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 evaluate the prognostic value of a radiomics model based on the peritumoral region of gli- oma． Methods : 138 patients with glioma were retrospectively analyzed ，medical imaging interaction toolkit ( MITK) software was used to obtain the magnetic resonance imaging (MRI) images of peritumoral area 5 mm，10 mm and 20 mm from the tumor edge and extract texture features．The texture features were screened the radiomics model was established and the radiomic score was calculated．A clinical prediction model and a combined predic- tion model along with Rad-score and clinical risk factors were established．The combined prediction model was dis- played as a nomogram，and the predictive performance of the model for survival in glioma patients was evaluated. Results : In the validation set，the C-index value of the radiomics model based on the peritumoral region 10 mm a- way from the tumor edge based on T2 weighted image (T2WI) images was 0. 663 (95% CI = 0. 72－0. 78) ，resul- ting in the best prediction performance．On the training set and validation set，the C-index of the nomogram was 0. 770 and 0. 730，respectively，indicating that the prediction performance of nomogram was better than those of the radiomics model and clinical prediction model．The model had the highest prediction effect on the 3-year survival rate of glioma patients (training set area under curve (AUC) = 0. 93，95% CI = 0. 83 － 0. 98 ; validation set AUC = 0. 88，95% CI = 0. 76 －0. 99) ．The calibration curve showed that the joint prediction nomogram in both the training set and the validation set had good performance． Conclusion The combined prediction model based on the preoperative T2WI images in the peritumoral region 10 mm from the tumor edge and the clinicopathological risk factors can accurately predict the prognosis of glioma，providing the best effect of prediction on the 3-year survival rate of glioma.