Detecting Adverse Pathology of Prostate Cancer With a Deep Learning Approach Based on a <scp>3D</scp> Swin‐Transformer Model and Biparametric <scp>MRI</scp>: A Multicenter Retrospective Study

Zhao, Litao; Bao, Jie; Wang, Ximing; Qiao, Xiaomeng; Shen, Junkang; Zhang, Yueyue; Jin, Pengfei; Ji, Yanting; Zhang, Ji; Su, Yueting; Ji, Libiao; Li, Zhenkai; Lu, Jian; Hu, Chunhong; Shen, Hailin; Tian, Jie; Liu, Jiangang

doi:10.1002/jmri.28963

Cited by 2 publications

(1 citation statement)

References 38 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A convolutional neural network (CNN) method could have greater individual effectiveness in real image analyses, which are expected to improve CAD in prostate MRIs. The CNN-based DL technique restructures and revolutionizes the present analytic model [9]. The main and real-time modules of medical prostate MRI analyses are diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and apparent diffusion coefficient (ADC) classifications.…”

Section: Introductionmentioning

confidence: 99%

Equilibrium Optimization Algorithm with Deep Learning Enabled Prostate Cancer Detection on MRI Images

Yang,

Shankar,

Kumar

et al. 2023

Biomedicines

View full text Add to dashboard Cite

The enlargement of the prostate gland in the reproductive system of males is considered a form of prostate cancer (PrC). The survival rate is considerably improved with earlier diagnosis of cancer; thus, timely intervention should be administered. In this study, a new automatic approach combining several deep learning (DL) techniques was introduced to detect PrC from MRI and ultrasound (US) images. Furthermore, the presented method describes why a certain decision was made given the input MRI or US images. Many pretrained custom-developed layers were added to the pretrained model and employed in the dataset. The study presents an Equilibrium Optimization Algorithm with Deep Learning-based Prostate Cancer Detection and Classification (EOADL-PCDC) technique on MRIs. The main goal of the EOADL-PCDC method lies in the detection and classification of PrC. To achieve this, the EOADL-PCDC technique applies image preprocessing to improve the image quality. In addition, the EOADL-PCDC technique follows the CapsNet (capsule network) model for the feature extraction model. The EOA is based on hyperparameter tuning used to increase the efficiency of CapsNet. The EOADL-PCDC algorithm makes use of the stacked bidirectional long short-term memory (SBiLSTM) model for prostate cancer classification. A comprehensive set of simulations of the EOADL-PCDC algorithm was tested on the benchmark MRI dataset. The experimental outcome revealed the superior performance of the EOADL-PCDC approach over existing methods in terms of different metrics.

show abstract

Section: Introductionmentioning

confidence: 99%

Equilibrium Optimization Algorithm with Deep Learning Enabled Prostate Cancer Detection on MRI Images

Yang,

Shankar,

Kumar

et al. 2023

Biomedicines

View full text Add to dashboard Cite

show abstract

Editorial for “Detecting Adverse Pathology of Prostate Cancer With a Deep Learning Approach Based on a 3D Swin‐Transformer Model and Biparametric MRI: A Multicenter Retrospective Study”

Adubeiro,

Nogueira

2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

P rostate cancer (PCa) is the second most prevalent cancer among men worldwide. 1 Timely and accurate diagnosis is important to avoid overtreatment of men with indolent, clinically insignificant PCa and to offer radical curative treatment with life-threatening, clinically significant PCa. 2 Radical prostatectomy (RP) has become the standard care for eligible patients because of its cancer control and improved survival. Although most patients remained disease-free after RP, 20%-30% of patients develop recurrence of the disease at follow-up. 3 Therefore, the assessment of reliable prognostic predictors of recurrence after RP is clinically important for guiding clinical decision-making and patient counseling. To date, several factors are considered adverse pathology (AP) features such as preoperative prostate-specific antigen (PSA) levels, Gleason score, tumor stage, surgical margin status, lymph node invasion, extracapsular extension (ECE), and seminal vesicle invasion (SVI). All of them have been identified as prognostic factors for recurrence after RP. 3,4 MRI has an established role in diagnosis of PCa. 5 Due to the complex nature of the PCa diagnosis pathway by MRI, diagnostic performance has varied widely. 6,7 The use of biparametric MRI, excluding dynamic contrast-enhanced (DCE), despite its enormous potential, is still controversial, particularly when there is suboptimal diagnostic quality for T2WI and DWI sequences. 8 Developing artificial intelligence models using machine learning, particularly deep learning, has an expanding role in radiology with great potential in prostate MRI. 9 In this JMRI paper, 10 the authors use a deep learning approach of 3D Swin-Transformer (TransNet) based on biparametric MRI to predicting AP of PCa. An integrated model combining TransNet signature and clinical characteristics (TransCL) has also been developed. These models can provide personalized surgical treatment planning and are very important for clinical decisions.

show abstract

Detecting Adverse Pathology of Prostate Cancer With a Deep Learning Approach Based on a 3D Swin‐Transformer Model and Biparametric MRI: A Multicenter Retrospective Study

Cited by 2 publications

References 38 publications

Equilibrium Optimization Algorithm with Deep Learning Enabled Prostate Cancer Detection on MRI Images

Equilibrium Optimization Algorithm with Deep Learning Enabled Prostate Cancer Detection on MRI Images

Editorial for “Detecting Adverse Pathology of Prostate Cancer With a Deep Learning Approach Based on a 3D Swin‐Transformer Model and Biparametric MRI: A Multicenter Retrospective Study”

Contact Info

Product

Resources

About