1
|
Pan N, Shi L, He D, Zhao J, Xiong L, Ma L, Li J, Ai K, Zhao L, Huang G. Prediction of prostate cancer aggressiveness using magnetic resonance imaging radiomics: a dual-center study. Discov Oncol 2024; 15:122. [PMID: 38625419 PMCID: PMC11019191 DOI: 10.1007/s12672-024-00980-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/09/2023] [Accepted: 04/11/2024] [Indexed: 04/17/2024] Open
Abstract
PURPOSE The Gleason score (GS) and positive needles are crucial aggressive indicators of prostate cancer (PCa). This study aimed to investigate the usefulness of magnetic resonance imaging (MRI) radiomics models in predicting GS and positive needles of systematic biopsy in PCa. MATERIAL AND METHODS A total of 218 patients with pathologically proven PCa were retrospectively recruited from 2 centers. Small-field-of-view high-resolution T2-weighted imaging and post-contrast delayed sequences were selected to extract radiomics features. Then, analysis of variance and recursive feature elimination were applied to remove redundant features. Radiomics models for predicting GS and positive needles were constructed based on MRI and various classifiers, including support vector machine, linear discriminant analysis, logistic regression (LR), and LR using the least absolute shrinkage and selection operator. The models were evaluated with the area under the curve (AUC) of the receiver-operating characteristic. RESULTS The 11 features were chosen as the primary feature subset for the GS prediction, whereas the 5 features were chosen for positive needle prediction. LR was chosen as classifier to construct the radiomics models. For GS prediction, the AUC of the radiomics models was 0.811, 0.814, and 0.717 in the training, internal validation, and external validation sets, respectively. For positive needle prediction, the AUC was 0.806, 0.811, and 0.791 in the training, internal validation, and external validation sets, respectively. CONCLUSIONS MRI radiomics models are suitable for predicting GS and positive needles of systematic biopsy in PCa. The models can be used to identify aggressive PCa using a noninvasive, repeatable, and accurate diagnostic method.
Collapse
Affiliation(s)
- Nini Pan
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Liuyan Shi
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Diliang He
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Jianxin Zhao
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Lianqiu Xiong
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Lili Ma
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Jing Li
- The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, 730000, Gansu, China
| | - Kai Ai
- Clinical and Technical Support, Philips Healthcare, Xi'an, China
| | - Lianping Zhao
- Department of Radiology, Gansu Provincial Hospital, Lanzhou, 730000, Gansu, China
| | - Gang Huang
- Department of Radiology, Gansu Provincial Hospital, Lanzhou, 730000, Gansu, China.
| |
Collapse
|
2
|
Kawase M, Goto T, Ebara S, Tatenuma T, Sasaki T, Ishihara T, Ikehata Y, Nakayama A, Toide M, Yoneda T, Sakaguchi K, Teishima J, Kobayashi T, Makiyama K, Inoue T, Kitamura H, Saito K, Koga F, Urakami S, Koie T. Nomogram Predicting Locally Advanced Prostate Cancer in Patients with Clinically Organ-Confined Disease Who Underwent Robot-Assisted Radical Prostatectomy: A Retrospective Multicenter Cohort Study in Japan (The MSUG94 Group). Ann Surg Oncol 2023; 30:6925-6933. [PMID: 37338747 DOI: 10.1245/s10434-023-13747-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Accepted: 05/28/2023] [Indexed: 06/21/2023]
Abstract
PURPOSE We created a clinically applicable nomogram to predict locally advanced prostate cancer using preoperative parameters and performed external validation using an external independent validation cohort. PATIENTS AND METHODS From a retrospective multicenter cohort study of 3622 Japanese patients with prostate cancer who underwent robot-assisted radical prostatectomy at ten institutions, the patients were divided into two groups (MSUG cohort and validation cohort). Locally advanced prostate cancer was defined as pathological T stage ≥ 3a. A multivariable logistic regression model was used to identify factors strongly associated with locally advanced prostate cancer. Bootstrap area under the curve was calculated to assess the internal validity of the prediction model. A nomogram was created as a practical application of the prediction model, and a web application was released to predict the probability of locally advanced prostate cancer. RESULTS A total of 2530 and 427 patients in the MSUG and validation cohorts, respectively, met the criteria for this study. On multivariable analysis, initial prostate-specific antigen, prostate volume, number of cancer-positive and cancer-negative biopsy cores, biopsy grade group, and clinical T stage were independent predictors of locally advanced prostate cancer. The nomogram predicting locally advanced prostate cancer was demonstrated (area under the curve 0.72). Using a nomogram cutoff of 0.26, 464 of 1162 patients (39.9%) could be correctly diagnosed with pT3, and 2311 of 2524 patients (91.6%) could avoid underdiagnosis. CONCLUSIONS We developed a clinically applicable nomogram with external validation to predict the probability of locally advanced prostate cancer in patients undergoing robot-assisted radical prostatectomy.
Collapse
Affiliation(s)
- Makoto Kawase
- Department of Urology, Gifu University Graduate School of Medicine, Gifu, Japan
| | - Takayuki Goto
- Department of Urology, Kyoto University Graduate School of Medicine, Kyoto, Japan
| | - Shin Ebara
- Department of Urology, Hiroshima City Hiroshima Citizens Hospital, Hiroshima, Japan
| | | | - Takeshi Sasaki
- Department of Nephro-Urologic Surgery and Andrology, Mie University Graduate School of Medicine, Tsu, Japan
| | - Takuma Ishihara
- Innovative and Clinical Research Promotion Center, Gifu University Hospital, Gifu, Japan
| | | | - Akinori Nakayama
- Department of Urology, Dokkyo Medical University Saitama Medical Center, Koshigaya, Japan
| | - Masahiro Toide
- Department of Urology, Tokyo Metropolitan Cancer and Infectious Diseases Center Komagome Hospital, Tokyo, Japan
| | - Tatsuaki Yoneda
- Department of Urology, Seirei Hamamatsu General Hospital, Hamamatsu, Japan
| | | | - Jun Teishima
- Department of Urology, Kobe City Hospital Organization Kobe City Medical Center West Hospital, Kobe, Japan
| | - Takashi Kobayashi
- Department of Urology, Kyoto University Graduate School of Medicine, Kyoto, Japan
| | | | - Takahiro Inoue
- Department of Nephro-Urologic Surgery and Andrology, Mie University Graduate School of Medicine, Tsu, Japan
| | | | - Kazutaka Saito
- Department of Urology, Dokkyo Medical University Saitama Medical Center, Koshigaya, Japan
| | - Fumitaka Koga
- Department of Urology, Tokyo Metropolitan Cancer and Infectious Diseases Center Komagome Hospital, Tokyo, Japan
| | | | - Takuya Koie
- Department of Urology, Gifu University Graduate School of Medicine, Gifu, Japan.
| |
Collapse
|
3
|
Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics. Cancers (Basel) 2021; 13:cancers13236065. [PMID: 34885175 PMCID: PMC8657292 DOI: 10.3390/cancers13236065] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Revised: 11/24/2021] [Accepted: 11/26/2021] [Indexed: 11/18/2022] Open
Abstract
Simple Summary The use of radiomics has been studied to predict Gleason Score from bi-parametric prostate MRI examinations. However, different combinations of type of input data (whole prostate gland/lesion features), sampling strategy, feature selection method and machine learning algorithm can be used. The impact of such choices was investigated and it was found that features extracted from the whole prostate gland were more stable to segmentation differences and produced better models (higher performance and less overfitting). This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion. Abstract Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.
Collapse
|
4
|
Wibmer AG, Kattan MW, Alessandrino F, Baur ADJ, Boesen L, Franco FB, Bonekamp D, Campa R, Cash H, Catalá V, Crouzet S, Dinnoo S, Eastham J, Fennessy FM, Ghabili K, Hohenfellner M, Levi AW, Ji X, Løgager V, Margolis DJ, Moldovan PC, Panebianco V, Penzkofer T, Puech P, Radtke JP, Rouvière O, Schlemmer HP, Sprenkle PC, Tempany CM, Vilanova JC, Weinreb J, Hricak H, Shukla-Dave A. International Multi-Site Initiative to Develop an MRI-Inclusive Nomogram for Side-Specific Prediction of Extraprostatic Extension of Prostate Cancer. Cancers (Basel) 2021; 13:cancers13112627. [PMID: 34071842 PMCID: PMC8198352 DOI: 10.3390/cancers13112627] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Revised: 04/29/2021] [Accepted: 05/21/2021] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND To develop an international, multi-site nomogram for side-specific prediction of extraprostatic extension (EPE) of prostate cancer based on clinical, biopsy, and magnetic resonance imaging- (MRI) derived data. METHODS Ten institutions from the USA and Europe contributed clinical and side-specific biopsy and MRI variables of consecutive patients who underwent prostatectomy. A logistic regression model was used to develop a nomogram for predicting side-specific EPE on prostatectomy specimens. The performance of the statistical model was evaluated by bootstrap resampling and cross validation and compared with the performance of benchmark models that do not incorporate MRI findings. RESULTS Data from 840 patients were analyzed; pathologic EPE was found in 320/840 (31.8%). The nomogram model included patient age, prostate-specific antigen density, side-specific biopsy data (i.e., Gleason grade group, percent positive cores, tumor extent), and side-specific MRI features (i.e., presence of a PI-RADSv2 4 or 5 lesion, level of suspicion for EPE, length of capsular contact). The area under the receiver operating characteristic curve of the new, MRI-inclusive model (0.828, 95% confidence limits: 0.805, 0.852) was significantly higher than that of any of the benchmark models (p < 0.001 for all). CONCLUSIONS In an international, multi-site study, we developed an MRI-inclusive nomogram for the side-specific prediction of EPE of prostate cancer that demonstrated significantly greater accuracy than clinical benchmark models.
Collapse
Affiliation(s)
- Andreas G. Wibmer
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA; (H.H.); (A.S.-D.)
- Correspondence: ; Tel.: +1-646-888-5409
| | - Michael W. Kattan
- Department of Quantitative Health Sciences in the Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, USA; (M.W.K.); (X.J.)
| | - Francesco Alessandrino
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA; (F.A.); (F.B.F.); (F.M.F.); (C.M.T.)
| | | | - Lars Boesen
- Herlev Gentofte University Hospital, 2730 Herlev, Denmark; (L.B.); (V.L.)
| | - Felipe Boschini Franco
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA; (F.A.); (F.B.F.); (F.M.F.); (C.M.T.)
| | - David Bonekamp
- DKFZ German Cancer Research Center, 69120 Heidelberg, Germany; (D.B.); (J.P.R.); (H.-P.S.)
| | - Riccardo Campa
- Department of Radiological Sciences, Oncology & Pathology, Sapienza University of Rome, 00185 Rome, Italy; (R.C.); (V.P.)
| | - Hannes Cash
- Charité University Hospital, 10117 Berlin, Germany; (A.D.J.B.); (H.C.); (T.P.)
- Department of Urology, University Magdeburg, 39120 Magdeburg, Germany
| | - Violeta Catalá
- Department of Radiology, Fundació Puigvert, 08025 Barcelona, Spain;
- Department of Uro-Radiology, Creu Blanca, 08034 Barcelona, Spain
| | - Sebastien Crouzet
- Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003 Lyon, France; (S.C.); (P.C.M.); (O.R.)
| | - Sounil Dinnoo
- Genitourinary and Women’s Imaging Departments, Lille University Hospital, 59037 Lille, France; (S.D.); (P.P.)
| | - James Eastham
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA;
| | - Fiona M. Fennessy
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA; (F.A.); (F.B.F.); (F.M.F.); (C.M.T.)
| | - Kamyar Ghabili
- Department of Urology, Yale School of Medicine, New Haven, CT 06510, USA; (K.G.); (P.C.S.)
| | - Markus Hohenfellner
- Department of Urology, University Hospital of Heidelberg, 69120 Heidelberg, Germany;
| | - Angelique W. Levi
- Department of Pathology, Yale School of Medicine, New Haven, CT 06510, USA;
| | - Xinge Ji
- Department of Quantitative Health Sciences in the Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, USA; (M.W.K.); (X.J.)
| | - Vibeke Løgager
- Herlev Gentofte University Hospital, 2730 Herlev, Denmark; (L.B.); (V.L.)
| | - Daniel J. Margolis
- Weill Cornell Medicine, Weill Cornell Imaging, New York-Presbyterian Hospital, New York, NY 10021, USA;
| | - Paul C. Moldovan
- Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003 Lyon, France; (S.C.); (P.C.M.); (O.R.)
| | - Valeria Panebianco
- Department of Radiological Sciences, Oncology & Pathology, Sapienza University of Rome, 00185 Rome, Italy; (R.C.); (V.P.)
| | - Tobias Penzkofer
- Charité University Hospital, 10117 Berlin, Germany; (A.D.J.B.); (H.C.); (T.P.)
- Berlin Institute of Health (BIH), 10178 Berlin, Germany
| | - Philippe Puech
- Genitourinary and Women’s Imaging Departments, Lille University Hospital, 59037 Lille, France; (S.D.); (P.P.)
| | - Jan Philipp Radtke
- DKFZ German Cancer Research Center, 69120 Heidelberg, Germany; (D.B.); (J.P.R.); (H.-P.S.)
- Department of Urology, University Hospital of Heidelberg, 69120 Heidelberg, Germany;
| | - Olivier Rouvière
- Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003 Lyon, France; (S.C.); (P.C.M.); (O.R.)
- Faculté de Médecine Lyon Est, Université de Lyon, 69003 Lyon, France
| | - Heinz-Peter Schlemmer
- DKFZ German Cancer Research Center, 69120 Heidelberg, Germany; (D.B.); (J.P.R.); (H.-P.S.)
| | - Preston C. Sprenkle
- Department of Urology, Yale School of Medicine, New Haven, CT 06510, USA; (K.G.); (P.C.S.)
| | - Clare M. Tempany
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA; (F.A.); (F.B.F.); (F.M.F.); (C.M.T.)
| | - Joan C. Vilanova
- Clínica Girona, Institute Catalan of Health-IDI, University of Girona, 17004 Girona, Spain;
| | - Jeffrey Weinreb
- Department of Radiology, Yale School of Medicine, New Haven, CT 06510, USA;
| | - Hedvig Hricak
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA; (H.H.); (A.S.-D.)
| | - Amita Shukla-Dave
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA; (H.H.); (A.S.-D.)
| |
Collapse
|