With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

Objective:To propose a model using the maximum intensity projection (MIP) of lung field computed tomography (CT) images and deep convolution neural network (CNN) and explore its value in identifying chronic obstructive pulmonary disease (COPD).Methods:A total of 201 subjects were selected from the Second Hospital of Dalian Medical University from January 2010 to May 2021. All subjects were included according to the inclusion criteria and were divided into COPD group (101 cases) and healthy controls group (100 cases). Each patient underwent a high-resolution CT scan of the chest and pulmonary function test. First, the lung field was extracted from CT images and the intrapulmonary MIP images were acquired. Second, with these MIP images as input, the model for identifying COPD was constructed based on a modified residual network (ResNet). Finally, the influence of the number of residual blocks on the performance of the models was investigated. Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to evaluate the identification efficiency.Results:The accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) of ResNet26 was 76.1%, 76.2%, 76.0%, 76.2%, and 76.0%, respectively; and the AUC of the test was 0.855 (95% CI: 0.799-0.901). The accuracy, sensitivity, specificity, PPV, NPV of ResNet50 was 77.6%, 76.2%, 79.0%, 78.6%, and 76.7%, respectively; and the AUC of the test was 0.854 (95% CI: 0.797-0.900). The accuracy, sensitivity, specificity, PPV, NPV of ResNet26d was 82.1%, 83.2%, 81.0%, 81.6%, and 82.7%, respectively; and the AUC of the test was 0.885 (95% CI: 0.830-0.926). Conclusions:The COPD identification model via MIP images from CT images within the lung and deep CNN is successfully constructed and achieves accurate COPD identification. And it can provide an effective tool for COPD screening.

Objective:To investigate the value of net water uptake (NWU) in predicting malignant edema (ME) in large hemispheric infarction (LHI).Methods:Fifty-six patients suffering from LHI in the General Hospital of Northern Theater Command from September 2017 to July 2018 were retrospectively analyzed, and their NWU was calculated separately. Patients were divided into two groups according to the occurrence of ME, which was defined as space-occupying infarct requiring decompressive craniectomy or death resulting from cerebral hernia in seven days from onset. The clinical characteristics were analyzed, and receiver operating characteristic (ROC) curve and respective area under curve (AUC) were used to assess the value of NWU and other factors.Results:After adjusting for atrial fibrillation, National Institutes of Health Stroke Scale scores at admission, and time from onset to imaging, multivariable analysis showed that NWU was an independent predictor of ME ( OR=1.226，95% CI 1.040-1.446, P=0.015). According to the ROC curve, NWU≥13.08% identified ME with great predictive power (AUC=0.813;sensitivity 0.64, specificity 0.94). Conclusions:NWU is an important predictor of ME in patients with LHI. It can help identify patients at risk of ME.

Objective To establish the MCF-7 cell models of Beclin 1 over-and low-expressions,and to detect the autophagic and apoptotic changes after 4 Gy irradiation,and to explore their molecular regulation mechanisms. Methods MCF-7,MCF-7 + 4Gy,MCF-7-Beclin 1 + 4Gy and MCF-7-Belcin 1 RNAi+ 4Gy groups were set up. Molecular biology method was used to construct Beclin 1 over-expression vector pcDNA3.1-Beclin 1,and to estabilish the Beclin 1 over- and low-expression cell models.After the cells were irradiated with 4 Gy, the autopahgic cell percentages were measured by fluorescence microscope with MDC staining, the apoptotic cell percentages were measured by FCM with AnnexinⅤ-FITC and PI staining,and the expressions of Beclin1,P53, Bcl-2 and Bax proteins were measured by Western blotting method.Results Compared with MCF-7 group,the autophagic and apoptotic cell percentages in MCF-7+4 Gy,MCF-7 Beclin 1 +4 Gy and MCF-7-Beclin 1 RNAi+4 Gy groups were significantly increased (P <0.05 or P <0.001 ),especially in MCF-7 Beclin 1+4 Gy group which was significantly higher than those in MCF-7 + 4 Gy (P < 0.05);while there was significant difference in the necrotic cell percentages between various groups. After 4 Gy irradiation, compared with MCF-7 group, the expression levels of Beclin 1,P53 and Bax proteins in MCF-7 + 4 Gy and MCF-7-Beclin 1 + 4 Gy groups were increased,but the expression levels of Bcl-2 protein were decreased,especially in MCF-7-Beclin 1 + 4 Gy group. Conclusion The MCF-7 cell models of Beclin 1 over-and low-expressions are successfully established,and ionizing radiation could induce the autophagy and apoptosis of MCF-7 cells,which is more obvious in Beclin 1 over-expression MCF-7 cells.Beclin 1 can activate P53,inhibit Bcl-2 and activate Bax,which forms the regulation of autophagy and apoptosis by P53 .

Objective To detect the inhibiting effects of ionizing radiation combined with inhibitors or inducer of autophagy and apoptosis on MCF7 cell line,and to provide the evidence for human breast cancer therapy radiation.Methods MCF7 cells were exposed to X-rays and randomly divided into 4 groups,including 0 Gy,4 Gy,4 Gy+rapamycin,4 Gy+3-MA,and 4 Gy+z-VAD-fmk groups,including 0 Gy,4 Gy,4 Gy+rapamycin,4 Gy+3-MA,and 4 Gy+z-VAD-fmk groups,respectively.The growth doubling time was calculated by MTT method.The specific protein expressions of LC3 autophagy and beclinl were detected by using Western blot and the difference of Drotein contents wasLC3 autophagy and beclinl were detected by using Western blot and the difference of Drotein contents was compared.The percentage of apoptosis of MCF7 cells was measured by flow cytometry (FCM).Resuits The growth doubling time of MCF7 cells in 4 Gy group wag longer than that in O Gy group(t=4.41,P