RESUMO
BACKGROUND: Presence of lymph node metastasis (LNM) influences prognosis and clinical decision-making in colorectal cancer. However, detection of LNM is variable and depends on a number of external factors. Deep learning has shown success in computational pathology, but has struggled to boost performance when combined with known predictors. METHODS: Machine-learned features are created by clustering deep learning embeddings of small patches of tumor in colorectal cancer via k-means, and then selecting the top clusters that add predictive value to a logistic regression model when combined with known baseline clinicopathological variables. We then analyze performance of logistic regression models trained with and without these machine-learned features in combination with the baseline variables. RESULTS: The machine-learned extracted features provide independent signal for the presence of LNM (AUROC: 0.638, 95% CI: [0.590, 0.683]). Furthermore, the machine-learned features add predictive value to the set of 6 clinicopathologic variables in an external validation set (likelihood ratio test, p < 0.00032; AUROC: 0.740, 95% CI: [0.701, 0.780]). A model incorporating these features can also further risk-stratify patients with and without identified metastasis (p < 0.001 for both stage II and stage III). CONCLUSION: This work demonstrates an effective approach to combine deep learning with established clinicopathologic factors in order to identify independently informative features associated with LNM. Further work building on these specific results may have important impact in prognostication and therapeutic decision making for LNM. Additionally, this general computational approach may prove useful in other contexts.
When colorectal cancers spread to the lymph nodes, it can indicate a poorer prognosis. However, detecting lymph node metastasis (spread) can be difficult and depends on a number of factors such as how samples are taken and processed. Here, we show that machine learning, which involves computer software learning from patterns in data, can predict lymph node metastasis in patients with colorectal cancer from the microscopic appearance of their primary tumor and the clinical characteristics of the patients. We also show that the same approach can predict patient survival. With further work, our approach may help clinicians to inform patients about their prognosis and decide on appropriate treatments.
RESUMO
We report on the initial 17 (11 male:6 female) brain autopsies from across Europe and the United States in the Parkinson's Progression Markers Initiative (PPMI). Clinical diagnoses were Parkinson's disease (n = 15), multiple system atrophy (n = 1), and Dementia with Lewy bodies (n = 1); average age of death = 72 ± 8 yr. Cognitive assessment at last evaluation was 5 with normal cognition, 7 with mild cognitive impairment, and 5 with dementia. Genetic assessment showed 4 participants were heterozygous or homozygous for GBA N370S and 3 were heterozygous carriers for LRRK2 R1441G or G2019S; 1 was an APOE ε2 carrier and 5 were APOE ε4 carriers. Longitudinal DAT neuroimaging as well as CSF and plasma biomarker data are summarized. Neuropathologic examination confirmed all clinical diagnoses and showed the expected frequencies of common comorbidities; no evidence of chronic traumatic encephalopathy was observed. Thus, brain autopsy data can provide confirmation, clarification, and new insights into the PD progression observed during life. As it grows, the PPMI brain autopsy program will provide a deeply-annotated research resource to the community of investigators focused on developing biomarkers for PD progression.