Objective:To establish an automatic classification approach for bone marrow cells based on microscopic hyperspectral imaging and three-dimensional spectral convolutional neural network (Spec-CNN).Methods:The research type is establishment of methodology. The study included 306 newly diagnosed patients' bone marrow smears under Wright's staining from the Department of Hematology of the First Medical Center of the PLA General Hospital from November 1st, 2013 to April 30th, 2024. The high-spectrum data and 4k image data of bone marrow cells were simultaneously collected using a microscopic hyperspectral-4k optical path integrated imaging system (with a spectral resolution of 400—1 000 nm). The high-spectrum data was used for model training, while the 4k image data recognized by morphologists was only used as a reference for labeling the high-spectrum data. The high-spectrum data set was divided into training set, validation set and test set in a ratio of 14∶6∶5. The training set and validation set were used to train and fine-tune the Spec-CNN model, and the test set was used to evaluate the model performance. The sensitivity, specificity ,accuracy ,and Kappa coefficient were calculated for comparing the manual annotation results as gold standard with the intelligent identification results of the Spec-CNN model. Five non-data set samples were used for external validation.Results:The acquired hyperspectral data and 4k imaging dataset comprised of 32 categories and 64 800 bone marrow cells. In the test set, the Spec-CNN model demonstrated weighted-average indicators on classification metrics across 32 cell types: sensitivity 87.79%, specificity 99.31%, and accuracy 98.78%, and Kappa coefficient 0.869. For external validation, the mean correct identification rate of bone marrow cells reached 83.28%.Conclusion:We successfully established an automatic classification method of bone marrow cells based on microscopic hyperspectral imaging and three-dimensional Spec-CNN. This method has a good automatic classification ability for 32 types of bone marrow nucleated cells, which has a certain auxiliary effect on improving the diagnosis efficiency of blood diseases for bone marrow morphologists.

Lung cancer is a leading cause of cancer-related deaths worldwide, with its high mortality rate primarily attributed to delayed diagnosis. Radiomics, by extracting abundant quantitative features from medical images, offers novel possibilities for early diagnosis and precise treatment of lung cancer. This article reviewed the latest advancements in radiomics for lung cancer management, particularly its integration with artificial intelligence (AI) to optimize diagnostic processes and personalize treatment strategies. Despite existing challenges, such as non-standardized image acquisition parameters and limitations in model reproducibility, the incorporation of AI significantly enhanced the precision and efficiency of image analysis, thereby improving the prediction of disease progression and the formulation of treatment plans. We emphasized the critical importance of standardizing image acquisition parameters and discussed the role of AI in advancing the clinical application of radiomics, alongside future research directions.
Humans ; Lung Neoplasms/diagnosis* ; Artificial Intelligence ; Early Detection of Cancer/methods* ; Precision Medicine ; Image Processing, Computer-Assisted/methods* ; Tomography, X-Ray Computed ; Radiomics

Objective:To establish an automatic classification approach for bone marrow cells based on microscopic hyperspectral imaging and three-dimensional spectral convolutional neural network (Spec-CNN).Methods:The research type is establishment of methodology. The study included 306 newly diagnosed patients' bone marrow smears under Wright's staining from the Department of Hematology of the First Medical Center of the PLA General Hospital from November 1st, 2013 to April 30th, 2024. The high-spectrum data and 4k image data of bone marrow cells were simultaneously collected using a microscopic hyperspectral-4k optical path integrated imaging system (with a spectral resolution of 400—1 000 nm). The high-spectrum data was used for model training, while the 4k image data recognized by morphologists was only used as a reference for labeling the high-spectrum data. The high-spectrum data set was divided into training set, validation set and test set in a ratio of 14∶6∶5. The training set and validation set were used to train and fine-tune the Spec-CNN model, and the test set was used to evaluate the model performance. The sensitivity, specificity ,accuracy ,and Kappa coefficient were calculated for comparing the manual annotation results as gold standard with the intelligent identification results of the Spec-CNN model. Five non-data set samples were used for external validation.Results:The acquired hyperspectral data and 4k imaging dataset comprised of 32 categories and 64 800 bone marrow cells. In the test set, the Spec-CNN model demonstrated weighted-average indicators on classification metrics across 32 cell types: sensitivity 87.79%, specificity 99.31%, and accuracy 98.78%, and Kappa coefficient 0.869. For external validation, the mean correct identification rate of bone marrow cells reached 83.28%.Conclusion:We successfully established an automatic classification method of bone marrow cells based on microscopic hyperspectral imaging and three-dimensional Spec-CNN. This method has a good automatic classification ability for 32 types of bone marrow nucleated cells, which has a certain auxiliary effect on improving the diagnosis efficiency of blood diseases for bone marrow morphologists.

Background::The incidence rate of lung cancer in women has significantly increased over the past decade, and previous evidence has indicated a significant relationship between the elevated levels of sex hormones and the risk of lung cancer. Therefore, we hypothesized that female hormone-related cancer (FHRC) patients, including breast, endometrial, cervical, and ovarian cancer patients, may experience a higher risk of developing subsequent lung cancer. This meta-analysis aimed to identify the risk of lung cancer among FHRC patients compared to the general population.Methods::The PubMed, Web of Science, EMBASE, Cochrane Library, and CNKI databases were searched up to May 11, 2022. Standardized incidence ratios (SIRs) with 95% confidence intervals (CIs) were used to identify the risk of subsequent lung cancer after FHRC. Subgroup analyses based on the follow-up time and tumor type were also conducted.Results::A total of 58 retrospective cohort studies involving 4,360,723 FHRC participants were included. The pooled results demonstrated that FHRC patients had a significantly increased risk of developing subsequent primary lung cancer (SIR = 1.61, 95% CI: 1.48-1.76, P <0.001). Subgroup analysis revealed an obvious trend of increasing lung cancer risk over time (SIRs for <5 years, ≥5 years, ≥10 years, ≥20 years, and ≥30 years after FHRC: 1.32, 1.59, 1.57, 1.68, and 1.95, respectively). In addition, subgroup analysis stratified by tumor type indicated an increased risk of developing subsequent lung cancer after breast (SIR = 1.25, P <0.001), endometrial (SIR = 1.40, P = 0.019), cervical (SIR = 2.56, P <0.001), and ovarian cancer (SIR = 1.50, P = 0.010). Conclusion::FHRC patients are more likely to develop lung cancer than the general population. Furthermore, the increased risk of subsequent primary lung cancer is more obvious with a longer survival time and is observed in all types of hormone-related cancer.Registration::International Platform of Registered Systematic Review and Meta-analysis Protocols: No. INPLASY202270044; https://inplasy.com/

Objective: To summarize the clinical characteristics of 141 patients with novel coronavirus pneumonia (NCP) and the imaging characteristics of High Resolution CT(HRCT) in the chest. Methods: From January 20, 2020 to 28, 141 NCP patients, 77 males and 64 females, with a median age of 49 (9,87), were retrospectively analyzed. The clinical features, laboratory examination indexes and HRCT findings of 141 NCP patients were analyzed. Results: In 141 NCP patients, 38 (26.95%) had a decrease in leukocyte count and 71 (50.35%) had a decrease in lymphocyte ratio. Among 141 NCP patients, 139 (98.58%) had fever (over 37.5 ° C), 106 (75.18%) coughed, 11 (7.80%) had headache, 41 (29.08%) coughed up sputum, 93 (65.96%) had chest distress, and 4 (2.84%) had diarrhea. HRCT of 141 NCP patients were abnormal, 52 (36.88%) showed ground glass shadow (GGO) and patchy shadow, mainly subpleural distribution; 23 (16.31%) showed GGO with focal consolidation; 27 (19.15%) had small patchy blur; 20 (14.18%) had large patchy consolidation; 48 (34.04%) had bronchovascular bundle thickening and vascular perforator sign; 5 (3.55%) had Air bronchus sign; small nodule shadow in 7 cases (4.96%); fibrosis, grid shadow or strip shadow in 5 cases (3.55%); bilateral pleural effusion in 7 cases (4.96%); mediastinal or bilateral hilar lymphadenopathy in 4 cases (2.84%). Conclusions The clinical features and HRCT images of NCP are various. Under the specific epidemiological background of NCP, HRCT scan of chest should be carried out in time to make early warning of disease.

Objective:To summarize the clinical and high resolution CT(HRCT) characteristics of 141 patients with COVID-19.Methods:From January 20 to 28, 2020, 141 COVID-19 patients, 77 males and 64 females, with a median age of 49 (9, 87), were enrolled in the study. The clinical features, laboratory test results and HRCT findings of all patients were analyzed retrospectively.Results:In all of the patients, the decreasing leukocyte countin 38 (26.95%) and lymphocyte ratio in 71 (50.35%), a fever over 37.5 ℃ in 139 (98.58%), coughing in 106 (75.18%), headache in 11 (7.80%), expectoration in 41 (29.08%), chest distress in 93 (65.96%), and diarrhea in 4 (2.84%) were found. The HRCT of all patients were abnormal, including ground glass opacity (GGO) with patchy opacity in 52 (36.88%) mainly distributed along subpleural area, GGO with focal consolidation in 23 (16.31%),small patchy opacity in 27 (19.15%),large patchy consolidation in 20 (14.18%),thickened bronchovascular bundleing and blood vessel crossing the lesion in 48 (34.04%), air bronchus sign in 5 (3.55%), small nodule in 7 (4.96%),fibrous stripes and reticular opacities in 5 (3.55%), bilateral pleural effusion in 7 (4.96%), and mediastinal or bilateral hilar lymphadenopathy in 4 (2.84%).Conclusions:The clinical and HRCT manifestations of COVID-19 are various. Under the specific epidemiological background of COVID-19, chest HRCT scan should be carried out as soon as possible for early warning of this disease.

Objective:To explore the value of low-dose CT in pregnancy with COVID-19.Methods:A retrospective analysis was performed on the clinical characteristics, laboratory tests, and chest CT findings of 12 pregnant women with COVID-19 diagnosed by nucleic acid testing in the Renmin Hospital of Wuhan University from January 20, 2020 to February 16, 2020. Two radiologists blinded to the reconstruction algorithm independently scored subjective image quality on a 5-point Likert scale. Image quality score ≥ 3 was acceptable in clinics. The CT radiation doses were recorded, including CT volume dose index (CTDI vol), dose length product (DLP), and effective radiation dose ( E). Two radiologists observed the distribution, shape, density, and other characteristics of lung lesions, and they also decided whether hilar, mediastinal lymphadenopathy, and pleural changed. Results:A total of 12 pregnant women with COVID-19, 8 had cough, 4 had fever, 2 had chest tightness, and 1 had dyspnea and diarrhea each. The CT image quality score of all patients was 3-4, with an average of 3.46, which fully met the clinical diagnosis requirements. The CTDI vol value was 1.13-4.31 mGy, with an average of 3.02 mGy. The DLP value was 34.48-75.29 mGy·cm, with an average of 55.48 mGy·cm. The Evalue was 0.48-1.05 mSv, with an average of 0.78 mSv. In all cases, chest CT examination showed abnormal manifestations after clinical symptoms, including unilateral lung lesions in 5 cases and bilateral lung lesions in 7 cases, 1 case of ground-glass opacity, 1 case of solidification, 7 cases of ground-glass and consolidation, 1 case of strip opacity, ground-glass, and consolidation and strip cable shadow coexisted in 2 cases. Conclusions:The application of low-dose CT scan in pregnant women with COVID-19 is completely feasible. CT mainly manifested as bilateral lung patchy and flaky ground-glass opacity with consolidation. Active and effective treatment can help recover and improve prognosis.

Costal cartilage is a commonly used filling and supporting material in clinical practice, which has many advantages, but chest wall deformity frequently occurs after autologous costal cartilage harvesting. In order to effectively reduce the incidence of chest wall deformity, experts and scholars have conducted a full exploration.Theauthor reviewed the related literatures and summarized the prevention of chest wall deformity after costal cartilage harvesting. On the basis of reasonable selection of surgical site and cartilage harvesting amount, the costochondral junction(CCJ)and optional cartilage should be preserved.The costal perichondrium should be sutured and autogeneic cartilage debris should be replanted during the operation. In addition, postoperative management should also limit the degree of chest movement and breathing range, such as external fixation and restrictions on physical exercise.

Costal cartilage is a commonly used filling and supporting material in clinical practice, which has many advantages, but chest wall deformity frequently occurs after autologous costal cartilage harvesting. In order to effectively reduce the incidence of chest wall deformity, experts and scholars have conducted a full exploration.Theauthor reviewed the related literatures and summarized the prevention of chest wall deformity after costal cartilage harvesting. On the basis of reasonable selection of surgical site and cartilage harvesting amount, the costochondral junction(CCJ)and optional cartilage should be preserved.The costal perichondrium should be sutured and autogeneic cartilage debris should be replanted during the operation. In addition, postoperative management should also limit the degree of chest movement and breathing range, such as external fixation and restrictions on physical exercise.

Objective: To understand the epidemiologic characteristics of fall in the elderly in Shanghai, as well as the differences between urban and rural areas, and provide evidence for targeted fall prevention and intervention. Methods: From January to March in 2017, a questionnaire survey was conducted in the elderly aged 60 or above selected from 7 urban communities and 6 rural communities in Shanghai to understand the epidemiologic characteristics of fall in the elderly and analyze the gender and urban-rural differences. Results: In urban area, a total of 3 386 elderly people were surveyed, in whom 441 (13.0%) had fall and 261 (7.7%) were injured after fall. In rural area, a total of 2 826 elderly people were surveyed, in whom 320 (11.3%) had fall and 169 (6.0%) were injured after fall. Fall risk in women were higher than that in men in both urban and rural areas with OR of 1.62 (95%CI: 1.42-1.86) and 1.16 (95%CI: 1.38-1.98) respectively, but the differences of fall related injury were not significant. Compared with urban areas, fall risk and fall related injury risk were both lower in rural areas with OR of 0.86 (95%CI: 0.73-0.99) and 0.74 (95%CI: 0.56-0.99). Compared with urban areas, men had lower risk for fall, and women had lower risk for fall related injury with OR of 0.68 (95%CI: 0.51-0.90) and 0.66 (95%CI: 0.47-0.93) respectively. Fall mainly occurred at home. Fall in urban area more frequently occurred on stairs, and fall in rural area more frequently occurred during farming. More than 60% of the falls had environmental risk factors. Slippery ground and uneven ground were main reasons. The incidence of fracture resulted from fall was high indicated by 89 fracture cases in urban areas (28.2%) and 64 fracture cases in rural areas (36.1%). Conclusions The risk for fall in Shanghai had gender and urban-rural differences. Targeted intervention should be conducted according to the characteristics of fall in the elderly.