A5085223970- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Bioinformatics and Genomic Networks
- Gene Regulatory Network Analysis
- Prostate Cancer Diagnosis and Treatment
- Cancer Genomics and Diagnostics
- Reproductive Biology and Fertility
- Gene expression and cancer classification
- Digital Imaging for Blood Diseases
- Assisted Reproductive Technology and Twin Pregnancy
- Ubiquitin and proteasome pathways
- Reproductive Health and Technologies
- CRISPR and Genetic Engineering
- Brain Tumor Detection and Classification
- COVID-19 diagnosis using AI
- RNA Research and Splicing
- 14-3-3 protein interactions
- Genetic factors in colorectal cancer
- Computational Drug Discovery Methods
- Plant tissue culture and regeneration
- ECG Monitoring and Analysis
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare and Education
- Molecular Biology Techniques and Applications
- MRI in cancer diagnosis
City University of New York
2024
New York City College of Technology
2023-2024
The Graduate Center, CUNY
2024
Memorial Sloan Kettering Cancer Center
2020-2022
Cornell University
2017-2022
Lander Institute
2018-2022
Kettering University
2022
Weill Cornell Medicine
2017-2021
Institute for Research in Fundamental Sciences
2015-2018
University of Tehran
2013-2015
Visual morphology assessment is routinely used for evaluating of embryo quality and selecting human blastocysts transfer after in vitro fertilization (IVF). However, the produces different results between embryologists as a result, success rate IVF remains low. To overcome uncertainties quality, multiple embryos are often implanted resulting undesired pregnancies complications. Unlike other imaging fields, embryology have not yet leveraged artificial intelligence (AI) unbiased, automated...
Abstract Breast cancer remains the most common type of and leading cause cancer-induced mortality among women with 2.4 million new cases diagnosed 523,000 deaths per year. Historically, a diagnosis has been initially performed using clinical screening followed by histopathological analysis. Automated classification cancers images is chciteallenging task accurate detection tumor sub-types. This process could be facilitated machine learning approaches, which may more reliable economical...
Background A definitive diagnosis of prostate cancer requires a biopsy to obtain tissue for pathologic analysis, but this is an invasive procedure and associated with complications. Purpose To develop artificial intelligence (AI)‐based model (named AI‐biopsy) the early using magnetic resonance (MR) images labeled histopathology information. Study Type Retrospective. Population Magnetic imaging (MRI) data sets from 400 patients suspected histological (228 acquired in‐house 172 external...
Breast cancer remains the most common type of and leading cause cancer-induced mortality among women with 2.4 million new cases diagnosed 523,000 deaths per year. Historically, a diagnosis has been initially performed using clinical screening followed by histopathological analysis. Automated classification cancers images is challenging task accurate detection tumor sub-types. This process could be facilitated machine learning approaches, which may more reliable economical compared to...
Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through deep learning-based model. When applied cohort 1,010 breast (Training set: n = 858, Test 152) from The Cancer Genome Atlas where 485 have high status, our model accurately classified achieving an area under the curve 0.822...
Knowledge of interaction types in biological networks is important for understanding the functional organization cell. Currently information-based approaches are widely used inferring gene regulatory interactions from genomics data, such as expression profiles; however, these do not provide evidence about regulation type (positive or negative sign) interaction.This paper describes a novel algorithm, "Signing Regulatory Networks" (SIREN), which can infer known network (GRN) given...
Abstract Morphology assessment has become the standard method for evaluation of embryo quality and selecting human blastocysts transfer in vitro fertilization (IVF). This process is highly subjective some embryos thus prone to bias. As a result, morphological results may vary extensively between embryologists cases fail accurately predict implantation live birth potential. Here we postulated that an artificial intelligence (AI) approach trained on thousands can reliably without intervention....
Background Artificial intelligence (AI) applications for cancer imaging conceptually begin with automated tumor detection, which can provide the foundation downstream AI tasks. However, supervised training requires many image annotations, and performing dedicated post hoc labeling is burdensome costly. Purpose To investigate whether clinically generated annotations be data mined from picture archiving communication system (PACS), automatically curated, used semisupervised of a brain MRI...
Abstract Extracapsular extension (ECE) is detected in approximately one-third of newly diagnosed prostate cancer (PCa) cases at stage T3a or higher and associated with increased rates positive surgical margins early biochemical recurrence following radical prostatectomy (RP). This study presents the development AutoRadAI, an end-to-end, user-friendly artificial intelligence (AI) pipeline designed for identification ECE PCa through analysis multiparametric MRI (mpMRI) fused histopathology....
Abstract This paper demonstrates that simplified Convolutional Neural Network (CNN) models can outperform traditional complex architectures, such as VGG-16, in the analysis of radiological images, particularly datasets with fewer samples. We introduce two adopted CNN LightCnnRad and DepthNet, designed to optimize computational efficiency while maintaining high performance. These were applied nine image datasets, both public in-house, including MRI, CT, X-ray, Ultrasound, evaluate their...
We described an integrated analysis of gene expression data including tissue-specific metabolic modeling and co-expression networks to identify new cancer biomarkers.
Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision help reduce human error. In this study, we utilize various computational methods based on convolutional neural networks (CNN) build a stand-alone pipeline effectively classify different histopathology images across types cancer. particular, demonstrate the utility our discriminate between two subtypes lung cancer, four...
Essential proteins are indispensable units for living organisms. Removing those leads to disruption of protein complexes and causing lethality. Recently, theoretical methods have been presented detect essential in interaction network. In these methods, an is predicted as a high-degree vertex However, data usually incomplete cannot high-connection due deficiency. Then, it critical design informative networks from other biological sources. this paper, we defined minimal set disrupt the maximum...