age, weight, hair coat score) explained only a small amount of variation in HEAT. In summary, level of HEAT varies in estrus females even under thermoneutral conditions. Because HEAT can persist for an extended time, direct effects on fertility important components are unavoidable. Whether HEAT is a good or bad component of the periovulatory microenvironment is the basis of ongoing and future studies.

When striving for a pregnancy, estrus is a critically important event. Higher estrus-associated temperatures (HEAT) are a hallmark feature in sexually active females. The importance of HEAT for pregnancy, however, remains unclear. Toward filling this critical knowledge gap, efforts described in the current study focused on examining variability of HEAT in individual animals, 2) defining the magnitude and persistence of HEAT, 3) identifying HEAT-associated factors, and 4) examining the similarity of HEAT between heifers and suckled beef cows when occurring at the onset of a spring breeding season. Although the magnitude and persistence of HEAT varied, 42.9% of heifers and 49% of cows reached temperatures ≥ 40 °C which in some cases persisted up to 6.5 and 10 h, respectively. When attempting to identify factors that could explain why some females exhibiting estrus remained hot for an extended time, available animal and environmental data contributed little. Even so, because HEAT can persist for an extended time, direct effects on fertility important components are unavoidable. Whether too much HEAT is good or bad for pregnancy is the basis of ongoing and future studies.

Pathway level subtyping identifies a slow-cycling biological phenotype associated with poor clinical outcomes in colorectal cancer.

Molecular stratification using gene-level transcriptional data has identified subtypes with distinctive genotypic and phenotypic traits, as exemplified by the consensus molecular subtypes (CMS) in colorectal cancer (CRC). Here, rather than gene-level data, we make use of gene ontology and biological activation state information for initial molecular class discovery. In doing so, we defined three pathway-derived subtypes (PDS) in CRC: PDS1 tumors, which are canonical/LGR5+ stem-rich, highly proliferative and display good prognosis; PDS2 tumors, which are regenerative/ANXA1+ stem-rich, with elevated stromal and immune tumor microenvironmental lineages; and PDS3 tumors, which represent a previously overlooked slow-cycling subset of tumors within CMS2 with reduced stem populations and increased differentiated lineages, particularly enterocytes and enteroendocrine cells, yet display the worst prognosis in locally advanced disease. These PDS3 phenotypic traits are evident across numerous bulk and single-cell datasets, and demark a series of subtle biological states that are currently under-represented in pre-clinical models and are not identified using existing subtyping classifiers.

JAK/STAT3 represents a therapeutic target for colorectal cancer patients with stromal-rich tumors.

Colorectal cancer (CRC) is a heterogenous malignancy underpinned by dysregulation of cellular signaling pathways. Previous literature has implicated aberrant JAK/STAT3 signal transduction in the development and progression of solid tumors. In this study we investigate the effectiveness of inhibiting JAK/STAT3 in diverse CRC models, establish in which contexts high pathway expression is prognostic and perform in depth analysis underlying phenotypes. In this study we investigated the use of JAK inhibitors for anti-cancer activity in CRC cell lines, mouse model organoids and patient-derived organoids. Immunohistochemical staining of the TransSCOT clinical trial cohort, and 2 independent large retrospective CRC patient cohorts was performed to assess the prognostic value of JAK/STAT3 expression. We performed mutational profiling, bulk RNASeq and NanoString GeoMx® spatial transcriptomics to unravel the underlying biology of aberrant signaling. Inhibition of signal transduction with JAK1/2 but not JAK2/3 inhibitors reduced cell viability in CRC cell lines, mouse, and patient derived organoids (PDOs). In PDOs, reduced Ki67 expression was observed post-treatment. A highly significant association between high JAK/STAT3 expression within tumor cells and reduced cancer-specific survival in patients with high stromal invasion (TSPhigh) was identified across 3 independent CRC patient cohorts, including the TrasnSCOT clinical trial cohort. Patients with high phosphorylated STAT3 (pSTAT3) within the TSPhigh group had higher influx of CD66b + cells and higher tumoral expression of PDL1. Bulk RNAseq of full section tumors showed enrichment of NFκB signaling and hypoxia in these cases. Spatial deconvolution through GeoMx® demonstrated higher expression of checkpoint and hypoxia-associated genes in the tumor (pan-cytokeratin positive) regions, and reduced lymphocyte receptor signaling in the TME (pan-cytokeratin- and αSMA-) and αSMA (pan-cytokeratin- and αSMA +) areas. Non-classical fibroblast signatures were detected across αSMA + regions in cases with high pSTAT3. Therefore, in this study we have shown that inhibition of JAK/STAT3 represents a promising therapeutic strategy for patients with stromal-rich CRC tumors. High expression of JAK/STAT3 proteins within both tumor and stromal cells predicts poor outcomes in CRC, and aberrant signaling is associated with distinct spatially-dependant differential gene expression.

Characterizing Neutrophil Subtypes in Cancer Using scRNA Sequencing Demonstrates the Importance of IL1ß/CXCR2 Axis in Generation of Metastasis-specific Neutrophils.

Neutrophils are a highly heterogeneous cellular population. However, a thorough examination of the different transcriptional neutrophil states between health and malignancy has not been performed. We utilized single-cell RNA sequencing of human and murine datasets, both publicly available and independently generated, to identify neutrophil transcriptomic subtypes and developmental lineages in health and malignancy. Datasets of lung, breast, and colorectal cancer were integrated to establish and validate neutrophil gene signatures. Pseudotime analysis was used to identify genes driving neutrophil development from health to cancer. Finally, ligand-receptor interactions and signaling pathways between neutrophils and other immune cell populations in primary colorectal cancer and metastatic colorectal cancer were investigated. We define two main neutrophil subtypes in primary tumors: an activated subtype sharing the transcriptomic signatures of healthy neutrophils; and a tumor-specific subtype. This signature is conserved in murine and human cancer, across different tumor types. In colorectal cancer metastases, neutrophils are more heterogeneous, exhibiting additional transcriptomic subtypes. Pseudotime analysis implicates IL1ß/CXCL8/CXCR2 axis in the progression of neutrophils from health to cancer and metastasis, with effects on T-cell effector function. Functional analysis of neutrophil-tumoroid cocultures and T-cell proliferation assays using orthotopic metastatic mouse models lacking Cxcr2 in neutrophils support our transcriptional analysis. We propose that the emergence of metastatic-specific neutrophil subtypes is driven by the IL1ß/CXCL8/CXCR2 axis, with the evolution of different transcriptomic signals that impair T-cell function at the metastatic site. Thus, a better understanding of neutrophil transcriptomic programming could optimize immunotherapeutic interventions into early and late interventions, targeting different neutrophil states. SIGNIFICANCE: We identify two recurring neutrophil populations and demonstrate their staged evolution from health to malignancy through the IL1ß/CXCL8/CXCR2 axis, allowing for immunotherapeutic neutrophil-targeting approaches to counteract immunosuppressive subtypes that emerge in metastasis.

Quantitative Skeletal Imaging and Image-Based Modeling in Pediatric Orthopaedics.

PURPOSE OF REVIEW: Musculoskeletal imaging serves a critical role in clinical care and orthopaedic research. Image-based modeling is also gaining traction as a useful tool in understanding skeletal morphology and mechanics. However, there are fewer studies on advanced imaging and modeling in pediatric populations. The purpose of this review is to provide an overview of recent literature on skeletal imaging modalities and modeling techniques with a special emphasis on current and future uses in pediatric research and clinical care. RECENT FINDINGS: While many principles of imaging and 3D modeling are relevant across the lifespan, there are special considerations for pediatric musculoskeletal imaging and fewer studies of 3D skeletal modeling in pediatric populations. Improved understanding of bone morphology and growth during childhood in healthy and pathologic patients may provide new insight into the pathophysiology of pediatric-onset skeletal diseases and the biomechanics of bone development. Clinical translation of 3D modeling tools developed in orthopaedic research is limited by the requirement for manual image segmentation and the resources needed for segmentation, modeling, and analysis. This paper highlights the current and future uses of common musculoskeletal imaging modalities and 3D modeling techniques in pediatric orthopaedic clinical care and research.

Cubonavicular Coalition: Magnetic Resonance Imaging Findings and Associated Pathology of a Rarely Reported Condition in 27 Patients.

RATIONALE AND OBJECTIVES: (1) Describe multimodality imaging of cubonavicular coalition (CNC) with magnetic resonance imaging (MRI) focus, (2) evaluate CNC associated foot and ankle pathology, (3) examine clinical presentation/symptoms associated with CNC, (4) record CNC treatment. MATERIALS AND METHODS: Retrospective Institutional Review Board (IRB) approved study. Picture Archiving and Communication System (PACS) databases searched for CNC. Final study population: 34 cases in 27 patients. Each CNC was reviewed for: coalition type (osseous versus non-osseous- cartilaginous versus fibrous), tendon and ligament pathology, bone marrow edema at CNC and adjacent joints, presence and severity of degenerative changes at CNC and adjacent joints, fractures, additional coalitions, laterality, and pes planus. MRI planes and radiographic views on which coalitions were best identified were recorded. Each CNC EMR was reviewed for: symptoms, trauma, management, patient demographics. Inter-reader reliability was performed for type of non-osseous coalition. RESULTS: Final cohort included 34 cases in 27 patients (average age: 34.7, range: 10-76; 71% female). No CNC was completely osseous. On MRI, 89.5% of coalitions were non-osseous and 5.3% were partially osseous. 76.5% of patients had referable symptoms including pain, limited motion, inability to bear weight. 23.5% of patients were surgically managed/pathologically proven. On MRI, 36.8% of patients had tendon pathology, 52.6% had ligamentous pathology, 100% had bone marrow edema-like signal abnormality about the CNC, and 88.2% had CNC degenerative changes. There was bone marrow edema-like signal abnormality at bones adjacent to the CNC in 52.6% and adjacent joint degenerative disease present in 50%. CNC was best identified on oblique radiographs and axial MRI. Inter-reader reliability for non-osseous coalition type was poor, Cronbach's alpha 0.554. CONCLUSION: CNC is subtle and findings of osteoarthritis or bone marrow edema-like about the cubonavicular articulation should raise suspicion for underlying coalition.

An EMR-Based Approach to Determine Frequency, Prescribing Pattern, and Characteristics of Patients Receiving Drugs with Pharmacogenomic Guidelines.

(1) Background: This retrospective analysis utilizing electronic medical record (EMR) data from a tertiary integrated health system sought to identify patients and prescribers who would benefit from pharmacogenomic (PGx) testing based on Clinical Pharmacogenetics Implementation Consortium (CPIC) guidelines. (2) Methods: EMR data from a clinical research data warehouse were analyzed from 845,518 patients that had an encounter between 2015 and 2019 at an academic medical center. Data were collected for 42 commercially available drugs with 52 evidence-based PGx guidelines from CPIC. Provider data were obtained through the EMR linked by specialty via national provider identification (NPI) number. (3) Results: A total of 845,518 patients had an encounter in the extraction period with 590,526 medication orders processed. A total of 335,849 (56.9%) patients had medication orders represented by CPIC drugs prescribed by 2803 providers, representing 239 distinct medications. (4) Conclusions: The results from this study show that over half of patients were prescribed a CPIC actionable medication from a variety of prescriber specialties. Understanding the magnitude of patients that may benefit from PGx testing, will enable the development of preemptive testing processes, physician support strategies, and pharmacist workflows to optimize outcomes should a PGx service be implemented.

Metabolic profiling stratifies colorectal cancer and reveals adenosylhomocysteinase as a therapeutic target.

The genomic landscape of colorectal cancer (CRC) is shaped by inactivating mutations in tumour suppressors such as APC, and oncogenic mutations such as mutant KRAS. Here we used genetically engineered mouse models, and multimodal mass spectrometry-based metabolomics to study the impact of common genetic drivers of CRC on the metabolic landscape of the intestine. We show that untargeted metabolic profiling can be applied to stratify intestinal tissues according to underlying genetic alterations, and use mass spectrometry imaging to identify tumour, stromal and normal adjacent tissues. By identifying ions that drive variation between normal and transformed tissues, we found dysregulation of the methionine cycle to be a hallmark of APC-deficient CRC. Loss of Apc in the mouse intestine was found to be sufficient to drive expression of one of its enzymes, adenosylhomocysteinase (AHCY), which was also found to be transcriptionally upregulated in human CRC. Targeting of AHCY function impaired growth of APC-deficient organoids in vitro, and prevented the characteristic hyperproliferative/crypt progenitor phenotype driven by acute deletion of Apc in vivo, even in the context of mutant Kras. Finally, pharmacological inhibition of AHCY reduced intestinal tumour burden in ApcMin/+ mice indicating its potential as a metabolic drug target in CRC.

Postoperative Imaging of the Ankle Tendons.

Ankle tendon pathology is an important cause of pain, instability, and disability. Surgical treatment is often employed when conservative management fails. The quantity and variety of ankle tendon repair/reconstruction surgeries have increased over time. As surgical techniques for ankle tendon surgery evolve and increase in prevalence, postoperative imaging of these tendons rises. Therefore, it is exceedingly important for radiologists to be familiar with these procedures, their expected postoperative appearance, imaging pitfalls, and potential complications. This article reviews the key imaging findings of a variety of common ankle tendon surgical procedures.

Genicular nerve radiofrequency ablation for the treatment of chronic knee joint pain: a real-world cohort study with evaluation of prognostic factors.

BACKGROUND: Genicular nerve radiofrequency ablation (GNRFA) is an effective treatment for chronic knee pain. However, there has been minimal investigation of real-world, long-term outcomes and factors that predict treatment success after GNRFA. OBJECTIVES: To evaluate the effectiveness of GNRFA for chronic knee pain in a real-world population and identify predictive factors. METHODS: Consecutive patients who underwent GNRFA at a tertiary academic center were identified. Demographic, clinical, and procedural characteristics were collected from the medical record. Outcome data were numeric rating scale (NRS) pain reduction and Patient Global Impression of Change (PGIC). Data were collected by standardized telephone survey. Predictors of success were evaluated with logistic and Poisson regression analyses. RESULTS: Of the 226 total patients identified, 134 (65.6 ± 12.7; 59.7% female) were successfully contacted and analyzed, with a mean follow-up time of 23.3 ± 11.0 months. Of those, 47.8% (n = 64; 95% CI: 39.5%-56.2%) and 61.2% (n = 82; 95% CI: 52.7%-69.0%) reported ≥50% NRS score reduction and ≥2-point NRS score reduction, respectively, and 59.0% (n = 79; 95% CI: 50.5%-66.9%) reported "much improved" on the PGIC questionnaire. Factors associated with a greater likelihood of treatment success (P < .05) were higher Kellgren-Lawrence osteoarthritis grade (2-4 vs 0-1); no baseline opioid, antidepressant, or anxiolytic medication use; and >3 nerves targeted. CONCLUSION: In this real-world cohort, approximately half of the participants experienced clinically meaningful improvements in knee pain after GNRFA at an average follow-up time of nearly 2 years. Factors associated with higher likelihood of treatment success were more advanced osteoarthritis (Kellgren-Lawrence Grade 2-4); no opioid, antidepressant, or anxiolytic medication use; and >3 nerves targeted.

Perceptual training and teaching medical students how to window and level chest radiographs.

Purpose: Perceptual errors account for a significant percent of errors in radiology. Reasons for failure to identify significant lesions are partially due to suboptimal differences in image contrast. The goal of this study is to determine if teaching trainees how to adjust image contrast, window, and level helps trainees identify pulmonary nodules on chest radiographs (CXRs). Approach: Fourteen medical students voluntarily participated. Subjects were asked to identify pulmonary nodules on CXRs before and after being taught how to adjust image contrast, window, and level. At the end of the study, subjects were given a survey assessing their perceptions about their training. Results: The experimental group was more confident in their ability to localize nodules relative to the control group ( P -value = 0.003). Subjects demonstrated statistically significant improvement in their ability to identify and localize nodules, with the experimental group performing better than the control group, though there was no statistically significant difference between groups. Participant survey indicated that they felt this training was beneficial, P -values for all survey responses were significant ( P -values all < 0.02 ). Conclusions: Teaching subjects how to window and level medical images may be a useful adjunct to current training for medical image interpretation.

Visual expertise is more than meets the eye: an examination of holistic visual processing in radiologists and architects.

Purpose: One of the dominant behavioral markers of visual-expert search strategy, holistic visual processing (HVP), suggests that experts process information from a larger region of space in conjunction with a more focused gaze pattern to improve search speed and accuracy. To date, extant literature suggests that visual search expertise is domain specific, including HVP and its associated behaviors. Approach: The current study is the first to use eye tracking to directly measure the HVP strategies of two expert groups, radiologists and architects, in comparison to one another and a novice control. Results: In doing so, we replicated and extended this prior research: visual expertise is domain specific. However, our eye-tracking data indicate that contrary to this prior work, HVP strategies are transferable across domains. Yet, despite the transfer of HVP strategies, there is neither reduced search time nor greater accuracy in visual search outside of an expert's domain. Conclusions: Therefore, our data suggest that HVP behaviors are a particular form of visual search mechanism that, outside of an expert's native search-ecology, are not necessarily conducive to more general visual search success. It is in addition to explicit knowledge of an expert's domain, how to search, and where to search, that HVP strategies are their most effective for visual search success.

MmCMS: mouse models' consensus molecular subtypes of colorectal cancer.

BACKGROUND: Colorectal cancer (CRC) primary tumours are molecularly classified into four consensus molecular subtypes (CMS1-4). Genetically engineered mouse models aim to faithfully mimic the complexity of human cancers and, when appropriately aligned, represent ideal pre-clinical systems to test new drug treatments. Despite its importance, dual-species classification has been limited by the lack of a reliable approach. Here we utilise, develop and test a set of options for human-to-mouse CMS classifications of CRC tissue. METHODS: Using transcriptional data from established collections of CRC tumours, including human (TCGA cohort; n = 577) and mouse (n = 57 across n = 8 genotypes) tumours with combinations of random forest and nearest template prediction algorithms, alongside gene ontology collections, we comprehensively assess the performance of a suite of new dual-species classifiers. RESULTS: We developed three approaches: MmCMS-A; a gene-level classifier, MmCMS-B; an ontology-level approach and MmCMS-C; a combined pathway system encompassing multiple biological and histological signalling cascades. Although all options could identify tumours associated with stromal-rich CMS4-like biology, MmCMS-A was unable to accurately classify the biology underpinning epithelial-like subtypes (CMS2/3) in mouse tumours. CONCLUSIONS: When applying human-based transcriptional classifiers to mouse tumour data, a pathway-level classifier, rather than an individual gene-level system, is optimal. Our R package enables researchers to select suitable mouse models of human CRC subtype for their experimental testing.

Beyond schwannomas and neurofibromas: a radiological and histopathological review of lesser-known benign lesions that arise in association with peripheral nerves.

Peripheral nerve sheath tumors comprise a significant percentage of both benign and malignant soft tissue tumors. The vast majority of these lesions are schwannomas and neurofibromas, which most radiologists are familiar with including the well-described multimodality imaging features. However, numerous additional often under-recognized benign entities associated with nerves exist. These rarer entities are becoming increasingly encountered with the proliferation of cross-sectional imaging, particularly magnetic resonance imaging (MRI). It is important for the radiologist to have a basic understanding of these entities as many have near-pathognomonic MR imaging features as well as specific clinical presentations that when interpreted in concert, often allows for a limited differential or single best diagnosis. The ability to provide a prospective, pre-intervention diagnosis based solely on imaging and clinical presentation is crucial as several of these entities are "do not touch" lesions, for which even a biopsy may have deleterious consequences. To our knowledge, the majority of these benign entities associated with nerves have only been described in scattered case reports or small case series. Therefore, the aim of this article is to provide a radiopathologic comprehensive review of these benign entities that arise in association with nerves with a focus on characteristic MRI features, unique histopathologic findings, and entity specific clinical exam findings/presentation.

Deep-learning prediction of amyloid deposition from early-phase amyloid positron emission tomography imaging.

OBJECTIVE: While the use of biomarkers for the detection of early and preclinical Alzheimer's Disease has become essential, the need to wait for over an hour after injection to obtain sufficient image quality can be challenging for patients with suspected dementia and their caregivers. This study aimed to develop an image-based deep-learning technique to generate delayed uptake patterns of amyloid positron emission tomography (PET) images using only early-phase images obtained from 0-20 min after radiotracer injection. METHODS: We prepared pairs of early and delayed [11C]PiB dynamic images from 253 patients (cognitively normal n = 32, fronto-temporal dementia n = 39, mild cognitive impairment n = 19, Alzheimer's disease n = 163) as a training dataset. The neural network was trained with the early images as the input, and the output was the corresponding delayed image. A U-net convolutional neural network (CNN) and a conditional generative adversarial network (C-GAN) were used for the deep-learning architecture and the data augmentation methods, respectively. Then, an independent test data set consisting of early-phase amyloid PET images (n = 19) was used to generate corresponding delayed images using the trained network. Two nuclear medicine physicians interpreted the actual delayed images and predicted delayed images for amyloid positivity. In addition, the concordance of the actual delayed and predicted delayed images was assessed statistically. RESULTS: The concordance of amyloid positivity between the actual versus AI-predicted delayed images was 79%(κ = 0.60) and 79% (κ = 0.59) for each physician, respectively. In addition, the physicians' agreement rate was at 89% (κ = 0.79) when the same image was interpreted. And, the actual versus AI-predicted delayed images were not readily distinguishable (correct answer rate, 55% and 47% for each physician, respectively). The statistical comparison of the actual versus the predicted delated images indicated that the peak signal-to-noise ratio (PSNR) was 21.8 dB ± 2.2 dB, and the structural similarity index (SSIM) was 0.45 ± 0.04. CONCLUSION: This study demonstrates the feasibility of an image-based deep-learning framework to predict delayed patterns of Amyloid PET uptake using only the early phase images. This AI-based image generation method has the potential to reduce scan time for amyloid PET and increase the patient throughput, without sacrificing diagnostic accuracy for amyloid positivity.

Preventive health therapy and behavior outcomes from a brown bag medication review for older adults.

BACKGROUND: Morbidity and mortality associated with preventable diseases can be reduced with the use of preventive health services. We evaluated the uptake and retention of preventive health behaviors and management of accidental medication poisonings in older adults after a health prevention educational component was combined with a brown bag medication review. METHODS: This study used a cohort design and was conducted in six urban senior centers and three independent senior living communities in Detroit, Michigan. Participants included 85 older adults (>60 years old) taking five or more medications with 63 participants returning follow up materials. Pharmacy personnel conducted brown bag medication reviews that were combined with a preventive health education component. Information was collected on medications, vaccinations, supplement use, and accidental medication poisoning management. Participants were given written recommendations on prescription medications and preventive health therapies to improve health and medication use. An investigator developed program satisfaction survey was administered immediately after the review. An investigator-developed follow-up preventive health implementation survey was conducted at least 3 months later to assess recommendation implementation. RESULTS: Participants' mean age was 75.9 ± 8.5 years. Fifty-six older adults had 124 recommendations in preventive health in total (1-5/participant). Eleven participants had no recommendations. Sixty-three participants (74%) returned follow-up preventive health surveys. Twenty-three percent of recommendations were already implemented with 34% planned to be done in the future. Poisoning management knowledge increased for 13 participants, reporting they would call the poison control center. The program was well received, with participants reporting high satisfaction scores (4.8 ± 0.7 out of 5). CONCLUSIONS: Brown bag medication reviews can be an effective method to promote the uptake of preventive health behaviors among older adults, but additional accidental medication poisoning management education is still needed.