1
|
Morelli L, Paganelli C, Marvaso G, Parrella G, Annunziata S, Vicini MG, Zaffaroni M, Pepa M, Summers PE, De Cobelli O, Petralia G, Jereczek-Fossa BA, Baroni G. Addressing intra- and inter-institution variability of a radiomic framework based on Apparent Diffusion Coefficient in prostate cancer. Med Phys 2024. [PMID: 39172115 DOI: 10.1002/mp.17355] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2024] [Revised: 06/27/2024] [Accepted: 08/05/2024] [Indexed: 08/23/2024] Open
Abstract
BACKGROUND Prostate cancer (PCa) is a highly heterogeneous disease, making tailored treatment approaches challenging. Magnetic resonance imaging (MRI), notably diffusion-weighted imaging (DWI) and the derived Apparent Diffusion Coefficient (ADC) maps, plays a crucial role in PCa characterization. In this context, radiomics is a very promising approach able to disclose insights from MRI data. However, the sensitivity of radiomic features to MRI settings, encompassing DWI protocols and multicenter variations, requires the development of robust and generalizable models. PURPOSE To develop a comprehensive radiomics framework for noninvasive PCa characterization using ADC maps, focusing on identifying reliable imaging biomarkers against intra- and inter-institution variations. MATERIALS AND METHODS Two patient cohorts, including an internal cohort (118 PCa patients) used for both training (75%) and hold-out testing (25%), and an external cohort (50 PCa patients) for independent testing, were employed in the study. DWI images were acquired with three different DWI protocols on two different MRI scanners: two DWI protocols acquired on a 1.5-T scanner for the internal cohort, and one DWI protocol acquired on a 3-T scanner for the external cohort. One hundred and seven radiomics features (i.e., shape, first order, texture) were extracted from ADC maps of the whole prostate gland. To address variations in DWI protocols and multicenter variability, a dedicated pipeline, including two-way ANOVA, sequential-feature-selection (SFS), and ComBat features harmonization was implemented. Mann-Whitney U-tests (α = 0.05) were performed to find statistically significant features dividing patients with different tumor characteristics in terms of Gleason score (GS) and T-stage. Support-Vector-Machine models were then developed to predict GS and T-stage, and the performance was assessed through the area under the curve (AUC) of receiver-operating-characteristic curves. RESULTS Downstream of ANOVA, two subsets of 38 and 41 features stable against DWI protocol were identified for GS and T-stage, respectively. Among these, SFS revealed the most predictive features, yielding an AUC of 0.75 (GS) and 0.70 (T-stage) in the hold-out test. Employing ComBat harmonization improved the external-test performance of the GS model, raising AUC from 0.72 to 0.78. CONCLUSION By incorporating stable features with a harmonization procedure and validating the model on an external dataset, model robustness, and generalizability were assessed, highlighting the potential of ADC and radiomics for PCa characterization.
Collapse
Affiliation(s)
- Letizia Morelli
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
| | - Chiara Paganelli
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
| | - Giulia Marvaso
- Department of Radiation Oncology, European Institute of Oncology (IEO), Milan, Italy
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Giovanni Parrella
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
| | - Simone Annunziata
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
| | - Maria Giulia Vicini
- Department of Radiation Oncology, European Institute of Oncology (IEO), Milan, Italy
| | - Mattia Zaffaroni
- Department of Radiation Oncology, European Institute of Oncology (IEO), Milan, Italy
| | - Matteo Pepa
- Department of Radiation Oncology, European Institute of Oncology (IEO), Milan, Italy
| | | | - Ottavio De Cobelli
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Department of Urology, European Institute of Oncology (IEO), Milan, Italy
| | - Giuseppe Petralia
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Department of Radiology, European Institute of Oncology (IEO), Milan, Italy
| | - Barbara Alicja Jereczek-Fossa
- Department of Radiation Oncology, European Institute of Oncology (IEO), Milan, Italy
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Guido Baroni
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
| |
Collapse
|
2
|
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
|
3
|
Yin X, Wang K, Wang L, Yang Z, Zhang Y, Wu P, Zhao C, Zhang J. Algorithms for classification of sequences and segmentation of prostate gland: an external validation study. Abdom Radiol (NY) 2024; 49:1275-1287. [PMID: 38436698 DOI: 10.1007/s00261-024-04241-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2023] [Revised: 02/05/2024] [Accepted: 02/05/2024] [Indexed: 03/05/2024]
Abstract
OBJECTIVES The aim of the study was to externally validate two AI models for the classification of prostate mpMRI sequences and segmentation of the prostate gland on T2WI. MATERIALS AND METHODS MpMRI data from 719 patients were retrospectively collected from two hospitals, utilizing nine MR scanners from four different vendors, over the period from February 2018 to May 2022. Med3D deep learning pretrained architecture was used to perform image classification,UNet-3D was used to segment the prostate gland. The images were classified into one of nine image types by the mode. The segmentation model was validated using T2WI images. The accuracy of the segmentation was evaluated by measuring the DSC, VS,AHD.Finally,efficacy of the models was compared for different MR field strengths and sequences. RESULTS 20,551 image groups were obtained from 719 MR studies. The classification model accuracy is 99%, with a kappa of 0.932. The precision, recall, and F1 values for the nine image types had statistically significant differences, respectively (all P < 0.001). The accuracy for scanners 1.436 T, 1.5 T, and 3.0 T was 87%, 86%, and 98%, respectively (P < 0.001). For segmentation model, the median DSC was 0.942 to 0.955, the median VS was 0.974 to 0.982, and the median AHD was 5.55 to 6.49 mm,respectively.These values also had statistically significant differences for the three different magnetic field strengths (all P < 0.001). CONCLUSION The AI models for mpMRI image classification and prostate segmentation demonstrated good performance during external validation, which could enhance efficiency in prostate volume measurement and cancer detection with mpMRI. CLINICAL RELEVANCE STATEMENT These models can greatly improve the work efficiency in cancer detection, measurement of prostate volume and guided biopsies.
Collapse
Affiliation(s)
- Xuemei Yin
- Department of Medical Imaging, First Hospital of Qinhuangdao, 066000, Qinhuangdao City, Hebei Province, China
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 100050, Beijing, China
| | - Kexin Wang
- School of Basic Medical Sciences, Capital Medical University, 100052, Beijing, China
| | - Liang Wang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 100050, Beijing, China
| | - Zhenghan Yang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 100050, Beijing, China
| | - Yaofeng Zhang
- Beijing Smart Tree Medical Technology Co. Ltd, 100011, Beijing, China
| | - Pengsheng Wu
- Beijing Smart Tree Medical Technology Co. Ltd, 100011, Beijing, China
| | - Chenglin Zhao
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 100050, Beijing, China.
| | - Jun Zhang
- Department of Medical Imaging, First Hospital of Qinhuangdao, 066000, Qinhuangdao City, Hebei Province, China.
| |
Collapse
|
4
|
Wang H, Wang K, Ma S, Gao G, Wang X. Investigation of radiomics models for predicting biochemical recurrence of advanced prostate cancer on pretreatment MR ADC maps based on automatic image segmentation. J Appl Clin Med Phys 2024; 25:e14244. [PMID: 38146796 PMCID: PMC11005965 DOI: 10.1002/acm2.14244] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 07/16/2023] [Accepted: 12/03/2023] [Indexed: 12/27/2023] Open
Abstract
OBJECTIVES To develop radiomics models based on automatic segmentation of the pretreatment apparent diffusion coefficient (ADC) maps for predicting the biochemical recurrence (BCR) of advanced prostate cancer (PCa). METHODS A total of 100 cases with pathologically confirmed PCa were retrospectively included in this study. These cases were randomly divided into training (n = 70) and test (n = 30) datasets. Two predictive models were constructed based on the combination of age, prostate specific antigen (PSA) level, Gleason score, and clinical staging before therapy and the prostate area (Model_1) or PCa area (Model_2). Another two predictive models were constructed based on only prostate area (Model_3) or PCa area (Model_4). The area under the receiver operating characteristic curve (ROC AUC) and precision-recall (PR) curve analysis were used to analyze the models' performance. RESULTS Sixty-five patients without BCR (BCR-) and 35 patients with BCR (BCR+) were confirmed. The age, PSA, volume, diameter and ADC value of the prostate and PCa were not significantly different between the BCR- and BCR+ groups or between the training and test datasets (all p > 0.05). The AUCs were 0.637 (95% CI: 0.434-0.838), 0.841 (95% CI: 0.695-0.940), 0.840 (95% CI: 0.698-0.983), and 0.808 (95% CI: 0.627-0.988) for Model_1 to Model_4 in the test dataset without significant difference. The 95% bootstrap confidence intervals for the areas under the PR curve of the four models were not statistically different. CONCLUSION The radiomics models based on automatically segmented prostate and PCa areas on the pretreatment ADC maps developed in our study can be promising in predicting BCR of advanced PCa.
Collapse
Affiliation(s)
- Huihui Wang
- Department of RadiologyPeking University First HospitalBeijingChina
| | - Kexin Wang
- School of Basic Medical SciencesCapital Medical UniversityBeijingChina
| | - Shuai Ma
- Department of RadiologyPeking University First HospitalBeijingChina
| | - Ge Gao
- Department of RadiologyPeking University First HospitalBeijingChina
| | - Xiaoying Wang
- Department of RadiologyPeking University First HospitalBeijingChina
| |
Collapse
|
5
|
Wang H, Wang K, Zhang Y, Chen Y, Zhang X, Wang X. Deep learning-based radiomics model from pretreatment ADC to predict biochemical recurrence in advanced prostate cancer. Front Oncol 2024; 14:1342104. [PMID: 38476369 PMCID: PMC10928490 DOI: 10.3389/fonc.2024.1342104] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2023] [Accepted: 02/05/2024] [Indexed: 03/14/2024] Open
Abstract
Purpose To develop deep-learning radiomics model for predicting biochemical recurrence (BCR) of advanced prostate cancer (PCa) based on pretreatment apparent diffusion coefficient (ADC) maps. Methods Data were collected retrospectively from 131 patients diagnosed with advanced PCa, randomly divided into training (n = 93) and test (n = 38) datasets. Pre-treatment ADC images were segmented using a pre-trained artificial intelligence (AI) model to identify suspicious PCa areas. Three models were constructed, including a clinical model, a conventional radiomics model and a deep-radiomics model. The receiver operating characteristic (ROC), precision-recall (PR) curve and decision curve analysis (DCA) were used to assess predictive performance in test dataset. The net reclassification index (NRI) and integrated discrimination improvement (IDI) were employed to compare the performance enhancement of the deep-radiomics model in relation to the other two models. Results The deep-radiomics model exhibited a significantly higher area under the curve (AUC) of ROC than the other two (P = 0.033, 0.026), as well as PR curve (AUC difference 0.420, 0.432). The DCA curve demonstrated superior performance for the deep-radiomics model across all risk thresholds than the other two. Taking the clinical model as reference, the NRI and IDI was 0.508 and 0.679 for the deep-radiomics model with significant difference. Compared with the conventional radiomics model, the NRI and IDI was 0.149 and 0.164 for the deep-radiomics model without significant difference. Conclusion The deep-radiomics model exhibits promising potential in predicting BCR in advanced PCa, compared to both the clinical model and the conventional radiomics model.
Collapse
Affiliation(s)
- Huihui Wang
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Kexin Wang
- School of Basic Medical Sciences, Capital Medical University, Beijing, China
| | - Yaofeng Zhang
- Beijing Smart Tree Medical Technology Co. Ltd., Beijing, China
| | - Yuke Chen
- Department of Urology, Peking University First Hospital, Beijing, China
| | - Xiaodong Zhang
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Xiaoying Wang
- Department of Radiology, Peking University First Hospital, Beijing, China
| |
Collapse
|
6
|
Li S, Wang KX, Li JL, He Y, Wang XY, Tang WR, Xie WH, Zhu W, Wu PS, Wang XP. AI-predicted mpMRI image features for the prediction of clinically significant prostate cancer. Int Urol Nephrol 2023; 55:2703-2715. [PMID: 37553543 PMCID: PMC10560153 DOI: 10.1007/s11255-023-03722-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Accepted: 07/21/2023] [Indexed: 08/10/2023]
Abstract
PURPOSE To evaluate the feasibility of using mpMRI image features predicted by AI algorithms in the prediction of clinically significant prostate cancer (csPCa). MATERIALS AND METHODS This study analyzed patients who underwent prostate mpMRI and radical prostatectomy (RP) at the Affiliated Hospital of Jiaxing University between November 2017 and December 2022. The clinical data collected included age, serum prostate-specific antigen (PSA), and biopsy pathology. The reference standard was the prostatectomy pathology, and a Gleason Score (GS) of 3 + 3 = 6 was considered non-clinically significant prostate cancer (non-csPCa), while a GS ≥ 3 + 4 was considered csPCa. A pre-trained AI algorithm was used to extract the lesion on mpMRI, and the image features of the lesion and the prostate gland were analyzed. Two logistic regression models were developed to predict csPCa: an MR model and a combined model. The MR model used age, PSA, PSA density (PSAD), and the AI-predicted MR image features as predictor variables. The combined model used biopsy pathology and the aforementioned variables as predictor variables. The model's effectiveness was evaluated by comparing it to biopsy pathology using the area under the curve (AUC) of receiver operation characteristic (ROC) analysis. RESULTS A total of 315 eligible patients were enrolled with an average age of 70.8 ± 5.9. Based on RP pathology, 18 had non-csPCa, and 297 had csPCa. PSA, PSAD, biopsy pathology, and ADC value of the prostate outside the lesion (ADCprostate) varied significantly across different ISUP grade groups of RP pathology (P < 0.001). Other clinical variables and image features did not vary significantly across different ISUP grade groups (P > 0.05). The MR model included PSAD, the ratio of ADC value between the lesion and the prostate outside the lesion (ADClesion/prostate), the signal intensity ratio of DWI between the lesion and the prostate outside the lesion (DWIlesion/prostate), and the ratio of DWIlesion/prostate to ADClesion/prostate. The combined model included biopsy pathology, ADClesion/prostate, mean signal intensity of the lesion on DWI (DWIlesion), DWI signal intensity of the prostate outside the lesion (DWIprostate), and signal intensity ratio of DWI between the lesion and the prostate outside the lesion (DWIlesion/prostate). The AUC of the MR model (0.830, 95% CI 0.743, 0.916) was not significantly different from that of biopsy pathology (0.820, 95% CI 0.728, 0.912, P = 0.884). The AUC of the combined model (0.915, 95% CI 0.849, 0.980) was higher than that of the biopsy pathology (P = 0.042) and MR model (P = 0.031). CONCLUSION The aggressiveness of prostate cancer can be effectively predicted using AI-extracted image features from mpMRI images, similar to biopsy pathology. The prediction accuracy was improved by combining the AI-extracted mpMRI image features with biopsy pathology, surpassing the performance of biopsy pathology alone.
Collapse
Affiliation(s)
- Song Li
- Zhejiang Chinese Medical University, China, The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Ke-Xin Wang
- School of Basic Medical Sciences, Capital Medical University, Beijing, China
| | - Jia-Lei Li
- Zhejiang Chinese Medical University, China, The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Yi He
- The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Xiao-Ying Wang
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Wen-Rui Tang
- The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Wen-Hua Xie
- The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Wei Zhu
- The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Peng-Sheng Wu
- Beijing Smart Tree Medical Technology Co. Ltd., Beijing, China
| | - Xiang-Peng Wang
- Beijing Smart Tree Medical Technology Co. Ltd., Beijing, China
| |
Collapse
|
7
|
Chaddad A, Tan G, Liang X, Hassan L, Rathore S, Desrosiers C, Katib Y, Niazi T. Advancements in MRI-Based Radiomics and Artificial Intelligence for Prostate Cancer: A Comprehensive Review and Future Prospects. Cancers (Basel) 2023; 15:3839. [PMID: 37568655 PMCID: PMC10416937 DOI: 10.3390/cancers15153839] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2023] [Revised: 07/25/2023] [Accepted: 07/26/2023] [Indexed: 08/13/2023] Open
Abstract
The use of multiparametric magnetic resonance imaging (mpMRI) has become a common technique used in guiding biopsy and developing treatment plans for prostate lesions. While this technique is effective, non-invasive methods such as radiomics have gained popularity for extracting imaging features to develop predictive models for clinical tasks. The aim is to minimize invasive processes for improved management of prostate cancer (PCa). This study reviews recent research progress in MRI-based radiomics for PCa, including the radiomics pipeline and potential factors affecting personalized diagnosis. The integration of artificial intelligence (AI) with medical imaging is also discussed, in line with the development trend of radiogenomics and multi-omics. The survey highlights the need for more data from multiple institutions to avoid bias and generalize the predictive model. The AI-based radiomics model is considered a promising clinical tool with good prospects for application.
Collapse
Affiliation(s)
- Ahmad Chaddad
- School of Artificial Intelligence, Guilin Universiy of Electronic Technology, Guilin 541004, China
- The Laboratory for Imagery, Vision and Artificial Intelligence, École de Technologie Supérieure (ETS), Montreal, QC H3C 1K3, Canada
| | - Guina Tan
- School of Artificial Intelligence, Guilin Universiy of Electronic Technology, Guilin 541004, China
| | - Xiaojuan Liang
- School of Artificial Intelligence, Guilin Universiy of Electronic Technology, Guilin 541004, China
| | - Lama Hassan
- School of Artificial Intelligence, Guilin Universiy of Electronic Technology, Guilin 541004, China
| | | | - Christian Desrosiers
- The Laboratory for Imagery, Vision and Artificial Intelligence, École de Technologie Supérieure (ETS), Montreal, QC H3C 1K3, Canada
| | - Yousef Katib
- Department of Radiology, Taibah University, Al Madinah 42361, Saudi Arabia
| | - Tamim Niazi
- Lady Davis Institute for Medical Research, McGill University, Montreal, QC H3T 1E2, Canada
| |
Collapse
|
8
|
Rodrigues A, Rodrigues N, Santinha J, Lisitskaya MV, Uysal A, Matos C, Domingues I, Papanikolaou N. Value of handcrafted and deep radiomic features towards training robust machine learning classifiers for prediction of prostate cancer disease aggressiveness. Sci Rep 2023; 13:6206. [PMID: 37069257 PMCID: PMC10110526 DOI: 10.1038/s41598-023-33339-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Accepted: 04/11/2023] [Indexed: 04/19/2023] Open
Abstract
There is a growing piece of evidence that artificial intelligence may be helpful in the entire prostate cancer disease continuum. However, building machine learning algorithms robust to inter- and intra-radiologist segmentation variability is still a challenge. With this goal in mind, several model training approaches were compared: removing unstable features according to the intraclass correlation coefficient (ICC); training independently with features extracted from each radiologist's mask; training with the feature average between both radiologists; extracting radiomic features from the intersection or union of masks; and creating a heterogeneous dataset by randomly selecting one of the radiologists' masks for each patient. The classifier trained with this last resampled dataset presented with the lowest generalization error, suggesting that training with heterogeneous data leads to the development of the most robust classifiers. On the contrary, removing features with low ICC resulted in the highest generalization error. The selected radiomics dataset, with the randomly chosen radiologists, was concatenated with deep features extracted from neural networks trained to segment the whole prostate. This new hybrid dataset was then used to train a classifier. The results revealed that, even though the hybrid classifier was less overfitted than the one trained with deep features, it still was unable to outperform the radiomics model.
Collapse
Affiliation(s)
- Ana Rodrigues
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal.
- Faculty of Medicine, University of Porto, Porto, Portugal.
| | - Nuno Rodrigues
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal
- LASIGE, Faculty of Sciences, University of Lisbon, Lisbon, Portugal
| | - João Santinha
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal
- Instituto Superior Técnico, University of Lisbon, Lisbon, Portugal
| | - Maria V Lisitskaya
- Cand. of Sci. (Med.), Radiologist at Radiology Department with CT and MRI, Medical Research and Educational Center, Lomonosov Moscow State University, Moscow, Russia
| | - Aycan Uysal
- Gulhane Medical School, University of Health Sciences, Ankara, Turkey
| | - Celso Matos
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal
| | - Inês Domingues
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia, Rua Pedro Nunes-Quinta da Nora, 3030-199, Coimbra, Portugal
- Centro de Investigação do Instituto Português de Oncologia do Porto (CI-IPOP): Grupo de Física Médica, Radiobiologia e Protecção Radiológica, Porto, Portugal
| | | |
Collapse
|
9
|
Canellas R, Kohli MD, Westphalen AC. The Evidence for Using Artificial Intelligence to Enhance Prostate Cancer MR Imaging. Curr Oncol Rep 2023; 25:243-250. [PMID: 36749494 DOI: 10.1007/s11912-023-01371-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/14/2022] [Indexed: 02/08/2023]
Abstract
PURPOSE OF REVIEW The purpose of this review is to summarize the current status of artificial intelligence applied to prostate cancer MR imaging. RECENT FINDINGS Artificial intelligence has been applied to prostate cancer MR imaging to improve its diagnostic accuracy and reproducibility of interpretation. Multiple models have been tested for gland segmentation and volume calculation, automated lesion detection, localization, and characterization, as well as prediction of tumor aggressiveness and tumor recurrence. Studies show, for example, that very robust automated gland segmentation and volume calculations can be achieved and that lesions can be detected and accurately characterized. Although results are promising, we should view these with caution. Most studies included a small sample of patients from a single institution and most models did not undergo proper external validation. More research is needed with larger and well-design studies for the development of reliable artificial intelligence tools.
Collapse
Affiliation(s)
- Rodrigo Canellas
- Department of Radiology, University of Washington, 1959 NE Pacific St., 2nd Floor, Seattle, WA, 98195, USA
| | - Marc D Kohli
- Clinical Informatics, Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, 94143, USA.,Imaging Informatics, UCSF Health, 500 Parnassus Ave, 3rd Floor, San Francisco, CA, 94143, USA
| | - Antonio C Westphalen
- Department of Radiology, University of Washington, 1959 NE Pacific St., 2nd Floor, Seattle, WA, 98195, USA. .,Department of Urology, University of Washington, 1959 NE Pacific St., 2nd Floor, Seattle, WA, 98195, USA. .,Department Radiation Oncology, University of Washington, 1959 NE Pacific St., 2nd Floor, Seattle, WA, 98195, USA.
| |
Collapse
|
10
|
Liu X, Tian J, Wu J, Zhang Y, Wang X, Zhang X, Wang X. Utility of diffusion weighted imaging-based radiomics nomogram to predict pelvic lymph nodes metastasis in prostate cancer. BMC Med Imaging 2022; 22:190. [DOI: 10.1186/s12880-022-00905-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Accepted: 09/29/2022] [Indexed: 11/06/2022] Open
Abstract
Abstract
Background
Preoperative pelvic lymph node metastasis (PLNM) prediction can help clinicians determine whether to perform pelvic lymph node dissection (PLND). The purpose of this research is to explore the feasibility of diffusion-weighted imaging (DWI)-based radiomics for preoperative PLNM prediction in PCa patients at the nodal level.
Methods
The preoperative MR images of 1116 pathologically confirmed lymph nodes (LNs) from 84 PCa patients were enrolled. The subjects were divided into a primary cohort (67 patients with 192 positive and 716 negative LNs) and a held-out cohort (17 patients with 43 positive and 165 negative LNs) at a 4:1 ratio. Two preoperative pelvic lymph node metastasis (PLNM) prediction models were constructed based on automatic LN segmentation with quantitative radiological LN features alone (Model 1) and combining radiological and radiomics features (Model 2) via multiple logistic regression. The visual assessments of junior (Model 3) and senior (Model 4) radiologists were compared.
Results
No significant difference was found between the area under the curve (AUCs) of Models 1 and 2 (0.89 vs. 0.90; P = 0.573) in the held-out cohort. Model 2 showed the highest AUC (0.83, 95% CI 0.76, 0.89) for PLNM prediction in the LN subgroup with a short diameter ≤ 10 mm compared with Model 1 (0.78, 95% CI 0.70, 0.84), Model 3 (0.66, 95% CI 0.52, 0.77), and Model 4 (0.74, 95% CI 0.66, 0.88). The nomograms of Models 1 and 2 yielded C-index values of 0.804 and 0.910, respectively, in the held-out cohort. The C-index of the nomogram analysis (0.91) and decision curve analysis (DCA) curves confirmed the clinical usefulness and benefit of Model 2.
Conclusions
A DWI-based radiomics nomogram incorporating the LN radiomics signature with quantitative radiological features is promising for PLNM prediction in PCa patients, particularly for normal-sized LNM.
Collapse
|
11
|
More than Meets the Eye: Using Textural Analysis and Artificial Intelligence as Decision Support Tools in Prostate Cancer Diagnosis—A Systematic Review. J Pers Med 2022; 12:jpm12060983. [PMID: 35743766 PMCID: PMC9225075 DOI: 10.3390/jpm12060983] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2022] [Revised: 06/12/2022] [Accepted: 06/14/2022] [Indexed: 11/30/2022] Open
Abstract
(1) Introduction: Multiparametric magnetic resonance imaging (mpMRI) is the main imagistic tool employed to assess patients suspected of harboring prostate cancer (PCa), setting the indication for targeted prostate biopsy. However, both mpMRI and targeted prostate biopsy are operator dependent. The past decade has been marked by the emerging domain of radiomics and artificial intelligence (AI), with extended application in medical diagnosis and treatment processes. (2) Aim: To present the current state of the art regarding decision support tools based on texture analysis and AI for the prediction of aggressiveness and biopsy assistance. (3) Materials and Methods: We performed literature research using PubMed MeSH, Scopus and WoS (Web of Science) databases and screened the retrieved papers using PRISMA principles. Articles that addressed PCa diagnosis and staging assisted by texture analysis and AI algorithms were included. (4) Results: 359 papers were retrieved using the keywords “prostate cancer”, “MRI”, “radiomics”, “textural analysis”, “artificial intelligence”, “computer assisted diagnosis”, out of which 35 were included in the final review. In total, 24 articles were presenting PCa diagnosis and prediction of aggressiveness, 7 addressed extracapsular extension assessment and 4 tackled computer-assisted targeted prostate biopsies. (5) Conclusions: The fusion of radiomics and AI has the potential of becoming an everyday tool in the process of diagnosis and staging of the prostate malignancies.
Collapse
|
12
|
Urakami A, Arimura H, Takayama Y, Kinoshita F, Ninomiya K, Imada K, Watanabe S, Nishie A, Oda Y, Ishigami K. Stratification of prostate cancer patients into low- and high-grade groups using multiparametric magnetic resonance radiomics with dynamic contrast-enhanced image joint histograms. Prostate 2022; 82:330-344. [PMID: 35014713 DOI: 10.1002/pros.24278] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Revised: 11/09/2021] [Accepted: 11/23/2021] [Indexed: 01/04/2023]
Abstract
PURPOSE This study aimed to investigate the potential of stratification of prostate cancer patients into low- and high-grade groups (GGs) using multiparametric magnetic resonance (mpMR) radiomics in conjunction with two-dimensional (2D) joint histograms computed with dynamic contrast-enhanced (DCE) images. METHODS A total of 101 prostate cancer regions extracted from the MR images of 44 patients were identified and divided into training (n = 31 with 72 cancer regions) and test datasets (n = 13 with 29 cancer regions). Each dataset included low-grade tumors (International Society of Urological Pathology [ISUP] GG ≤ 2) and high-grade tumors (ISUP GG ≥ 3). A total of 137,970 features consisted of mpMR image (16 types of images in four sequences)-based and joint histogram (DCE images at 10 phases)-based features for each cancer region. Joint histogram features can visualize temporally changing perfusion patterns in prostate cancer based on the joint histograms between different phases or subtraction phases of DCE images. Nine signatures (a set of significant features related to GGs) were determined using the best combinations of features selected using the least absolute shrinkage and selection operator. Further, support vector machine models with the nine signatures were built based on a leave-one-out cross-validation for the training dataset and evaluated with receiver operating characteristic (ROC) curve analysis. RESULTS The signature showing the best performance was constructed using six features derived from the joint histograms, DCE original images, and apparent diffusion coefficient maps. The areas under the ROC curves for the training and test datasets were 1.00 and 0.985, respectively. CONCLUSION This study suggests that the proposed approach with mpMR radiomics in conjunction with 2D joint histogram computed with DCE images could have the potential to stratify prostate cancer patients into low- and high-GGs.
Collapse
Affiliation(s)
- Akimasa Urakami
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Hidetaka Arimura
- Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Yukihisa Takayama
- Department of Radiology, Faculty of Medicine, Fukuoka University, Fukuoka, Japan
| | - Fumio Kinoshita
- Department of Anatomic Pathology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Kenta Ninomiya
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Kenjiro Imada
- Department of Urology, Prostate, Kidney, Adrenal Surgery, Kyushu University Hospital, Fukuoka, Japan
| | - Sumiko Watanabe
- Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Akihiro Nishie
- Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Yoshinao Oda
- Department of Anatomic Pathology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Kousei Ishigami
- Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| |
Collapse
|
13
|
Ferro M, de Cobelli O, Musi G, del Giudice F, Carrieri G, Busetto GM, Falagario UG, Sciarra A, Maggi M, Crocetto F, Barone B, Caputo VF, Marchioni M, Lucarelli G, Imbimbo C, Mistretta FA, Luzzago S, Vartolomei MD, Cormio L, Autorino R, Tătaru OS. Radiomics in prostate cancer: an up-to-date review. Ther Adv Urol 2022; 14:17562872221109020. [PMID: 35814914 PMCID: PMC9260602 DOI: 10.1177/17562872221109020] [Citation(s) in RCA: 53] [Impact Index Per Article: 26.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2021] [Accepted: 05/30/2022] [Indexed: 12/24/2022] Open
Abstract
Prostate cancer (PCa) is the most common worldwide diagnosed malignancy in male population. The diagnosis, the identification of aggressive disease, and the post-treatment follow-up needs a more comprehensive and holistic approach. Radiomics is the extraction and interpretation of images phenotypes in a quantitative manner. Radiomics may give an advantage through advancements in imaging modalities and through the potential power of artificial intelligence techniques by translating those features into clinical outcome prediction. This article gives an overview on the current evidence of methodology and reviews the available literature on radiomics in PCa patients, highlighting its potential for personalized treatment and future applications.
Collapse
Affiliation(s)
- Matteo Ferro
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy, via Ripamonti 435 Milano, Italy
| | - Ottavio de Cobelli
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy; Department of Oncology and Hematology-Oncology, Università degli Studi di Milano, Milan, Italy
| | - Gennaro Musi
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy; Department of Oncology and Hematology-Oncology, Università degli Studi di Milano, Milan, Italy
| | - Francesco del Giudice
- Department of Urology, Policlinico Umberto I, Sapienza University of Rome, Rome, Italy
| | - Giuseppe Carrieri
- Department of Urology and Organ Transplantation, University of Foggia, Foggia, Italy
| | - Gian Maria Busetto
- Department of Urology and Organ Transplantation, University of Foggia, Foggia, Italy
| | | | - Alessandro Sciarra
- Department of Urology, Policlinico Umberto I, Sapienza University of Rome, Rome, Italy
| | - Martina Maggi
- Department of Urology, Policlinico Umberto I, Sapienza University of Rome, Rome, Italy
| | - Felice Crocetto
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Biagio Barone
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Vincenzo Francesco Caputo
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Michele Marchioni
- Department of Medical, Oral and Biotechnological Sciences, G. d’Annunzio, University of Chieti, Chieti, Italy; Urology Unit, ‘SS. Annunziata’ Hospital, Chieti, Italy
- Department of Urology, ASL Abruzzo 2, Chieti, Italy
| | - Giuseppe Lucarelli
- Department of Emergency and Organ Transplantation, Urology, Andrology and Kidney Transplantation Unit, University of Bari, Bari, Italy
| | - Ciro Imbimbo
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Francesco Alessandro Mistretta
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy
- Università degli Studi di Milano, Milan, Italy
| | - Stefano Luzzago
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy
- Università degli Studi di Milano, Milan, Italy
| | - Mihai Dorin Vartolomei
- Department of Cell and Molecular Biology, George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Târgu Mures, Târgu Mures, Romania
- Department of Urology, Medical University of Vienna, Vienna, Austria
| | - Luigi Cormio
- Urology and Renal Transplantation Unit, Department of Medical and Surgical Sciences, University of Foggia, Foggia, Italy
- Urology Unit, Bonomo Teaching Hospital, Foggia, Italy
| | | | - Octavian Sabin Tătaru
- Institution Organizing University Doctoral Studies, I.O.S.U.D., George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Târgu Mures, Târgu Mures, Romania
| |
Collapse
|
14
|
Ma M, Gan L, Liu Y, Jiang Y, Xin L, Liu Y, Qin N, Cheng Y, Liu Q, Xu L, Zhang Y, Wang X, Zhang X, Ye J, Wang X. Radiomics features based on automatic segmented MRI images: Prognostic biomarkers for triple-negative breast cancer treated with neoadjuvant chemotherapy. Eur J Radiol 2021; 146:110095. [PMID: 34890936 DOI: 10.1016/j.ejrad.2021.110095] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2021] [Revised: 11/12/2021] [Accepted: 11/30/2021] [Indexed: 12/31/2022]
Abstract
PURPOSE To establish radiomics prediction models based on automatic segmented magnetic resonance imaging (MRI) for predicting the systemic recurrence of triple-negative breast cancer (TNBC) in patients after neoadjuvant chemotherapy (NAC). MATERIALS AND METHODS A total of 147 patients with TNBC who underwent NAC between January 2009 and December 2018 were enrolled in this study. Clinicopathologic data were collected, and the differences between the recurrent and nonrecurrent patients were analyzed by univariate and multivariate analyses. Patients were randomly divided into training and testing sets. The training set consisted of 104 patients (recurrence: 22, nonrecurrence: 82), and the testing set consisted of 43 patients (recurrence: 9, nonrecurrence: 34). To establish the radiomics prediction model, we used a deep learning segmentation model to automatically segment tumor areas on dynamiccontrast-enhanced-MRI images of pre- and post-NAC magnetic resonance examinations. Radiomics features were then extracted from the tumor areas. Three MRI radiomics models were developed in the training set: a radiomics model based on pre-NAC MRI features (model 1), a radiomics model based on post-NAC MRI features (model 2), and a radiomics model based on both pre- and post-NAC MRI features (model 3). A clinical model for predicting systemic recurrence was built in the training set using independent clinical prediction factors. Receiver operating characteristic curve analysis was used to evaluate the performance of the radiomics and clinical models. RESULTS The clinical model yielded areas under the curve (AUCs) of 0.747 in the training set and 0.737 in the testing set in terms of predicting systemic recurrence. Models 1, 2, and 3 yielded AUCs of 0.879, 0.91, and 0.963 in the training set and 0.814, 0.802, and 0.933 in the testing set, respectively, in terms of predicting systemic recurrence. All of the radiomics models had achieved higher AUCs than the clinical model in the testing set. DeLong test was used to compare the AUCs between the models and indicated that the predictive performance of model 3 was better than the clinical model, and the difference was statistically significant (p < 0.05). CONCLUSION The radiomics models built based on the combination of pre- and post-NAC MRI features showed good performance in predicting whether patients with TNBC will have systemic recurrence within 3 years post-NAC. This can help us non-invasively identify which patients are at high risk of recurrence post-NAC, so that we can strengthen follow-up and treatment of these patients. Then the prognosis of these patients might be improved.
Collapse
Affiliation(s)
- Mingming Ma
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Liangyu Gan
- Breast Disease Center, Peking University First Hospital, Beijing, China
| | - Yinhua Liu
- Breast Disease Center, Peking University First Hospital, Beijing, China
| | - Yuan Jiang
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Ling Xin
- Breast Disease Center, Peking University First Hospital, Beijing, China
| | - Yi Liu
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Naishan Qin
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Yuanjia Cheng
- Breast Disease Center, Peking University First Hospital, Beijing, China
| | - Qian Liu
- Breast Disease Center, Peking University First Hospital, Beijing, China
| | - Ling Xu
- Breast Disease Center, Peking University First Hospital, Beijing, China
| | - Yaofeng Zhang
- Beijing Smart Tree Medical Technology Co. Ltd., Beijing, China
| | - Xiangpeng Wang
- Beijing Smart Tree Medical Technology Co. Ltd., Beijing, China
| | - Xiaodong Zhang
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Jingming Ye
- Breast Disease Center, Peking University First Hospital, Beijing, China.
| | - Xiaoying Wang
- Department of Radiology, Peking University First Hospital, Beijing, China.
| |
Collapse
|
15
|
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
|
16
|
Abstract
PURPOSE OF REVIEW The purpose of this review was to identify the most recent lines of research focusing on the application of artificial intelligence (AI) in the diagnosis and staging of prostate cancer (PCa) with imaging. RECENT FINDINGS The majority of studies focused on the improvement in the interpretation of bi-parametric and multiparametric magnetic resonance imaging, and in the planning of image guided biopsy. These initial studies showed that AI methods based on convolutional neural networks could achieve a diagnostic performance close to that of radiologists. In addition, these methods could improve segmentation and reduce inter-reader variability. Methods based on both clinical and imaging findings could help in the identification of high-grade PCa and more aggressive disease, thus guiding treatment decisions. Though these initial results are promising, only few studies addressed the repeatability and reproducibility of the investigated AI tools. Further, large-scale validation studies are missing and no diagnostic phase III or higher studies proving improved outcomes regarding clinical decision making have been conducted. SUMMARY AI techniques have the potential to significantly improve and simplify diagnosis, risk stratification and staging of PCa. Larger studies with a focus on quality standards are needed to allow a widespread introduction of AI in clinical practice.
Collapse
Affiliation(s)
- Pascal A T Baltzer
- Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
| | | |
Collapse
|