Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images
Abstract Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classifica...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-49159-1 |
| _version_ | 1797398030246215680 |
|---|---|
| author | Te-Li Huang Nan-Han Lu Yung-Hui Huang Wen-Hung Twan Li-Ren Yeh Kuo-Ying Liu Tai-Been Chen |
| author_facet | Te-Li Huang Nan-Han Lu Yung-Hui Huang Wen-Hung Twan Li-Ren Yeh Kuo-Ying Liu Tai-Been Chen |
| author_sort | Te-Li Huang |
| collection | DOAJ |
| description | Abstract Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden’s index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications. |
| first_indexed | 2024-03-09T01:18:50Z |
| format | Article |
| id | doaj.art-a7bfc4cd71174297877422bc15366d9f |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T01:18:50Z |
| publishDate | 2023-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a7bfc4cd71174297877422bc15366d9f2023-12-10T12:18:07ZengNature PortfolioScientific Reports2045-23222023-12-011311910.1038/s41598-023-49159-1Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound imagesTe-Li Huang0Nan-Han Lu1Yung-Hui Huang2Wen-Hung Twan3Li-Ren Yeh4Kuo-Ying Liu5Tai-Been Chen6Department of Radiology, Kaohsiung Veterans General HospitalDepartment of Medical Imaging and Radiological Science, I-Shou UniversityDepartment of Medical Imaging and Radiological Science, I-Shou UniversityDepartment of Life Sciences, National Taitung UniversityDepartment of Anesthesiology, E-DA Cancer Hospital, I-Shou UniversityDepartment of Radiology, E-DA Hospital, I-Shou UniversityDepartment of Medical Imaging and Radiological Science, I-Shou UniversityAbstract Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden’s index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.https://doi.org/10.1038/s41598-023-49159-1 |
| spellingShingle | Te-Li Huang Nan-Han Lu Yung-Hui Huang Wen-Hung Twan Li-Ren Yeh Kuo-Ying Liu Tai-Been Chen Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images Scientific Reports |
| title | Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images |
| title_full | Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images |
| title_fullStr | Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images |
| title_full_unstemmed | Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images |
| title_short | Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images |
| title_sort | transfer learning with cnns for efficient prostate cancer and bph detection in transrectal ultrasound images |
| url | https://doi.org/10.1038/s41598-023-49159-1 |
| work_keys_str_mv | AT telihuang transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages AT nanhanlu transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages AT yunghuihuang transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages AT wenhungtwan transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages AT lirenyeh transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages AT kuoyingliu transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages AT taibeenchen transferlearningwithcnnsforefficientprostatecancerandbphdetectionintransrectalultrasoundimages |