A5089881940- Cancer Immunotherapy and Biomarkers
- Immunotherapy and Immune Responses
- T-cell and B-cell Immunology
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Colorectal Cancer Screening and Detection
- Advanced Radiotherapy Techniques
- Cell Image Analysis Techniques
- Image Retrieval and Classification Techniques
- Advanced Neuroimaging Techniques and Applications
- Advanced Vision and Imaging
- Cerebrospinal fluid and hydrocephalus
- Advanced X-ray and CT Imaging
- Generative Adversarial Networks and Image Synthesis
- CAR-T cell therapy research
- Data Visualization and Analytics
- Computer Graphics and Visualization Techniques
- Functional Brain Connectivity Studies
- Molecular Biology Techniques and Applications
- MRI in cancer diagnosis
- 3D Shape Modeling and Analysis
- Advanced Image and Video Retrieval Techniques
- Esophageal Cancer Research and Treatment
Memorial Sloan Kettering Cancer Center
2018-2024
Allama Iqbal Medical College
2024
National University of Sciences and Technology
2022
Stony Brook University
2016-2019
Loyola University Medical Center
2019
The University of Texas at Austin
2010
The glymphatic system (GS) hypothesis states that advective driven cerebrospinal fluid (CSF) influx from the perivascular spaces into interstitial space rapidly transport solutes and clear waste brain. However, presence of advection in neuropil is contested are claimed to be transported by diffusion only. To address this controversy, we implemented a regularized version optimal mass (rOMT) problem, wherein advection/diffusion equation only priori assumption required. rOMT analysis with...
This work presents a novel framework for spherical mesh parameterization. An efficient angle-preserving parameterization algorithm is introduced, which based on dynamic Yamabe flow and the conformal welding method with solid theoretic foundation. area-preserving also discussed, discrete optimal mass transport theory. Furthermore, algorithm, polar decomposition method, balancing angle distortion area presented. The algorithms are tested 3D geometric data experiments demonstrate efficiency...
Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual (VC), are critical for diagnosing ultimately removing polyps (precursors of colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed (from CT scans) if found, the OC procedure performed physically traverse via endoscope remove these polyps. In this paper, we present deep learning framework, Extended Directional CycleGAN, lossy unpaired image-to-image translation between augment video...
Abstract We introduce a classification of breast tumors into seven classes which are more clearly defined by interpretable mRNA signatures along the PAM50 gene set than five traditional intrinsic subtypes. Each subtype is partially concordant with one our classes, and two additional correspond to division Luminal B Normal subtypes expression Her2 group. Our class shows similarity myoepithelial mammary cell phenotype, including TP63 (specificity: 80.8% sensitivity: 82.8%), exhibits best...
In the clinic, resected tissue samples are stained with Hematoxylin-and-Eosin (H&E) and/or Immunhistochemistry (IHC) stains and presented to pathologists on glass slides or as digital scans for diagnosis assessment of disease progression. Cell-level quantification, e.g. in IHC protein expression scoring, can be extremely inefficient subjective. We present DeepLIIF (https://deepliif.org), a first free online platform efficient reproducible scoring. outperforms current state-of-the-art...
Objective.To propose a novel moment-based loss function for predicting 3D dose distribution the challenging conventional lung intensity modulated radiation therapy plans. The is convex and differentiable can easily incorporate clinical volume histogram (DVH) domain knowledge in any deep learning (DL) framework without computational overhead.Approach.We used large dataset of 360 (240 training, 50 validation 70 testing) patients with 2 Gy × 30 fractions to train DL model using clinically...
We present a computer-aided detection algorithm for polyps in optical colonoscopy images. Polyps are the precursors to colon cancer. In US alone, 14 million colonoscopies performed every year, mostly screen polyps. Optical has been shown have an approximately 25% polyp miss rate due convoluted folds and bends colon. this work, we automatic detect these use machine learning infer depth map given image then detailed pre-built profile delineate boundaries of image. achieved best recall 84.0%...
Background and purposeMinimizing acute esophagitis (AE) in locally advanced non-small cell lung cancer (LA-NSCLC) is critical given the proximity between esophagus tumor. In this pilot study, we developed a clinical platform for quantification of accumulated doses volumetric changes via weekly Magnetic Resonance Imaging (MRI) adaptive radiotherapy (RT).Material methodsEleven patients treated intensity-modulated RT to 60–70 Gy 2–3 Gy-fractions with concurrent chemotherapy underwent MRIs....
In current clinical practice, noisy and artifact-ridden weekly cone-beam computed tomography (CBCT) images are only used for patient setup during radiotherapy. Treatment planning is done once at the beginning of treatment using high-quality CT (pCT) manual contours organs-at-risk (OARs) structures. If quality CBCT can be improved while simultaneously segmenting OAR structures, this provide critical information adapting radiotherapy mid-treatment as well deriving biomarkers response. Using a...
Accurate segmentation of abdominal organs from medical images is an essential part surgical planning and computer-aided disease diagnosis. Many existing algorithms are specialized for the healthy organs. Cystic pancreas especially challenging due to its low contrast boundaries, variability in shape, location stage pancreatic cancer. We present a semi-automatic algorithm pancreata with cysts. In automatic approaches which amenable atlas/statistical shape approaches, cysts can have even higher...
We present a method for registration and visualization of corresponding supine prone virtual colonoscopy scans based on eigenfunction analysis fold modeling. In colonoscopy, CT are acquired with the patient in two positions, their is desirable so that physicians can corroborate findings between scans. Our algorithm performs this efficiently through use Fiedler vector representation (the second Laplace-Beltrami operator). This employed to first perform global colon positions. The then locally...
Significance A major problem in data science is representation of so that the variables driving key functions can be uncovered and explored. Correlation analysis widely used to simplify networks feature by reducing redundancies, but makes limited use network topology, relying on comparison direct neighbor variables. The proposed method incorporates relational or functional profiles neighboring along multiple common neighbors, which are fitted with Gaussian mixture models compared using a...
Automated segmentation of the esophagus is critical in image-guided/adaptive radiotherapy lung cancer to minimize radiation-induced toxicities such as acute esophagitis. We have developed a semantic physics-based data augmentation method for segmenting both planning CT (pCT) and cone beam (CBCT) using 3D convolutional neural networks. One hundred ninety-one cases with their pCTs CBCTs from four independent datasets were used train modified U-Net architecture multi-objective loss function...
Abstract As predictive biomarkers of response to immune checkpoint inhibitors (ICIs) remain a major unmet clinical need in patients with urothelial carcinoma (UC), we sought identify tissue‐based benefit ICIs using multiplex immunofluorescence and integrate these findings previously identified peripheral blood response. Fifty‐five pretreatment 12 paired on‐treatment UC specimens were from treated nivolumab or without ipilimumab. Whole tissue sections stained 12‐plex mIF panel, including CD8,...