Accuracy of machine learning models using ultrasound images in prostate cancer diagnosis
Keywords:
Accuracy, machine learning models,, ultrasound images, prostate cancer diagnosisAbstract
Background: The literature on the accuracy of machine learning models using ultrasound images in prostate cancer diagnosis reveals a dynamic landscape marked by both significant advancements and persistent challenges. The introduction establishes the importance of integrating machine learning with ultrasound imaging to improve diagnostic precision, particularly in a domain fraught with high stakes due to the complexities associated with prostate cancer. The initial studies highlight the potential of machine learning to standardize interpretations, as evidenced by the comparative analysis of labeling strategies that demonstrated superior performance with digital pathologist annotations over radiologist labels (Bhattacharya et al., 2021). Literature Review: As the review progresses, it becomes clear that traditional ultrasound imaging faces limitations, such as low resolution and high inter-observer variability, which can compromise diagnostic accuracy (Akatsuka et al., 2022). The literature advocates for the application of artificial intelligence (AI) technologies to enhance the reliability of cancer grading, emphasizing the critical role of accurate pathological grading in treatment decision-making. Further analysis reveals a growing body of work focused on the integration of advanced machine learning techniques, including deep learning and hybrid models that combine traditional and innovative approaches (Luijten et al., 2022). Conclusion: In conclusion, the literature collectively underscores the transformative potential of machine learning and deep learning techniques in enhancing the accuracy of prostate cancer diagnosis using ultrasound images. Despite the promising advancements, the field faces critical challenges, particularly regarding the need for robust datasets, the integration of AI into clinical practice, and the necessity for standardized evaluation criteria. Addressing these challenges will be pivotal in realizing the full potential of AI technologies in improving diagnostic outcomes and patient management in prostate cancer.
References
Bhattacharya, I., S. Lim, D., Lin Aung, H., Liu, X., Seetharaman, A., A. Kunder, C., Shao, W., J. C. Soerensen, S., E. Fan, R., Ghanouni, P., J. To'o, K., D. Brooks, J., A. Sonn, G., & Rusu, M., 2021. Bridging the gap between prostate radiology and pathology through machine learning. [PDF]
Akatsuka, J., Numata, Y., Morikawa, H., Sekine, T., Kayama, S., Mikami, H., Yanagi, M., Endo, Y., Takeda, H., Toyama, Y., Yamaguchi, R., Kimura, G., Kondo, Y., & Yamamoto, Y., 2022. A data-driven ultrasound approach discriminates pathological high grade prostate cancer. ncbi.nlm.nih.gov
Li, H., Hung Lee, C., Chia, D., Lin, Z., Huang, W., & Heng Tan, C., 2022. Machine Learning in Prostate MRI for Prostate Cancer: Current Status and Future Opportunities. ncbi.nlm.nih.gov
Luijten, B., Chennakeshava, N., C. Eldar, Y., Mischi, M., & J. G. van Sloun, R., 2022. Ultrasound Signal Processing: From Models to Deep Learning. [PDF]
Hashem, H., Alsakar, Y., Elgarayhi, A., Elmogy, M., & Sallah, M., 2022. An Enhanced Deep Learning Technique for Prostate Cancer Identification Based on MRI Scans. [PDF]
Yin, H. & Buduma, N., 2022. Prostate Lesion Detection and Salient Feature Assessment Using Zone-Based Classifiers. [PDF]
Bhattacharya, I., S. Khandwala, Y., Vesal, S., Shao, W., Yang, Q., J.C. Soerensen, S., E. Fan, R., Ghanouni, P., A. Kunder, C., D. Brooks, J., Hu, Y., Rusu, M., & A. Sonn, G., 2022. A review of artificial intelligence in prostate cancer detection on imaging. ncbi.nlm.nih.gov
Bechelli, S., 2022. Computer-Aided Cancer Diagnosis via Machine Learning and Deep Learning: A comparative review. [PDF]
Baek, J., M O’Connell, A., & J Parker, K., 2022. Improving breast cancer diagnosis by incorporating raw ultrasound parameters into machine learning. ncbi.nlm.nih.gov
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Christine, Fransiska (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors publishing here keep copyright but grant the journal first publication rights, under a Creative Commons Attribution-NonCommercial 4.0 License. They can distribute their work non-exclusively elsewhere with an acknowledgment of its first publication in this journal. Posting the work online before and during submission for earlier and greater citation is encouraged, reflecting Open Access benefits.
