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.

Impact of encorafenib on survival of patients with BRAFV600E-mutant metastatic colorectal cancer in a real-world setting

PURPOSE

Patients with BRAFV600E-mutant metastatic colorectal cancer (mCRC) have a dismal prognosis. The best strategies in these patients remain elusive. Against this background, we report the clinical course of patients with BRAFV600E-mutant mCRC to retrieve the best treatment strategy.

PATIENTS AND METHODS

Clinico-pathological data were extracted from the electronic health records. Kaplan-Meier method was used to estimate overall (OS) and progression-free survival (PFS). Objective response rate (ORR) was assessed according to RECIST 1.1.

RESULTS

In total, 51 patients were enrolled. FOLFOXIRI was administered to 12 patients; 29 patients received FOLFOX or FOLFIRI as first-line treatment. Median OS was 17.6 months. Median PFS with FOLFOXIRI (13.0 months) was significantly prolonged (HR 0.325) as compared to FOLFOX/FOLFIRI (4.3 months). However, this failed to translate into an OS benefit (p = 0.433). Interestingly, addition of a monoclonal antibody to chemotherapy associated with superior OS (HR 0.523). A total of 64.7% patients received further-line therapy, which included a BRAF inhibitor in 17 patients. Targeted therapy associated with very favourable OS (25.1 months).

CONCLUSION

Patients with BRAFV600E-mutated mCRC benefit from the addition of an antibody to first-line chemotherapy. Further-line treatment including a BRAF inhibitor has a dramatic impact on survival.

Multimodal survival prediction in advanced pancreatic cancer using machine learning

Background

Existing risk scores appear insufficient to assess the individual survival risk of patients with advanced pancreatic ductal adenocarcinoma (PDAC) and do not take advantage of the variety of parameters that are collected during clinical care.

Methods

In this retrospective study, we built a random survival forest model from clinical data of 203 patients with advanced PDAC. The parameters were assessed before initiation of systemic treatment and included age, CA19-9, C-reactive protein, metastatic status, neutrophil-to-lymphocyte ratio and total serum protein level. Separate models including imaging and molecular parameters were built for subgroups.

Results

Over the entire cohort, a model based on clinical parameters achieved a c-index of 0.71. Our approach outperformed the American Joint Committee on Cancer (AJCC) staging system and the modified Glasgow Prognostic Score (mGPS) in the identification of high- and low-risk subgroups. Inclusion of the KRAS p.G12D mutational status could further improve the prediction, whereas radiomics data of the primary tumor only showed little benefit. In an external validation cohort of PDAC patients with liver metastases, our model achieved a c-index of 0.67 (mGPS: 0.59).

Conclusions

The combination of multimodal data and machine-learning algorithms holds potential for personalized prognostication in advanced PDAC already at diagnosis.

•

We developed a machine-learning-based prediction model that outperforms the AJCC staging system and mGPS.

•

Applying our model to an external validation cohort demonstrates generalizability.

•

Explainable machine learning enables to understand the decision making of our model and identifies relevant parameters.

•

Combining clinical, imaging and genetic data holds potential for personalized prognostication in advanced PDAC.

HER2 expression and markers of phosphoinositide-3-kinase pathway activation define a favorable subgroup of metastatic pulmonary adenocarcinomas

OBJECTIVES

Pulmonary adenocarcinomas (ADC) can be sub-grouped based on dominant oncogenic drivers. EGFR mutations define an entity of metastatic ADC with favorable prognosis and high susceptibility to EGFR tyrosine kinase inhibition. In contrast, the clinical impact of additional ERBB family members in ADC is less defined. To this end we prospectively studied HER2 expression, gene amplification, and mutation in relation to outcome of patients with advanced or metastatic ADC.

MATERIALS AND METHODS

Diagnostic tumor biopsies from 193 sequential patients with stage III/IV ADC were prospectively studied for HER2 expression by immunohistochemistry (IHC). Cases with IHC scores 2+ or 3+ were analyzed by HER2 chromogenic in situ hybridization (CISH), and sequencing of HER2 exons 20 and 23. Additional prospectively determined biomarkers included PTEN, cMET, pAKT, and pERK expression, KRAS, EGFR, BRAF and PIK3CA mutations, and ALK fluorescence ISH (FISH).

RESULTS AND CONCLUSION

HER2-IHC was feasible in 176 (91.2%) cases. Of 53 (30%) cases with IHC scores 2+/3+, 45 (85%) could be studied by CISH and 34 (64%) by sequencing. The lower number of HER2-mutational analyses resulted from exhaustion of tumor tissue and DNA following mutational analysis of KRAS, EGFR, BRAF and PIK3CA. HER2 amplification was detected in 4 cases (2.3%), while no mutation was found. HER2 expression correlated with expression of pAKT and cMET. Expression of HER2 and pAKT was associated with favorable overall survival in stage IV disease. HER2-expressing ADC more frequently harbored KRAS mutations, while HER2 expression was absent in all 4 cases with BRAF mutation. HER2-IHC was not predictive of HER2 gene amplification or mutation, which both were rare events in prospectively studied patients with advanced or metastatic ADC. Expression of HER2 and pAKT define a population of patients with stage IV ADC with a distinct disease course, who could benefit from specifically tailored pharmacotherapies.