BACKGROUND: Glioblastoma (GBM) is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification. METHODS: We developed a highly reproducible, personalized prognostication, and clinical subgrouping system using machine learning (ML) on routine clinical data, magnetic resonance imaging (MRI), and molecular measures from 2838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, and III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]). RESULTS: The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I-II and I-III of 1.62 (95% CI: 1.43-1.84, P < .001) and 3.48 (95% CI: 2.94-4.11, P < .001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort. CONCLUSIONS: Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach to personalized patient management and clinical trial stratification in GBM.

• Klíčová slova
• glioblastoma, machine learning, mpMRI, prognostic subgrouping, survival,
• MeSH
• dospělí MeSH
• glioblastom * patologie   klasifikace   mortalita   diagnostické zobrazování   MeSH
• lidé středního věku MeSH
• lidé MeSH
• magnetická rezonanční tomografie metody   MeSH
• míra přežití MeSH
• mladý dospělý MeSH
• nádory mozku * patologie   klasifikace   mortalita   diagnostické zobrazování   MeSH
• následné studie MeSH
• prognóza MeSH
• senioři MeSH
• strojové učení * MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mladý dospělý MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• multicentrická studie MeSH

IMPORTANCE: International guidelines lack consistency in their recommendations regarding routine imaging in the follow-up after pancreatic resection for pancreatic ductal adenocarcinoma (PDAC). Consequently, follow-up strategies differ between centers worldwide. OBJECTIVE: To compare clinical outcomes, including recurrence-focused treatment and survival, in patients with PDAC recurrence who received symptomatic follow-up or routine imaging after pancreatic resection in international centers affiliated with the European-African Hepato-Pancreato-Biliary Association (E-AHPBA). DESIGN, SETTING, AND PARTICIPANTS: This was a prospective, international, cross-sectional study. Patients from a total of 33 E-AHPBA centers from 13 countries were included between 2020 and 2021. According to the predefined study protocol, patients who underwent PDAC resection and were diagnosed with disease recurrence were prospectively included. Patients were stratified according to postoperative follow-up strategy: symptomatic follow-up (ie, without routine imaging) or routine imaging. EXPOSURES: Symptomatic follow-up or routine imaging in patients who underwent PDAC resection. MAIN OUTCOMES AND MEASURES: Overall survival (OS) was estimated with Kaplan-Meier curves and compared using the log-rank test. To adjust for potential confounders, multivariable logistic regression was used to evaluate the association between follow-up strategy and recurrence-focused treatment. Multivariable Cox proportional hazard analysis was used to study the independent association between follow-up strategy and OS. RESULTS: Overall, 333 patients (mean [SD] age, 65 [11] years; 184 male [55%]) with PDAC recurrence were included. Median (IQR) follow-up at time of analysis 2 years after inclusion of the last patient was 40 (30-58) months. Of the total cohort, 98 patients (29%) received symptomatic follow-up, and 235 patients (71%) received routine imaging. OS was 23 months (95% CI, 19-29 months) vs 28 months (95% CI, 24-30 months) in the groups who received symptomatic follow-up vs routine imaging, respectively (P = .01). Routine imaging was associated with receiving recurrence-focused treatment (adjusted odds ratio, 2.57; 95% CI, 1.22-5.41; P = .01) and prolonged OS (adjusted hazard ratio, 0.75; 95% CI, 0.56-.99; P = .04). CONCLUSION AND RELEVANCE: In this international, prospective, cross-sectional study, routine follow-up imaging after pancreatic resection for PDAC was independently associated with receiving recurrence-focused treatment and prolonged OS.

• MeSH
• duktální karcinom slinivky břišní * chirurgie   mortalita   diagnostické zobrazování   patologie   MeSH
• lidé středního věku MeSH
• lidé MeSH
• lokální recidiva nádoru * MeSH
• míra přežití MeSH
• nádory slinivky břišní * chirurgie   mortalita   MeSH
• následné studie MeSH
• pankreatektomie * MeSH
• prospektivní studie MeSH
• průřezové studie MeSH
• senioři MeSH
• Check Tag
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• multicentrická studie MeSH

Chest X-ray (CXR) is considered to be the most widely used modality for detecting and monitoring various thoracic findings, including lung carcinoma and other pulmonary lesions. However, X-ray imaging shows particular limitations when detecting primary and secondary tumors and is prone to reading errors due to limited resolution and disagreement between radiologists. To address these issues, we developed a deep-learning-based automatic detection algorithm (DLAD) to automatically detect and localize suspicious lesions on CXRs. Five radiologists were invited to retrospectively evaluate 300 CXR images from a specialized oncology center, and the performance of individual radiologists was subsequently compared with that of DLAD. The proposed DLAD achieved significantly higher sensitivity (0.910 (0.854-0.966)) than that of all assessed radiologists (RAD 10.290 (0.201-0.379), p < 0.001, RAD 20.450 (0.352-0.548), p < 0.001, RAD 30.670 (0.578-0.762), p < 0.001, RAD 40.810 (0.733-0.887), p = 0.025, RAD 50.700 (0.610-0.790), p < 0.001). The DLAD specificity (0.775 (0.717-0.833)) was significantly lower than for all assessed radiologists (RAD 11.000 (0.984-1.000), p < 0.001, RAD 20.970 (0.946-1.000), p < 0.001, RAD 30.980 (0.961-1.000), p < 0.001, RAD 40.975 (0.953-0.997), p < 0.001, RAD 50.995 (0.985-1.000), p < 0.001). The study results demonstrate that the proposed DLAD could be utilized as a decision-support system to reduce radiologists' false negative rate.

• Klíčová slova
• YOLO, computer-aided diagnosis, convolutional neural network, deep learning, lung cancer, object detection, pulmonary lesion,
• Publikační typ
• časopisecké články MeSH