Search

Background: The advances in deep learning-based pathological image analysis have invoked tremendous insights into cancer prognostication. Still, lack of interpretability remains a significant barrier to clinical application. Methods: We established an integrative prognostic neural network for intrahepatic cholangiocarcinoma (iCCA), towards a comprehensive evaluation of both architectural and fine-grained information from whole-slide images. Then, leveraging on multi-modal data, we conducted extensive interrogative approaches to the models, to extract and visualize the morphological features that most correlated with clinical outcome and underlying molecular alterations. Results: The models were developed and optimized on 373 iCCA patients from our center and demonstrated consistent accuracy and robustness on both internal (n = 213) and external (n = 168) cohorts. The occlusion sensitivity map revealed that the distribution of tertiary lymphoid structures, the geometric traits of the invasive margin, the relative composition of tumor parenchyma and stroma, the extent of necrosis, the presence of the disseminated foci, and the tumor-adjacent micro-vessels were the determining architectural features that impacted on prognosis. Quantifiable morphological vector extracted by CellProfiler demonstrated that tumor nuclei from high-risk patients exhibited significant larger size, more distorted shape, with less prominent nuclear envelope and textural contrast. The multi-omics data (n = 187) further revealed key molecular alterations left morphological imprints that could be attended by the network, including glycolysis, hypoxia, apical junction, mTORC1 signaling, and immune infiltration. Conclusions: We proposed an interpretable deep-learning framework to gain insights into the biological behavior of iCCA. Most of the significant morphological prognosticators perceived by the network are comprehensible to human minds. [ABSTRACT FROM AUTHOR]

Background: Microvascular invasion (MVI) is recognized as a prognostic factor associated with poor outcome in hepatocellular carcinoma (HCC) patients after curative resection. It remains unclear, however, whether MVI can provide prognostic information for patients at a specific tumor stage.Methods: Consecutive HCC patients who underwent curative resection in years of 2007 and 2008 (discovery cohort) were enrolled in this retrospective study. Patients were stratified by the Barcelona Clinic Liver Cancer (BCLC) staging system. The prognostic significance of MVI for overall survival (OS) and recurrence-free survival (RFS) was studied in each subgroup. The clinical significance of MVI was validated in another cohort of patients underwent curative surgery in the year of 2006 (validation cohort).Results: Of the 1540 patients in the discovery cohort, 389 (25.3%) patients had detectable MVI. Occurrence rates of MVI in the BCLC stage 0, A, and B subgroups were 12.4, 26.2, and 34.4%, respectively. In univariate analysis, MVI was associated with poor OS and RFS (P < 0.001 for both) in HCC patients at stage A, with poor OS in patients at stage 0 (P = 0.028), and with poor RFS at stage B (P = 0.039). In multivariate analysis, MVI was an independent risk factor for OS (HR = 1.431, 95% CI, 1.163-1.761, P < 0.001) and RFS (HR = 1.400, 95% CI, 1.150-1.705, P = 0.001) in patients at stage A; and an independent risk factor for RFS (P = 0.043) in patients at stage B. A similar clinical significance of MVI was found in the validation cohort.Conclusions: MVI has limited prognostic value for HCC patients at BCLC stages 0 and B. For those at stage A, MVI was associated with patient survival and may help to select patients with high risk of disease recurrence. [ABSTRACT FROM AUTHOR]