Prognostic value of deep learning-derived body composition in advanced pancreatic cancer-a retrospective multicenter study.

BACKGROUND: Despite the prognostic relevance of cachexia in pancreatic cancer, individual body composition has not been routinely integrated into treatment planning. In this multicenter study, we investigated the prognostic value of sarcopenia and myosteatosis automatically extracted from routine computed tomography (CT) scans of patients with advanced pancreatic ductal adenocarcinoma (PDAC). PATIENTS AND METHODS: We retrospectively analyzed clinical imaging data of 601 patients from three German cancer centers. We applied a deep learning approach to assess sarcopenia by the abdominal muscle-to-bone ratio (MBR) and myosteatosis by the ratio of abdominal inter- and intramuscular fat to muscle volume. In the pooled cohort, univariable and multivariable analyses were carried out to analyze the association between body composition markers and overall survival (OS). We analyzed the relationship between body composition markers and laboratory values during the first year of therapy in a subgroup using linear regression analysis adjusted for age, sex, and American Joint Committee on Cancer (AJCC) stage. RESULTS: Deep learning-derived MBR [hazard ratio (HR) 0.60, 95% confidence interval (CI) 0.47-0.77, P < 0.005] and myosteatosis (HR 3.73, 95% CI 1.66-8.39, P < 0.005) were significantly associated with OS in univariable analysis. In multivariable analysis, MBR (P = 0.019) and myosteatosis (P = 0.02) were associated with OS independent of age, sex, and AJCC stage. In a subgroup, MBR and myosteatosis were associated with albumin and C-reactive protein levels after initiation of therapy. Additionally, MBR was also associated with hemoglobin and total protein levels. CONCLUSIONS: Our work demonstrates that deep learning can be applied across cancer centers to automatically assess sarcopenia and myosteatosis from routine CT scans. We highlight the prognostic role of our proposed markers and show a strong relationship with protein levels, inflammation, and anemia. In clinical practice, automated body composition analysis holds the potential to further personalize cancer treatment.

Smaller panel, similar results: genomic profiling and molecularly informed therapy in pancreatic cancer.

BACKGROUND: Pancreatic cancer has a dismal prognosis. One reason is resistance to cytotoxic drugs. Molecularly matched therapies might overcome this resistance but the best approach to identify those patients who may benefit is unknown. Therefore, we sought to evaluate a molecularly guided treatment approach. MATERIALS AND METHODS: We retrospectively analyzed the clinical outcome and mutational status of patients with pancreatic cancer who received molecular profiling at the West German Cancer Center Essen from 2016 to 2021. We carried out a 47-gene DNA next-generation sequencing (NGS) panel. Furthermore, we assessed microsatellite instability-high/deficient mismatch repair (MSI-H/dMMR) status and, sequentially and only in case of KRAS wild-type, gene fusions via RNA-based NGS. Patient data and treatment were retrieved from the electronic medical records. RESULTS: Of 190 included patients, 171 had pancreatic ductal adenocarcinoma (90%). One hundred and three patients had stage IV pancreatic cancer at diagnosis (54%). MMR analysis in 94 patients (94/190, 49.5%) identified 3 patients with dMMR (3/94, 3.2%). Notably, we identified 32 patients with KRAS wild-type status (16.8%). To identify driver alterations in these patients, we conducted an RNA-based fusion assay on 13 assessable samples and identified 5 potentially actionable fusions (5/13, 38.5%). Overall, we identified 34 patients with potentially actionable alterations (34/190, 17.9%). Of these 34 patients, 10 patients (10/34, 29.4%) finally received at least one molecularly targeted treatment and 4 patients had an exceptional response (>9 months on treatment). CONCLUSIONS: Here, we show that a small-sized gene panel can suffice to identify relevant therapeutic options for pancreatic cancer patients. Informally comparing with previous large-scale studies, this approach yields a similar detection rate of actionable targets. We propose molecular sequencing of pancreatic cancer as standard of care to identify KRAS wild-type and rare molecular subsets for targeted treatment strategies.