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*

Opioid analgesics are currently known as the best analgesics. However， toxicity and side effects such as constipation， tolerance and addiction severely limit their clinical application. With the in-depth understanding of the signal transduction mechanism of opioid receptors and the continuous advancement of drug design technology， researchers have managed to develop many promising new methods to get low-toxic and more efficient opioid analgesics， which are different from the traditional morphine skeleton structure modifications. This article focuses on three new research strategies of G-protein biased activation，“ one drug-multiple targets” and peripheral activation. The basic principles of relative separation of analgesic activity and adverse drug reaction by each strategy are introduced， and the latest research progress of representative drugs is briefly reviewed. Among them， the recently approved novel opioid analgesics oliceridine and tegileridine are G-protein biased μ-opioid receptor agonists， Cebranopadol is a typical “one drug-multiple targets” analgesic， and NFEPP is a representative drug of peripheral opioid receptor agonists. The above several strategies complement each other and provide reference for the development of new opioid analgesic drugs.

Objective:To explore the feasibility of applying ArcherQA to independent dose verification of MR-guided online adaptive radiotherapy (ART) plans performed on Elekta Unity 1.5 Tesla (T) magnetic resonance-linear accelerator (MR-Linac).Methods:The dose calculation accuracy of ArcherQA under a specific magnetic field was validated using a homogeneous water phantom. A total of 32 patients who received MR-guided online ART on Elekta Unity were randomly selected by lottery, with 32 offline plans and 177 online plans for five treatment sites (brain, mediastinum, liver, kidney, and vertebral body) enrolled. Finally, the γ pass rates (threshold: 10%; criteria: 3 mm/3% and 2 mm/2%) were compared among the result upon independent dose verification of ArcherQA, measurements of ArcCheck, and calculations using the Monaco treatment planning system (TPS) to quantitatively evaluate the accuracy and efficiency of ArcherQA in independent dose verification of online plans on Elekta Unity.Results:ArcherQA was proven accurate in calculating the dose distribution of therapeutic photon beams under the specific magnetic field. With the 3 mm/3% criterion, the γ pass rates of verification result exceeded 99% in all square fields of a water phantom. Under the stricter 2 mm/2% criterion, the γ pass rates also surpassed 95% in all square fields except 20 cm × 20 cm field. Regarding the verification of treatment plans, the ArcherQA result were found to be highly consistent with those measured or calculated using ArcCheck and Monaco TPS, with the average γ pass rates exceeding 99% under the 3 mm/3% criterion and above 97% under the 2 mm/2% criterion. ArcherQA was acceptably efficient for independent dose verification of online plans, with 50 to 150 s, (108 s on average) required to complete the independent dose verification of 177 online plans.Conclusions:ArcherQA allows for accurately and efficiently calculating the dose distribution of therapeutic photon beams under a specific magnetic field, establishing it as an effective supplementary tool for independent dose calculation of MR-guided offline and online ART plans, thereby ensuring the safety of patient treatment plans.

Schwann cells (SCs), a type of glial cell in the peripheral nervous system, can serve as a source of mesenchymal stem cells (MSCs) to repair injured pulp. This study aimed to investigate the role of SCs in tooth germ development and repair of pulp injury. We performed RNA-seq and immunofluorescent staining on tooth germs at different developmental stages. The effect of L-type calcium channel (LTCC) blocker nimodipine on SCs odontogenic differentiation was analyzed by real-time polymerase chain reaction and Alizarin Red S staining. We used the PLP1-CreERT2/ Rosa26-GFP tracing mice model to examine the role of SCs and Cav 1.2 in self-repair after pulp injury. SC-specific markers expressed in rat tooth germs at different developmental stages. Nimodipine treatment enhanced mRNA levels of osteogenic markers (DSPP, DMP1, and Runx2) but decreased calcium nodule formation. SCs-derived cells increased following pulp injury and Ca v 1.2 showed a similar response pattern as SCs. The different SCs phenotypes are coordinated in the whole process to ensure tooth development. Blocking the LTCC with nimodipine promoted SCs odontogenic differentiation. Moreover, SCs participate in the process of injured dental pulp repair as a source of MSCs, and Cav 1.2 may regulate this process.

Schwann cells (SCs), a type of glial cell in the peripheral nervous system, can serve as a source of mesenchymal stem cells (MSCs) to repair injured pulp. This study aimed to investigate the role of SCs in tooth germ development and repair of pulp injury. We performed RNA-seq and immunofluorescent staining on tooth germs at different developmental stages. The effect of L-type calcium channel (LTCC) blocker nimodipine on SCs odontogenic differentiation was analyzed by real-time polymerase chain reaction and Alizarin Red S staining. We used the PLP1-CreERT2/ Rosa26-GFP tracing mice model to examine the role of SCs and Cav 1.2 in self-repair after pulp injury. SC-specific markers expressed in rat tooth germs at different developmental stages. Nimodipine treatment enhanced mRNA levels of osteogenic markers (DSPP, DMP1, and Runx2) but decreased calcium nodule formation. SCs-derived cells increased following pulp injury and Ca v 1.2 showed a similar response pattern as SCs. The different SCs phenotypes are coordinated in the whole process to ensure tooth development. Blocking the LTCC with nimodipine promoted SCs odontogenic differentiation. Moreover, SCs participate in the process of injured dental pulp repair as a source of MSCs, and Cav 1.2 may regulate this process.

Schwann cells (SCs), a type of glial cell in the peripheral nervous system, can serve as a source of mesenchymal stem cells (MSCs) to repair injured pulp. This study aimed to investigate the role of SCs in tooth germ development and repair of pulp injury. We performed RNA-seq and immunofluorescent staining on tooth germs at different developmental stages. The effect of L-type calcium channel (LTCC) blocker nimodipine on SCs odontogenic differentiation was analyzed by real-time polymerase chain reaction and Alizarin Red S staining. We used the PLP1-CreERT2/ Rosa26-GFP tracing mice model to examine the role of SCs and Cav 1.2 in self-repair after pulp injury. SC-specific markers expressed in rat tooth germs at different developmental stages. Nimodipine treatment enhanced mRNA levels of osteogenic markers (DSPP, DMP1, and Runx2) but decreased calcium nodule formation. SCs-derived cells increased following pulp injury and Ca v 1.2 showed a similar response pattern as SCs. The different SCs phenotypes are coordinated in the whole process to ensure tooth development. Blocking the LTCC with nimodipine promoted SCs odontogenic differentiation. Moreover, SCs participate in the process of injured dental pulp repair as a source of MSCs, and Cav 1.2 may regulate this process.

Objective:To analyze the dosimetric effects on off-center tumour treatment plan resulting from the MR-Linac-based isocenter position radiotherapy plan.Methods:The cases of 19 patients who were treated in Sun Yat-sen University Cancer Center in 2020 were collected in this study. Two different IMRT plans were designed for each patient with off-center tumor both for group A with planned isocenter position as IMRT and group B with planed target center position as geometric center. The conformity index and homogeneity index of target, the dose normal tissue and the number of MU were compared between two plans.Results:The two IMRT plans met clinical dosimetric requirements. No statistical differences were found both in homogeneity index and conformity index ( P>0.05). Also there was no differences found in doses to normal tissues. However, the MU number (1 149±903, t=2.804, P=0.012) in group A was higher than that in group B (970±652). Conclusions:It is feasible to perform MR-Linac-based off-center treatment plan.

Objective:To investigate the feasibility of applying the ArcherQA three-dimensional (3D) dosimetric verification system in intensity-modulated radiotherapy (IMRT) plans for nasopharyngeal carcinoma (NPC).Methods:A retrospective analysis was conducted for 105 NPC patients′ IMRT plans developed using the Eclipse treatment planning system (TPS). Dose verification was conducted using the ArcherQA system and through portal dosimetry (PD). Moreover, this study compared γ passing rates (criteria: 3 mm/3%, TH = 10%) between ArcherQA and PD and the doses delivered to the target volume ( Dmean, D90%) and organs at risk (OARs) ( Dmean) between ArcherQA and TPS, and analyzed the 3D γ passing rates of each organ at risk calculated by ArcherQA. Results:The average 3D γ passing rate calculated by ArcherQA was (99.04±1.01)%, and the average 2D γ passing rate measured by PD was (99.49±0.78)%, with statistically significant differences ( t=-3.35, P< 0.05). The dosimetric differences to the target volume between ArcherQA and TPS were as follows: the average difference in Dmean to the gross tumor volume (GTV) was (0.57±0.48)%, and the average difference in D90% was (0.65±0.56)%. For the target volume, the average γ passing rate was (97.67±3.43)% for GTV, (97.80±4.35)% for GTVnd-L, (97.82±4.07)% for GTVnd-R, (97.88±2.44)% for CTV1, and (96.64±4.32)% for CTV2. The mean dose difference of each target volume was CTV1 (0.57±0.46)%, GTVnd-L (0.85±0.55)%, GTVnd-R (0.73±0.55)%, and CTV2 (0.88±0.52)%. For OARs, the mean γ passing rate was (99.93±0.22)% for the brainstem, (99.17±2.82)% for the optic chiasm, (100±0)% for the lens, (99.56±1.05)% for the spinal cord, (99.00±2.06)% for the thyroid, and (87.86±10.42)% for the trachea. Statistically significant differences in the average doses to OARs were observed ( t=-14.62 to 4.82, P<0.05), except for those to the left optic nerve, the right hippocampus, and the right parotid gland. Conclusions:Based on the high-performance GPU platform and the Monte Carlo dose algorithm, ArcherQA can provide accurate 3D dose distribution and 3D γ passing rates inside patients according to CT images and provide the dose volume histogram (DVH) of various regions of interest (ROIs). Therefore, the ArcherQA three-dimensional dose verification system can be applied to IMRT plans for NPC. Moreover, it is inducive to improve the treatment efficiency since it does not occupy the accelerator operation time.

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.

Psoriasis is a common clinical chronic inflammatory skin disease with a complex and diverse etiology and unrevealed pathogenesis. In traditional Chinese medicine （TCM）， psoriasis is caused by internal and external factors. To be specific， external factors such as external wind， cold， dampness， heat， insects， and other pathogenic factors can result in Qi obstruction， blood stasis， and loss of nourishment in the skin， and internal and external factors such as wind， dampness， and toxic qi attacking the exterior， heat and dryness in the blood aspect， difficulty in flourishing due to blood dryness， and blood deficiency in the body， combined with external contraction of wind and dryness trigger the disease. Modern doctors have conducted research from the blood aspect， including blood heat， blood deficiency， blood stasis， and blood dryness. Modern medicine believes that it is related to genetics， immunity， infection， and other factors， and the research on its mechanism focuses on genetic susceptibility， immune system disorder， bacterial infection， and other aspects. At present， various clinical therapies are available， mainly including systematic treatment and local external application of drugs. While treating psoriasis， TCM mainly employs oral administration or external application of Chinese medicine and traditional therapies to regulate the immune system and gene targets and resist oxidation， with high safety and few adverse reactions. At present， although the research on the mechanism of TCM in the treatment of psoriasis has been gradually deepened， there are few detailed summaries on the mechanism of TCM in the prevention and treatment of psoriasis. Based on the research on TCM and western medicine in the treatment of psoriasis， this paper reviewed the mechanism of TCM in the prevention and treatment of psoriasis and proposed a comprehensive clinical and experimental research profile， aiming to provide references for further exploring the pathogenesis， treatment， and corresponding mechanism of psoriasis.