Research progress of artificial intelligence in pathological subtypes classification and gene expression analysis of lung adenocarcinoma / 中国胸心血管外科临床杂志

@#Lung adenocarcinoma is a prevalent histological subtype of non-small cell lung cancer with different morphologic and molecular features that are critical for prognosis and treatment planning. In recent years, with the development of artificial intelligence technology, its application in the study of pathological subtypes and gene expression of lung adenocarcinoma has gained widespread attention. This paper reviews the research progress of machine learning and deep learning in pathological subtypes classification and gene expression analysis of lung adenocarcinoma, and some problems and challenges at the present stage are summarized and the future directions of artificial intelligence in lung adenocarcinoma research are foreseen.

Advances in the Study of Invasive Non-mucinous Adenocarcinoma with Different Pathological Subtypes / 中国肺癌杂志

Lung cancer is the leading cause of cancer death in the world today, and adenocarcinoma is the most common histopathological type of lung cancer. In May 2021, World Health Organization (WHO) released the 5th edition of the WHO classification of thoracic tumors, which classifies invasive non-mucinous adenocarcinoma (INMA) into lepidic adenocarcinoma, acinar adenocarcinoma, papillary adenocarcinoma, solid adenocarcinoma, and micropapillary adenocarcinoma based on its histological characteristics. These five pathological subtypes differ in clinical features, treatment and prognosis. A complete understanding of the characteristics of these subtypes is essential for the clinical diagnosis, treatment options, and prognosis predictions of patients with lung adenocarcinoma, including recurrence and progression. This article will review the grading system, morphology, imaging prediction, lymph node metastasis, surgery, chemotherapy, targeted therapy and immunotherapy of different pathological subtypes of INMA.
.

Diagnostic value of three-dimensional reconstruction technique in new classification criteria of lung adenocarcinoma / 中国胸心血管外科临床杂志

@#Objective    To evaluate the application value of three-dimensional (3D) reconstruction in preoperative surgical diagnosis of new classification criteria for lung adenocarcinoma, which is helpful to develop a deep learning model of artificial intelligence in the auxiliary diagnosis and treatment of lung cancer. Methods    The clinical data of 173 patients with ground-glass lung nodules with a diameter of ≤2 cm, who were admitted from October 2018 to June 2020 in our hospital were retrospectively analyzed. Among them, 55 were males and 118 were females with a median age of 61 (28-82) years. Pulmonary nodules in different parts of the same patient were treated as independent events, and a total of 181 subjects were included. According to the new classification criteria of pathological types, they were divided into pre-invasive lesions (atypical adenomatous hyperplasia and and adenocarcinoma in situ), minimally invasive adenocarcinoma and invasive adenocarcinoma. The relationship between 3D reconstruction parameters and different pathological subtypes of lung adenocarcinoma, and their diagnostic values were analyzed by multiplanar reconstruction and volume reconstruction techniques. Results    In different pathological types of lung adenocarcinoma, the diameter of lung nodules (P<0.001), average CT value (P<0.001), consolidation/tumor ratio (CTR, P<0.001), type of nodules (P<0.001), nodular morphology (P<0.001), pleural indenlation sign (P<0.001), air bronchogram sign (P=0.010), vascular access inside the nodule (P=0.005), TNM staging (P<0.001) were significantly different, while nodule growth sites were not (P=0.054). At the same time, it was also found that with the increased invasiveness of different pathological subtypes of lung adenocarcinoma, the proportion of dominant signs of each group gradually increased. Meanwhile, nodule diameter and the average CT value or CTR were independent risk factors for malignant degree of lung adenocarcinoma. Conclusion    Imaging signs of lung adenocarcinoma in 3D reconstruction, including nodule diameter, the average CT value, CTR, shape, type, vascular access conditions, air bronchogram sign, pleural indenlation sign, play an important role in the diagnosis of lung adenocarcinoma subtype and can provide guidance for personalized therapy to patients in clinics.

Value of PET/CT Combined with CT Three-dimensional Reconstruction in Distinguishing Different Pathological Subtypes of Early Lung Adenocarcinoma / 中国肺癌杂志

BACKGROUND@#The good prognosis of lepidic predominant invasive adenocarcinoma (LPA) and adenocarcinoma in situ (AIS)/microinvasive adenocarcinoma (MIA) in the pathological subtypes of early lung adenocarcinoma is similar, and the means to distinguish LPA from non-LPA is urgently needed in clinical practice. This study intends to analyze the correlation between positron emission computed tomography (PET)/computed tomography (CT) maximal standard uptake value (SUVmax) with CT three-dimensional reconstruction parameters and the pathological subtypes of early lung adenocarcinoma with part-solid nodules (PSNs) in preoperative imaging.@*METHODS@#The data of early lung adenocarcinoma patients who underwent anatomical pneumonectomy at the Department of Thoracic Surgery of Northern Jiangsu People's Hospital from January 2016 to January 2019 retrospectively analyzed and subsolid nodules on imaging were showed. All patients with enhanced chest CT and PET/CT data can be obtained completely, using Mimics software to perform three-dimensional reconstruction to obtain tumor volume, 3-dimensional mean-CT value (3Dm-CT) of tumor and SUVmax, using SPSS 25.0 for statistical analysis and GraphPad Prism 8.3.0 for drawing receiver operating curve (ROC). P0.7 were included in the multivariate ROC curve analysis, and the joint predictor (AUC=0.835) was obtained with medium or above predictive value.@*CONCLUSIONS@#PET/CT SUVmax and CT three-dimensional reconstruction parameters have a significant correlation with the different pathological subtypes of early lung adenocarcinoma with PSNs in imaging. The combination of SUVmax, tumor volume, ground glass component volume and 3Dm-CT of solid/ground glass component CT value has certain value in identifying the pathological subtype of early stage lung adenocarcinoma with PSNs nodules in imaging.

Differences of CT features for different subtypes of pulmonary neuroendocrine tumors / 实用放射学杂志

Objective To investigate the differences of CT features for different subtypes of pulmonary neuroendocrine tumors (PNETs).Methods CT imaging data of 41 patients with PNETs and 5 patients of lung cancer with neuroendocrine differentiation confirmed by pathology were analyzed retrospectively,and the differences in CT features among pathological subtypes were explored. Results Among the pathological subtypes of 41 PNETs,the statistical differences in the CT features including vascular invasion,the metastatic lymphadenopathy in the hilus and mediastinum were found(P<0.05).However,no differences were found in other imaging findings (lesion location,spiculation,bronchial invasion,atelectasis and obstructive pneumonia,and pleural effusion or thickening)among the subtypes (P>0.05).Among those subtypes PNETs and lung cancer with neuroendocrine differentiation,the differences in tumor size,vascular invasion,and metastatic lymphadenopathy in the hilus and mediastinum were also found (P<0.05).However,no differences were found in other imaging findings (P>0.05).In addition,there were differences in tumor size among different enhancement types and different metastastic presences in the lung or outside of the chest (P<0.05).Conclusion CT shows certain differences among the different subtypes of PNETs,which may be helpful for the differential diagnosis but not specific.