[Clinicopathological Features and Prognosis of Patients Newly Diagnosed With Lung Adenocarcinoma With Both EGFR Mutation and C-MET Amplification].

Objective To explore the clinicopathological features and prognosis of the patients newly diagnosed with lung adenocarcinoma with both EGFR mutation and C-MET amplification.Methods The pathological sections were reviewed.EGFR mutation was detected by amplification refractory mutation system-quantitative real-time polymerase chain reaction,and C-MET amplification by fluorescence in situ hybridization.The clinicopathological features and survival data of the patients newly diagnosed with lung adenocarcinoma with both EGFR mutation and C-MET amplification were analyzed retrospectively.Results In 11 cases of EGFR mutation combined with C-MET amplification,complex glands and solid high-grade components were observed under a microscope in 10 cases except for one case with a cell block,the tissue structure of which was difficult to be evaluated.The incidence of lung adenocarcinoma in the patients with EGFR mutation combined with C-MET amplification at clinical stage Ⅳ was higher than that in the EGFR mutation or C-MET amplification group (all P<0.001),whereas the difference was not statistically significant between the EGFR mutation group and C-MET amplification group at each clinical stage (all P>0.05).There was no significant difference in the trend of survival rate between EGFR gene group and C-MET amplification group (χ2=0.042,P=0.838),while the survival of the patients with EGFR mutation combined with C-MET amplification was worse than that of the patients with EGFR mutation (χ2=246.72,P<0.001) or C-MET amplification (χ2=236.41,P<0.001).Conclusions The patients newly diagnosed with lung adenocarcinoma with EGFR mutation plus C-MET amplification demonstrate poor histological differentiation,rapid progress,and poor prognosis.The patients are often in the advanced stage when being diagnosed with cancer.Attention should be paid to this concurrent adverse driving molecular event in clinical work.With increasing availability,the inhibitors targeting C-MET may serve as an option to benefit these patients in the near future.

Toward Source-Free Cross Tissues Histopathological Cell Segmentation via Target-Specific Finetuning.

Recognition and quantitative analytics of histopathological cells are the golden standard for diagnosing multiple cancers. Despite recent advances in deep learning techniques that have been widely investigated for the automated segmentation of various types of histopathological cells, the heavy dependency on specific histopathological image types with sufficient supervised annotations, as well as the limited access to clinical data in hospitals, still pose significant challenges in the application of computer-aided diagnosis in pathology. In this paper, we focus on the model generalization of cell segmentation towards cross-tissue histopathological images. Remarkably, a novel target-specific finetuning-based self-supervised domain adaptation framework is proposed to transfer the cell segmentation model to unlabeled target datasets, without access to source datasets and annotations. When performed on the target unlabeled histopathological image set, the proposed method only needs to tune very few parameters of the pre-trained model in a self-supervised manner. Considering the morphological properties of pathological cells, we introduce two constraint terms at both local and global levels into this framework to access more reliable predictions. The proposed cross-domain framework is validated on three different types of histopathological tissues, showing promising performance in self-supervised cell segmentation. Additionally, the whole framework can be further applied to clinical tools in pathology without accessing the original training image data. The code and dataset are released at: https://github.com/NeuronXJTU/SFDA-CellSeg.