VISTA: VIsual Semantic Tissue Analysis for pancreatic disease quantification in murine cohorts.
VISTA: VIsual Semantic Tissue Analysis for pancreatic disease quantification in murine cohorts.
复制标题
DOI：
10.1038/s41598-020-78061-3
复制
发表时间：
2020-12-01
影响因子：
4.6
通讯作者：
Chang YH
中科院分区：
文献类型：
--
作者：
Ternes L;Huang G;Lanciault C;Thibault G;Riggers R;Gray JW;Muschler J;Chang YH
使用动物模型的机制性疾病进展研究需要客观和可量化的组织病理学评估。目前的定量在很大程度上依赖于染色方法，这些方法可能是昂贵的，劳动/时间密集的，在实验室和批次之间不一致的，并且产生不均匀的染色，容易引起误解和研究者偏见。我们开发了一种利用深度学习的自动语义分割工具，用于仅依赖于苏木精和伊红染色的胰腺组织切片快速客观地量化组织学特征。该工具分割正常腺泡结构、腺泡-导管化生（ADM）的导管表型和发育异常，Dice系数分别为0.79、0.70和0.79。为了处理不准确的逐像素手动注释，还使用淀粉酶和泛角蛋白的免疫染色平均结构相似性指数（SSIM）分别为0.925和0.920，针对生物真实性评估了预测准确性。我们的工具的疾病区域定量与免疫染色标记物（DAPI、淀粉酶和细胞角蛋白;斯皮尔曼相关性评分= 0.86、0.97和0.92）在未见过的数据集中的定量相关（n = 25）。此外，我们的工具区分ADM与异型增生，这是不可靠的区分与免疫染色，并证明了普遍性跨鼠队列胰腺疾病。我们量化了具有致癌Kras驱动疾病的小鼠队列的组织学特征丰度的变化，并且预测符合生物学预期，显示基质扩张，正常腺泡组织减少，以及随着疾病进展ADM和发育不良增加。我们的工具有望加速和改善动物研究中胰腺疾病的量化，并成为跨实验室的统一量化工具。
Mechanistic disease progression studies using animal models require objective and quantifiable assessment of tissue pathology. Currently quantification relies heavily on staining methods which can be expensive, labor/time-intensive, inconsistent across laboratories and batch, and produce uneven staining that is prone to misinterpretation and investigator bias. We developed an automated semantic segmentation tool utilizing deep learning for rapid and objective quantification of histologic features relying solely on hematoxylin and eosin stained pancreatic tissue sections. The tool segments normal acinar structures, the ductal phenotype of acinar-to-ductal metaplasia (ADM), and dysplasia with Dice coefficients of 0.79, 0.70, and 0.79, respectively. To deal with inaccurate pixelwise manual annotations, prediction accuracy was also evaluated against biological truth using immunostaining mean structural similarity indexes (SSIM) of 0.925 and 0.920 for amylase and pan-keratin respectively. Our tool’s disease area quantifications were correlated to the quantifications of immunostaining markers (DAPI, amylase, and cytokeratins; Spearman correlation score = 0.86, 0.97, and 0.92) in unseen dataset (n = 25). Moreover, our tool distinguishes ADM from dysplasia, which are not reliably distinguished with immunostaining, and demonstrates generalizability across murine cohorts with pancreatic disease. We quantified the changes in histologic feature abundance for murine cohorts with oncogenic Kras-driven disease, and the predictions fit biological expectations, showing stromal expansion, a reduction of normal acinar tissue, and an increase in both ADM and dysplasia as disease progresses. Our tool promises to accelerate and improve the quantification of pancreatic disease in animal studies and become a unifying quantification tool across laboratories.
登录
查看更多内容
从胰腺内肿瘤中向胰腺导管腺癌的进展：模拟模型的结果。
影响因子：
3.6
作者：
Peters, Mary Linton B.;Eckel, Andrew;Mueller, Peter P.;Tramontano, Angela C.;Weaver, Davis T.;Lietz, Anna;Hur, Chin;Kong, Chung Yin;Pandharipande, Pan, V
通讯作者：
Pandharipande, Pan, V
DOI：
10.1109/jbhi.2020.2975151
发表时间：
2021-02-01
影响因子：
7.7
作者：
Lahiani, Amal;Klaman, Irina;Klaiman, Eldad
通讯作者：
Klaiman, Eldad
影响因子：
3.3
作者：
Franc, B;De la Salmonière, P;Chastang, C
通讯作者：
Chastang, C
影响因子：
2.4
作者：
Schau, Geoffrey F.;Burlingame, Erik A.;Chang, Young H.
通讯作者：
Chang, Young H.
影响因子：
4.6
作者：
Burlingame EA;McDonnell M;Schau GF;Thibault G;Lanciault C;Morgan T;Johnson BE;Corless C;Gray JW;Chang YH
通讯作者：
Chang YH