Interpretable deep learning insights: Unveiling the role of 1 Gy volume on lymphopenia after radiotherapy in breast cancer.

BACKGROUND: Lymphopenia is known for its significance on poor survivals in breast cancer (BC) patients. Considering full dosimetric data, this study aimed to develop and validate predictive models for lymphopenia after radiotherapy (RT) in BC. MATERIAL AND METHODS: BC patients treated with adjuvant RT were eligible in this multicenter study. The study endpoint was lympopenia, defined as the reduction in absolute lymphocytes and graded lymphopenia after RT. The dose-volume histogram (DVH) data of related critical structures and clinical factors were taken into account for the development of dense neural network (DNN) predictive models. The developed DNN models were validated using external patient cohorts. RESULTS: Totally 918 consecutive patients with invasive BC enrolled. The training, testing, and external validating datasets consisted of 589, 203, and 126 patients, respectively. Treatment volumes at nearly all dose levels of the DVH were significant predictors for lymphopenia following RT, including volumes at very low-dose 1 Gy (V1) of organs at risk (OARs) including lung, heart and body, especially ipsilateral-lung V1. A final DNN model, combining full DVH dosimetric parameters of OARs and three key clinical factors, achieved a predictive accuracy of 75 % or higher. CONCLUSION: This study demonstrated and externally validated the significance of full dosimetric data, particularly the volume of low dose at as low as 1 Gy of critical structures on lymphopenia after radiation in BC patients. The significance of V1 deserves special attention, as modern VMAT RT technology often has a relatively high value of this parameter. Further study warranted for RT plan optimization.

Survival Outcome Analysis of Stereotactic Body Radiotherapy and Immunotherapy (SBRT-IO) versus SBRT-Alone in Unresectable Hepatocellular Carcinoma.

Introduction: While combination of stereotactic body radiotherapy (SBRT) and immunotherapy are promising, their efficacy and safety have not been compared with SBRT-alone in patients with unresectable hepatocellular carcinoma (HCC). Methods: This retrospective study included 100 patients with nonmetastatic, unresectable HCC in two hospitals. Eligible patients had tumor nodules ≤3 and Child-Pugh liver function score of A5 to B7. Seventy patients received SBRT-alone, and 30 patients underwent combined SBRT and immunotherapy (SBRT-IO). Overall survival (OS), time to progression (TTP), overall response rate (ORR), and toxicity were analyzed. We adjusted for the potential confounding factors using propensity score matching. Results: The median tumor size was 7.3 cm (range, 2.6-18 cm). Twenty-five (25%) of patients had vascular invasion. Before propensity score matching, the 1-year and 3-year OS rate was 89.9% and 59.8% in the SBRT-IO group and 75.7% and 42.3% in SBRT-alone group (p = 0.039). After propensity score matching (1:2), 25 and 50 patients were selected from the SBRT-IO and SBRT-alone group. The 1-year and 3-year OS was 92.0% and 63.9% in the SBRT-IO group versus 74.0% and 43.3% in the SBRT-alone group (p = 0.034). The 1-year and 3-year TTP was better in SBRT-IO group (1-year: 68.9% vs. 58.9% and 3-year: 61.3% vs. 32.5%, p = 0.057). The ORR of 88% (complete response [CR]: 56%, partial response [PR]: 22%) in SBRT-IO arm was significantly better than 50% (CR: 20%, PR: 30%) in the SBRT-alone arm (p = 0.006). Three patients (12%) developed ≥grade 3 immune-related treatment adverse events (n = 2 hepatitis, n = 1 dermatitis) leading to permanent treatment discontinuation. Conclusion: Adding immunotherapy to SBRT resulted in better survival with manageable toxicities. Prospective randomized trial is warranted.

Clinical factors and major pathological response after neoadjuvant chemoimmunotherapy in potentially resectable lung squamous cell carcinoma.

Objective: Major pathological response (MPR) helps evaluate the prognosis of patients with lung squamous cell carcinoma (LUSC). However, the clinical factors that affect the achievement of MPR after neoadjuvant chemoimmunotherapy (NCIO) in patients with LUSC remain unclear. This study aimed to explore the clinical factors affecting the MPR after NCIO in patients with potentially resectable LUSC. Methods: This retrospective study included patients with stage IIB-IIIC LUSC who underwent surgical resection after receiving NCIO at a center between March 2020 and November 2022. In addition to the postoperative pathological remission rate, sex, age, body mass index (BMI), smoking history, TNM stage, hematological and imaging test results, and other indicators were examined before NCIO. According to the pathological response rate of the surgically removed tumor tissue, the patients were split into MPR and non-MPR groups. Results: In total, 91 LUSC patients who met the study's eligibility criteria were enrolled: 32 (35%) patients in the non-MPR group and 59 (65%) in the MPR group, which included 43 cases of pathological complete remission (pCR). Pre-treatment lymphocyte level (LY) (odds ratio [OR] =5.997), tumor burden (OR=0.958), N classification (OR=15.915), radiographic response (OR=11.590), pulmonary atelectasis (OR=5.413), and PD-L1 expression (OR=1.028) were independently associated with MPR (all P < 0.05). Based on these six independent predictors, we developed a nomogram model of prediction having an area under the curve (AUC) of 0.914 that is simple to apply clinically to predict the MPR. The MPR group showed greater disease-free survival (DFS) than the non-MPR group, according to the survival analysis (P < 0.001). Conclusion: The MPR rate of NCIO for potentially resectable LUSC was 65%. LY, tumor burden, N classification, radiographic response, pulmonary atelectasis, and PD-L1 expression in patients with LUSC before NCIO were the independent and ideal predictors of MPR. The developed nomogram demonstrated a good degree of accuracy and resilience in predicting the MPR following NCIO, indicating that it is a useful tool for assuring customized therapy for patients with possibly resectable LUSC.

Hypofractionated Stereotactic Radiation Therapy Dosimetric Tolerances for the Inferior Aspect of the Brachial Plexus: A Systematic Review.

We sought to systematically review and summarize dosimetric factors associated with radiation-induced brachial plexopathy (RIBP) after stereotactic body radiation therapy (SBRT) or hypofractionated image guided radiation therapy (HIGRT). From published studies identified from searches of PubMed and Embase databases, data quantifying risks of RIBP after 1- to 10-fraction SBRT/HIGRT were extracted and summarized. Published studies have reported <10% risks of RIBP with maximum doses (Dmax) to the inferior aspect of the brachial plexus of 32 Gy in 5 fractions and 25 Gy in 3 fractions. For 10-fraction HIGRT, risks of RIBP appear to be low with Dmax < 40 to 50 Gy. For a given dose value, greater risks are anticipated with point volume-based metrics (ie, D0.03-0.035cc: minimum dose to hottest 0.03-0.035 cc) versus Dmax. With SBRT/HIGRT, there were insufficient published data to predict risks of RIBP relative to brachial plexus dose-volume exposure. Minimizing maximum doses and possibly volume exposure of the brachial plexus can reduce risks of RIBP after SBRT/HIGRT. Further study is needed to better understand the effect of volume exposure on the brachial plexus and whether there are location-specific susceptibilities along or within the brachial plexus structure.

Low-dose radiation therapy mobilizes antitumor immunity: New findings and future perspectives.

Radiotherapy has unique immunostimulatory and immunosuppressive effects. Although high-dose radiotherapy has been found to have systemic antitumor effects, clinically significant abscopal effects were uncommon on the basis of irradiating single lesion. Low-dose radiation therapy (LDRT) emerges as a novel approach to enhance the antitumor immune response due to its role as a leverage to reshape the tumor immune microenvironment (TIME). In this article, from bench to bedside, we reviewed the possible immunomodulatory role of LDRT on TIME and systemic tumor immune environment, and outlined preclinical evidence and clinical application. We also discussed the current challenges when LDRT is used as a combination therapy, including the optimal dose, fraction, frequency, and combination of drugs. The advantage of low toxicity makes LDRT potential to be applied in multiple lesions to amplify antitumor immune response in polymetastatic disease, and its intersection with other disciplines might also make it a direction for radiotherapy-combined modalities.

Treatment-Related Pneumonitis of EGFR Tyrosine Kinase Inhibitors Plus Thoracic Radiation Therapy in Patients With Non-Small Cell Lung Cancer: A Systematic Review and Meta-Analysis.

Thoracic radiation therapy (RT) for non-small cell lung cancers may overcome resistance to tyrosine kinase inhibitors (TKIs). However, the risk of severe treatment-related pneumonitis (TRP) is a major concern, and the results of the combined treatment remain controversial. Therefore, we aimed to systematically review existing publications and provide a meta-analysis of TRP from a combined therapy of thoracic RT and TKIs. A systematic literature review was performed using the PubMed-MEDLINE and Embase databases to identify eligible publications. The number of severe TRP cases of grade 3 or higher was extracted and then analyzed by fixed or randomized model meta-analysis. Heterogeneity tests were performed using the I² and τ² statistics. Subgroup analyses were conducted on the types of RT and the sequence of the combined treatment. Our literature search identified 37 eligible studies with 1143 patients. Severe TRP occurred in 3.8% (95% CI, 1.8%-6.5%) of patients overall, and fatal pneumonitis occurred rarely in 0.1% (95% CI, 0.0%-0.3%). In the subgroup analysis, the severe TRP proportion was 2.3% (95% CI, 1.0%-4.1%) for patients under definitive (chemo)RT (19 studies, n = 702) versus 2.9% (95% CI, 1.3%-5.1%) for patients who received local stereotactic body RT or palliative RT (15 studies, n = 361). The severe TRP rate was 4.9% (95% CI, 2.4%-8.1%) for concurrent TKI and RT (26 studies, n = 765), which was significantly higher than TRP of 0.4% (95% CI, 0.0%-3.1%) for sequential therapy (6 studies, n = 200). Our meta-analysis showed that combined thoracic RT and epidermal growth factor receptor-TKI therapy has an acceptable risk of severe TRP and rare mortality in patients with non-small cell lung cancers. Concurrent treatment is less tolerable and should be administered with caution. Further investigations using osimertinib are required as the data on its effects are limited.

Dosimetric analysis of brachial plexopathy after stereotactic body radiotherapy: Significance of organ delineation.

OBJECTIVES: Examine the significance of contouring the brachial plexus (BP) for toxicity estimation and select metrics for predicting radiation-induced brachial plexopathy (RIBP) after stereotactic body radiotherapy. MATERIALS AND METHODS: Patients with planning target volume (PTV) ≤ 2 cm from the BP were eligible. The BP was contoured primarily according to the RTOG 1106 atlas, while subclavian-axillary veins (SAV) were contoured according to RTOG 0236. Apical PTVs were classified as anterior (PTV-A) or posterior (PTV-B) PTVs. Variables predicting grade 2 or higher RIBP (RIBP2) were selected through least absolute shrinkage and selection operator regression and logistic regression. RESULTS: Among 137 patients with 140 BPs (median follow-up, 32.1 months), 11 experienced RIBP2. For patients with RIBP2, the maximum physical dose to the BP (BP-Dmax) was 46.5 Gy (median; range, 35.7 to 60.7 Gy). Of these patients, 54.5 % (6/11) satisfied the RTOG limits when using SAV delineation; among them, 83.3 % (5/6) had PTV-B. For patients with PTV-B, the maximum physical dose to SAV (SAV-Dmax) was 11.2 Gy (median) lower than BP-Dmax. Maximum and 0.3 cc biologically effective doses to the BP based on the linear-quadratic-linear model (BP-BEDmax LQL and BP-BED0.3cc LQL, α/ß = 3) were selected as predictive variables with thresholds of 118 and 73 Gy, respectively. CONCLUSION: Contouring SAV may significantly underestimate the RIBP2 risk in dosimetry, especially for patients with PTV-B. BP contouring indicated BP-BED0.3cc LQL and BP-BEDmax LQL as potential predictors of RIBP2.

Dosimetric Effect of Thymus and Thoracic Duct on Radiation-Induced Lymphopenia in Patients With Primary Lung Cancer Who Received Thoracic Radiation.

Purpose: Radiation-induced lymphopenia is a well-recognized factor for tumor control and survival in patients with cancer. This study aimed to determine the role of radiation dose to the thymus and thoracic duct on radiation-induced lymphopenia. Methods and Materials: Patients with primary lung cancer treated with thoracic radiation therapy between May 2015 and February 2020 with whole blood count data were eligible. Clinical characteristics, including age, gender, histology, stage, chemotherapy regimen, radiation dosimetry, and absolute lymphocyte count (ALC) were collected. The thymus and thoracic duct were contoured by one investigator for consistency and checked by one senior physician. The primary endpoint was radiation-induced decrease in lymphocytes, defined as the difference in ALC (DALC) before and after radiation therapy. Results: The data of a total of 116 consecutive patients were retrospectively retrieved. Significant correlations were found between DALC and several clinical factors. These factors include stage, chemotherapy or concurrent chemoradiation, biologically effective dose (BED), mean lung dose, mean body dose, effective dose to immune cells (EDIC), mean thymus dose (MTD), and mean thoracic duct dose (MTDD) (all P < .05). Ridge regression showed that DALC = 0.0063 × BED + 0.0172 × EDIC + 0.0002 × MTD + 0.0147 × MTDD + 0.2510 (overall P = .00025 and F = 5.85). The combination model has the highest area under the curve of 0.77 (P < .001) when fitting the logistic regression model on DALC categorized as binary endpoint. The sensitivity and specificity of the combined model were 89% and 58%, respectively. Conclusions: This study demonstrated for the first time that radiation doses to the thymus and thoracic duct are strongly associated with radiation-induced lymphopenia patients with lung cancer. Further validation studies are needed to implement thymus and thoracic duct as organs at risk.

Comparing effectiveness of image perturbation and test retest imaging in improving radiomic model reliability.

Image perturbation is a promising technique to assess radiomic feature repeatability, but whether it can achieve the same effect as test-retest imaging on model reliability is unknown. This study aimed to compare radiomic model reliability based on repeatable features determined by the two methods using four different classifiers. A 191-patient public breast cancer dataset with 71 test-retest scans was used with pre-determined 117 training and 74 testing samples. We collected apparent diffusion coefficient images and manual tumor segmentations for radiomic feature extraction. Random translations, rotations, and contour randomizations were performed on the training images, and intra-class correlation coefficient (ICC) was used to filter high repeatable features. We evaluated model reliability in both internal generalizability and robustness, which were quantified by training and testing AUC and prediction ICC. Higher testing performance was found at higher feature ICC thresholds, but it dropped significantly at ICC = 0.95 for the test-retest model. Similar optimal reliability can be achieved with testing AUC = 0.7-0.8 and prediction ICC > 0.9 at the ICC threshold of 0.9. It is recommended to include feature repeatability analysis using image perturbation in any radiomic study when test-retest is not feasible, but care should be taken when deciding the optimal feature repeatability criteria.

Effect of radiation fractionation on IDO1 via the NF-κB/COX2 axis in non-small cell lung cancer.

Radiotherapy (RT) is the mainstay treatment modality for lung cancer. We recently reported that conventionally fractionated radiotherapy (CRT) with daily fractionation of 2Gy significantly increased the activity of indoleamine 2,3-dioxygenase (IDO1), a known immune checkpoint, which predicted poorer long-term survival in patients with non-small cell lung cancer (NSCLC), while stereotactic body radiotherapy (SBRT) using fractionation size of 10Gy did not increase IDO1 activity and had better survival. Here we hypothesized that the hypofractionated SBRT kind of dose fraction stimulates host antitumor immunity via downregulating IDO1 in which CRT could not. We tested this hypothesis in vitro and in vivo using 10Gyx1 and 2Gyx8 fractionations in the laboratory. The results demonstrated that, although there was an initial downregulation after RT, the expression of IDO1 was ultimately upregulated by both fractionation regimens. The 10Gyx1 regimen had minimum upregulation, while the 2Gyx8 regimen significantly increased in IDO1 expression which was positively correlated with the elevated expressions of p-NF-κB and COX2. Pharmacological inhibition of COX2 abolished RT-induced IDO1 expression. Furthermore, the IDO1 inhibitor, D-1-methyl-tryptophan (D-1MT), exerted RT-related tumor-killing effects in the NSCLC cell lines and mouse models. These findings suggest that, in addition to being an immune suppressor, IDO1 may serve as an adaptive resistance factor in RT. Furthermore, an unappreciated mechanism may exist, where a larger fraction size might be superior to conventional sizes in cancer treatment. This study may provide a rationale for future research in using IDO1 as a biomarker to personalize RT dose fractionation and COX2 inhibitor to decrease radiation immune suppression from CRT.

Efficacy, safety, and correlative biomarkers of bintrafusp alfa in recurrent or metastatic nasopharyngeal cancer patients: a phase II clinical trial.

Background: The strategy of dual blockade of TGF-ß and PD-L1 pathways has not been previously tested in platinum-refractory recurrent or metastatic nasopharyngeal cancer (R/M NPC) patients. This study aimed to evaluate the safety and efficacy of bintrafusp alfa in refractory R/M NPC patients. Methods: In this single-arm, single-centre phase II clinical trial, 38 histologically confirmed R/M NPC patients were enrolled and administered with bintrafusp alfa every 2 weeks. Primary endpoint was objective response rate (ORR) per Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1). Secondary endpoints included progression-free survival (PFS), overall survival (OS), duration of response (DOR), and safety. Findings: Thirty-eight patients were accrued (33 men; median age, 54 years). ORR was 23.7% (complete response, n = 2; partial response, n = 7). The median DOR was 19.2 months, median PFS was 2.3 months, median OS was 17.0 months, and 1-year OS rate was 63.2%. Unfortunately, 25 patients (65.7%) progressed within 8 weeks of treatment, 15 patients (39.5%) and 8 patients (21.1%) developed hyper-progressive disease (HPD) per RECIST v1.1 and tumor growth rate (TGR) ratio respectively. Sixteen patients (42.4%) experienced ≥ grade 3 treatment-related adverse events (TRAEs), most commonly anemia (n = 9, 23.7%) and secondary malignancies (n = 4, 10.5%). TRAEs led to permanent treatment discontinuation in 7 patients. Patients with strong suppression of plasma TGFß1 level at week 8 were unexpectedly associated with worse ORR (9.1% vs 44.4%, P = 0.046) and development of HPD. There was no correlation between PD-L1 expression and ORR. Interpretation: Bintrafusp alfa demonstrated modest activity in R/M NPC but high rates of HPD and treatment discontinuation secondary to TRAEs are concerning. Funding: The project was supported by Alice Ho Miu Ling Nethersole Charity Foundation Professorship Endowed Fund and Merck KGaA.

The predictive role of soluble programmed death ligand 1 in digestive system cancers.

Introduction: The prognostic role of soluble programmed death ligand 1 (sPD-L1) in digestive system cancers (DSCs) remains inconclusive. This study aimed to explore the predictive value of sPD-L1 expression in DSCs. Methods: Comprehensive searches were run on the electronic databases (PubMed, Web of Science, EMBASE, and the Cochrane Library) to identify studies that assessed the prognostic role of sPD-L1 in DSCs. Review Manager software (version 5.3) was used for all analyses. Pooled data for survival outcomes were measured as hazard ratios (HRs), 95% confidence intervals (CIs), and odds ratios and their 95% CIs. Results: The search identified 18 studies involving 2,070 patients with DSCs. The meta-outcome revealed that a high level of sPD-L1 was related to poorer overall survival (HR, 3.06; 95% CI: 2.22-4.22, p<0.001) and disease-free survival (HR, 2.53; 95% CI: 1.67-3.83, p<0.001) in DSCs. Individually, the prognostic significance of high level of sPD-L1 expression was the highest in hepatic cell carcinoma (HR, 4.76; p<0.001) followed by gastric cancer (HR=3.55, p<0.001). Conclusion: sPD-L1 may be a prognostic factor in DSCs for overall survival and disease-free survival. Inflammatory cytokines, treatment approaches, and other factors may affect the expression of sPD-L1. Therefore, the prognostic value of sPD-L1 for recurrence and metastasis should be further investigated. sPD-L1 may also predict response to treatment. Well-designed prospective studies with standard assessment methods should be conducted to determine the prognostic value of sPD-L1 in DSCs.

Respiratory Invariant Textures From Static Computed Tomography Scans for Explainable Lung Function Characterization.

PURPOSE: The inherent characteristics of lung tissue independent of breathing maneuvers may provide fundamental information for function assessment. This paper attempted to correlate textural signatures from computed tomography (CT) with pulmonary function measurements. MATERIALS AND METHODS: Twenty-one lung cancer patients with thoracic 4-dimensional CT, DTPA-single-photon emission CT ventilation ( VNM ) scans, and available spirometry measurements (forced expiratory volume in 1 s, FEV 1 ; forced vital capacity, FVC; and FEV 1 /FVC) were collected. In subregional feature discovery, function-correlated candidates were identified from 79 radiomic features based on the statistical strength to differentiate defected/nondefected lung regions. Feature maps (FMs) of selected candidates were generated on 4-dimensional CT phases for a voxel-wise feature distribution study. Quantitative metrics were applied for validations, including the Spearman correlation coefficient (SCC) and the Dice similarity coefficient for FM- VNM spatial agreement assessments, intraclass correlation coefficient for FM interphase robustness evaluations, and FM-spirometry comparisons. RESULTS: At the subregion level, 8 function-correlated features were identified (effect size>0.330). The FMs of candidates yielded moderate-to-strong voxel-wise correlations with the reference VNM . The FMs of gray level dependence matrix dependence nonuniformity showed the highest robust (intraclass correlation coefficient=0.96 and P <0.0001) spatial correlation, with median SCCs ranging from 0.54 to 0.59 throughout the 10 breathing phases. Its phase-averaged FM achieved a median SCC of 0.60, a median Dice similarity coefficient of 0.60 (0.65) for high (low) functional lung volumes, and a correlation of 0.565 (0.646) between the spatially averaged feature values and FEV 1 (FEV 1 /FVC). CONCLUSIONS: The results provide further insight into the underlying association of specific pulmonary textures with both local ( VNM ) and global (FEV 1 /FVC, FEV 1 ) functions. Further validations of the FM generalizability and the standardization of implementation protocols are warranted before clinically relevant investigations.

A super-voxel-based method for generating surrogate lung ventilation images from CT.

Purpose: This study aimed to develop and evaluate CTVISVD , a super-voxel-based method for surrogate computed tomography ventilation imaging (CTVI). Methods and Materials: The study used four-dimensional CT (4DCT) and single-photon emission computed tomography (SPECT) images and corresponding lung masks from 21 patients with lung cancer obtained from the Ventilation And Medical Pulmonary Image Registration Evaluation dataset. The lung volume of the exhale CT for each patient was segmented into hundreds of super-voxels using the Simple Linear Iterative Clustering (SLIC) method. These super-voxel segments were applied to the CT and SPECT images to calculate the mean density values (D mean) and mean ventilation values (Vent mean), respectively. The final CT-derived ventilation images were generated by interpolation from the D mean values to yield CTVISVD. For the performance evaluation, the voxel- and region-wise differences between CTVISVD and SPECT were compared using Spearman's correlation and the Dice similarity coefficient index. Additionally, images were generated using two deformable image registration (DIR)-based methods, CTVIHU and CTVIJac, and compared with the SPECT images. Results: The correlation between the D mean and Vent mean of the super-voxel was 0.59 ± 0.09, representing a moderate-to-high correlation at the super-voxel level. In the voxel-wise evaluation, the CTVISVD method achieved a stronger average correlation (0.62 ± 0.10) with SPECT, which was significantly better than the correlations achieved with the CTVIHU (0.33 ± 0.14, p < 0.05) and CTVIJac (0.23 ± 0.11, p < 0.05) methods. For the region-wise evaluation, the Dice similarity coefficient of the high functional region for CTVISVD (0.63 ± 0.07) was significantly higher than the corresponding values for the CTVIHU (0.43 ± 0.08, p < 0.05) and CTVIJac (0.42 ± 0.05, p < 0.05) methods. Conclusion: The strong correlation between CTVISVD and SPECT demonstrates the potential usefulness of this novel method of ventilation estimation for surrogate ventilation imaging.

Regorafenib induces NOX5-mediated endoplasmic reticulum stress and potentiates the anti-tumor activity of cisplatin in non-small cell lung cancer cells.

Lung cancer is one of the most commonly diagnosed cancers worldwide. Although cisplatin-based chemotherapy regimens serve a pivotal role in non-small cell lung cancer (NSCLC) treatment, drug resistance and serious side effects limited its further clinical application. Regorafenib, a small-molecule multi-kinase inhibitor, was demonstrated to have promising anti-tumor activity in various solid tumors. In the present study, we found that regorafenib markedly enhanced cisplatin-induced cytotoxicity in lung cancer cells by activating reactive oxygen species (ROS)-mediated endoplasmic reticulum stress (ER Stress), c-Jun N-terminal kinase (JNK) and p38 mitogen-activated protein kinase (MAPK) signaling pathways. Regorafenib increased ROS generation by promoting NADPH oxidase 5 (NOX5) expression, and knocking down NOX5 attenuated ROS-mediated cytotoxicity of regorafenib in lung cancer cells. Additionally, mice xenograft model validated that synergistic anti-tumor effects of combined treatment with regorafenib and cisplatin. Our results suggested that combination therapy with regorafenib and cisplatin may serve as a potential therapeutic strategy for some NSCLC patients.

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification.

Background: Accurate assessment of coronavirus disease 2019 (COVID-19) lung involvement through chest radiograph plays an important role in effective management of the infection. This study aims to develop a two-step feature merging method to integrate image features from deep learning and radiomics to differentiate COVID-19, non-COVID-19 pneumonia and normal chest radiographs (CXR). Methods: In this study, a deformable convolutional neural network (deformable CNN) was developed and used as a feature extractor to obtain 1,024-dimensional deep learning latent representation (DLR) features. Then 1,069-dimensional radiomics features were extracted from the region of interest (ROI) guided by deformable CNN's attention. The two feature sets were concatenated to generate a merged feature set for classification. For comparative experiments, the same process has been applied to the DLR-only feature set for verifying the effectiveness of feature concatenation. Results: Using the merged feature set resulted in an overall average accuracy of 91.0% for three-class classification, representing a statistically significant improvement of 0.6% compared to the DLR-only classification. The recall and precision of classification into the COVID-19 class were 0.926 and 0.976, respectively. The feature merging method was shown to significantly improve the classification performance as compared to using only deep learning features, regardless of choice of classifier (P value <0.0001). Three classes' F1-score were 0.892, 0.890, and 0.950 correspondingly (i.e., normal, non-COVID-19 pneumonia, COVID-19). Conclusions: A two-step COVID-19 classification framework integrating information from both DLR and radiomics features (guided by deep learning attention mechanism) has been developed. The proposed feature merging method has been shown to improve the performance of chest radiograph classification as compared to the case of using only deep learning features.

Radiation-induced inferior brachial plexopathy after stereotactic body radiotherapy: Pooled analyses of risks.

INTRODUCTION: Radiation-induced brachial plexopathy (RIBP), resulting in symptomatic motor or sensory deficits of the upper extremity, is a risk after exposure of the brachial plexus to therapeutic doses of radiation. We sought to model dosimetric factors associated with risks of RIBP after stereotactic body radiotherapy (SBRT). METHODS: From a prior systematic review, 4 studies were identified that included individual patient data amenable to normal tissue complication probability (NTCP) modelling after SBRT for apical lung tumors. Two probit NTCP models were derived: one from 4 studies (including 221 patients with 229 targets and 18 events); and another from 3 studies (including 185 patients with 192 targets and 11 events) that similarly contoured the brachial plexus. RESULTS: NTCP models suggest ≈10% risks associated with brachial plexus maximum dose (Dmax) of ∼32-34 Gy in 3 fractions and ∼40-43 Gy in 5 fractions. RIBP risks increase with increasing brachial plexus Dmax. Compared to previously published data from conventionally-fractionated or moderately-hypofractionated radiotherapy for breast, lung and head and neck cancers (which tend to utilize radiation fields that circumferentially irradiate the brachial plexus), SBRT (characterized by steep dose gradients outside of the target volume) exhibits a much less steep dose-response with brachial plexus Dmax > 90-100 Gy in 2-Gy equivalents. CONCLUSIONS: A dose-response for risk of RIBP after SBRT is observed relative to brachial plexus Dmax. Comparisons to data from less conformal radiotherapy suggests potential dose-volume dependences of RIBP risks, though published data were not amenable to NTCP modelling of dose-volume measures associated with RIBP after SBRT.

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification.

Background: The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification. Methods: Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models. Results: Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images. Conclusions: The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

Sequential transarterial chemoembolisation and stereotactic body radiotherapy followed by immunotherapy as conversion therapy for patients with locally advanced, unresectable hepatocellular carcinoma (START-FIT): a single-arm, phase 2 trial.

BACKGROUND: The synergy between locoregional therapies and immune checkpoint inhibitors has not been investigated as conversion therapy for unresectable hepatocellular carcinoma. We aimed to investigate the activity of sequential transarterial chemoembolisation (TACE) and stereotactic body radiotherapy followed by avelumab (an anti-PD-L1 drug) for locally advanced, unresectable hepatocellular carcinoma. METHODS: START-FIT was a single-arm, phase 2 trial in patients with locally advanced hepatocellular carcinoma who were not suitable for curative treatment, conducted in two hospitals in Hong Kong and one in Shenzhen, China. Eligible patients were those aged 18 years or older with an Eastern Cooperative Oncology Group performance status 0-1, Child-Pugh liver function score A5 to B7, tumour size of at least 5 cm, a maximum of three tumour lesions, and adequate hepatic, renal, and bone marrow function. Participants received TACE on day 1, followed by stereotactic body radiotherapy (27·5-40·0 Gy in five fractions) at day 28. Avelumab (10 mg/kg) was administered 14 days following stereotactic body radiotherapy and every 2 weeks thereafter. The primary endpoint was the proportion of patients deemed amenable to curative treatment, defined as those who had a sustained complete or partial treatment response for at least 2 months and if curative treatment could be performed (ie, resection, radiofrequency ablation, or transplantation), analysed by intention to treat. Safety was also analysed in the intention-to-treat population. This trial is registered with ClinicalTrials.gov (NCT03817736) and has been completed. FINDINGS: Between March 18, 2019, and Jan 27, 2021, 33 patients (32 [97%] men and one [3%] woman) were enrolled. The median sum of the largest diameters of lesions was 15·1 cm (IQR 8·3-14·9). 21 (64%) patients had macrovascular invasion (hepatic vein [n=13], branched portal vein [n=3], or both [n=5]). Median follow-up was 17·2 months (IQR 7·8-25·8). 18 (55%) patients were deemed amenable to curative treatment: four (12%) of 33 patients had curative treatment (resection [n=2] or radiofrequency ablation [n=2]), and 14 (42%) had a radiological complete response and opted for close surveillance. 11 (33%) of 33 patients had treatment-related adverse events that were grade 3 or worse. The most common treatment-related grade 3 or worse adverse event was transient increase in alanine aminotransferase or aspartate aminotransferase (five [15%]) after TACE. Five (15%) patients developed immune-related adverse events of grade 3 or worse (three had hepatitis, two had dermatitis). INTERPRETATION: To our knowledge, this is the first prospective trial using the combination of immunotherapy and locoregional treatment as conversion therapy for locally advanced unresectable hepatocellular carcinoma, with promising results. Future randomised trials with larger cohorts of patients are warranted. FUNDING: Merck.