دورية أكاديمية
A Comparative Study of Automated Deep Learning Segmentation Models for Prostate MRI.
العنوان: | A Comparative Study of Automated Deep Learning Segmentation Models for Prostate MRI. |
---|---|
المؤلفون: | Rodrigues NM; LASIGE, Faculty of Sciences, University of Lisbon, 1749-016 Lisbon, Portugal.; Champalimaud Foundation, Centre for the Unknown, 1400-038 Lisbon, Portugal., Silva S; LASIGE, Faculty of Sciences, University of Lisbon, 1749-016 Lisbon, Portugal., Vanneschi L; NOVA Information Management School (NOVA IMS), Campus de Campolide, Universidade Nova de Lisboa, 1070-312 Lisboa, Portugal., Papanikolaou N; Champalimaud Foundation, Centre for the Unknown, 1400-038 Lisbon, Portugal. |
المصدر: | Cancers [Cancers (Basel)] 2023 Feb 25; Vol. 15 (5). Date of Electronic Publication: 2023 Feb 25. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: MDPI Country of Publication: Switzerland NLM ID: 101526829 Publication Model: Electronic Cited Medium: Print ISSN: 2072-6694 (Print) Linking ISSN: 20726694 NLM ISO Abbreviation: Cancers (Basel) Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI |
مستخلص: | Prostate cancer is one of the most common forms of cancer globally, affecting roughly one in every eight men according to the American Cancer Society. Although the survival rate for prostate cancer is significantly high given the very high incidence rate, there is an urgent need to improve and develop new clinical aid systems to help detect and treat prostate cancer in a timely manner. In this retrospective study, our contributions are twofold: First, we perform a comparative unified study of different commonly used segmentation models for prostate gland and zone (peripheral and transition) segmentation. Second, we present and evaluate an additional research question regarding the effectiveness of using an object detector as a pre-processing step to aid in the segmentation process. We perform a thorough evaluation of the deep learning models on two public datasets, where one is used for cross-validation and the other as an external test set. Overall, the results reveal that the choice of model is relatively inconsequential, as the majority produce non-significantly different scores, apart from nnU-Net which consistently outperforms others, and that the models trained on data cropped by the object detector often generalize better, despite performing worse during cross-validation. |
References: | IEEE Trans Med Imaging. 2016 Apr;35(4):1077-89. (PMID: 26685226) Sci Rep. 2020 Aug 31;10(1):14315. (PMID: 32868836) CA Cancer J Clin. 2021 May;71(3):209-249. (PMID: 33538338) Strahlenther Onkol. 2020 Oct;196(10):932-942. (PMID: 32221622) Med Image Anal. 2022 Nov;82:102620. (PMID: 36148705) IEEE Trans Med Imaging. 2022 Oct 04;PP:. (PMID: 36194719) Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2018 Sep;11045:3-11. (PMID: 32613207) Entropy (Basel). 2022 Apr 14;24(4):. (PMID: 35455214) IEEE Trans Med Imaging. 2010 Jun;29(6):1310-20. (PMID: 20378467) Comput Biol Med. 2022 Sep 28;150:106124. (PMID: 36208597) Adv Radiat Oncol. 2020 Feb 08;5(3):473-481. (PMID: 32529143) Biomed Tech (Berl). 2022 Nov 04;:. (PMID: 36332194) Nat Methods. 2021 Feb;18(2):203-211. (PMID: 33288961) Med Image Anal. 2022 Apr;77:102347. (PMID: 35085952) Cancers (Basel). 2021 Dec 01;13(23):. (PMID: 34885175) |
معلومات مُعتمدة: | UIDB/00408/2020; UIDP/00408/2020; DSAIPA/DS/0113/2019; 2021/05322/BD. Fundação para a Ciência e Tecnologia |
فهرسة مساهمة: | Keywords: deep learning; prostate cancer; prostate detection; prostate segmentation |
تواريخ الأحداث: | Date Created: 20230311 Latest Revision: 20230313 |
رمز التحديث: | 20240628 |
مُعرف محوري في PubMed: | PMC10001231 |
DOI: | 10.3390/cancers15051467 |
PMID: | 36900261 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2072-6694 |
---|---|
DOI: | 10.3390/cancers15051467 |