Large cell neuroendocrine carcinoma (LCNEC) of the urinary tract is a rare disease. We present a relatively large retrospective cohort of urinary LCNEC, 20 from the urinary bladder, and 2 from the ureter, from a single institution. The patients included 16 men and 6 women with a median age of 74.5 years. Most LCNEC presented at an advanced stage with tumors invading the muscularis propria and beyond (21/22). Eight cases were pure LCNEC, while 14 cases were mixed with other histologic types, including conventional urothelial carcinoma (n=9), carcinoma in situ (n=7), small cell carcinoma (n=6), and urothelial carcinoma with glandular (n=3) features. Most LCNEC expressed neuroendocrine markers synaptophysin (22/22), chromogranin (13/16), CD56 (7/7), TTF1 (8/8), and INSM1 (2/3). They were negative for common urothelial markers including HMWCK (0/3), p40/p63 (0/6), CK20 (0/10), and had variable GATA3 staining (4/8). Ki-67 stained 25% to nearly 100% tumor cell nuclei. Patient survival was associated with cancer stage, and pure LCNEC showed worse survival than mixed LCNEC. Compared with small cell carcinoma at similar stages from a prior study, LCNEC had a worse prognosis only when patients developed metastatic disease. For organ-confined LCNEC, neoadjuvant chemotherapy followed by radical resection is the treatment option to achieve long-term survival.

Objective: This study explores a semi-supervised learning (SSL), pseudo-labeled strategy using diverse datasets such as head and neck cancer (HNCa) to enhance lung cancer (LCa) survival outcome predictions, analyzing handcrafted and deep radiomic features (HRF/DRF) from PET/CT scans with hybrid machine learning systems (HMLSs). Methods: We collected 199 LCa patients with both PET and CT images, obtained from TCIA and our local database, alongside 408 HNCa PET/CT images from TCIA. We extracted 215 HRFs and 1024 DRFs by PySERA and a 3D autoencoder, respectively, within the ViSERA 1.0.0 software, from segmented primary tumors. The supervised strategy (SL) employed an HMLS–PCA connected with six classifiers on both HRFs and DRFs. The SSL strategy expanded the datasets by adding 408 pseudo-labeled HNCa cases (labeled by the Random Forest algorithm) to 199 LCa cases, using the same HMLS techniques. Furthermore, principal component analysis (PCA) linked with four survival prediction algorithms were utilized in the survival hazard ratio analysis. Results: The SSL strategy outperformed the SL method (p << 0.001), achieving an average accuracy of 0.85 ± 0.05 with DRFs from PET and PCA + Multi-Layer Perceptron (MLP), compared to 0.69 ± 0.06 for the SL strategy using DRFs from CT and PCA + Light Gradient Boosting (LGB). Additionally, PCA linked with Component-wise Gradient Boosting Survival Analysis on both HRFs and DRFs, as extracted from CT, had an average C-index of 0.80, with a log rank p-value << 0.001, confirmed by external testing. Conclusions: Shifting from HRFs and SL to DRFs and SSL strategies, particularly in contexts with limited data points, enabling CT or PET alone, can significantly achieve high predictive performance.

Background/Objectives: Pembrolizumab monotherapy is approved in Canada for first-line treatment of advanced NSCLC with PD-L1 ≥ 50% and no EGFR/ALK aberrations. However, approximately 55% of these patients do not respond to pembrolizumab, underscoring the need for the early intervention of non-responders to optimize treatment strategies. Distinguishing the 55% sub-cohort prior to treatment is a real-world dilemma. Methods: In this retrospective study, we analyzed two patient cohorts treated with pembrolizumab monotherapy (training set: n = 97; test set: n = 17). The treatment response was assessed using baseline and follow-up CT scans via RECIST 1.1 criteria. Results: A logistic regression model, incorporating pre-treatment CT radiomic features of lung tumors and clinical variables, achieved high predictive accuracy (AUC: 0.85 in training; 0.81 in testing, 95% CI: 0.63–0.99). Notably, radiomic features from the peritumoral region were found to be independent predictors, complementing the standard CT evaluations and other clinical characteristics. Conclusions: This pragmatic model offers a valuable tool to guide first-line treatment decisions in NSCLC patients with high PD-L1 expression and has the potential to advance personalized oncology and improve timely disease management.

Health Canada approved pembrolizumab in the first-line setting for advanced non-small-cell lung cancer with PD-L1 ≥ 50% and no EGFR/ALK aberration. The keynote 024 trial showed 55% of such patients progress with pembrolizumab monotherapy. We propose that the combination of baseline CT and clinical factors can help identify those patients who may progress. In 138 eligible patients from our institution, we retrospectively collected their baseline variables, including baseline CT findings (primary lung tumor size and metastatic site), smoking pack years, performance status, tumor pathology, and demographics. The treatment response was assessed via RECIST 1.1 using the baseline and first follow-up CT. Associations between the baseline variables and progressive disease (PD) were tested by logistic regression analyses. The results showed 46/138 patients had PD. The baseline CT “number of involved organs” by metastasis and smoking pack years were independently associated with PD (p < 0.05), and the ROC analysis showed a good performance of the model that integrated these variables in predicting PD (AUC: 0.79). This pilot study suggests that the combination of baseline CT disease and smoking PY can identify who may progress on pembrolizumab monotherapy and can potentially facilitate decision-making for the optimal first-line treatment in the high PD-L1 cohort.

PURPOSE: Chemotherapy is the primary treatment for metastatic nonseminomatous germ cell tumors (mNSGCTs), but patients often encounter postchemotherapy residual disease. Accurate noninvasive methods are needed to predict the histology of these masses, guiding treatment and reserving surgery for those with teratoma. This study aims to enhance predictive accuracy by integrating computed tomography (CT) radiomics features with miRNAs (miR371-375) to distinguish between teratoma and nonteratoma histology in postchemotherapy residual masses. METHODS: We retrospectively identified 111 lesions, divided into training and test sets (n = 78 v 33) with equal class distribution. 3D Slicer was used to segment lesions with a short axis of >10 mm from the postchemo-presurgical CT images, and radiomics features were extracted. Presurgery plasma miR371-375 levels were measured by real-time polymerase chain reaction. Four machine learning models evaluated the predictive value of radiomics alone (R-only) and combined with miR371-375 levels, and the best performer was selected. Clinical factors associated with teratoma from univariate analysis were included in multivariate analysis with the best radiomics signature to assess their impact on predicting teratoma histology. RESULTS: The CatBoost (CB) model R + 371 + 375 exhibited the best and most robust overall accuracy for predicting residual teratoma, with the highest AUC values (0.96, 95% CI, 0.88 to 1.0 for training, 0.83, 95% CI, 0.68 to 0.98 for testing) and a well-balanced sensitivity and specificity. Univariate analysis identified presurgery alpha-fetoprotein ( P = .01), beta-human chorionic gonadotropin ( P = .01), initial teratoma pathology ( P = .01), and lymph node metastases ( P = .02) as significant predictors for teratoma. Multivariate analysis included these features and the radiomics signature, which was the strongest independent predictor ( P < .0001). CONCLUSION: Combining miR371-375 with CT radiomics features improves the accuracy of predicting teratoma histology of postchemotherapy residual disease in mNSGCTs and, therefore, has the potential to guide treatment decision making.

The PACIFIC trial showed a survival benefit with durvalumab through five years in stage III unresectable non-small cell lung cancer (NSCLC). However, optimal use of imaging to detect disease progression remains unclearly defined for this population. An expert working group convened to consider available evidence and clinical experience and develop recommendations for follow-up imaging after concurrent chemotherapy and radiation therapy (CRT). Voting on agreement was conducted anonymously via online survey. Follow-up imaging was recommended for all suitable patients after CRT completion regardless of whether durvalumab is received. Imaging should occur every 3 months in Year 1, at least every 6 months in Year 2, and at least every 12 months in Years 3–5. Contrast computed tomography was preferred; routine brain imaging was not recommended for asymptomatic patients. The medical oncologist should follow-up during Year 1 of durvalumab therapy, with radiation oncologist involvement if pneumonitis is suspected; medical and radiation oncologists can subsequently alternate follow-up. Some patients can transition to the family physician/community primary care team at the end of Year 2. In Years 1–5, patients should receive information regarding smoking cessation, comorbidity management, vaccinations, and general follow-up care. These recommendations provide guidance on follow-up imaging for patients with stage III unresectable NSCLC whether or not they receive durvalumab consolidation therapy.