A5083346483- Radiomics and Machine Learning in Medical Imaging
- Glioma Diagnosis and Treatment
- MRI in cancer diagnosis
- Prostate Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Prostate Cancer Treatment and Research
- Medical Image Segmentation Techniques
- Medical Imaging and Analysis
- Brain Tumor Detection and Classification
- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- 3D Shape Modeling and Analysis
- Cancer, Hypoxia, and Metabolism
- Cell Image Analysis Techniques
- Lung Cancer Research Studies
- Sex and Gender in Healthcare
- Colorectal Cancer Screening and Detection
- Anatomy and Medical Technology
- Advanced Neural Network Applications
- Mathematical Biology Tumor Growth
- Digital Media Forensic Detection
- Advanced Radiotherapy Techniques
- Microtubule and mitosis dynamics
- Brain Metastases and Treatment
Medical College of Wisconsin
2021-2025
Abstract Introduction This study determines the relationship between diffusion and perfusion-based MRI signatures radio-pathomic maps of tumor pathology in a large, multi-site cohort. Methods included perfusion imaging from pre-surgical relative cerebral blood volume (rCBV) images UPenn-GBM dataset arterial spin labeling (ASL) UCSF-PDGM dataset. Diffusion fractional anisotropy (FA) estimates derived tensor (DTI) for each subject institution. A previously validated autopsy-based model was...
Digital pathology is becoming an increasingly popular area of advancement in both research and clinically. Pathologists are now able to manage interpret slides digitally, as well collaborate with external pathologists digital copies slides. Differences slide scanners include variation resolution, image contrast, optical properties, which may influence downstream processing. This study tested the hypothesis that varying would result differences computed pathomic features on prostate cancer...
Autopsy-based radio-pathomic maps of glioma pathology have shown substantial promise inidentifying areas non-enhancing tumor presence, which may be able to differentiate subsets patients that respond favorably treatments such as bevacizumab mixed efficacy evidence. We tested the hypthesis phenotypes fronts can distinguish between glioblastoma will and visually capture treatment response.
Currently, contrast-enhancing margins on T1WI are used to guide treatment of gliomas, yet tumor invasion beyond the region is a known confounding factor. Therefore, this study postmortem tissue samples aligned with clinically acquired MRIs quantify relationship between intensity values and cellularity as well develop radio-pathomic model predict using MR imaging data.This single-institution 93 collected at examination from 44 patients brain cancer. Tissue were processed, stained H&E,...
One in eight men will be affected by prostate cancer (PCa) their lives. While the current clinical standard prognostic marker for PCa is Gleason score, it subject to inter-reviewer variability. This study compares two machine learning methods discriminating between cancerous regions on digitized histology from 47 patients. Whole-slide images were annotated a GU fellowship-trained pathologist each pattern. High-resolution tiles extracted and unlabeled tissue. Patients separated into training...
Objectives Intensity variation in multi-parametric magnetic resonance imaging (MP-MRI) is a confounding factor MRI analyses. Previous studies have employed several normalization methods, but there lack of consensus on which method results the most comparable images across vendors and acquisitions. This study used MP-MRI collected from patients with confirmed prostate, brain, or breast cancer to examine common intensity methods identify best harmonizes values cofounds. Materials Multiple were...
INTRODUCTION: Glioblastoma (GBM) is the most common primary CNS malignancy, with one- and five-year survival rates of 41% 5%, respectively. Extent resection correlates increased survival, but tools to predict long-term survivors (LTS) after gross-total (GTR) are lacking. Radio-pathomic maps cell density, trained using MRI autopsy tissue, identify tumor features not readily identifiable on traditional MRI. This study evaluates these in GBM survivors. METHODS: Using UCSF-PDGM dataset, we...
Prostate cancer (PCa) is the most diagnosed non-cutaneous in men. Despite therapies such as radical prostatectomy, which considered curative, distant metastases may form, resulting biochemical recurrence (BCR). This study used radiomic features calculated from multi-parametric magnetic resonance imaging (MP-MRI) to evaluate their ability predict BCR and PCa presence. Data a total of 279 patients, 46 experienced BCR, undergoing MP-MRI prior surgery were assessed for this study. After surgery,...
has often been proposed as a quantitative imaging biomarker for diagnosis, prognosis, and treatment response assessment various tumors. None of the many software tools
Background Diffusion‐weighted imaging (DWI) is commonly used to detect prostate cancer, and a major clinical challenge differentiating aggressive from indolent disease. Purpose To compare 14 site‐specific parametric fitting implementations applied the same dataset of whole‐mount pathologically validated DWI test hypothesis that cancer differentiation varies with different algorithms. Study Type Prospective. Population Thirty‐three patients prospectively imaged prior prostatectomy. Field...
Prostate cancer (PCa) is the most diagnosed non-cutaneous in men. Despite therapies such as radical prostatectomy, which considered curative, distant metastases may form resulting biochemical recurrence (BCR). This study used radiomic features calculated from multi-parametric magnetic resonance imaging (MP-MRI) to evaluate their ability predict BCR and PCa presence. Data a total of 279 patients, 46 experienced BCR, undergoing MP-MRI prior surgery were assessed for this study. After surgery,...
This study identified a clinically significant subset of patients with glioma tumor outside contrast enhancement present at autopsy and subsequently developed method for detecting nonenhancing using radio-pathomic mapping. We tested the hypothesis that autopsy-based probability maps would be able to noninvasively identify areas infiltrative beyond traditional imaging signatures.
Registration is the process of transforming images so they are aligned in same coordinate space. In medical field, image registration often used to align multi-modal or multi-parametric organ. A uniquely challenging subset cross-modality registration—the task aligning captured with different scanning methodologies. this study, we present a transformer-based deep learning pipeline for performing cross-modality, radiology-pathology human prostate samples. While existing solutions...
The presence and extent of cribriform patterned Gleason 4 (G4) glands are associated with poor prognosis following radical prostatectomy. This study used whole-mount prostate histology multiparametric magnetic resonance imaging (MP-MRI) to evaluate diffusion differences in G4 gland morphology. Fourty-eight patients underwent MP-MRI prior prostatectomy, whom 22 had regions both fused (G4CG G4FG, respectively). After surgery, the was sliced using custom, patient-specific 3D-printed slicing...
Prostate cancer is the most commonly diagnosed in men, accounting for 27% of new male diagnoses 2022. If organ-confined, removal prostate through radical prostatectomy considered curative; however, distant metastases may occur, resulting a poor patient prognosis. This study sought to determine whether quantitative pathomic features differ patients who biochemically experience biological recurrence after surgery. Whole-mount histology from 78 was analyzed this study. In total, 614 slides were...
Abstract Background Autopsy-based radio-pathomic maps of glioma pathology have shown substantial promise inidentifying areas non-enhancing tumor presence, which may be able to differentiate subsets patients that respond favorably treatments such as bevacizumab mixed efficacy evidence. We tested the hypthesis phenotypes fronts can distinguish between glioblastoma will and visually capture treatment response. Methods T1, T1C, FLAIR, ADC images were used generate characteristics for 79...
<title>Abstract</title> Intensity variation in multi-parametric magnetic resonance imaging (MP-MRI) poses challenges for MRI analyses. Previous studies have employed several normalization methods, but a lack of consensus on which results the most comparable images exists. This study analyzed MP-MRI data from patients with prostate, brain, or breast cancer to evaluate common intensity methods best harmonize intensities across sites, vendors, and field strengths. Additionally, we calculated...
This study applied autopsy-based radio-pathomic maps to the pre-surgical PENN-GBM dataset test hypothesis that predicted tumor composition of contrast-enhancing and FLAIR-hyperintense regions identify distinct pathological features glioblastoma. We find greater within region is indicative IDH1-wildtype mutation status, show larger tumors tend have less contrast-enhancement more non-enhancing FLAIR hyperintensity. technique could be used non-invasively aggressive tumors.
This study sought to compare previously published autopsy-based radio-pathomic maps of pre-surgical cellularity and tumor probability beyond-contrast 5-ALA guided resection margins assess concordance in identifying non-enhancing between the techniques. In a series 10 cases, were able identify areas prior surgery that coincided with either or future recurrence 7 suggesting highlighted on these indicate active, progressive tumor.
We tested the hypothesis that autopsy-based radio-pathomic maps of glioblastoma pathology reveal distinct phenotypes (hypercellular, hypocellular, hybrid, and well-circumscribed fronts) differ in patient survival bevacizumab treatment response. Patients with tumor invasion beyond contrast showed worse outcomes compared to patients tumors. Additionally, hypocellular components non-enhancing front selectively benefit from treatment, an observable reduction volume over course use.
Abstract INTRODUCTION Sex-determining region Y-box 2 (SOX2) has recently been used as a marker for pluripotency to identify cellular glioblastoma invasion pathologically. This can be areas of tumor consisting sparse individual cells, likely highlighting the furthest margin invasion. study aligned large format SOX2 stained tissue samples conventional MRI determine demographic factors that impact presence positive outside T1 contrast-enhanced margin. METHODS The cohort this consisted 36...
Abstract BACKGROUND Glioblastoma (GBM) remains the most devastating central nervous system malignancy with poor overall survival (OS), even gross total resection (GTR) and chemoradiation. Identifying factors associated long-term (LTS) in GBM patients is challenging but crucial for improving prognostic models. This study compares an internal dataset of top 10% survivors (n=14) against a combined external cohort 528 who underwent GTR. METHODS We used previously published machine...