Next Article in Journal
Deciphering the Role of Cancer Stem Cells: Drivers of Tumor Evolution, Therapeutic Resistance, and Precision Medicine Strategies
Next Article in Special Issue
Multi-Modal Machine Learning for Evaluating the Predictive Value of Pelvimetric Measurements (Pelvimetry) for Anastomotic Leakage After Restorative Low Anterior Resection
Previous Article in Journal
E. coli Biomolecules Increase Glycolysis and Invasive Potential in Lung Adenocarcinoma
Previous Article in Special Issue
The Thermal Ablation with MRgFUS: From Physics to Oncological Applications
 
 
Article
Peer-Review Record

Retrospectively Quantified T2 Improves Detection of Clinically Significant Peripheral Zone Prostate Cancer

Cancers 2025, 17(3), 381; https://doi.org/10.3390/cancers17030381
by Haoran Sun 1,2, Lixia Wang 1, Timothy Daskivich 3, Shihan Qiu 1,2, Hsu-Lei Lee 1, Chang Gao 4, Rola Saouaf 5, Eric Lo 3, Alessandro D’Agnolo 6, Hyung Kim 3, Debiao Li 1,2,* and Yibin Xie 1,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Cancers 2025, 17(3), 381; https://doi.org/10.3390/cancers17030381
Submission received: 3 January 2025 / Revised: 21 January 2025 / Accepted: 22 January 2025 / Published: 24 January 2025
(This article belongs to the Special Issue Medical Imaging and Artificial Intelligence in Cancer)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this study, the authors focused on the added value of retrospective T2 mapping by comparing and combining the estimated T2 maps with conventional T2-weighted images in radiomics.

The retrospective single-center analysis comprised 61 consecutive patients (50 csPCa lesions and 26 ciPCa lesions). These were predominantly low- or intermediate (6 or 7 (3+4)) and PIRADS 4 lesions that were enrolled. Please comment on that further, as mpMRI efficacy is mainly associated with the aggressivenes of the disease. How it may affect your model accuracy?

Interesingly, no features from DWI and ADC were included in the development of the radiomics models. Please develop this issue furhter in the discussion rather then just mention in the limitations.

As you stated that the model improves the prediction of peripheral zone csPCa aggressiveness, please futher comment how it can be implemented in clinical practice?

Author Response

Thank you for your comments. Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The authors examined the value of estimated T2 maps produced by a deep-learning network in prostate multiparametric MRI (mpMRI) for detecting clinically significant prostate cancer (csPCa).

            Some comments are listed below.

1.     The authors could consider using the developed radiomics model of mpMRI +PSA or other clinical characteristics to increase the accuracy in the diagnosis of csPCa.

2.     In the discussion, the authors could compare the advantages and disadvantages of the developed radiomics model of mpMRI with PET MRI.

3.     Provide the full name of the abbreviation in the legends of figures and tables.

4.     Reference 5 is old. Are there any additional papers that support the authors’ conclusion?

Author Response

Thank you for your comments. Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop