ABSTRACT
This study introduces a novel image reconstruction technique based on a diffusion model that is conditioned on the native data domain. Our method is applied to multi-coil MRI and quantitative MRI (qMRI) reconstruction, leveraging the domain-conditioned diffusion model within the frequency and parameter domains. The prior MRI physics are used as embeddings in the diffusion model, enforcing data consistency to guide the training and sampling process, characterizing MRI k-space encoding in MRI reconstruction, and leveraging MR signal modeling for qMRI reconstruction. Furthermore, a gradient descent optimization is incorporated into the diffusion steps, enhancing feature learning and improving denoising. The proposed method demonstrates a significant promise, particularly for reconstructing images at high acceleration factors. Notably, it maintains great reconstruction accuracy for static and quantitative MRI reconstruction across diverse anatomical structures. Beyond its immediate applications, this method provides potential generalization capability, making it adaptable to inverse problems across various domains.
ABSTRACT
PURPOSE: There are limited data available on the real-world patterns of molecular testing in men with advanced prostate cancer. We thus sought to evaluate next-generation sequencing (NGS) testing in the United States, focused on single versus serial NGS testing, the different disease states of testing (hormone-sensitive v castration-resistant, metastatic vs nonmetastatic), tissue versus plasma circulating tumor DNA (ctDNA) assays, and how often actionable data were found on each NGS test. METHODS: The Prostate Cancer Precision Medicine Multi-Institutional Collaborative Effort clinical-genomic database was used for this retrospective analysis, including 1,597 patients across 15 institutions. Actionable NGS data were defined as including somatic alterations in homologous recombination repair genes, mismatch repair deficiency, microsatellite instability (MSI-high), or a high tumor mutational burden ≥10 mut/MB. RESULTS: Serial NGS testing (two or more NGS tests with specimens collected more than 60 days apart) was performed in 9% (n = 144) of patients with a median of 182 days in between test results. For the second NGS test and beyond, 82.1% (225 of 274) of tests were from ctDNA assays and 76.1% (217 of 285) were collected in the metastatic castration-resistant setting. New actionable data were found on 11.1% (16 of 144) of second NGS tests, with 3.5% (5 of 144) of tests detecting a new BRCA2 alteration or MSI-high. A targeted therapy (poly (ADP-ribose) polymerase inhibitor or immunotherapy) was given after an actionable result on the second NGS test in 31.3% (5 of 16) of patients. CONCLUSION: Repeat somatic NGS testing in men with prostate cancer is infrequently performed in practice and can identify new actionable alterations not present with initial testing, suggesting the utility of repeat molecular profiling with tissue or blood of men with metastatic castration-resistant prostate cancer to guide therapy choices.
Subject(s)
Antineoplastic Agents , Circulating Tumor DNA , Prostatic Neoplasms , Male , Humans , Retrospective Studies , Prostatic Neoplasms/diagnosis , Prostatic Neoplasms/genetics , Prostatic Neoplasms/drug therapy , Circulating Tumor DNA/genetics , Antineoplastic Agents/therapeutic use , Poly(ADP-ribose) Polymerase Inhibitors/therapeutic use , High-Throughput Nucleotide Sequencing/methodsABSTRACT
PURPOSE: This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust. METHODS: Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitative T 1 $$ {\mathrm{T}}_1 $$ mapping as an example, the proposed method was applied to the brain, knee and phantom data. RESULTS: The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping. CONCLUSION: This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.
Subject(s)
Algorithms , Brain , Deep Learning , Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Phantoms, Imaging , Magnetic Resonance Imaging/methods , Humans , Image Processing, Computer-Assisted/methods , Brain/diagnostic imaging , Knee/diagnostic imaging , Artifacts , Supervised Machine LearningABSTRACT
OBJECTIVE: Endovascular aneurysm repair (EVAR) has been used worldwide to treat abdominal aortic aneurysms (AAAs). Outcomes after EVAR within and outside the instruction for use (IFU) remain controversial. We analyzed long-term outcomes of EVAR within-the-IFU compared with that outside-the-IFU and baseline clinical/anatomical characteristics that influence outcomes of EVAR. METHODS: The study included 546 patients who underwent EVAR for infrarenal AAA from 1997 to 2021 at 2 Korean medical centers. The primary endpoint was graft-related adverse events (GRAEs), including type 1 or 3 endoleak, reintervention (included open conversion), aneurysm sac enlargement, aneurysm-related mortality (ARM), rupture, stent-graft migration, and stent thrombotic occlusion. RESULTS: The patients who underwent EVAR outside the IFU were 287 (52.6%). A neck angle of >60° was most common outside the IFU criteria (n=146, 50.9%). This study revealed that patients outside the IFU had a higher rate of GRAEs compared with patients within the IFU (hazard ratio [HR]: 1.879; 95% confidence interval [CI]: 1.045-2.386). A neck angle of >60° was a significant risk factor for GRAEs (adjusted HR: 2.229; 95% CI: 1.418-3.503), type 1 or 3 endoleak (adjusted HR: 2.640; 95% CI: 1.343-5.189), and reintervention (adjusted HR: 1.891; 95% CI: 1.055-3.388). CONCLUSIONS: Our study revealed EVAR with outside the IFU was associated with increased GRAEs, mainly attributed to endoleak and ARM, compared with EVAR with within the IFU. In addition, severe neck angulation was an independent risk factor for GRAEs, type 1 or 3 endoleak, and reintervention. CLINICAL IMPACT: Our study revealed endovascular aneurysm repair (EVAR) with outside-the-instruction for use (IFU) was associated with increased graft-related adverse events (GRAEs) compared with EVAR with within-the-IFU. In the low-risk population, the incidence of GRAEs and Aneurysm related mortality were higher in the outside-the-IFU group rather than within-the-IFU group. In addition, severe neck angulation was an independent risk factor for GRAEs, type 1 or 3 endoleak and reintervention.
ABSTRACT
Small-cell carcinomas (SCCs) of the genitourinary (GU) tract are rare malignancies with high metastatic potential. The most common primary sites are the bladder and prostate, but case reports of primary SCC of the kidney, ureter, and urethra also exist. The majority of patients present with gross hematuria, irritative or obstructive urinary symptoms, and symptoms of locoregionally advanced or metastatic disease at initial presentation. SCC of the bladder presents with nodal or metastatic involvement in the majority of cases and requires the use of platinum-based chemotherapy in combination with surgery and/or radiation. SCC of the prostate is most commonly seen in the metastatic castrate-resistant setting, and aggressive variant disease presents with a greater propensity for visceral metastases, osteolytic lesions, and relatively low serum prostate-specific antigen for volume of disease burden. Multiple retrospective and prospective randomized studies support the use of a multimodal approach combining platinum-based systemic therapy regimens with radiation and/or surgery for localized disease. This evidence-based strategy is reflected in multiple consensus guidelines. Emerging data suggest that small-cell bladder and prostate cancers transdifferentiate from a common progenitor of conventional urothelial bladder carcinoma and prostatic acinar adenocarcinoma, respectively. Areas of active basic research include efforts to identify the key genetic and epigenetic drivers involved in the emergence of small cell cancers to exploit them for novel therapies. Here, we review these efforts, discuss diagnosis and currently supported management strategies, and summarize ongoing clinical trials evaluating novel therapies to treat this rare, aggressive GU cancer.