From pixels to patient care: deep learning-enabled pathomics signature offers precise outcome predictions for immunotherapy in esophageal squamous cell cancer.

BACKGROUND: Immunotherapy has significantly improved survival of esophageal squamous cell cancer (ESCC) patients, however the clinical benefit was limited to only a small portion of patients. This study aimed to perform a deep learning signature based on H&E-stained pathological specimens to accurately predict the clinical benefit of PD-1 inhibitors in ESCC patients. METHODS: ESCC patients receiving PD-1 inhibitors from Shandong Cancer Hospital were included. WSI images of H&E-stained histological specimens of included patients were collected, and randomly divided into training (70%) and validation (30%) sets. The labels of images were defined by the progression-free survival (PFS) with the interval of 4 months. The pretrained ViT model was used for patch-level model training, and all patches were projected into probabilities after linear classifier. Then the most predictive patches were passed to RNN for final patient-level prediction to construct ESCC-pathomics signature (ESCC-PS). Accuracy rate and survival analysis were performed to evaluate the performance of ViT-RNN survival model in validation cohort. RESULTS: 163 ESCC patients receiving PD-1 inhibitors were included for model training. There were 486,188 patches of 1024*1024 pixels from 324 WSI images of H&E-stained histological specimens after image pre-processing. There were 120 patients with 227 images in training cohort and 43 patients with 97 images in validation cohort, with balanced baseline characteristics between two groups. The ESCC-PS achieved an accuracy of 84.5% in the validation cohort, and could distinguish patients into three risk groups with the median PFS of 2.6, 4.5 and 12.9 months (P < 0.001). The multivariate cox analysis revealed ESCC-PS could act as an independent predictor of survival from PD-1 inhibitors (P < 0.001). A combined signature incorporating ESCC-PS and expression of PD-L1 shows significantly improved accuracy in outcome prediction of PD-1 inhibitors compared to ESCC-PS and PD-L1 anlone, with the area under curve value of 0.904, 0.924, 0.610 for 6-month PFS and C-index of 0.814, 0.806, 0.601, respectively. CONCLUSIONS: The outcome supervised pathomics signature based on deep learning has the potential to enable superior prognostic stratification of ESCC patients receiving PD-1 inhibitors, which convert the images pixels to an effective and labour-saving tool to optimize clinical management of ESCC patients.

Impact of nab-paclitaxel plus PD-1/PD-L1 inhibitor on chemorefractory relapsed small-cell lung cancer.

Background: The present study evaluated the efficacy and safety of nab-paclitaxel (nab-PTX) with a concurrent PD-1/PD-L1 inhibitor in patients with refractory relapsed small-cell lung cancer (SCLC). Patients & methods: We retrospectively analyzed 240 patients with refractory relapsed SCLC: 40 patients were treated with nab-PTX plus PD-1/PD-L1 inhibitor, and 200 received traditional chemotherapy. Results: Median progression-free survival in the nab-PTX plus PD-1/PD-L1 inhibitor and traditional chemotherapy groups was 3.6 and 2.5 months (p = 0.0021), respectively. The median overall survival was 8.0 and 5.2 months (p = 0.0002), respectively. No new safety issues were identified. Conclusion: Nab-PTX plus PD-1/PD-L1 inhibitor significantly improved survival in patients with refractory relapsed SCLC compared with traditional chemotherapy.

Most patients with refractory relapsed small-cell lung cancer (SCLC) have few treatment options and dismal survival rates. This study analyzed the clinical outcomes and safety profiles of patients treated with nab-paclitaxel (nab-PTX) plus PD-1/PD-L1 inhibitor compared with patients treated with conventional chemotherapy. Notably, treatment with nab-paclitaxel and PD-1/PD-L1 inhibitor was associated with more favorable clinical outcomes, including better overall response and disease control rates, as well as longer overall survival and progression-free survival. In terms of side effect profiles, the two groups were balanced and had a similar incidence of grade ≥3 adverse events, including depleted blood cells and hair loss. To the best of our knowledge, we are the first to report the use of nab-PTX plus PD-1/PD-L1 inhibitor in the treatment of refractory relapsed SCLC. In addition, nab-PTX plus PD-1/PD-L1 inhibitor showed more effective antitumor activity in patients with secondary tumors in the liver, further confirming that nab-PTX plus PD-1/PD-L1 inhibitor is effective for patients with refractory relapsed SCLC.

Development and Validation of Nomograms for Predicting Pneumonia in Patients with COVID-19 and Lung Cancer.

Background: COVID-19 has spread worldwide, becoming a global threat to public health and can lead to complications, especially pneumonia, which can be life-threatening. However, in lung cancer patients, the prediction of pneumonia and severe pneumonia has not been studied. We aimed to develop effective models to assess pneumonia after SARS-CoV-2 infection in lung cancer patients to guide COVID-19 management. Methods: We retrospectively recruited 621 lung cancer patients diagnosed with COVID-19 via SARS-CoV-2 RT-PCR analysis in two medical centers and divided into training and validation group, respectively. Univariate and multivariate logistic regression analysis were used to identify independent risk factors of all-grade pneumonia and ≥ grade 2 pneumonia in the training group. Nomograms were established based on independent predictors and verified in the validation group. C-index, ROC curves, calibration curve, and DCA were used to evaluate the nomograms. Subgroup analyses in immunotherapy or thoracic radiotherapy patients were then conducted. Results: Among 621 lung cancer patients infected with SARS-CoV-2, 203 (32.7%) developed pneumonia, and 66 (10.6%) were ≥ grade 2. Multivariate logistic regression analysis showed that diabetes, thoracic radiotherapy, low platelet and low albumin at diagnosis of COVID-19 were significantly associated with all-grade pneumonia. The C-indices of the prediction nomograms in the training group and validation group were 0.702 and 0.673, respectively. Independent predictors of ≥ grade 2 pneumonia were age, KPS, thoracic radiotherapy, platelet and albumin at COVID 19 diagnosis, with C-indices of 0.811 and 0.799 in the training and validation groups. In the thoracic radiotherapy subgroup, 40.8% and 11% patients developed all-grade and ≥grade 2 pneumonia, respectively. The rates in the immunotherapy subgroup were 31.3% and 6.6%, respectively. Conclusion: We developed nomograms predicting the probability of pneumonia in lung cancer patients infected with SARS-CoV-2. The models showed good performance and can be used in the clinical management of COVID-19 in lung cancer patients. Higher-risk patients should be managed with enhanced protective measures and appropriate intervention.

Safety and Efficacy of Concurrent or Sequential Radiotherapy Plus (PD-1) Inhibitors in Oligometastatic Esophageal Cancer.

Purpose: We assess real-world outcomes, including safety and efficacy, of concurrent or sequential treatment with radiotherapy plus programmed cell death protein 1 (PD-1) inhibitors in patients with oligometastatic esophageal cancer (OMEC). Methods: This cohort study retrospectively collected clinical data of patients with synchronous or metachronous OMEC. All patients underwent concurrent or sequential treatment with radiotherapy plus PD-1 inhibitors. Each patient had up to five measurable metastatic lesions and up to three organs involved. Study endpoints were progression-free survival (PFS), treatment-related toxicities, locoregional progression-free survival (LRPFS), objective response rate (ORR), and disease control rate (DCR). Description statistics and Kaplan-Meier models were used for statistical analysis. Results: A total of 86 patients were included, most of whom were diagnosed with squamous cell carcinoma histology (98%) and presented with synchronous OMEC (64%). The median follow-up period was 17 months (range: 6-32 months), the median PFS was 15.2 months (95% confidence interval: 12.1-18.2 months); and the 1- and 2-year PFS rates were 61.4% and 26.7%, respectively. The 1- and 2-year LRPFS were 91.3% and 57.3%, respectively. The ORR and DCR were 46.5% and 91.8%, respectively. Forty-two patients (48.8%) experienced grade 3 or higher treatment-related adverse events (TRAEs); a grade 5 treatment-related adverse event was observed in one patient (1.2%) who died of immune-related pneumonitis. Conclusion: Combining radiotherapy with PD-1 inhibitors is a safe and effective treatment option for patients with OMEC. No new safety concerns were identified in this study. However, due to the potential risk of cumulative toxicity, an individual risk-benefit assessment for each patient is required prior to treatment initiation.

Prophylactic cranial irradiation-related lymphopenia affects survival in patients with limited-stage small cell lung cancer.

Background: The study aimed to identify the relations of the absolute lymphocyte count (ALC) nadir during prophylactic cranial irradiation (PCI) and patient outcomes in limited-stage small cell lung cancer (LS-SCLC). Methods: We analyzed 268 L S-SCLC patients who underwent PCI from 2012 to 2019. ALC values were collected prior, during, and 3 months post PCI. Kaplan-Meier and Cox regression analyses were performed to assess the relation of ALC to patient prognosis. Two nomograms were developed on the basis of clinical variables for survival prediction. Results: Compared with the ALC before PCI (1.13 × 109 cells/L), the ALC nadir during PCI was significantly reduced by 0.68 × 109 cells/L (P < 0.001) and raised to 1.02 × 109 cells/L 3 months post PCI. Patients with a low ALC nadir during PCI (<0.68 × 109 cells/L) had inferior progression free survival (PFS) (median PFS: 17.2 m vs. 43.7 m, P = 0.019) and overall survival (OS) (median OS: 29.0 m vs 39.1 m, P = 0.012). Multivariate Cox analysis revealed that age, smoking history, clinical stage, and ALC nadir were independent OS (P = 0.006, P = 0.005, P < 0.001 and P = 0.027, respectively), as well as independent PFS predictors (P = 0.032, P = 0.012, P = 0.012 and P = 0.018, respectively). After internal cross-validation, the corrected concordance indices of the predictive nomograms for PFS and OS were 0.637 and 0.663, respectively. Conclusion: LS-SCLC patients with a low ALC nadir during PCI likely have worse survival outcomes. Dynamic evaluation of the ALC during PCI is recommended for LS-SCLC patients.

Comparison of the Incidence Rate of Radiation Pneumonitis Observed in Patients with Advanced Lung Adenocarcinoma Treated with Simultaneous Thoracic Radiotherapy and 1G/2G/3G EGFR-TKIs.

Purpose: The present study aimed to evaluate the incidence rate of radiation pneumonitis (RP) in patients with advanced lung adenocarcinoma treated with first-generation (1G), second-generation (2G), or third-generation (3G) epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) combined with thoracic radiotherapy (TRT). Patients and Methods: Patients with advanced lung adenocarcinoma simultaneously treated with 1G/2G/3G EGFR-TKIs and TRT between 2015-2021 at Shandong Cancer Hospital and Institute were screened. The incidence rate of clinical and imaging RP was compared between the three groups. Results: A total of 200 patients treated with EGFR-TKIs were enrolled in this study, including 100 patients who were treated with 1G EGFR-TKIs, 50 patients who were treated with 2G EGFR-TKIs, and 50 patients who were treated with 3G EGFR-TKIs (patients matched in a 2:1:1 ratio for tumor characteristics). The overall incidence of clinical RP in the 1G, 2G, and 3G EGFR-TKI groups were 29%, 48%, and 28% (p=0.043), respectively, and that of imaging RP were 33%, 58%, and 36% (p=0.010), respectively. The incidence of RP with a clinical grade ≥3 in the three groups were 14%, 28%, and 12% (p=0.055), respectively, and that with an imaging grade ≥3 in the three groups were 11%, 32%, and 10% (p=0.002), respectively. The incidence of clinical RP was higher in the CFRT group than in the SBRT group, with an overall clinical grade of 38% vs 10% (p<0.001) and imaging grade of 46% vs 10% (p<0.001), respectively. In the multivariate analysis, only GTV volume was an independent predictive factor for all risks of clinical and imaging RP. V20 and grouping of 1G/2G/3G EGFR-TKIs were other independent predictive factors for the risk factors of RP for imaging grades. Conclusion: Compared with 2G EGFR-TKIs combined with TRT, 1G or 3G EGFR-TKIs combined with TRT achieved a lower incidence of RP.

Transformation from Small Cell to Squamous Cell Carcinoma in a Thymic Carcinoma Patient with a Durable Response to Anlotinib: A Case Report.

The most common pathologic type of thymic carcinoma (TC) is squamous cell carcinoma (SCC). Small cell carcinoma is relatively rare, accounting for approximately 2% to 5% of all thymic tumors. Histologic transformation of TC has not yet been reported. Available treatments for TC patients who progress after first-line therapy are limited, which contributes to their poor prognosis. We reported an extraordinary case of a 66-year-old man who was diagnosed with thymic small cell carcinoma that transformed into SCC after third-line treatment. Surprisingly, the patient had a progression-free survival (PFS) of 25 months and an overall survival (OS) of 10 years on anlotinib as fourth-line therapy. The tolerance was well. Thus, anlotinib may be a safe and promising treatment for TC patients, especially those who undergo histologic transformation.

Association between immune-related adverse events and the efficacy of PD-1 inhibitors in advanced esophageal cancer.

Introduction: Recent developments in immune checkpoint inhibitors (ICIs) have improved the treatment outcomes of esophageal cancer (EC); however, it may initiate immune-related adverse events (irAEs) in some patients. The ICIs' therapeutic efficacy is associated with irAEs in patients with non-small cell lung cancer or renal cell carcinoma, although this association is unknown in EC. The purpose of this study was to explore the association between irAEs and the efficacy of programmed death 1 (PD-1) inhibitors in EC patients. Patients and methods: This study included patients with advanced EC treated with PD-1 inhibitors. The patients were divided into two groups according to the occurrence of irAEs. Afterward, the efficacy was compared between the irAE-negative and irAE-positive groups, and we analyzed the predictive factors of irAEs and survival. Results: Overall, 295 patients were included in this study. Baseline characteristics were balanced in the irAE-negative and irAE-positive groups. In total, 143 (48.47%) patients experienced irAEs. The most frequent irAEs were anemia (49, 16.61%), hyperthyroidism (45, 15.25%), and pneumonitis (44, 14.92%). In total, 33 (11.19%) patients had grade ≥ 3 irAEs and pneumonitis have 15 (5.08%). No grade 5 adverse events were observed. A total of 52 (17.63%) and 91 (30.85%) patients had single and multiple irAEs, respectively. Compared with patients without irAEs, those with irAEs had significantly higher objective response rate (ORR) (37.76% vs. 25.00%, p = 0.018) and disease control rate (DCR) (92.31% vs. 83.55%, p = 0.022). Univariate Cox analyses indicated the significant association between irAEs and improved median progression-free survival (PFS) (10.27 vs. 6.2 months, p < 0.001) and overall survival (OS) (15.4 vs. 9.2 months, p < 0.001). In multivariate analyses, irAEs were independently associated with longer PFS (p = 0.011) and OS (p = 0.002). Moreover, multivariate analysis revealed that cycles > 8, radiation, as well as antiangiogenic therapy were strongly associated with irAEs development (p < 0.001, p = 0.002, and p = 0.025, respectively). Conclusion: In advanced EC, patients with irAEs showed markedly better efficacy in ORR, DCR, PFS, and OS compared with patients without irAEs.

A novel deep learning prognostic system improves survival predictions for stage III non-small cell lung cancer.

BACKGROUND: Accurate prognostic prediction plays a crucial role in the clinical setting. However, the TNM staging system fails to provide satisfactory individual survival prediction for stage III non-small cell lung cancer (NSCLC). The performance of the deep learning network for survival prediction in stage III NSCLC has not been explored. OBJECTIVES: This study aimed to develop a deep learning-based prognostic system that could achieve better predictive performance than the existing staging system for stage III NSCLC. METHODS: In this study, a deep survival learning model (DSLM) for stage III NSCLC was developed based on the Surveillance, Epidemiology, and End Results (SEER) database and was independently tested with another external cohort from our institute. DSLM was compared with the Cox proportional hazard (CPH) and random survival forest (RSF) models. A new prognostic system for stage III NSCLC was also proposed based on the established deep learning model. RESULTS: The study included 16,613 patients with stage III NSCLC from the SEER database. DSLM showed the best performance in survival prediction, with a C-index of 0.725 in the validation set, followed by RSF (0.688) and CPH (0.683). DSLM also showed C-indices of 0.719 and 0.665 in the internal and real-world external testing datasets, respectively. In addition, the new prognostic system based on DSLM (AUROC = 0.744) showed better performance than the TNM staging system (AUROC = 0.561). CONCLUSION: In this study, a new, integrated deep learning-based prognostic model was developed and evaluated for stage III NSCLC. This novel approach may be valuable in improving patient stratification and potentially provide meaningful prognostic information that contributes to personalized therapy.