Medical informatics from the macro- to micro-scale is increasingly available for a range of detection/diagnosis/theragnostic applications tailored to each patient's history and current condition. Prostatic adenocarcinoma (CAP) is the second most common malignancy among men with an estimated 220,000 new cases in the USA in 2008. With the advent of multi-parametric high resolution (3 Tesla (T)) prostate MRI, providing anatomic, biochemical, and physiologic information, it has become increasingly important to identify the potential value of this information in pre-operative or pre-therapeutic CAP screening. However, in vivo prostate MRI lacks the resolution and ground truth diagnostic accuracy histopathological examination of biopsy cores provides. A first step toward getting prostate MRI for CAP into the clinic would be validating the information provided from MR at the cellular level. However, validating MRI against histological ground truth currently lacks the means to link the information provided by radiological imaging and pathology seamlessly. This is primarily due to a lack of interoperability between informatics representations and tools. One missing element, for instance, is robust and accurate image registration tools to align the multi-modal volumetric data sets. The overarching goal of this collaborative project between the University of Pennsylvania, Rutgers University, and Siemens Corporate Research is to develop and evaluate multi-modal image analysis and machine learning techniques within a software framework that will enable efficient analysis, correlation, and interpretation of multi-functional, multi-resolution patient data. The availability of these multi-modal, multi- scale analysis tools will enable alignment of radiology and pathological data which in turn will (a) enable building and validation of supervised computerized decision support systems for detection and grading of CAP from radiology and pathology data and (b) building meta-classifiers for CAP by integrating multi- modal, multi-scale disease signatures. Such a set of prostate-specific informatics tools promises clinical benefits including improved patient prognoses, more accurate disease diagnoses, and therapeutic recommendations. More generally, the tools developed as part of this project will also enable radiologic/pathologic studies in other disease entities. The specific goals of this project are 1) to develop cross-platform, open source, grid-enabled annotation, image analysis and image registration tools that will enable cross modality validation of radiology data (multi-functional 3 T prostate MRI) with expert histopathological annotation of prostatectomy specimens and provide independent computer-aided predictions of cancer extent and grade on radiology and histopathology, 2) curate an open source caGRID- connected database of prostate MRI and histopathological specimens that will enable development of quantitative signatures for detection and grading of CAP across multiple scales and imaging modalities.

Public Health Relevance

The goal of this project is to develop a software tool kit (based on the XIP application from Siemens corporation) that will allow scientists to study prostate cancer by combining data from multiple imaging modalities (radiology and pathology) with molecular methodologies (including proteins, genes, epigenetic data). The results of this fused and combined data sets will allow scientists to create a more robust system based view of prostate cancer which allow prediction of diagnosis, follow outcomes of therapeutic treatment and facilitate discovery of new treatment options

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Research Project (R01)
Project #
5R01CA136535-04
Application #
8305155
Study Section
Special Emphasis Panel (ZRG1-SBIB-S (50))
Program Officer
Tandon, Pushpa
Project Start
2009-07-17
Project End
2014-06-30
Budget Start
2012-07-01
Budget End
2013-06-30
Support Year
4
Fiscal Year
2012
Total Cost
$619,383
Indirect Cost
$59,370
Name
University of Pennsylvania
Department
Pathology
Type
Schools of Medicine
DUNS #
042250712
City
Philadelphia
State
PA
Country
United States
Zip Code
19104
Ginsburg, Shoshana B; Algohary, Ahmad; Pahwa, Shivani et al. (2017) Radiomic features for prostate cancer detection on MRI differ between the transition and peripheral zones: Preliminary findings from a multi-institutional study. J Magn Reson Imaging 46:184-193
Prasanna, Prateek; Patel, Jay; Partovi, Sasan et al. (2017) 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. Eur Radiol 27:4188-4197
Lee, George; Veltri, Robert W; Zhu, Guangjing et al. (2017) Nuclear Shape and Architecture in Benign Fields Predict Biochemical Recurrence in Prostate Cancer Patients Following Radical Prostatectomy: Preliminary Findings. Eur Urol Focus 3:457-466
Wan, Tao; Bloch, B Nicolas; Plecha, Donna et al. (2016) A Radio-genomics Approach for Identifying High Risk Estrogen Receptor-positive Breast Cancers on DCE-MRI: Preliminary Results in Predicting OncotypeDX Risk Scores. Sci Rep 6:21394
Madabhushi, Anant; Lee, George (2016) Image analysis and machine learning in digital pathology: Challenges and opportunities. Med Image Anal 33:170-175
Litjens, Geert J S; Elliott, Robin; Shih, Natalie N C et al. (2016) Computer-extracted Features Can Distinguish Noncancerous Confounding Disease from Prostatic Adenocarcinoma at Multiparametric MR Imaging. Radiology 278:135-45
Xu, Jun; Xiang, Lei; Liu, Qingshan et al. (2016) Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images. IEEE Trans Med Imaging 35:119-30
Tiwari, P; Prasanna, P; Wolansky, L et al. (2016) Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study. AJNR Am J Neuroradiol 37:2231-2236
Ginsburg, Shoshana B; Taimen, Pekka; Merisaari, Harri et al. (2016) Patient-specific pharmacokinetic parameter estimation on dynamic contrast-enhanced MRI of prostate: Preliminary evaluation of a novel AIF-free estimation method. J Magn Reson Imaging 44:1405-1414
Penzias, Gregory; Janowczyk, Andrew; Singanamalli, Asha et al. (2016) AutoStitcher: An Automated Program for Efficient and Robust Reconstruction of Digitized Whole Histological Sections from Tissue Fragments. Sci Rep 6:29906

Showing the most recent 10 out of 93 publications