3D model of Tumor Habitat

Shape Changes between treatment effects and tumor recurrence

Radiation necrosis vs. tumor recurrence using radiomics on routine MRI

Survival prediction in Glioblastoma patients using radiomics analysis

Studying structural deformations in Glioblastoma to predict patient survival

Radiogenomic analysis of brain tumors

About Us

BrIC lab focuses on developing neuroinformatics techniques using machine learning, statistical modeling, and pattern recognition for applications in brain tumors and neurological disorders. One of the primary focuses of BrIC lab is to identify computerized image-based (also known as radiomic) phenotypes, and their associations with genomics (radiogenomics) and histo-pathology (radio-pathomics) for disease characterization.

Our vision is to conduct interdisciplinary and translational research in personalized diagnostics towards early diagnosis, prognosis, and response to treatment for  different neurological conditions including brain tumors. Through our clinical collaborations and research efforts, we aim to build technologies with a potential for near-term clinical impact in customizing personalized treatments and improving patient survival.

Our lab is located at Case Western Reserve University,  within School of Medicine and Case Comprehensive Cancer Center, and is affiliated with the Center for Computational Imaging and Personalized Diagnostics


Please check the research page for specific projects and research focus of our group.

April 03, 2020

Congrats Sukanya for successfully defending her MS thesis defense

Congrats to Sukanya Iyer, MS student at BrIC lab, for successfully defending her thesis defense. She did an outstanding job. 

March 13, 2020

Work on quality assessment won accolades at SPIE

Our demo on quality assessment tools for medical imaging: MRQy and HistoQC won the Live Demonstration Certificate of Merit at the SPIE 2020 Medical Imaging Conference. The work was in collaboration with InVent lab led by Dr. Viswanath at CCIPD. 

February 11, 2020

BrIC lab paper awarded the "Most Cited Paper Award 2017"

BrIC lab paper entitled "Radiomic features from the peritumoral brain parenchyma on treatment-naïve multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: Preliminary findings", was published in European Radiology in 2017, and has received 57 citations in the two years following publication (2018-2019). It was, therefore, awarded a "Most Cited Paper Award 2017" for receiving the second highest number of citations.

December 20, 2019

BrIC lab awarded the prestigious V Foundation Award

BrIC lab in collaboration with Cleveland Clinic was awarded a 3-year V Foundation Translational Award for their work on capturing tumor heterogeneity on post-treatment MRIs

December 20, 2019

Niha Beig to serve term as Trainee Editorial Board member for journal Radiology: Artificial Intelligence

Niha has been selected for a one-year term as a Trainee Editorial Board member for the journal Radiology: Artificial Intelligence. Niha will learn the intricacies of scientific journalism, contribute to content on the applications of artificial intelligence in radiology and help continue to build the future of the journal. 

October 15, 2019

Three BrIC lab papers have been accepted at SPIE

BrIC lab's paper on identifying gender-specific differences in ASD versus controls using deep learning features combined with hand-crafted features, has been accpeted for publication at SPIE 2020.

Ashish's paper has also been accepted, entitled "Quality assessment of MRI using a dense neural network model".

Ramon's paper entitled "lesson-habitat' radiomics to distinguish radiation necrosis from tumor recurrence on post-treatment MRI in metastatic brain tumor," has also been accepted for publication.

October 13, 2019

Dr. Tiwari gave 3 keynote talks at MICCAI 2019 workshops

Dr. Tiwari gave keynotes talks at 3 workshops at MICCAI this year. On 13th October, she talked at AI in neuro-oncology workshop. On the 17th, she presented BrIC lab's work at the Medical Image Learning with Less Labels and Imperfect Data Workshop and BrainLes workshop

Please reload

Recent News