Objective To develop a combined model integrating radiomics and 3D deep learning features for improving the predictive efficacy of overall survival in non-small cell lung cancer(NSCLC)patients undergoing radiotherapy,thereby providing a foundation for optimizing individualized radiotherapy strategies.Methods A retrospective analysis was conducted on 522 NSCLC patients from 3 centers.Radiomics features were extracted from the tumor region of interest on radiotherapy planning CT scans,and a 3D-SE-ResNet was constructed to extract deep learning features.Following feature extraction,features were selected via univariate Cox analysis and Lasso-Cox regression,and a combined model was established by fusing the two feature types through principal component analysis.The discriminative ability of the model was evaluated using the concordance index(C-index)and the area under the receiver operating characteristic curve(AUC),while the risk stratification efficacy was verified by Kaplan-Meier survival analysis.Results The predictive performance of deep learning features was significantly superior to that of radiomics features(C-index:0.73 vs 0.65).The combined model achieved the highest predictive performance in the training set,internal test set,and external test set(C-index:0.74,0.69,0.72 respectively),with higher AUC values for predicting 1-year,2-year,and 3-year OS than either single model.Kaplan-Meier analysis showed significant differences in survival between the high-and low-risk groups(Log-rank test,P<0.001),and calibration curves indicated good consistency between predicted and actual survival outcomes.Conclusion The combined model integrating radiomics and 3D deep learning features can accurately predict survival outcomes in NSCLC patients undergoing radiotherapy.The multi-center validation results support its potential application in prognosis stratification for individualized radiotherapy.

Intrahepatic cholangiocarcinoma (ICC) is the second most common primary malignant tumor of the liver, characterized by high lethality and poor prognosis. Among the three subtypes of ICC, the intrahepatic mass-forming cholangiocarcinoma (IMCC) is the most prevalent. In recent years, the incidence of IMCC has been continuously rising, and its differential diagnosis and prognostic prediction have received widespread attention. Multimodal functional magnetic resonance imaging (MRI) integrates the advantages of various imaging modalities, capable of monitoring tumor hemodynamic changes, cellular metabolism, and other factors. Radiomics, with MRI as its basis, utilizes high-throughput extraction of imaging features to non-invasively acquire information on intra-tumor heterogeneity, subsequently assisting in the diagnosis of liver tumors. This article mainly summarizes the advancements in the application of multimodal functional MRI and MRI-based radiomics in the differential diagnosis and prognostic prediction of IMCC.

Objective To develop a combined model integrating radiomics and 3D deep learning features for improving the predictive efficacy of overall survival in non-small cell lung cancer(NSCLC)patients undergoing radiotherapy,thereby providing a foundation for optimizing individualized radiotherapy strategies.Methods A retrospective analysis was conducted on 522 NSCLC patients from 3 centers.Radiomics features were extracted from the tumor region of interest on radiotherapy planning CT scans,and a 3D-SE-ResNet was constructed to extract deep learning features.Following feature extraction,features were selected via univariate Cox analysis and Lasso-Cox regression,and a combined model was established by fusing the two feature types through principal component analysis.The discriminative ability of the model was evaluated using the concordance index(C-index)and the area under the receiver operating characteristic curve(AUC),while the risk stratification efficacy was verified by Kaplan-Meier survival analysis.Results The predictive performance of deep learning features was significantly superior to that of radiomics features(C-index:0.73 vs 0.65).The combined model achieved the highest predictive performance in the training set,internal test set,and external test set(C-index:0.74,0.69,0.72 respectively),with higher AUC values for predicting 1-year,2-year,and 3-year OS than either single model.Kaplan-Meier analysis showed significant differences in survival between the high-and low-risk groups(Log-rank test,P<0.001),and calibration curves indicated good consistency between predicted and actual survival outcomes.Conclusion The combined model integrating radiomics and 3D deep learning features can accurately predict survival outcomes in NSCLC patients undergoing radiotherapy.The multi-center validation results support its potential application in prognosis stratification for individualized radiotherapy.

Intrahepatic cholangiocarcinoma (ICC) is the second most common primary malignant tumor of the liver, characterized by high lethality and poor prognosis. Among the three subtypes of ICC, the intrahepatic mass-forming cholangiocarcinoma (IMCC) is the most prevalent. In recent years, the incidence of IMCC has been continuously rising, and its differential diagnosis and prognostic prediction have received widespread attention. Multimodal functional magnetic resonance imaging (MRI) integrates the advantages of various imaging modalities, capable of monitoring tumor hemodynamic changes, cellular metabolism, and other factors. Radiomics, with MRI as its basis, utilizes high-throughput extraction of imaging features to non-invasively acquire information on intra-tumor heterogeneity, subsequently assisting in the diagnosis of liver tumors. This article mainly summarizes the advancements in the application of multimodal functional MRI and MRI-based radiomics in the differential diagnosis and prognostic prediction of IMCC.

Atrial fibrillation (AF) is one of the most common arrhythmias, associated with high morbidity, mortality, and healthcare costs, and it places a significant burden on both individuals and society. Anti-arrhythmic drugs are the most commonly used strategy for treating AF. However, drug therapy faces challenges because of its limited efficacy and potential side effects. Catheter ablation is widely used as an alternative treatment for AF. Nevertheless, because the mechanism of AF is not fully understood, the recurrence rate after ablation remains high. In addition, the outcomes of ablation can vary significantly between medical institutions and patients, especially for persistent AF. Therefore, the issue of which ablation strategy is optimal is still far from settled. Computational modeling has the advantages of repeatable operation, low cost, freedom from risk, and complete control, and is a useful tool for not only predicting the results of different ablation strategies on the same model but also finding optimal personalized ablation targets for clinical reference and even guidance. This review summarizes three-dimensional computational modeling simulations of catheter ablation for AF, from the early-stage attempts such as Maze III or circumferential pulmonary vein isolation to the latest advances based on personalized substrate-guided ablation. Finally, we summarize current developments and challenges and provide our perspectives and suggestions for future directions.

Objective:To evaluate the efficacy and safety of eltrombopag for children with thrombocytopenia after hematopoietic stem cell transplantation (HSCT).Methods:Clinical data of 24 patients with thrombocytopenia after HSCT,who were treated with eltrombopag in the Department of Pediatrics, Sun Yat-sen Memorial Hospital, Sun Yat-sen University from August 1, 2018 to April 1, 2019 were analyzed retrospectively. The response rate and adverse reactions of eltrombopag were evaluated. Patients were divided into groups by source of hematopoietic stem cells (umbilical cord blood group and peripheral stem cell group) and type of disease (malignant and non-malignant disease group) and the clinical outcomes between groups were compared. Rank Sum test was used for comparisons between groups.Results:Among 24 cases, 15 were males and 9 females, the age of starting eltrombopag was 7.7 (2.6-13.7) years, the time of eltrombopag treatment after HSCT was 27.5 (8.0-125.0) days, the time from treatment to complete response (CR) was 23.5 (6.0-83.0) days, with the treatment course 36.5 (8.0-90.0) days. The total dose of eltrombopag was 1 400(200-5 900) mg. Complete response rate was 92% (22/24),without eltrombopag related adverse reactions. Comparing with peripheral stem cell group ( n=8), the course and total dose of eltrombopag in umbilical cord blood group ( n=16) were significantly reduced(24.5 (8.0-81.0) vs. 65.5 (35.0-90.0) d, Z=-3.004, P=0.002; 900.0 (200.0-3 850.0) vs. 2 862.5 (1 175.0-5 900.0) mg, Z=-2.604, P=0.007), but no significant differences were found in the time from treatment to complete response, platelet count after 2 weeks of eltrombopag withdrawal or platelet count at the end point of follow-up (all P>0.05). Comparing malignant patients ( n=12) and non-malignant patients ( n=12), no significant differences were found in the time from treatment to complete response, course, total dose, platelet count after 2 weeks of eltrombopag withdrawal, and platelet count at the end point of follow-up in non-malignant patients (all P>0.05). Conclusion:Eltrombopag is safe and maybe effective for thrombocytopenia after HSCT, especially for umbilical cord blood transplantation.

Objective To compare acute toxicity for stage Ⅱ-Ⅲ patients with rectal cancer irradiated with helical tomotherapy (HT) and conventional five-field intensity-modulated radiotherapy (5-IMRT).Methods The data of 84 stage Ⅱ-Ⅲ patients with rectal adenocarcinoma treated with concurrent chemoradiotherapy (CRT) were retrospectively analyzed.19 patients underwent postoperative CRT,and 65 patients underwent preoperative CRT.43 patients received radiotherapy with HT and 41 patients with 5-IMRT.The delineation on clinical target volume (CTV) and gross tumor target (GTV) was similar for two groups.The CTV to plan tumor volume (PTV) margins were 1.0 cm for patients with 5-1MRT and 0.5 cm for patients with HT.For all patients,a dose of 45.0-50.4 Gy,in daily fractions of 1.8 Gy,was delivered to PTV.For 45 patients with high risk factors,simultaneous integrated boost (SIB) was given to the tumor or tumor bed of a total dose of 55.0-60.0 Gy,in daily fractions of 2.1-2.3 Gy.Before treatment,the patients treated with HT underwent scanning by the tomotherapy-integrated megavoltage computed tomography (MVCT) scan modality and were positioned by co-registration of these images to the original kilovoltage planning CT image set.Concurrent capecitabine every day 1 600 mg/m2,twice daily on every day in the week.Results The rates of grade ≥ 2 acute cystitis were 7.0 ％ (3 cases) in HT group and 2.4 ％ (1 case) in 5-IMRT group (P =0.616),and ≥3 grade acute diarrhea were 4.7 ％ (2 cases) and 12.2 ％ (5 cases),respectively (P =0.259).≥2 grade leukopenia were 48.8 ％ (21 cases) and 19.5 ％ (8 cases),respectively (P =0.005),≥1 grade anemia were 34.9 ％ (15 cases) and 14.6 ％ (6 cases),respectively (P =0.032),and ≥1 grade thrombocytopenia were 23.3 ％ (10 cases) and 14.6 ％ (6 cases),respectively (P =0.314).Conclusions There is no significant difference in acute diarrhea and cystitis for patients treated with HT and 5-IMRT.Leukopenia and anemia in patients treated with HT are worse than those in patients with 5-IMRT,and thrombocytopenia is similar in the two groups.

Objective To analyze the response rate and prognostic factors for patients with locally recurrent rectal cancer treated with hypofractionated chemoradiotherapy without reresection.Methods Totally 52 patients with locally recurrent rectal cancer received hypofractionated irradiation and concurrent chemotherapy from January 2006 to January 2013 were enrolled.All patients received intensity-modulated radiotherapy (IMRT).The median dose was 63.4 Gy (61.6-64.4 Gy) at 2.2-2.3 Gy/f,5 f/week.Thirteen patients underwent prophylactic irradiation at lymph nodes region,the total dose of 45-50.4 Gy with conventional fraction and a simultaneous integrated boost was used.All patients received concurrent chemotherapy,capecitabine at 1 650 mg·m-2 ·d-1,divided into 2 times,5 d/week.The variables were compared by the chi-square test or Fisher's exact test.Local control (LC) and overall survival (OS) were calculated with using the Kaplan-Meier method.Results For all patients,the clinical complete response (CR),partial response (PR),stable disease (SD) and progressive disease (PD) was 23.1％,38.5％,32.7％ and 5.8％,respectively.The response rate (CR + PR) for patients with previous irradiation to pelvis and without were 37.1％ and 71.1％,respectively (x2 =5.40,P ＜ 0.05);for patients with 1 and 2 or more recurrent subsites were 81.8％ and 46.7％,respectively (x2 =6.63,P ＜ 0.05).Acute grade 3 skin and hematologic toxicities occurred in 19 patients (36.5％) and 1 patient (1.9％),respectively.None occurred grade 4 toxicity and none occurred grade 3 or more gastrointestinal and urologic toxicities.Four patients showed severe late toxicity of anastomotic stricture and performed a stoma at transverse colon.No other severe late toxicities were observed.The LC at 5 years was 49.1％ and the OS was 23.1％.Conclusions For patients with locally recurrent rectal cancer,hypofractionated chemoradiotherapy without resection is an acceptable and effective regimen,the response rate and long-term outcomes are promising.