A Deep Learning Model for Prostate Adenocarcinoma Classification in Needle Biopsy Whole-Slide Images Using Transfer Learning.

A Deep Learning Model for Prostate Adenocarcinoma Classification in Needle Biopsy Whole-Slide Images Using Transfer Learning.
复制标题

DOI:
10.3390/diagnostics12030768
复制
发表时间:
2022-03-21
期刊:
Diagnostics (Basel, Switzerland)
影响因子:
--
通讯作者:
Kanavati F
Kanavati F
中科院分区:
其他
文献类型:
--
作者:
Tsuneki M;Abe M;Kanavati F

文献摘要

参考文献

被引文献

相似文献

穿刺活检标本中前列腺腺癌的组织病理学诊断对于确定最佳前列腺癌治疗至关重要。由于病理学家使用显微镜诊断大量包含12个核心活检标本的病例是耗时的手动系统,并且人力资源有限,因此有必要开发能够快速、准确地筛选大量组织病理学前列腺穿刺活检标本的新技术。计算病理学应用可以帮助病理学家从全幻灯片图像(WSI)中检测和分类前列腺腺癌,这对于常规病理实践将大有裨益。在本文中,我们训练了能够将穿刺活检 WSI 分类为腺癌和良性(非肿瘤)病变的深度学习模型。我们在针刺活检、经尿道前列腺电切术 (TUR-P) 和癌症基因组图谱 (TCGA) 公共数据集测试集上评估了模型,在针刺活检测试集中实现了高达 0.978 的 ROC-AUC,在腺癌的 TCGA 测试集中实现了高达 0.9873 的 ROC-AUC。
The histopathological diagnosis of prostate adenocarcinoma in needle biopsy specimens is of pivotal importance for determining optimum prostate cancer treatment. Since diagnosing a large number of cases containing 12 core biopsy specimens by pathologists using a microscope is time-consuming manual system and limited in terms of human resources, it is necessary to develop new techniques that can rapidly and accurately screen large numbers of histopathological prostate needle biopsy specimens. Computational pathology applications that can assist pathologists in detecting and classifying prostate adenocarcinoma from whole-slide images (WSIs) would be of great benefit for routine pathological practice. In this paper, we trained deep learning models capable of classifying needle biopsy WSIs into adenocarcinoma and benign (non-neoplastic) lesions. We evaluated the models on needle biopsy, transurethral resection of the prostate (TUR-P), and The Cancer Genome Atlas (TCGA) public dataset test sets, achieving an ROC-AUC up to 0.978 in needle biopsy test sets and up to 0.9873 in TCGA test sets for adenocarcinoma.
DOI: 10.3390/cancers13215368
发表时间: 2021-10-26
期刊: Cancers
影响因子: 5.2
作者:
Kanavati F;Tsuneki M
通讯作者: Tsuneki M
DOI: 10.1038/s41598-020-66333-x
发表时间: 2020-06-09
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Kanavati, Fahdi;Toyokawa, Gouji;Tsuneki, Masayuki
通讯作者: Tsuneki, Masayuki
深度学习用于自动格里森模式分类,以确定前列腺活检的等级组别
DOI: 10.1007/s00428-019-02577-x
发表时间: 2019-07-01
期刊: VIRCHOWS ARCHIV
影响因子: 3.5
作者:
Lucas, Marit;Jansen, Ilaria;Marquering, Henk A.
通讯作者: Marquering, Henk A.
DOI: 10.3390/s21206708
发表时间: 2021-10-09
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
Hammouda K;Khalifa F;El-Melegy M;Ghazal M;Darwish HE;Abou El-Ghar M;El-Baz A
通讯作者: El-Baz A
DOI: 10.1002/path.5662
发表时间: 2021-06
期刊: The Journal of pathology
影响因子: --
作者:
da Silva LM;Pereira EM;Salles PG;Godrich R;Ceballos R;Kunz JD;Casson A;Viret J;Chandarlapaty S;Ferreira CG;Ferrari B;Rothrock B;Raciti P;Reuter V;Dogdas B;DeMuth G;Sue J;Kanan C;Grady L;Fuchs TJ;Reis-Filho JS
通讯作者: Reis-Filho JS