For a growing population of low- and intermediate-risk prostate cancer (CaP) patients, active surveillance may be biologically or psychologically undesirable. Yet the short- and long-term complications and co-morbidities associated with radical whole-organ therapies (e.g. intensity modulated radiation therapy) are still associated with a risk of treatment-related morbidity. With radical whole gland therapies, in certain patients who are more sensitive to radiation treatment, high dosage spots in the rectum and in the bladder can lead to complications including chronic rectal bleeding, diarrhea, and urinary symptoms such as cystitis. Laser induced interstitial thermal therapy (LITT) is a novel form of controlled, targeted thermal ablation that may offer measurable advantages over other ablative therapies for focal prostate therapy. Because LITT is MRI compatible, it enables an imaging advantage over other surgical or ablation techniques that utilize transrectal ultrasound to target and monitor treatment. However successful adoption of focal therapy for the treatment of CaP will hinge on several critical issues: 1) Can we accurately identify index lesions and cancers within the prostate? 2) Appropriate follow-up of patients treated with focal therapy and 3) How to detect recurrent/persistent disease? The introduction of multi-parametric (MP) MRI (T2w, dynamic contrast enhanced (DCE), Diffusion (DWI)) has allowed for (1) improved detection sensitivity and specificity for CaP localization, and (2) evaluating treatment response in the prostate. However there exists a need for (1) novel computational image analysis tools to quantitatively integrate MP-MRI parameters for improved CaP classification in vivo and (2) non-rigid registration tools for enabling targeted therapy and evaluation of post-treatment changes. In this study we will employ sophisticated computer vision, image analysis, computer assisted diagnostic (CAD) and deformable registration tools in conjunction with MP-MRI to be used in conjunction with a small clinical trial involving 40 patients with documented CaP for (a) automated delineation of tumor regions on pre-treatment MP-MRI to thereby identify the specific regions for ablation via LITT, and (b) identify and delineate locally recurrent disease within and outside the ablation zone for post-LITT evaluation. Regions identified via CAD on pre-LITT MRI will be targeted for therapy, while on post-LITT MP-MRI, regions identified as being suspicious for CaP recurrence (on account of large changes in MR imaging markers) will be evaluated via needle core biopsy. The tools developed in this project will be integrated into a practical and feasible treatment paradigm for focal treatment of low-risk localized CaP which will allow patients to avoid the complications associated with radical whole-gland therapy. This inter-disciplinary, translational project combines engineering expertise in terms of CAD on MP-MRI, multimodal image registration and machine learning and clinical expertise in interventional radiology, prostate MRI, and MRI guided focal therapy.

Public Health Relevance

In this study we will leverage sophisticated computer vision, image analysis, computer assisted diagnostic and deformable registration tools in conjunction with multi-parametric (MP) MRI in prostate cancer (CaP) patients for (a) automated delineation of tumor regions on pre-treatment MP-MRI and thereby identify the specific regions for ablation via laser induced interstitial thermal therapy (LITT), and (b) identify and delineate locally recurrent disease within and outside the ablation zone for post-LITT evaluation. The tools developed in this project will be integrated into a feasible treatment paradigm for focal treatment of low-risk localized CaP which will allow patients to avoid the complications associated with radical whole-gland therapy.

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Exploratory/Developmental Grants (R21)
Project #
5R21CA167811-03
Application #
8544441
Study Section
Special Emphasis Panel (ZRG1-SBIB-W (56))
Program Officer
Farahani, Keyvan
Project Start
2012-09-12
Project End
2014-08-31
Budget Start
2013-09-01
Budget End
2014-08-31
Support Year
3
Fiscal Year
2013
Total Cost
$241,056
Indirect Cost
$74,281
Name
Case Western Reserve University
Department
Biomedical Engineering
Type
Schools of Engineering
DUNS #
077758407
City
Cleveland
State
OH
Country
United States
Zip Code
44106
Rusu, Mirabela; Rajiah, Prabhakar; Gilkeson, Robert et al. (2017) Co-registration of pre-operative CT with ex vivo surgically excised ground glass nodules to define spatial extent of invasive adenocarcinoma on in vivo imaging: a proof-of-concept study. Eur Radiol 27:4209-4217
Kim, Joseph J; Bennett, Neal K; Devita, Mitchel S et al. (2017) Optical High Content Nanoscopy of Epigenetic Marks Decodes Phenotypic Divergence in Stem Cells. Sci Rep 7:39406
Cruz-Roa, Angel; Gilmore, Hannah; Basavanhally, Ajay et al. (2017) Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent. Sci Rep 7:46450
Rusu, Mirabela; Purysko, Andrei S; Verma, Sadhna et al. (2017) Computational imaging reveals shape differences between normal and malignant prostates on MRI. Sci Rep 7:41261
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
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
Janowczyk, Andrew; Basavanhally, Ajay; Madabhushi, Anant (2017) Stain Normalization using Sparse AutoEncoders (StaNoSA): Application to digital pathology. Comput Med Imaging Graph 57:50-61
Viswanath, Satish E; Tiwari, Pallavi; Lee, George et al. (2017) Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases. BMC Med Imaging 17:2
Lu, Cheng; Xu, Hongming; Xu, Jun et al. (2016) Multi-Pass Adaptive Voting for Nuclei Detection in Histopathological Images. Sci Rep 6:33985
Leo, Patrick; Lee, George; Shih, Natalie N C et al. (2016) Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images. J Med Imaging (Bellingham) 3:047502

Showing the most recent 10 out of 57 publications