Machine Learning and Radiomics of Bone Scintigraphy: Their Role in Predicting Recurrence of Localized or Locally Advanced Prostate Cancer

Yu-De Wang; Chi-Ping Huang; You-Rong Yang; Hsi-Chin Wu; Yu-Ju Hsu; Yi-Chun Yeh; Pei-Chun Yeh; Kuo-Chen Wu; Chia-Hung Kao

doi:10.3390/diagnostics13213380

Machine Learning and Radiomics of Bone Scintigraphy: Their Role in Predicting Recurrence of Localized or Locally Advanced Prostate Cancer

Diagnostics (Basel). 2023 Nov 3;13(21):3380. doi: 10.3390/diagnostics13213380.

Authors

Yu-De Wang^{1

2}, Chi-Ping Huang^{2

3}, You-Rong Yang², Hsi-Chin Wu^{3

4}, Yu-Ju Hsu⁵, Yi-Chun Yeh⁵, Pei-Chun Yeh⁵, Kuo-Chen Wu^{5

6}, Chia-Hung Kao^{1

5

7

8}

Affiliations

¹ Graduate Institute of Biomedical Sciences, School of Medicine, College of Medicine, China Medical University, Taichung 404327, Taiwan.
² Department of Urology, China Medical University Hospital, Taichung 404327, Taiwan.
³ School of Medicine, China Medical University, Taichung 406040, Taiwan.
⁴ Department of Urology, China Medical University Beigang Hospital, Yunlin 651012, Taiwan.
⁵ Artificial Intelligence Center, China Medical University Hospital, Taichung 404327, Taiwan.
⁶ Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 106319, Taiwan.
⁷ Department of Nuclear Medicine and PET Center, China Medical University Hospital, Taichung 404327, Taiwan.
⁸ Department of Bioinformatics and Medical Engineering, Asia University, Taichung 413305, Taiwan.

Abstract

Background: Machine-learning (ML) and radiomics features have been utilized for survival outcome analysis in various cancers. This study aims to investigate the application of ML based on patients' clinical features and radiomics features derived from bone scintigraphy (BS) and to evaluate recurrence-free survival in local or locally advanced prostate cancer (PCa) patients after the initial treatment.

Methods: A total of 354 patients who met the eligibility criteria were analyzed and used to train the model. Clinical information and radiomics features of BS were obtained. Survival-related clinical features and radiomics features were included in the ML model training. Using the pyradiomics software, 128 radiomics features from each BS image's region of interest, validated by experts, were extracted. Four textural matrices were also calculated: GLCM, NGLDM, GLRLM, and GLSZM. Five training models (Logistic Regression, Naive Bayes, Random Forest, Support Vector Classification, and XGBoost) were applied using K-fold cross-validation. Recurrence was defined as either a rise in PSA levels, radiographic progression, or death. To assess the classifier's effectiveness, the ROC curve area and confusion matrix were employed.

Results: Of the 354 patients, 101 patients were categorized into the recurrence group with more advanced disease status compared to the non-recurrence group. Key clinical features including tumor stage, radical prostatectomy, initial PSA, Gleason Score primary pattern, and radiotherapy were used for model training. Random Forest (RF) was the best-performing model, with a sensitivity of 0.81, specificity of 0.87, and accuracy of 0.85. The ROC curve analysis showed that predictions from RF outperformed predictions from other ML models with a final AUC of 0.94 and a p-value of <0.001. The other models had accuracy ranges from 0.52 to 0.78 and AUC ranges from 0.67 to 0.84.

Conclusions: The study showed that ML based on clinical features and radiomics features of BS improves the prediction of PCa recurrence after initial treatment. These findings highlight the added value of ML techniques for risk classification in PCa based on clinical features and radiomics features of BS.

Keywords: bone scintigraphy; machine learning; prostate cancer; radiomics; recurrence.

Grants and funding

This study is supported in part by China Medical University Hospital (DMR-112-072, DMR-112-073). The funders had no role in the study design, data collection, analysis, the decision to publish, or the preparation of the manuscript. No additional external funding was received for this study.