Background::Artificial intelligence (AI) technology represented by deep learning has made remarkable achievements in digital pathology, enhancing the accuracy and reliability of diagnosis and prognosis evaluation. The spatial distribution of CD3 + and CD8 + T cells within the tumor microenvironment has been demonstrated to have a significant impact on the prognosis of colorectal cancer (CRC). This study aimed to investigate CD3 CT (CD3 + T cells density in the core of the tumor [CT]) prognostic ability in patients with CRC by using AI technology. Methods::The study involved the enrollment of 492 patients from two distinct medical centers, with 358 patients assigned to the training cohort and an additional 134 patients allocated to the validation cohort. To facilitate tissue segmentation and T-cells quantification in whole-slide images (WSIs), a fully automated workflow based on deep learning was devised. Upon the completion of tissue segmentation and subsequent cell segmentation, a comprehensive analysis was conducted.Results::The evaluation of various positive T cell densities revealed comparable discriminatory ability between CD3 CT and CD3-CD8 (the combination of CD3 + and CD8 + T cells density within the CT and invasive margin) in predicting mortality (C-index in training cohort: 0.65 vs. 0.64; validation cohort: 0.69 vs. 0.69). The CD3 CT was confirmed as an independent prognostic factor, with high CD3 CT density associated with increased overall survival (OS) in the training cohort (hazard ratio [HR] = 0.22, 95% confidence interval [CI]: 0.12–0.38, P <0.001) and validation cohort (HR = 0.21, 95% CI: 0.05–0.92, P = 0.037). Conclusions::We quantify the spatial distribution of CD3 + and CD8 + T cells within tissue regions in WSIs using AI technology. The CD3 CT confirmed as a stage-independent predictor for OS in CRC patients. Moreover, CD3 CT shows promise in simplifying the CD3-CD8 system and facilitating its practical application in clinical settings.

Primary liver cancer is a common malignant digestive system tumor, with hepatocellular carcinoma being the most common pathological type. Radiomics significantly boosts the efficiency of predictions by accurately capturing the intrinsically heterogeneous features of tumors that are difficult to discern with the human eye in imaging images. This article outlines the background and concepts of radiomics, introduces its latest research progress in various aspects, such as diagnosis and differential diagnosis, prediction of pathological molecular subtypes, efficacy evaluation, and survival prediction, and further discusses its limitations and prospects in HCC.

Objective:To investigate the current funding landscape of medical artificial intelligence (AI) projects in National Natural Science Foundation of China (NSFC) from 2015 to 2019.Methods:From 2015 to 2019, AI-related projects in NSFC Medical Science Department were collected. Comprehensive analysis was performed in the projects information including year, title, supporting institution, fund type, research findings, etc.Results:NSFC has funded a total of 278 projects related to artificial intelligence, with the total funding amount of 139 million yuan. The number of projects and the funding amount were increasing year by year. Among these, 90% (249/278) were general programs and young scientist funds; 53% (148/278) of the projects were regionally distributed in Beijing, Shanghai and Guangdong; 66% (184/278) of the projects were imaging-related researches; the projects mainly focused on diseases with high incidence in China, including neoplastic diseases, cardiovascular and nervous system diseases.Conclusion:The AI-related projects funded by NSFC are characterized by rapid growth in number and fund amounts, wide coverage of disciplines, and diverse types of research diseases. However, the unbalanced distribution of regions, research fields, and supporting institutions demands more attention in future.

Objective:To explore the value of a radiomics nomogram based on T 1WI for prediction of the relapse of osteosarcoma after surgery within 1 year from multicenter data. Methods:The imaging and clinical data of 107 patients with pathologica1ly confirmed osteosarcoma who received neoadjuvant chemotherapy before surgery from 6 hospitals from January 2009 to October 2017 were retrospectively analyzed. A training cohort consisted of 75 patients from firstly enrolled 4 hospitals and an independent validation cohort of 32 patients from other 2 hospitals. Pretreatment T 1WI was used to extract radiomics features. Least absolute shrinkage and selection operator (LASSO) regression was applied to reduce the dimension and then the radiomics signature was constructed to predict the relapse of osteosarcoma after surgery within 1 year in training cohort. Independent clinical risk factors were screened using one-way logistic regression, and then a radiomics nomogram incorporated the radiomics signature and MRI characteristics was developed by multivariate logistic regression. The predictive nomogram was evaluated using receiver operating characteristic (ROC) curve in the training cohort, and validated in the independent validation cohort. The calibration curve was used to evaluate the agreement between prediction and actual observation and the decision curve was used to demonstrate the clinical usefulness. Results:Based on T 1WI from multicenter institutions, the radiomics signature was built using 2 valuable selected features that were significantly associated with relapse within 1 year. Two selected features included 1 gray-level co-occurrence matrices (GLCM) feature (L_G_1.0_GLCM_homogeneity1, LASSO coefficient 3.122) and 1 gray-level run length matrix (GLRLM) feature (GLRLM_RP, LASSO coefficient -2.474). The prediction nomogram including radiomics signature and MRI characteristics (joint invasion and perivascular involvement) showed good discrimination with the area under the ROC curve of 0.884 and 0.821 in the training and validation cohorts, respectively. The calibration curve showed that the nomogram achieved good agreement between prediction and actual observation. Decision curve analysis demonstrated that the radiomics nomogram was clinically useful when the threshold probability was greater than 21%. Conclusion:The radiomics nomogram based on T 1WI can be used as a non-invasive quantitative tool to predict relapse of osteosarcoma within 1 year before treatment, which provides support for clinical decision-making in osteosarcoma.

Objective: To evaluate the effect of height (HT), total body weight (TBW), body mass index (BMI), lean body weight (LBW), body surface area (BSA) and blood volume (BV) on aortic and liver contrast enhancement during upper abdominal contrast-enhanced CT scans. Methods: One hundred and thirteen enrolled patients underwent upper abdominal multiphase contrast-enhanced CT scans. The enhancement (ΔHU) of aorta in hepatic arterial phase and liver parenchyma in portal venous phase were measured and calculated. The ΔHU values difference of aorta and liver parenchyma in subgroups between males and females, TBW<60 kg and TBW≥60 kg, BMI<25 kg/m² and BMI≥25 kg/m² were compared. To evaluate the effect of the patient′s body parameters on aortic and hepatic enhancement, we performed simple linear regression analyses between the change in CT numbers per gram of iodine (ΔHU/gI) at aorta and liver and each of the following: HT, TBW, BMI, LBW, BSA, and BV. Pearson and t test were used. Results: The mean ΔHU values of aorta and liver were significantly lower at males than that of at females (P<0.05). They were higher at TBW<60 kg patients than at TBW≥60 kg patients(P<0.05), and the mean ΔHU values of the liver at BMI<25 kg/m² patients were significantly higher than at BMI≥25 kg/m² patients(P<0.05). The proportion of the ΔHU values at liver less than 50 HU was higher at males (18.3%, 11/60) than at females (7.5%, 4/53). The most obvious negative correlation coefficients were found between the ΔHU/gI of aorta and LBW at hepatic arterial phase (r=-0.559, P<0.01), and between the ΔHU/gI of liver and BSA at portal venous phase (r=-0.680, P<0.01). Conclusion LBW or BSA could be the alternative body index to TBW for the calculation of personalized iodine dose protocol at aortic and liver enhanced CT scans.

Objective To explore the optimal body size index for the calculation of iodine contrast agent dose required for multiphase liver enhanced CT scans based on the total body weight (TBW),lean body weight (LBW)and body surface area (BSA).Methods Two hundred and twenty enrolled patients were randomly divided into three groups,TBW-group (n＝75),LBW-group (n＝72)and BSA-group (n＝73),and administrated iodine doses were 600 mg I/TBW(kg),780 mg I/LBW(kg)and 22 g I/BSA(m2 ),respectively.All patients had taken upper abdominal plain scans and triple-phase enhanced CT scans.The enhanced values (ΔHU)of the aorta at hepatic arterial phase (HAP),the portal vein and liver parenchyma at portal venous phase (PVP)were compared.The correlation coefficients of adjusted maximal hepatic enhancement(aMHE)with TBW,LBW and BSA in three groups were evaluated,respectively.Results There were no statistical differences in the ΔHU values of the aorta at HAP and the portal vein and liver parenchyma at PVP in the three groups respectively.The smallest variances of the aorta at HAP,the portal vein and liver parenchyma at PVP were found in the LBW group. The aMHE showed mildly positive correlation with TBW (r＝0.230)with a P value of 0.047,but it was consistent with LBW (r＝0.158)and BSA (r＝－0.1 54)with corresponding P values of 0.1 85 and 0.1 9 2 ,respectively.Conclusion Compared with TBW and BSA,iodine contrast agent dose calculated based on the patient’s LBW can improve the patient-to-patient uniformities on aorta,portal vein and liver enhancement during the liver multiphase enhanced CT scans.The LBW is the best body index for the calculation of iodine dose on liver enhanced CT scans.

To develop and validate a fat-suppressed (T2 weighted-magnetic resonance imaging, T2W-MRI) based radiomics signature to preoperatively evaluate the histologic grade (grade I/II VS. grade III) of invasive breast cancer.
 Methods: A total of 202 patients with MRI examination and pathologically confirmed invasive breast cancer from June 2011 to February 2017 were retrospectively enrolled. After retrieving fat-suppressed T2W images and tumor segmentation, radiomics features were extracted and valuable features were selected to build a radiomic signature with the least absolute shrinkage and selection operator (LASSO) method. Mann-Whitney U test was used to explore the correlation between radiomics signature and histologic grade. Receiver operating characteristics (ROC) curve was applied to determine the discriminative performance of the radiomics signature [area under curre (AUC), sensitivity, specificity, and accuracy]. An independent validation dataset was used to confirm the discriminatory power of radiomics signature. 
 Results: Eight radiomics features were selected to build a radiomics signature, which showed good performance for preoperatively evaluating histologic grade of invasive breast cancer, with an AUC of 0.802 (95% CI 0.729 to 0.875), sensitivity of 78.7%, specificity of 70.3% and accuracy of 73.7% in training dataset and AUC of 0.812 (95% CI 0.686 to 0.938), sensitivity of 80.0%, specificity of 73.3% and accuracy of 76.0% in the validation dataset.
 Conclusion: The fat-suppressed T2W-MRI based radiomics signature can be used to preoperatively evaluate the histologic grade of invasive breast cancer, which may assist clinical decision-maker.
Breast Neoplasms ; diagnostic imaging ; Humans ; Magnetic Resonance Imaging ; Preoperative Care ; ROC Curve ; Retrospective Studies

To build a CT-based radiomics predictive mode to evaluate the differentiation degree of the esophageal squamous carcinoma.
 Methods: A total of 160 patients with surgical pathology, complete clinical data and chest CT scanning before operation were retrospectively collected from January 2008 to August 2016. All patients were assigned randomly to a primary data set and an independent validation. Texture analysis was performed on CT images, while the carcinomas were performed by manual segmentation to extract the radiomics features. Radiomics features were extracted and 9 radiomics signatures were finally selected after dimension reduction. Radiomics features were extracted and established via Matlab. Multivariable logistic regression analysis was performed to build the predictive model. A 10-fold cross-validation was used for selecting parameters in the least absolute shrinkage and selection operator (LASSO) model by minimum criteria. The receiver operating characteristic (ROC) curves and areas under ROC curve (AUC) were used to compare the model performance in the primary validation and the independent validation for evaluating the differentiation degree of esophageal squamous carcinoma.
 Results: Radiomics signature showed great effect in discriminating primary data set and independent validation. The predictive model had a good performance in primary data set. The AUC was 0.791, the sensitivity was 81.6%, and specificity was 72.3%. In the independent validation, the AUC was 0.757, the sensitivity was 70.0%, and the specificity was 73.0%.
 Conclusion: The predictive model can be used for evaluating the differentiation degree of esophageal squamous carcinoma efficiently, which can be helpful to clinicians in diagnosis and choice of treatment for esophageal squamous carcinoma.
Carcinoma, Squamous Cell ; Esophageal Neoplasms ; Humans ; ROC Curve ; Retrospective Studies ; Tomography, X-Ray Computed

To investigate the effects of different wavelet filters on correlation and diagnostic performance of radiomics features.
 Methods: A total of 143 colorectal cancer (CRC) patients (64 positive in lymph node metastasis and 79 negative) with contrast-enhanced CT examination were recruited. After labeling the tumor area by experienced radiologists, radiomics wavelets features based on 48 different wavelets were extracted using in-house software coded by Matlab. The correlation coefficients of the features with same names between different wavelets were calculated and got the distribution of high-correlation features between each wavelet. The least absolute shrinkage and selection operator (LASSO) was used to build signatures between lymph node metastasis and wavelet features data set based on different wavelets. The numbers of features in signatures and diagnostic performance were compared using Delong's test.
 Results: With the difference of wavelet order increased, the number of high-correlation features between two wavelets decreased. Some features were prone to high correlation between different wavelets. When building radiomics signature based on single wavelet, signatures built from 'rbio2.2', 'sym7' and 'db7' did well in predicting lymph node metastasis. The signature based on Daubechies wavelet feature set had the highest performance in predicting lymph node metastasis, while the signature from Biorthogonal wavelet features was worst. Improvement was significant in diagnostic performance after excluding the high-correlation features in the whole features set (P=0.004).
 Conclusion: In order to reduce the data redundancy of features, it is recommended to select wavelets with large differences in wavelet orders when calculating radiomics wavelet features. It is necessary to remove high correlation features for improving the diagnostic performance of radiomics signature.
Colorectal Neoplasms ; Humans ; Lymphatic Metastasis ; Retrospective Studies

Purpose Lymph-vascular invasion (LVI) is a risk factor for the prognosis of colorectal cancer, and it is of great value to evaluate the status of lymphatic vessels before treatment. This study aims to predict colorectal cancer LVI preoperatively based on radiomics. Materials and Methods Radiomics features were extracted from preoperative CT images of colorectal cancer retrospectively collected and radiomics labels were constructed. The predictive efficacy of radiomics labels were assessed and internally verified. Joint predictive factors were established by combining clinical factors with independent predictive efficacy and radiomics labels, and their predictive efficacy was evaluated. Results Radiomics labels consisted of 58 radiomics features were correlated with LVI status (P<0.0001)with the former showing good discrimination ability[C-index 0.719,95% CI:0.715-0.723]and classification ability(sensitivity 0.726, specificity 0.628) with internal validation (C-index 0.720). Joint predictive factors containing radiomics labels and carcino-embryonic antigen further enhanced the predictability of radiomics labels (C-index 0.751, sensitivity 0.788, specificity 0.667). Conclusion The radiomics labels built in this study can provide individualized prediction of LVI status of patients with colorectal cancer before surgery. Joint predictive factors in combination with clinical risk factors further improved predictive efficacy.