A5081763257- Prostate Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neural Network Applications
- AI in cancer detection
- Functional Brain Connectivity Studies
- Transcranial Magnetic Stimulation Studies
- Medical Imaging and Analysis
- Ultrasound and Hyperthermia Applications
- Ultrasound Imaging and Elastography
- Heart Rate Variability and Autonomic Control
- Neural dynamics and brain function
- Medical Image Segmentation Techniques
- Neural and Behavioral Psychology Studies
- Prostate Cancer Treatment and Research
- Advanced Vision and Imaging
- Neuroscience and Neural Engineering
- Suicide and Self-Harm Studies
- Photoreceptor and optogenetics research
- Lanthanide and Transition Metal Complexes
- Pain Mechanisms and Treatments
- Neuroscience and Neuropharmacology Research
- Advanced MRI Techniques and Applications
- Advanced Image Processing Techniques
- Ultrasound and Cavitation Phenomena
- Food Security and Health in Diverse Populations
Stanford University
2018-2024
Stanford Medicine
2021-2024
Johns Hopkins University
2024
Magnetic resonance imaging (MRI) is an increasingly important tool for the diagnosis and treatment of prostate cancer. However, interpretation MRI suffers from high inter-observer variability across radiologists, thereby contributing to missed clinically significant cancers, overdiagnosed low-risk frequent false positives. Interpretation could be greatly improved by providing radiologists with answer key that clearly shows cancer locations on MRI. Registration histopathology images patients...
Automated methods for detecting prostate cancer and distinguishing indolent from aggressive disease on Magnetic Resonance Imaging (MRI) could assist in early diagnosis treatment planning. Existing automated of detection mostly rely ground truth labels with limited accuracy, ignore pathology characteristics observed resected tissue, cannot selectively identify (Gleason Pattern≥4) Pattern=3) cancers when they co-exist mixed lesions. In this paper, we present a radiology-pathology fusion...
Purpose While multi‐parametric magnetic resonance imaging (MRI) shows great promise in assisting with prostate cancer diagnosis and localization, subtle differences appearance between normal tissue lead to many false positive negative interpretations by radiologists. We sought automatically detect aggressive (Gleason pattern 4) indolent 3) on a per‐pixel basis MRI facilitate the targeting of during biopsy. Methods created Stanford Prostate Cancer Network (SPCNet), convolutional neural...
Purpose Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis; however, subtle differences between and confounding conditions render MRI interpretation challenging. The tissue collected from patients who undergo radical prostatectomy provides a unique opportunity correlate histopathology images of the with preoperative accurately map extent onto MRI. We seek develop an open‐source, easy‐to‐use platform align presurgical resected prostates in underwent...
The use of MRI for prostate cancer diagnosis and treatment is increasing rapidly. However, identifying the presence extent on remains challenging, leading to high variability in detection even among expert radiologists. Improvement essential reducing this maximizing clinical utility MRI. To date, such improvement has been limited by lack accurately labeled datasets. Data from patients who underwent radical prostatectomy enables spatial alignment digitized histopathology images resected with...
Abstract Mounting evidence demonstrates that the central nervous system (CNS) orchestrates glucose homeostasis by sensing and modulating peripheral metabolism. Glucose responsive neuronal populations have been identified in hypothalamus several corticolimbic regions. However, how these CNS gluco-regulatory regions modulate levels is not well understood. To better understand this process, we simultaneously measured interstitial concentrations local field potentials 3 human subjects from...
Abstract Transcranial magnetic stimulation (TMS) is increasingly used as a noninvasive technique for neuromodulation in research and clinical applications, yet its mechanisms are not well understood. Here, we present the first in-human study evaluating effects of TMS using intracranial electrocorticography (iEEG) neurosurgical patients. We evaluated safety gel-based phantom. then performed TMS-iEEG 20 participants with no adverse events. Next, brain-wide responses to single pulses...
Pain is a complex experience that remains largely unexplored in naturalistic contexts, hindering our understanding of its neurobehavioral representation ecologically valid settings. To address this, we employed multimodal, data-driven approach integrating intracranial electroencephalography, pain self-reports, and facial expression quantification to characterize the neural behavioral correlates acute twelve epilepsy patients undergoing continuous monitoring with audiovisual recordings. High...
Abstract Transcranial magnetic stimulation (TMS) is increasingly deployed in the treatment of neuropsychiatric illness, under presumption that specific cortical targets can alter ongoing neural activity and cause circuit-level changes brain function. While electrophysiological effects TMS have been extensively studied with scalp electroencephalography (EEG), this approach most useful for evaluating low-frequency at surface. As such, little known about how perturbs rhythmic among deeper...
Automated detection of aggressive prostate cancer on Magnetic Resonance Imaging (MRI) can help guide targeted biopsies and reduce unnecessary invasive biopsies. However, automated methods often have a sensitivity-specificity trade-off (high sensitivity with low specificity or vice-versa), making them unsuitable for clinical use. Here, we study the utility integrating prior information about zonal distribution cancers radiology-pathology fusion model in reliably identifying indolent MRI. Our...
Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis. It can spare men with a normal exam from undergoing invasive biopsy while making biopsies more accurate in lesions suspicious for cancer. Yet, the subtle differences between and confounding conditions, render interpretation of MRI challenging. The tissue collected patients that undergo pre-surgical radical prostatectomy provides unique opportunity correlate histopathology images entire order accurately...
Magnetic resonance imaging (MRI) is an increasingly important tool for the diagnosis and treatment of prostate cancer. However, interpretation MRI suffers from high inter-observer variability across radiologists, thereby contributing to missed clinically significant cancers, overdiagnosed low-risk frequent false positives. Interpretation could be greatly improved by providing radiologists with answer key that clearly shows cancer locations on MRI. Registration histopathology images patients...
Magnetic Resonance Imaging (MRI) is widely used for screening and staging prostate cancer. However, many cancers have subtle features which are not easily identifiable on MRI, resulting in missed diagnoses alarming variability radiologist interpretation. Machine learning models been developed an effort to improve cancer identification, but current localize using MRI-derived features, while failing consider the disease pathology characteristics observed resected tissue. In this paper, we...
The interpretation of prostate MRI suffers from low agreement across radiologists due to the subtle differences between cancer and normal tissue. Image registration addresses this issue by accurately mapping ground-truth labels surgical histopathology images onto MRI. Cancer achieved image can be used improve radiologists' training deep learning models for early detection cancer. A major limitation current automated approaches is that they require manual segmentations, which a time-consuming...