635 Hits in 6.5 sec

Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology

Deepa Darshini Gunashekar, Lars Bielak, Leonard Hägele, Benedict Oerther, Matthias Benndorf, Anca-L. Grosu, Thomas Brox, Constantinos Zamboglou, Michael Bock
2022 Radiation Oncology  
The CNN uses a U-Net architecture which was trained on multi-parametric MRI data from 122 patients to automatically segment the prostate gland and prostate tumor lesions.  ...  The CNN achieved a mean Dice Sorensen Coefficient 0.62 and 0.31 for the prostate gland and the tumor lesions -with the radiologist drawn ground truth and 0.32 with whole-mount histology ground truth for  ...  ., Novi, MI, United States) in creation of new software and data processing techniques used in major parts of this work is gratefully acknowledged.  ... 
doi:10.1186/s13014-022-02035-0 pmid:35366918 pmcid:PMC8976981 fatcat:gfjy2z7r7bfvxd45pwedzj7fii

Machine learning applications in prostate cancer magnetic resonance imaging

Renato Cuocolo, Maria Brunella Cipullo, Arnaldo Stanzione, Lorenzo Ugga, Valeria Romeo, Leonardo Radice, Arturo Brunetti, Massimo Imbriaco
2019 European Radiology Experimental  
With this review, we aimed to provide a synopsis of recently proposed applications of machine learning (ML) in radiology focusing on prostate magnetic resonance imaging (MRI).  ...  The following potential clinical applications in different settings are outlined, many of them based only on MRI-unenhanced sequences: gland segmentation; assessment of lesion aggressiveness to distinguish  ...  [54] trained a ML algorithm with paired CT and MRI datasets in order to generate synthetic CT images to be used for patient radiation therapy setup and dose calculation.  ... 
doi:10.1186/s41747-019-0109-2 pmid:31392526 pmcid:PMC6686027 fatcat:7x3egaxnjzcdpngl5vogww27gi

Spectral embedding-based registration (SERg) for multimodal fusion of prostate histology and MRI

Eileen Hwuang, Mirabela Rusu, Sudha Karthigeyan, Shannon C. Agner, Rachel Sparks, Natalie Shih, John E. Tomaszewski, Mark Rosen, Michael Feldman, Anant Madabhushi, Sebastien Ourselin, Martin A. Styner
2014 Medical Imaging 2014: Image Processing  
Nine pairs of synthetic T1-weighted to T2-weighted brain MRI were registered under the following conditions: five levels of noise (0%, 1%, 3%, 5%, and 7%) and two levels of bias field (20% and 40%) each  ...  We also spatially align twenty-six ex vivo histology sections and in vivo prostate MRI in order to map the spatial extent of prostate cancer onto corresponding radiologic imaging.  ...  Summary of experimental protocol for synthetic T1-w and T2-w BrainWeb and clinical prostate histology and MRI data.  ... 
doi:10.1117/12.2044317 dblp:conf/miip/HwuangRKASSTRFM14 fatcat:4saaiovoyfgrddhfuq7vkcovoa

Computer-aided diagnosis: detection and localization of prostate cancer within the peripheral zone

Andrik Rampun, Zhili Chen, Paul Malcolm, Bernie Tiddeman, Reyer Zwiggelaar
2015 International Journal for Numerical Methods in Biomedical Engineering  
We are focusing on developing a CAD tool for the detection and localisation of abnormal region within the PZ in T2-MRI imaging.  ...  Secondly, the development of the proposed method and its application in prostate cancer detection and localisation using a single MRI modality with the results comparable to the state-of-the-art multi-modality  ...  This work was funded in part by the NISCHR Biomedical Research Unit for Advanced Medical Imaging and Visualization.  ... 
doi:10.1002/cnm.2745 pmid:26313267 fatcat:wavimncnhjba5lzyw2qxdjcxmm

Elastic registration of multimodal prostate MRI and histology via multiattribute combined mutual information

Jonathan Chappelow, B. Nicolas Bloch, Neil Rofsky, Elizabeth Genega, Robert Lenkinski, William DeWolf, Anant Madabhushi
2011 Medical Physics (Lancaster)  
Results: Elastic registration using the multivariate MI formulation is demonstrated for 150 corresponding sets of prostate images from 25 patient studies with T2-weighted and dynamic-contrast enhanced  ...  Purpose: By performing registration of preoperative multiprotocol in vivo magnetic resonance ͑MR͒ images of the prostate with corresponding whole-mount histology ͑WMH͒ sections from postoperative radical  ...  T2-w MRI, for the synthetic data set.  ... 
doi:10.1118/1.3560879 pmid:21626933 pmcid:PMC3078156 fatcat:5xk7kmfge5d7fobjrl462yryfy

Multimodal Self-Supervised Learning for Medical Image Analysis [article]

Aiham Taleb, Christoph Lippert, Tassilo Klein, Moin Nabi
2020 arXiv   pre-print
In other words, we exploit synthetic images for self-supervised pretraining, instead of downstream tasks directly, in order to circumvent quality issues associated with synthetic images, while improving  ...  We showcase our approach on four downstream tasks: Brain tumor segmentation and survival days prediction using four MRI modalities, Prostate segmentation using two MRI modalities, and Liver segmentation  ...  In the BraTS and Prostate benchmarks, we use T2-weighted MRI. In the Prostate dataset, we use T2-weighted MRI scans to generate the ADC diffusion-weighted scans.  ... 
arXiv:1912.05396v2 fatcat:klwchysg4ney3phlmlawyrzxvi

Machine Learning in Prostate MRI for Prostate Cancer: Current Status and Future Opportunities

Huanye Li, Chau Hung Lee, David Chia, Zhiping Lin, Weimin Huang, Cher Heng Tan
2022 Diagnostics  
The Prostate Imaging Reporting and Data System (PI-RADS) is an established imaging-based scoring system that scores the probability of clinically significant prostate cancer on MRI to guide management.  ...  Advances in our understanding of the role of magnetic resonance imaging (MRI) for the detection of prostate cancer have enabled its integration into clinical routines in the past two decades.  ...  For prostate zones, WG = whole gland, PZ = peripheral zone, TZ = transition zone.  ... 
doi:10.3390/diagnostics12020289 pmid:35204380 pmcid:PMC8870978 fatcat:rpaecwqodveqplmvuyvu5ne52m

Normal and Variant Pelvic Anatomy on MRI

Ashish P. Wasnik, Michael B. Mazza, Peter S. Liu
2011 Magnetic Resonance Imaging Clinics of North America  
Sagittal T2-weighted image demonstrates anterior linear defect in the lower uterine segment (arrow) compatible with cesarean section scar.  ...  Finally, whole-pelvis imaging is performed using a wide FOV in conjunction with the surface coil.  ... 
doi:10.1016/j.mric.2011.05.001 pmid:21816330 fatcat:4y5fso5bzfezflwg7dflgleeom

Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management—Current Trends and Future Perspectives

Octavian Sabin Tătaru, Mihai Dorin Vartolomei, Jens J. Rassweiler, Oșan Virgil, Giuseppe Lucarelli, Francesco Porpiglia, Daniele Amparore, Matteo Manfredi, Giuseppe Carrieri, Ugo Falagario, Daniela Terracciano, Ottavio de Cobelli (+3 others)
2021 Diagnostics  
Digital pathology is becoming highly assisted by AI to help researchers in analyzing larger data sets and providing faster and more accurate diagnoses of prostate cancer lesions.  ...  When applied to diagnostic imaging, AI has shown excellent accuracy in the detection of prostate lesions as well as in the prediction of patient outcomes in terms of survival and treatment response.  ...  Quantitative results showed no significant differences in dose volume histogram and planning target volumes, showing that in the future ML-MRI methods could generate synthetic CT images from MRI and could  ... 
doi:10.3390/diagnostics11020354 pmid:33672608 pmcid:PMC7924061 fatcat:jqktyzjrhjh2jaxvlpk3pomube

Learning Non-rigid Deformations for Robust, Constrained Point-based Registration in Image-Guided MR-TRUS Prostate Intervention

John A. Onofrey, Lawrence H. Staib, Saradwata Sarkar, Rajesh Venkataraman, Cayce B. Nawaf, Preston C. Sprenkle, Xenophon Papademetris
2017 Medical Image Analysis  
State-of-the-art, clinical MR-TRUS image fusion relies upon semi-automated segmentations of the prostate in both the MR and the TRUS images to perform non-rigid surface-based registration of the gland.  ...  Segmentation of the prostate in TRUS imaging is itself a challenging task and prone to high variability.  ...  Validation Using Synthetic Data We leveraged our large database to generate a set of realistic, synthetic TRUS prostate shapes with known non-rigid deformations and known segmentation errors on which we  ... 
doi:10.1016/ pmid:28431275 pmcid:PMC5514316 fatcat:x6zntiw2gfgg5hk5zmuoy5t6k4

Registration of pre-surgical MRI and whole-mount histopathology images in prostate cancer patients with radical prostatectomy via RAPSODI [article]

Mirabela Rusu, Christian A. Kunder, Nikola C. Teslovich, Jeffrey B Wang, Rewa R. Sood, Wei Shao, Leo C. Chan, Robert West, Richard Fan, Pejman Ghanouni, James B. Brooks, Geoffrey A. Sonn
2019 arXiv   pre-print
543 histopathology slices that were registered to corresponding T2 weighted MRI slices.  ...  Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis.  ...  All summarized methods require as input the in vivo pre-surgical T2 weighted MRI, digitized serial histopathology images, and the segmentation of the prostate on MRI and histopathology images; Additional  ... 
arXiv:1907.00324v2 fatcat:636ftyvq7zf25k2yfnwgrdqp64

Front Matter: Volume 12032

Ivana Išgum, Olivier Colliot
2022 Medical Imaging 2022: Image Processing  
These two-number sets start with 00,  ...  diffusion-weighted data using tagged magnetic resonance imaging [ models for organ contouring in head and neck radiotherapy [12032-13] 0G Automatic classification of MRI contrasts using a deep siamese  ...  inference for quantifying inter-observer variability in segmentation of anatomical structures [12032-55] 1N Parotid gland segmentation with nnU-Net: deployment scenario and inter-observer variability  ... 
doi:10.1117/12.2638192 fatcat:ikfgnjefaba2tpiamxoftyi6sa

Multiparametric MRI for Prostate Cancer Characterization: Combined Use of Radiomics Model with PI-RADS and Clinical Parameters

Piotr Woźnicki, Niklas Westhoff, Thomas Huber, Philipp Riffel, Matthias F. Froelich, Eva Gresser, Jost von Hardenberg, Alexander Mühlberg, Maurice Stephan Michel, Stefan O. Schoenberg, Dominik Nörenberg
2020 Cancers  
Segmentations of the whole prostate glands and index lesions were performed manually in apparent diffusion coefficient (ADC) maps and T2-weighted MRI.  ...  Radiomic features were extracted from regions corresponding to the whole prostate gland and index lesion.  ...  Image Segmentations For each patient, the whole prostate gland, peripheral and transition zones, as well as index lesions of the prostate were manually segmented on T2-weighted images.  ... 
doi:10.3390/cancers12071767 pmid:32630787 fatcat:pbd4aj6wljf6nh4gd4r2g6go4u

Molecular imaging and fusion targeted biopsy of the prostate

Baowei Fei, Peter T. Nieh, Viraj A. Master, Yun Zhang, Adeboye O. Osunkoya, David M. Schuster
2016 Clinical and translational imaging  
Results-Molecular imaging with PET and MRI shows promising results in the early detection of prostate cancer.  ...  Purpose-This paper provides a review on molecular imaging with positron emission tomography (PET) and magnetic resonance imaging (MRI) for prostate cancer detection and its applications in fusion targeted  ...  Fig. 1 .Fig. 2 . 12 Multiparametric MRI of the prostate: T2-weighted MRI (left), DCE-MRI (middle), and diffusion-weighted MRI (right) of the same Imaging.  ... 
doi:10.1007/s40336-016-0214-7 pmid:28971090 pmcid:PMC5621648 fatcat:zogw3brx5bd3lerltvgxbaqjna

18F-Choline PET/MRI: The Additional Value of PET for MRI-Guided Transrectal Prostate Biopsies

M. Piert, J. Montgomery, L. P. Kunju, J. Siddiqui, V. Rogers, T. Rajendiran, T. D. Johnson, X. Shao, M. S. Davenport
2016 Journal of Nuclear Medicine  
The biopsy procedure was performed after registration of real-time transrectal ultrasound with T2-weighted MR and included imageguided cores plus standard cores.  ...  Methods: Within an ongoing prospective clinical trial, hybrid 18 F-choline PET/CT and multiparametric 3T MRI (mpMRI) of the pelvis were performed in 36 subjects with a rising prostate-specific antigen  ...  In vivo MRI pelvis examinations of the prostate gland with and without contrast material was performed before biopsy.  ... 
doi:10.2967/jnumed.115.170878 pmid:26985061 pmcid:PMC5819614 fatcat:prhv3msbgvbz5b642alob2ueau
« Previous Showing results 1 — 15 out of 635 results