With the rapid development of artificial intelligence, computational pathology has been seamlessly integrated into the entire clinical workflow, which encompasses diagnosis, treatment, prognosis, and biomarker discovery. This integration has significantly enhanced clinical accuracy and efficiency while reducing the workload for clinicians. Traditionally, research in this field has depended on the collection and labeling of large datasets for specific tasks, followed by the development of task-specific computational pathology models. However, this approach is labor intensive and does not scale efficiently for open-set identification or rare diseases. Given the diversity of clinical tasks, training individual models from scratch to address the whole spectrum of clinical tasks in the pathology workflow is impractical, which highlights the urgent need to transition from task-specific models to foundation models (FMs). In recent years, pathological FMs have proliferated. These FMs can be classified into three categories, namely, pathology image FMs, pathology image-text FMs, and pathology image-gene FMs, each of which results in distinct functionalities and application scenarios. This review provides an overview of the latest research advancements in pathological FMs, with a particular emphasis on their applications in oncology. The key challenges and opportunities presented by pathological FMs in precision oncology are also explored.
Humans ; Precision Medicine/methods* ; Medical Oncology/methods* ; Artificial Intelligence ; Neoplasms/pathology* ; Computational Biology/methods*

Objective To predict the invasion degree of subsolid nodule(SSN)lung adenocarcinoma using a combined model incorporating artificial intelligence(AI)quantitative parameters and imaging signs,and to validate the predictive efficacy of this model.Methods A total of 281 SSN lung adenocarcinoma CT images in 243 patients were retrospectively collected and randomly divided into training set(224 cases)and validation set(57 cases)in an 8∶2 ratio,with atypical adenomatous hyperplasia(A AH)+adenocarcinoma in situ(AIS)+minimally invasive adenocarcinoma(MIA)(191 cases)as the non-invasive adenocarcinoma(I AC)group and I AC(90 cases)as the IAC group.Multivariate logistic regression analysis was performed based on the AI quantitative parameters and CT signs in the training set to obtain independent predictors of IAC.A combined model and nomogram were then constructed and validated.The diagnostic efficacy and clinical applicability of the model were evaluated by the receiver operating characteristic(ROC)curve,calibration curve,and clinical decision curve analysis(DCA).Results Multivariate logistic regression analysis of the training set showed nodule type,spicule sign,vascular abnormality,long diameter＞11.5 mm,median CT value＞—426.25 HU,and mass＞391.5 mg were independent predictors of IAC(P＜0.05).The area under the curve(AUC)of the training set model,based on these independent predictive factors,was 0.915[95％confidence interval(CI)0.875-0.954],and the AUC of the validation set model was 0.903(95％CI 0.824-0.982),indicating both the training set and validation set models had high efficacy in distinguishing IAC.The nomogram model,which quantified these independent factors,demonstrated enhanced predictive power for IAC.The calibration curve indicated good fit of the prediction model,and the clinical DCA showed the model had good clinical applicability.Conclusion The model combining AI quantitative parameters and imaging signs has a higher ability to predict the risk of IAC,compared to a single indicator.It helps clinicians in determining the appropriate surgical timing,formulating surgical methods,and reducing overtreatment.

Objective To predict the invasion degree of subsolid nodule(SSN)lung adenocarcinoma using a combined model incorporating artificial intelligence(AI)quantitative parameters and imaging signs,and to validate the predictive efficacy of this model.Methods A total of 281 SSN lung adenocarcinoma CT images in 243 patients were retrospectively collected and randomly divided into training set(224 cases)and validation set(57 cases)in an 8∶2 ratio,with atypical adenomatous hyperplasia(A AH)+adenocarcinoma in situ(AIS)+minimally invasive adenocarcinoma(MIA)(191 cases)as the non-invasive adenocarcinoma(I AC)group and I AC(90 cases)as the IAC group.Multivariate logistic regression analysis was performed based on the AI quantitative parameters and CT signs in the training set to obtain independent predictors of IAC.A combined model and nomogram were then constructed and validated.The diagnostic efficacy and clinical applicability of the model were evaluated by the receiver operating characteristic(ROC)curve,calibration curve,and clinical decision curve analysis(DCA).Results Multivariate logistic regression analysis of the training set showed nodule type,spicule sign,vascular abnormality,long diameter＞11.5 mm,median CT value＞—426.25 HU,and mass＞391.5 mg were independent predictors of IAC(P＜0.05).The area under the curve(AUC)of the training set model,based on these independent predictive factors,was 0.915[95％confidence interval(CI)0.875-0.954],and the AUC of the validation set model was 0.903(95％CI 0.824-0.982),indicating both the training set and validation set models had high efficacy in distinguishing IAC.The nomogram model,which quantified these independent factors,demonstrated enhanced predictive power for IAC.The calibration curve indicated good fit of the prediction model,and the clinical DCA showed the model had good clinical applicability.Conclusion The model combining AI quantitative parameters and imaging signs has a higher ability to predict the risk of IAC,compared to a single indicator.It helps clinicians in determining the appropriate surgical timing,formulating surgical methods,and reducing overtreatment.

With the rapid development of artificial intelligence technology, its applications in medical imaging have become increasingly extensive. This review aimed to analyze the current development status and future direction of intelligent imaging technology by investigating its application in various medical departments. To achieve this, we conducted a comprehensive search of various data sources up to 2024, including PubMed, Web of Science, and Google Scholar, based on the principle of comprehensive search. A total of 332 articles were screened, and after applying the inclusion and exclusion criteria, 56 articles were selected for this study. According to the findings, intelligent imaging technology exhibits robust image recognition capabilities, making it applicable across diverse medical imaging modalities within hospital departments. This technology offers an efficient solution for the analysis of various medical images by extracting and accurately identifying complex features. Consequently, it significantly aids in the detection and diagnosis of clinical diseases. Its high accuracy, sensitivity, and specificity render it an indispensable tool in clinical diagnostics and related tasks, thereby enhancing the overall quality of healthcare services. The application of intelligent imaging technology in healthcare significantly enhances the efficiency of clinical diagnostics, resulting in more accurate and timely patient assessments. This advanced technology offers a faster and more precise diagnostic approach, ultimately improving patient care and outcomes. This review analyzed the socioeconomic changes brought about by intelligent imaging technology to provide a more comprehensive evaluation. Also, we systematically analyzed the current shortcomings of intelligent imaging technology and its future development directions, to enable future research.
Humans ; Artificial Intelligence ; Diagnostic Imaging/methods* ; Hospitals

Objective:To explore the status of "socialized hospitalization" of chronic obstructive pulmonary disease (COPD) patients and its influencing factors, and propose constructive coping strategies.Methods:From June 2018 to June 2020, convenience sampling was used to select 256 COPD patients admitted to Hangzhou First People's Hospital as the research object. The self-designed Socialized Hospitalization Status and Influencing Factors Questionnaire was used to investigate patients. Single factor analysis and multivariate Logistic regression analysis were used to analyze the influencing factors of the "socialized hospitalization" of COPD patients.Results:Among 256 COPD patients, 239 effective samples were finally obtained, and 61 cases (25.52%) were "socialized hospitalization". The hospitalization time of patients with "socialized hospitalization" was longer than those with non-"socialized hospitalization", and the difference was statistically significant ( t=16.510, P<0.01) . Hospitalization expenses were higher than those with non-"socialized hospitalization", and the difference was statistically significant ( t=17.820, P<0.01) . The results of single factor analysis showed that there were statistically significant differences in the age, course of illness, type of medical insurance, hospital admission method, hospital-acquired infection, mental status score, dyspnea score, and basic life activity ability in patients with "socialized hospitalization" and non-"socialized hospitalization" ( P<0.05) . The results of multivariate Logistic regression analysis showed that the patient's age, type of medical insurance, hospital admission method, hospital-acquired infection, mental status, dyspnea, and basic life activity ability were the influencing factors of COPD patients' "socialized hospitalization", and the difference was statistically significant ( P<0.05) . Conclusions:Various physiological and pathological conditions and family conditions are the influencing factors of "socialized hospitalization" in COPD patients. The allocation of medical resources should be balanced, the nursing system should be perfected, and the technical level and quality of medical and nursing staff should be improved to ease the pressure of "socialized hospitalization".

Objective To investigate the effect of improving the human immunodeficiency virus (HIV)posi-tive detection rate by single sample nucleic acid amplification test (SS-NAT) in Shenzhen ,and to explore the effect of SS-NAT on reducing the risk of HIV infection in transfusion .Methods 269 228 blood samples were performed parallel detection by SS-NAT (Procleix Tigris ) and two kinds of enzyme-linked immuno sorbent assay(ELISA)reagents ,and then the samples with nonreactive by ELISA and reactive by SS-NAT were tested by HIV identification assay .The blood donors with reactive HIV identification assay were made tracing tests . All the samples with reactive by ELISA or HIV identification assay were sent to the Shenzhen Center for Dis-ease Control and Prevention (CDC) for Western Blot (WB) diagnostic tests .Results The samples with reac-tive by the third generation ELISA reagents ,the fourth generation ELISA reagents ,both ELISA reagents and SS-NAT were 188 ,340 ,422 and 103 ,which reactive rate was 0 .698‰(188/269 228) ,1 .263‰(340/269 228) , 1 .567‰(422/269 228) and 0 .383‰(103/269 228) ,respectively .We found four samples with nonreactive by ELISA but reactive by SS-NAT .The four donors were found HIV reactive by both ELISA and SS-NAT after tracing .All the samples with reactive by ELISA or HIV identification assay were sent to CDC for confirmatory tests and 103 of them were positive .The positive detection rate of transfusion-transmissible HIV infection af-ter ELISA detection was 1∶67 307(4/269 228) .Conclusion The application of SS-NAT in blood screening can improve the HIV positive detection rate ,shorten window period of HIV detection and reduce residual risk of transfusion-transmissible HIV infection ,and then blood safety can be effectively improved .

OBJECTIVE:To establish the method for simultaneous contents determination of 5 kinds of acid and alkaline componentsin anti-cold compound preparation. METHODS:HPLC method was adopted. The workstation was Auto·Blend Plus software of ACQUITY Arc system. The determination was performed on Discovery?HS F5-5 column with mobile phase consisted of acid mixture-base mixture-methanol-0.3% triethylamine (gradient elution) at the flow rate of 1.0 mL/min. The detection wavelengths were set at 270 nm (acetaminophen,salicylamide,chlorphenamine maleate,triprolidine hydrochloride) and 299 nm (aspirin). The column temperature was 35 ℃,the sample size was 20 μ L. RESULTS:The linear ranges of acetaminophen, salicylamide,acetylsalicylic acid,chlorphenamine maleate,triprolidine hydrochloride were 26-411 μ g/mL(r＝0.999 6),16-254 μg/mL(r＝0.999 8),16-748 μg/mL(r＝0.998 1),35-565 μg/mL(r＝0.999 8)and 25-404 μg/mL(r＝0.999 7),respectively. LOQ were 3.6,3.1,4.0,9.6,6.3 μ g/mL;LOD were 1.9,1.3,1.4,2.9,2.3 μ g/mL,respectively. RSDs of intermediate precision, stability and reproducibility tests were all lower than 2%. Average recoveries were 100.0%-102.0%(RSD＝0.59%,n＝9), 95.2%-101.0%(RSD＝1.55%,n＝9),96.2%-99.9%(RSD＝1.24%,n＝9),96.2%-101.5%(RSD＝1.57%,n＝9),96.3%-98.9%(RSD＝0.83%,n＝9),respectively. RSDs of durability tests were lower than 3%. CONCLUSIONS:The method is simple, accurate,precise,stable,reproducible and durable,and can be used for simultaneous contents determination of 5 kinds of acid and alkaline components in anti-cold compound preparation.

Objective The aim of this study is to investigate the cerebral cortical thickness changes in type 2 diabetes mellitus (T2DM) using a whole brain cortical thickness mapping system based on brain magnetic resonance imaging (MRI).Methods High resolution three-dimensional T1-weighted fast spoiled gradient recalled echo MR images were obtained from 16 patients with T2DM, as well as from 16 normal controls. The whole brain cortical thickness maps were generated, and the cortical thickness of each brain region was calculated according to gyral based regions of interest (ROI) using an automated labeling system by the Freesurfer software. We compared mean cortical thickness at each brain region by the analysis of covariance with age and sex as covariates. The regional difference of the cortical thickness over the whole brain was compared by the analysis of surface-based cortical thickness.Results Mean cortical thicknesses analysis showed bilateral cerebrum in the patients with T2DM (left: 2.52±0.07 mm; right: 2.51±0.08 mm) were significant thinner than those in the normal controls (left: 2.56±0.09 mm; right: 2.56±0.09 mm) (both P<0.05). Regional cortical thinning in T2DM was demonstrated in the paracentral lobule, postcentral gyrus, lateral occipital gyrus, lingual gyrus, precuneus, superior temporal gyrus, middle temporal gyrus, inferior temporal gyrus and posterior cingulate gyrus, compared to the normal controls. The cortical thickness of left middle cingulate and right inferior temporal gyrus were negatively correlated with the disease course.Conclusion A widespread cortical thinning was revealed in patients with T2DM by the analysis of brain cortical thickness on MR. Our finding supports the idea that T2DM could lead to subtle diabetic brain structural changes.
Aged ; Cerebral Cortex ; pathology ; Diabetes Mellitus, Type 2 ; diagnostic imaging ; pathology ; Female ; Humans ; Magnetic Resonance Imaging ; methods ; Male ; Middle Aged ; Pilot Projects

An 70-year-old male come for swallowing pain 5 years, turning worse 10 months. Laryngoscopy showed a tumor with rough surface at the laryngeal surface of epiglottic. Outpatient pathology: poorly differentiated carcinoma of the larynx. CT: the root of epiglottic is slightly thickened. He accepted the partial laryngectomy, tracheotomy, bilateral functional neck dissection. Pathology: atypical carcinoid of larynx.
Aged ; Carcinoid Tumor ; pathology ; Epiglottis ; pathology ; Humans ; Laryngeal Neoplasms ; pathology ; Laryngectomy ; Laryngoscopy ; Larynx ; pathology ; Male ; Neck Dissection ; Tracheotomy

OBJECTIVETo investigate the efficacy and safety of second-generation tyrosine kinase inhibitors (TK-II) combined with allogeneic hematopoietic stem cell transplantation (allo-HSCT) in the treatment of high-risk Philadelphia chromosome positive (Ph⁺) leukemia.

METHODSThe clinical data of 17 cases of high-risk Ph⁺ leukemia patients underwent allo-HSCT were retrospectively analyzed, including 1 case in accelerated phase and 7 cases in blast crises of chronic myeloid leukemia, and 9 cases of Ph⁺ acute lymphoblastic leukemia. Nilotinib or Dasatinib were administered before and (or) after allo-HSCT in all patients.

RESULTSAll patients successfully engrafted. Median times to neutrophil and platelet recovery were 12 days (range 10-14) and 15 days (range 11- 23), respectively. Acute GVHD developed in 7 patients: 6 patients had grade 1 to 2 and 1 patient grade 3. Chronic GVHD developed in 6 patients, all were limited and no lethal GVHD occurred. At a median follow-up of 17(range 3-60) months, 11(64.7%) patients survived disease free, 6 patients relapsed and 5 died.

CONCLUSIONTK-II combined with allo-HSCT effectively improved the remission rate of high-risk Ph⁺ leukemia and reduced recurrence after allo-HSCT, which represented an important improvement in the treatment of patients with high-risk Ph+ leukemia.

Adolescent ; Adult ; Female ; Hematopoietic Stem Cell Transplantation ; Humans ; Leukemia, Myelogenous, Chronic, BCR-ABL Positive ; therapy ; Male ; Middle Aged ; Philadelphia Chromosome ; Precursor Cell Lymphoblastic Leukemia-Lymphoma ; therapy ; Protein Kinase Inhibitors ; therapeutic use ; Protein-Tyrosine Kinases ; antagonists & inhibitors ; Retrospective Studies ; Transplantation, Homologous ; Young Adult