Ahmad Algohary1, Satish Viswanath1, Rakesh Shiradkar1, Soumya Ghose1, Shivani Pahwa2, Daniel Moses3, Ivan Jambor4, Ronald Shnier3, Maret Böhm3, Anne-Maree Haynes3, Phillip Brenner5, Warick Delprado6, James Thompson3, Marley Pulbrock3, Andrei S Purysko7, Sadhna Verma8, Lee Ponsky9, Phillip Stricker5, Anant Madabhushi1. 1. Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA. 2. Department of Radiology, Case Western Reserve University, Cleveland, Ohio, USA. 3. Garvan Institute of Medical Research, Sydney, Australia. 4. Department of Diagnostic Radiology, University of Turku, Turku, Finland. 5. Department of Urology, St. Vincent's Hospital, Sydney, Australia. 6. Douglass Hanly Moir Pathology, Sydney, Australia. 7. Section of Abdominal Imaging and Nuclear Radiology Department, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA. 8. Department of Radiology, College of Medicine, University of Cincinnati, Cincinnati, OH, USA. 9. Department of Urology, Case Western Reserve University, Cleveland, Ohio, USA.
Abstract
BACKGROUND: Radiomic analysis is defined as computationally extracting features from radiographic images for quantitatively characterizing disease patterns. There has been recent interest in examining the use of MRI for identifying prostate cancer (PCa) aggressiveness in patients on active surveillance (AS). PURPOSE: To evaluate the performance of MRI-based radiomic features in identifying the presence or absence of clinically significant PCa in AS patients. STUDY TYPE: Retrospective. SUBJECTS MODEL: MRI/TRUS (transperineal grid ultrasound) fusion-guided biopsy was performed for 56 PCa patients on AS who had undergone prebiopsy. FIELD STRENGTH/SEQUENCE: 3T, T2 -weighted (T2 w) and diffusion-weighted (DW) MRI. ASSESSMENT: A pathologist histopathologically defined the presence of clinically significant disease. A radiologist manually delineated lesions on T2 w-MRs. Then three radiologists assessed MRIs using PIRADS v2.0 guidelines. Tumors were categorized into four groups: MRI-negative-biopsy-negative (Group 1, N = 15), MRI-positive-biopsy-positive (Group 2, N = 16), MRI-negative-biopsy-positive (Group 3, N = 10), and MRI-positive-biopsy-negative (Group 4, N = 15). In all, 308 radiomic features (First-order statistics, Gabor, Laws Energy, and Haralick) were extracted from within the annotated lesions on T2 w images and apparent diffusion coefficient (ADC) maps. The top 10 features associated with clinically significant tumors were identified using minimum-redundancy-maximum-relevance and used to construct three machine-learning models that were independently evaluated for their ability to identify the presence and absence of clinically significant disease. STATISTICAL TESTS: Wilcoxon rank-sum tests with P < 0.05 considered statistically significant. RESULTS: Seven T2 w-based (First-order Statistics, Haralick, Laws, and Gabor) and three ADC-based radiomic features (Laws, Gradient and Sobel) exhibited statistically significant differences (P < 0.001) between malignant and normal regions in the training groups. The three constructed models yielded overall accuracy improvement of 33, 60, 80% and 30, 40, 60% for patients in testing groups, when compared to PIRADS v2.0 alone. DATA CONCLUSION: Radiomic features could help in identifying the presence and absence of clinically significant disease in AS patients when PIRADS v2.0 assessment on MRI contradicted pathology findings of MRI-TRUS prostate biopsies. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.
BACKGROUND: Radiomic analysis is defined as computationally extracting features from radiographic images for quantitatively characterizing disease patterns. There has been recent interest in examining the use of MRI for identifying prostate cancer (PCa) aggressiveness in patients on active surveillance (AS). PURPOSE: To evaluate the performance of MRI-based radiomic features in identifying the presence or absence of clinically significant PCa in AS patients. STUDY TYPE: Retrospective. SUBJECTS MODEL: MRI/TRUS (transperineal grid ultrasound) fusion-guided biopsy was performed for 56 PCa patients on AS who had undergone prebiopsy. FIELD STRENGTH/SEQUENCE: 3T, T2 -weighted (T2 w) and diffusion-weighted (DW) MRI. ASSESSMENT: A pathologist histopathologically defined the presence of clinically significant disease. A radiologist manually delineated lesions on T2 w-MRs. Then three radiologists assessed MRIs using PIRADS v2.0 guidelines. Tumors were categorized into four groups: MRI-negative-biopsy-negative (Group 1, N = 15), MRI-positive-biopsy-positive (Group 2, N = 16), MRI-negative-biopsy-positive (Group 3, N = 10), and MRI-positive-biopsy-negative (Group 4, N = 15). In all, 308 radiomic features (First-order statistics, Gabor, Laws Energy, and Haralick) were extracted from within the annotated lesions on T2 w images and apparent diffusion coefficient (ADC) maps. The top 10 features associated with clinically significant tumors were identified using minimum-redundancy-maximum-relevance and used to construct three machine-learning models that were independently evaluated for their ability to identify the presence and absence of clinically significant disease. STATISTICAL TESTS: Wilcoxon rank-sum tests with P < 0.05 considered statistically significant. RESULTS: Seven T2 w-based (First-order Statistics, Haralick, Laws, and Gabor) and three ADC-based radiomic features (Laws, Gradient and Sobel) exhibited statistically significant differences (P < 0.001) between malignant and normal regions in the training groups. The three constructed models yielded overall accuracy improvement of 33, 60, 80% and 30, 40, 60% for patients in testing groups, when compared to PIRADS v2.0 alone. DATA CONCLUSION: Radiomic features could help in identifying the presence and absence of clinically significant disease in AS patients when PIRADS v2.0 assessment on MRI contradicted pathology findings of MRI-TRUS prostate biopsies. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.
Authors: M Nezzo; M G Di Trani; A Caporale; R Miano; A Mauriello; P Bove; S Capuani; G Manenti Journal: Eur J Radiol Date: 2016-08-02 Impact factor: 3.528
Authors: Geert J S Litjens; Robin Elliott; Natalie N C Shih; Michael D Feldman; Thiele Kobus; Christina Hulsbergen-van de Kaa; Jelle O Barentsz; Henkjan J Huisman; Anant Madabhushi Journal: Radiology Date: 2015-07-17 Impact factor: 11.105
Authors: Duc Fehr; Harini Veeraraghavan; Andreas Wibmer; Tatsuo Gondo; Kazuhiro Matsumoto; Herbert Alberto Vargas; Evis Sala; Hedvig Hricak; Joseph O Deasy Journal: Proc Natl Acad Sci U S A Date: 2015-11-02 Impact factor: 11.205
Authors: Shoshana B Ginsburg; Satish E Viswanath; B Nicolas Bloch; Neil M Rofsky; Elizabeth M Genega; Robert E Lenkinski; Anant Madabhushi Journal: J Magn Reson Imaging Date: 2014-06-18 Impact factor: 4.813
Authors: Daniel Palumbo; Brian Yee; Patrick O'Dea; Shane Leedy; Satish Viswanath; Anant Madabhushi Journal: Annu Int Conf IEEE Eng Med Biol Soc Date: 2011
Authors: Prathyush Chirra; Patrick Leo; Michael Yim; B Nicolas Bloch; Ardeshir R Rastinehad; Andrei Purysko; Mark Rosen; Anant Madabhushi; Satish E Viswanath Journal: J Med Imaging (Bellingham) Date: 2019-06-14
Authors: Rodrigo Delgadillo; John C Ford; Matthew C Abramowitz; Alan Dal Pra; Alan Pollack; Radka Stoyanova Journal: Strahlenther Onkol Date: 2020-08-21 Impact factor: 3.621
Authors: Harri Merisaari; Pekka Taimen; Rakesh Shiradkar; Otto Ettala; Marko Pesola; Jani Saunavaara; Peter J Boström; Anant Madabhushi; Hannu J Aronen; Ivan Jambor Journal: Magn Reson Med Date: 2019-11-08 Impact factor: 4.668
Authors: Michele Avanzo; Lise Wei; Joseph Stancanello; Martin Vallières; Arvind Rao; Olivier Morin; Sarah A Mattonen; Issam El Naqa Journal: Med Phys Date: 2020-06 Impact factor: 4.071