RESUMO
PURPOSE: We focus on the problem of scarcity of annotated training data for nucleus recognition in Ki-67 immunohistochemistry (IHC)-stained pancreatic neuroendocrine tumor (NET) images. We hypothesize that deep learning-based domain adaptation is helpful for nucleus recognition when image annotations are unavailable in target data sets. METHODS: We considered 2 different institutional pancreatic NET data sets: one (ie, source) containing 38 cases with 114 annotated images and the other (ie, target) containing 72 cases with 20 annotated images. The gold standards were manually annotated by 1 pathologist. We developed a novel deep learning-based domain adaptation framework to count different types of nuclei (ie, immunopositive tumor, immunonegative tumor, nontumor nuclei). We compared the proposed method with several recent fully supervised deep learning models, such as fully convolutional network-8s (FCN-8s), U-Net, fully convolutional regression network (FCRN) A, FCRNB, and fully residual convolutional network (FRCN). We also evaluated the proposed method by learning with a mixture of converted source images and real target annotations. RESULTS: Our method achieved an F1 score of 81.3% and 62.3% for nucleus detection and classification in the target data set, respectively. Our method outperformed FCN-8s (53.6% and 43.6% for nucleus detection and classification, respectively), U-Net (61.1% and 47.6%), FCRNA (63.4% and 55.8%), and FCRNB (68.2% and 60.6%) in terms of F1 score and was competitive with FRCN (81.7% and 70.7%). In addition, learning with a mixture of converted source images and only a small set of real target labels could further boost the performance. CONCLUSION: This study demonstrates that deep learning-based domain adaptation is helpful for nucleus recognition in Ki-67 IHC stained images when target data annotations are not available. It would improve the applicability of deep learning models designed for downstream supervised learning tasks on different data sets.
Assuntos
Antígeno Ki-67 , Humanos , Imuno-HistoquímicaRESUMO
Quantitative biomarkers are key prognostic and predictive factors in the diagnosis and treatment of cancer. In the clinical laboratory, the majority of biomarker quantitation is still performed manually, but digital image analysis (DIA) methods have been steadily growing and account for around 25% of all quantitative immunohistochemistry (IHC) testing performed today. Quantitative DIA is primarily employed in the analysis of breast cancer IHC biomarkers, including estrogen receptor, progesterone receptor, and human epidermal growth factor receptor 2/neu; more recently clinical applications have expanded to include human epidermal growth factor receptor 2/neu in gastroesophageal adenocarcinomas and Ki-67 in both breast cancer and gastrointestinal and pancreatic neuroendocrine tumors. Evidence in the literature suggests that DIA has significant benefits over manual quantitation of IHC biomarkers, such as increased objectivity, accuracy, and reproducibility. Despite this fact, a number of barriers to the adoption of DIA in the clinical laboratory persist. These include difficulties in integrating DIA into clinical workflows, lack of standards for integrating DIA software with laboratory information systems and digital pathology systems, costs of implementing DIA, inadequate reimbursement relative to those costs, and other factors. These barriers to adoption may be overcome with international standards such as Digital Imaging and Communications in Medicine (DICOM), increased adoption of routine digital pathology workflows, the application of artificial intelligence to DIA, and the emergence of new clinical applications for DIA.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Patologia Clínica/métodos , Humanos , Processamento de Imagem Assistida por Computador/tendências , Patologia Clínica/tendênciasRESUMO
OBJECTIVE: To validate the 2010 American Joint Committee on Cancer (AJCC) and 2006 European Neuroendocrine Tumor Society (ENETS) tumor staging systems for pancreatic neuroendocrine tumors (PanNETs) using the largest, single-institution series of surgically resected patients in the literature. BACKGROUND: The natural history and prognosis of PanNETs have been poorly defined because of the rarity and heterogeneity of these neoplasms. Currently, there are 2 main staging systems for PanNETs, which can complicate comparisons of reports in the literature and thereby hinder progress against this disease. METHODS: Univariate and multivariate analyses were conducted on the prognostic factors of survival using 326 sporadic, nonfunctional, surgically resected PanNET patients who were cared for at our institution between 1984 and 2011. Current and proposed models were tested for survival prognostication validity as measured by discrimination (Harrel's c-index, HCI) and calibration. RESULTS: Five-year overall-survival rates for AJCC stages I, II, and IV are 93% (88%-99%), 74% (65%-83%), and 56% (42%-73%), respectively, whereas ENETS stages I, II, III, and IV are 97% (92%-100%), 87% (80%-95%), 73% (63%-84%), and 56% (42%-73%), respectively. Each model has an HCI of 0.68, and they are no different in their ability to predict survival. We developed a simple prognostic tool just using grade, as measured by continuous Ki-67 labeling, sex, and binary age that has an HCI of 0.74. CONCLUSIONS: Both the AJCC and ENETS staging systems are valid and indistinguishable in their survival prognostication. A new, simpler prognostic tool can be used to predict survival and decrease interinstitutional mistakes and uncertainties regarding these neoplasms.
Assuntos
Tumores Neuroendócrinos/patologia , Nomogramas , Neoplasias Pancreáticas/patologia , Adulto , Idoso , Idoso de 80 Anos ou mais , Técnicas de Apoio para a Decisão , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Análise Multivariada , Gradação de Tumores , Estadiamento de Neoplasias , Tumores Neuroendócrinos/mortalidade , Tumores Neuroendócrinos/cirurgia , Neoplasias Pancreáticas/mortalidade , Neoplasias Pancreáticas/cirurgia , Reprodutibilidade dos Testes , Análise de Sobrevida , Carga TumoralRESUMO
The grading system for pancreatic neuroendocrine tumors (PanNETs) adopted in 2010 by the World Health Organization (WHO) mandates the use of both mitotic rate and Ki67/MIB-1 index in defining the proliferative rate and assigning the grade. In cases when these measures are not concordant for grade, it is recommended to assign the higher grade, but specific data justifying this approach do not exist. Thus, we counted mitotic figures and immunolabeled, using the Ki67 antibody, 297 WHO mitotic grade 1 and 2 PanNETs surgically resected at a single institution. We quantified the Ki67 proliferative index by marking at least 500 cells in "hot spots" and by using digital image analysis software to count each marked positive/negative cell and then compared the results with histologic features and overall survival. Of 264 WHO mitotic grade 1 PanNETs, 33% were WHO grade 2 by Ki67 proliferative index. Compared with concordant grade 1 tumors, grade-discordant tumors were more likely to have metastases to lymph node (56% vs. 34%) (P<0.01) and to distant sites (46% vs. 12%) (P<0.01). Discordant mitotic grade 1 PanNETs also showed statistically significantly more infiltrative growth patterns, perineural invasion, and small vessel invasion. Overall survival was significantly different (P<0.01), with discordant mitotic grade 1 tumors showing a median survival of 12 years compared with 16.7 years for concordant grade 1 tumors. Conversely, mitotic grade 1/Ki67 grade 2 PanNETs showed few significant differences from tumors that were mitotic grade 2 and either Ki67 grade 1 or 2. Our data demonstrate that mitotic rate and Ki67-based grades of PanNETs are often discordant, and when the Ki67 grade is greater than the mitotic grade, clinical outcomes and histopathologic features are significantly worse than concordant grade 1 tumors. Patients with discordant mitotic grade 1/Ki67 grade 2 tumors have shorter overall survival and larger tumors with more metastases and more aggressive histologic features. These data strongly suggest that Ki67 labeling be performed on all PanNETs in addition to mitotic rate determination to define more accurately tumor grade and prognosis.