Objective To observe the value of Cox proportional hazards regression model constructed based on high-resolution MRI for predicting the risk of esophageal squamous cell carcinoma(ESCC)progression after definitive chemoradiotherapy(dCRT).Methods Thirty ESCC patients who underwent dCRT were retrospectively enrolled.Quantitative and qualitative indicators of primary tumor and imaging-defined metastatic lymph nodes were analyzed based on pre-treatment high-resolution M RI.The progression-free survival(PFS)of patients were recorded.A Cox proportional hazards regression model was established to predict the risk of tumor progression based on MRI indices,and the risks of tumor progression were stratified into high and low according to the median prediction.PFS rates were compared between patients with high or low risk of tumor progression.Results Tumor thickness(HR[95％CI]=1.210[1.025,1.429],P=0.024),relationship between the tumor and aorta(HR[95％CI]=4.275[1.064,17.168],P=0.041)and lymph node signal change rate on delayed phase pre-treatment MRI(HR[95％CI]=0.049[0.007,0.362],P=0.003)were all independent factors for predicting PFS.Based on Cox proportional hazards regression model and its predicted value,PFS rate in high risk patients was lower than that in low risk patients(P＜0.05).Conclusion High-resolution MRI could be used to predict prognosis of ESCC after dCRT.

In the evolution of colorectal cancer imaging technology in the past 40 years,application of multislice spiral CT and high-resolution MRI has not only propelled the anatomical staging of colorectal cancer into the era of precision,but also achieved quantitative stratification of tumor recurrence risk through detection of key indicators like extramural vascular invasion.Breakthroughs in functional imaging techniques such as diffusion-weighted imaging are of greater milestone significance,which improved the detection rate of metastatic lesions and constructed the foundation for early intervention.The integration of radiomics and artificial intelligence(AI)technologies has further enabled the non-invasive prediction of tumor molecular subtypes and optimized clinical decision pathways through treatment response modeling.However,development in the field still faces multiple bottlenecks.Looking ahead to the future,building a multimodal intelligent diagnosis and treatment ecosystem is the core direction of development of colorectal cancer imaging.Risk stratification models that integrate clinical-imaging-pathological data,prospective multicenter data pools and interdisciplinary collaboration platforms will promote imaging from traditional"auxiliary diagnostic tool"towards a paradigm shift as"treatment decision-making engine".

MRI has been widely used in early detection,preoperative assessment,therapeutic efficacy evaluation and prognosis prediction of breast cancer due to advantages such as high soft tissue resolution,non-radiation and repeatability.The era of precision medicine has posed new challenges of MRI for breast cancer.Future research should delve into multi-sequence microscopic imaging,deeply explore the intrinsic correlation between radiomics and genomic information,furtherly improve computational power to fully exert the role of MRI for breast cancer.The advances of MRI applicated in breast cancer under the background of precision imaging were reviewed in this article.

Objective:To investigate the application value of a joint prediction model based on lymph node imaging features in evaluating lymph node metastasis of locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT).Methods:The retrospective cohort study was conducted. The clinicopathological data of 215 LARC patients who were admitted to Peking University Cancer Hospital & Institute from July 2010 to June 2015 were collected. There were 131 males and 84 females, aged (56.7±10.1)years. All 215 patients were randomly divided into a training set of 143 cases and a testing set of 72 cases using a 2∶1 ratio of random seed numbers. The training set was used to construct the prediction model, and the testing set was used to validate the performance of prediction model. Observation indicators: (1) lymph node metastasis in LARC patients after nCRT; (2) imaging feature selection and model construction and evaluation. Com-parison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Univariate and multivariate analyses were conducted using the Logistic regression model. Performance evaluation of prediction model was conducted using the receiver operating characteristic (ROC) curve. The area under the curve (AUC), accuracy, sensitivity, and specificity were calculated. Calibration curves and decision curves were used to evaluate the consistency and clinical application value of the prediction model. Results:(1) Lymph node metastasis in LARC patients after nCRT. Of the 215 LARC patients after nCRT, results of postoperative pathological examination showed that there were 162 cases with negative lymph node metastasis and 53 cases with positive lymph node metastasis, showing significant differences in age and maximum short-axis diameter of lymph node between them ( t=2.178, Z=-5.305, P<0.05). (2) Imaging feature selection and model construction and evaluation. Forty-one imaging features were extracted from the 215 LARC patients after nCRT, including 9 gray-level first-order features, 24 gray-level co-occurrence matrix features and 8 shape features. The score of lymph node (LNscore) in 162 cases with negative lymph node metastasis and 53 cases with positive lymph node metastasis were 0.18(0.10,0.33) and 0.39(0.23,0.54), respectively, showing a significant difference between them ( Z=-5.487, P<0.05). Results of multivariate analysis showed that maximum short-axis diameter of lymph node and LNscore were independent factors influencing lymph node metastasis of LARC patients after nCRT ( odds ratio=1.277, 25.514, 95% confidence interval as 1.010-1.614, 2.003-324.964, P<0.05). A Logistic regression joint prediction model was constructed by incorporating the maximum short-axis diameter of lymph node and LNscore. The ROC curves results showed that the AUC, accuracy, sensitivity, and specificity of the joint prediction model in the training set were 0.779 (95% confidence interval as 0.702-0.844), 72.7%, 71.4%, and 73.2%, respectively. The above indicators in the testing set were 0.805 (95% confidence interval as 0.694-0.889), 80.6%, 66.7%, and 85.2%, respectively. Calibration curves in both training set and test set showed good agreement with the ideal curve, indicating high calibration. Decision curves demonstrated the model′s clinical utility with a high net benefit. Conclusion:The maximum short-axis diameter of lymph node and LNscore are independent factors influencing lymph node metastasis of LARC patients after nCRT. The joint prediction model constructed based on the above indicators can be used to predict lymph node metastasis in LARC patients after nCRT.

Objective To explore changes of topological properties and functional connectivity(FC)of global brain network in breast cancer(BC)patients accompanied by emotional disorders.Methods Forty-three female BC patients(BC group)and 43 age-and education-matched healthy controls(HC group)were prospectively enrolled.The scores of fear of cancer recurrence-total(FCR-total),fear of cancer recurrence inventory(FCRI),general anxiety disorder-7(GAD-7)and patient health questionnaire-9(PHQ-9)for 43 patients in BC group,as well as of anxiety sensitivity index-3(ASI-3),meta-cognitions about health questionnaire(MCQ-HA)and EuroQoL 5-dimension 5-level questionnaire(EQ-5D-5L)for 40 patients in BC group were obtained to evaluate emotional disorders.Meanwhile,the scores of GAD-7 and PHQ-9 were obtained in HC group to exclude for anxiety and depression.Using resting-state functional MRI(rs-fMRI),topological attributes and FC of global brain network were analyzed,and the topological attribute indicators of global brain network were compared between groups.Based on voxel-wise analysis,the regions in global brain related to FC strength(FCS)correlated with each clinical scale score in BC group were analyzed,and spatial similarity analysis of FCS was performed.The correlations of FCS at brain region level and clinical scale scores in BC group were observed.Results All patients in BC group were accompanied by emotional disorders.The clustering coefficient in BC group was lower than that in HC group(t=-2.261,P=0.027).Brain regions related to FCS values correlated with each clinical scale score in BC group were widely distributed in sensorimotor network and higher-order brain network,etc.,and their FCS values were correlated.FCS of ventrolateral nucleus of right thalamus and caudate nucleus were positively correlated with FCR-total(r=0.459,P=0.004)and FCRI(r=0.488,P=0.005).Conclusion BC patients with emotions disorders had dysfunction of brain functional segregation,as well as enhanced FCS in brain regions such as ventrolateral nucleus of right thalamus and caudate nucleus.

MRI has been widely used in early detection,preoperative assessment,therapeutic efficacy evaluation and prognosis prediction of breast cancer due to advantages such as high soft tissue resolution,non-radiation and repeatability.The era of precision medicine has posed new challenges of MRI for breast cancer.Future research should delve into multi-sequence microscopic imaging,deeply explore the intrinsic correlation between radiomics and genomic information,furtherly improve computational power to fully exert the role of MRI for breast cancer.The advances of MRI applicated in breast cancer under the background of precision imaging were reviewed in this article.

Objective To explore changes of topological properties and functional connectivity(FC)of global brain network in breast cancer(BC)patients accompanied by emotional disorders.Methods Forty-three female BC patients(BC group)and 43 age-and education-matched healthy controls(HC group)were prospectively enrolled.The scores of fear of cancer recurrence-total(FCR-total),fear of cancer recurrence inventory(FCRI),general anxiety disorder-7(GAD-7)and patient health questionnaire-9(PHQ-9)for 43 patients in BC group,as well as of anxiety sensitivity index-3(ASI-3),meta-cognitions about health questionnaire(MCQ-HA)and EuroQoL 5-dimension 5-level questionnaire(EQ-5D-5L)for 40 patients in BC group were obtained to evaluate emotional disorders.Meanwhile,the scores of GAD-7 and PHQ-9 were obtained in HC group to exclude for anxiety and depression.Using resting-state functional MRI(rs-fMRI),topological attributes and FC of global brain network were analyzed,and the topological attribute indicators of global brain network were compared between groups.Based on voxel-wise analysis,the regions in global brain related to FC strength(FCS)correlated with each clinical scale score in BC group were analyzed,and spatial similarity analysis of FCS was performed.The correlations of FCS at brain region level and clinical scale scores in BC group were observed.Results All patients in BC group were accompanied by emotional disorders.The clustering coefficient in BC group was lower than that in HC group(t=-2.261,P=0.027).Brain regions related to FCS values correlated with each clinical scale score in BC group were widely distributed in sensorimotor network and higher-order brain network,etc.,and their FCS values were correlated.FCS of ventrolateral nucleus of right thalamus and caudate nucleus were positively correlated with FCR-total(r=0.459,P=0.004)and FCRI(r=0.488,P=0.005).Conclusion BC patients with emotions disorders had dysfunction of brain functional segregation,as well as enhanced FCS in brain regions such as ventrolateral nucleus of right thalamus and caudate nucleus.

Objective:To investigate the application value of a joint prediction model based on lymph node imaging features in evaluating lymph node metastasis of locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT).Methods:The retrospective cohort study was conducted. The clinicopathological data of 215 LARC patients who were admitted to Peking University Cancer Hospital & Institute from July 2010 to June 2015 were collected. There were 131 males and 84 females, aged (56.7±10.1)years. All 215 patients were randomly divided into a training set of 143 cases and a testing set of 72 cases using a 2∶1 ratio of random seed numbers. The training set was used to construct the prediction model, and the testing set was used to validate the performance of prediction model. Observation indicators: (1) lymph node metastasis in LARC patients after nCRT; (2) imaging feature selection and model construction and evaluation. Com-parison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Univariate and multivariate analyses were conducted using the Logistic regression model. Performance evaluation of prediction model was conducted using the receiver operating characteristic (ROC) curve. The area under the curve (AUC), accuracy, sensitivity, and specificity were calculated. Calibration curves and decision curves were used to evaluate the consistency and clinical application value of the prediction model. Results:(1) Lymph node metastasis in LARC patients after nCRT. Of the 215 LARC patients after nCRT, results of postoperative pathological examination showed that there were 162 cases with negative lymph node metastasis and 53 cases with positive lymph node metastasis, showing significant differences in age and maximum short-axis diameter of lymph node between them ( t=2.178, Z=-5.305, P<0.05). (2) Imaging feature selection and model construction and evaluation. Forty-one imaging features were extracted from the 215 LARC patients after nCRT, including 9 gray-level first-order features, 24 gray-level co-occurrence matrix features and 8 shape features. The score of lymph node (LNscore) in 162 cases with negative lymph node metastasis and 53 cases with positive lymph node metastasis were 0.18(0.10,0.33) and 0.39(0.23,0.54), respectively, showing a significant difference between them ( Z=-5.487, P<0.05). Results of multivariate analysis showed that maximum short-axis diameter of lymph node and LNscore were independent factors influencing lymph node metastasis of LARC patients after nCRT ( odds ratio=1.277, 25.514, 95% confidence interval as 1.010-1.614, 2.003-324.964, P<0.05). A Logistic regression joint prediction model was constructed by incorporating the maximum short-axis diameter of lymph node and LNscore. The ROC curves results showed that the AUC, accuracy, sensitivity, and specificity of the joint prediction model in the training set were 0.779 (95% confidence interval as 0.702-0.844), 72.7%, 71.4%, and 73.2%, respectively. The above indicators in the testing set were 0.805 (95% confidence interval as 0.694-0.889), 80.6%, 66.7%, and 85.2%, respectively. Calibration curves in both training set and test set showed good agreement with the ideal curve, indicating high calibration. Decision curves demonstrated the model′s clinical utility with a high net benefit. Conclusion:The maximum short-axis diameter of lymph node and LNscore are independent factors influencing lymph node metastasis of LARC patients after nCRT. The joint prediction model constructed based on the above indicators can be used to predict lymph node metastasis in LARC patients after nCRT.

Objective To observe the value of Cox proportional hazards regression model constructed based on high-resolution MRI for predicting the risk of esophageal squamous cell carcinoma(ESCC)progression after definitive chemoradiotherapy(dCRT).Methods Thirty ESCC patients who underwent dCRT were retrospectively enrolled.Quantitative and qualitative indicators of primary tumor and imaging-defined metastatic lymph nodes were analyzed based on pre-treatment high-resolution M RI.The progression-free survival(PFS)of patients were recorded.A Cox proportional hazards regression model was established to predict the risk of tumor progression based on MRI indices,and the risks of tumor progression were stratified into high and low according to the median prediction.PFS rates were compared between patients with high or low risk of tumor progression.Results Tumor thickness(HR[95％CI]=1.210[1.025,1.429],P=0.024),relationship between the tumor and aorta(HR[95％CI]=4.275[1.064,17.168],P=0.041)and lymph node signal change rate on delayed phase pre-treatment MRI(HR[95％CI]=0.049[0.007,0.362],P=0.003)were all independent factors for predicting PFS.Based on Cox proportional hazards regression model and its predicted value,PFS rate in high risk patients was lower than that in low risk patients(P＜0.05).Conclusion High-resolution MRI could be used to predict prognosis of ESCC after dCRT.

In the evolution of colorectal cancer imaging technology in the past 40 years,application of multislice spiral CT and high-resolution MRI has not only propelled the anatomical staging of colorectal cancer into the era of precision,but also achieved quantitative stratification of tumor recurrence risk through detection of key indicators like extramural vascular invasion.Breakthroughs in functional imaging techniques such as diffusion-weighted imaging are of greater milestone significance,which improved the detection rate of metastatic lesions and constructed the foundation for early intervention.The integration of radiomics and artificial intelligence(AI)technologies has further enabled the non-invasive prediction of tumor molecular subtypes and optimized clinical decision pathways through treatment response modeling.However,development in the field still faces multiple bottlenecks.Looking ahead to the future,building a multimodal intelligent diagnosis and treatment ecosystem is the core direction of development of colorectal cancer imaging.Risk stratification models that integrate clinical-imaging-pathological data,prospective multicenter data pools and interdisciplinary collaboration platforms will promote imaging from traditional"auxiliary diagnostic tool"towards a paradigm shift as"treatment decision-making engine".