Interpretable attention-based deep learning ensemble for personalized ovarian cancer treatment without manual annotations.

Inhibition of pathological angiogenesis has become one of the first FDA approved targeted therapies widely tested in anti-cancer treatment, i.e. VEGF-targeting monoclonal antibody bevacizumab, in combination with chemotherapy for frontline and maintenance therapy for women with newly diagnosed ovarian cancer. Identification of the best predictive biomarkers of bevacizumab response is necessary in order to select patients most likely to benefit from this therapy. Hence, this study investigates the protein expression patterns on immunohistochemical whole slide images of three angiogenesis related proteins, including Vascular endothelial growth factor, Angiopoietin 2 and Pyruvate kinase isoform M2, and develops an interpretable and annotation-free attention based deep learning ensemble framework to predict the bevacizumab therapeutic effect on patients with epithelial ovarian cancer or peritoneal serous papillary carcinoma using tissue microarrays (TMAs). In evaluation with five-fold cross validation, the proposed ensemble model using the protein expressions of both Pyruvate kinase isoform M2 and Angiopoietin 2 achieves a notably high F-score (0.99±0.02), accuracy (0.99±0.03), precision (0.99±0.02), recall (0.99±0.02) and AUC (1.00±0). Kaplan-Meier progression free survival analysis confirms that the proposed ensemble is able to identify patients in the predictive therapeutic sensitive group with low cancer recurrence (p<0.001), and the Cox proportional hazards model analysis further confirms the above statement (p=0.012). In conclusion, the experimental results demonstrate that the proposed ensemble model using the protein expressions of both Pyruvate kinase isoform M2 and Angiopoietin 2 can assist treatment planning of bevacizumab targeted therapy for patients with ovarian cancer.

A Weakly Supervised Deep Learning Method for Guiding Ovarian Cancer Treatment and Identifying an Effective Biomarker.

Ovarian cancer is a common malignant gynecological disease. Molecular target therapy, i.e., antiangiogenesis with bevacizumab, was found to be effective in some patients of epithelial ovarian cancer (EOC). Although careful patient selection is essential, there are currently no biomarkers available for routine therapeutic usage. To the authors' best knowledge, this is the first automated precision oncology framework to effectively identify and select EOC and peritoneal serous papillary carcinoma (PSPC) patients with positive therapeutic effect. From March 2013 to January 2021, we have a database, containing four kinds of immunohistochemical tissue samples, including AIM2, c3, C5 and NLRP3, from patients diagnosed with EOC and PSPC and treated with bevacizumab in a hospital-based retrospective study. We developed a hybrid deep learning framework and weakly supervised deep learning models for each potential biomarker, and the experimental results show that the proposed model in combination with AIM2 achieves high accuracy 0.92, recall 0.97, F-measure 0.93 and AUC 0.97 for the first experiment (66% training and 34%testing) and high accuracy 0.86 ± 0.07, precision 0.9 ± 0.07, recall 0.85 ± 0.06, F-measure 0.87 ± 0.06 and AUC 0.91 ± 0.05 for the second experiment using five-fold cross validation, respectively. Both Kaplan-Meier PFS analysis and Cox proportional hazards model analysis further confirmed that the proposed AIM2-DL model is able to distinguish patients gaining positive therapeutic effects with low cancer recurrence from patients with disease progression after treatment (p < 0.005).

Comprehensive Profiling of Poor-Risk Paired Primary and Recurrent Triple-Negative Breast Cancers Reveals Immune Phenotype Shifts.

PURPOSE: Emerging data suggest immune checkpoint inhibitors have reduced efficacy in heavily pretreated triple-negative breast cancers (TNBC), but underlying mechanisms are poorly understood. To better understand the phenotypic evolution of TNBCs, we studied the genomic and transcriptomic profiles of paired tumors from patients with TNBC. EXPERIMENTAL DESIGN: We collected paired primary and metastatic TNBC specimens from 43 patients and performed targeted exome sequencing and whole-transcriptome sequencing. From these efforts, we ascertained somatic mutation profiles, tumor mutational burden (TMB), TNBC molecular subtypes, and immune-related gene expression patterns. Stromal tumor-infiltrating lymphocytes (stromal TIL), recurrence-free survival, and overall survival were also analyzed. RESULTS: We observed a typical TNBC mutational landscape with minimal shifts in copy number or TMB over time. However, there were notable TNBC molecular subtype shifts, including increases in the Lehmann/Pietenpol-defined basal-like 1 (BL1, 11.4%-22.6%) and mesenchymal (M, 11.4%-22.6%) phenotypes, and a decrease in the immunomodulatory phenotype (IM, 31.4%-3.2%). The Burstein-defined basal-like immune-activated phenotype was also decreased (BLIA, 42.2%-17.2%). Among downregulated genes from metastases, we saw enrichment of immune-related Kyoto Encyclopedia of Genes and Genomes pathways and gene ontology (GO) terms, and decreased expression of immunomodulatory gene signatures (P < 0.03) and percent stromal TILs (P = 0.03). There was no clear association between stromal TILs and survival. CONCLUSIONS: We observed few mutational shifts, but largely consistent transcriptomic shifts in longitudinally paired TNBCs. Transcriptomic and IHC analyses revealed significantly reduced immune-activating gene expression signatures and TILs in recurrent TNBCs. These data may explain the observed lack of efficacy of immunotherapeutic agents in heavily pretreated TNBCs. Further studies are ongoing to better understand these initial observations.See related commentary by Savas and Loi, p. 526.

Mechanical property characterization of hundreds of single nuclei based on microfluidic constriction channel.

As label-free biomarkers, the mechanical properties of nuclei are widely treated as promising biomechanical markers for cell type classification and cellular status evaluation. However, previously reported mechanical parameters were derived from only around 10 nuclei, lacking statistical significances due to low sample numbers. To address this issue, nuclei were first isolated from SW620 and A549 cells, respectively, using a chemical treatment method. This was followed by aspirating them through two types of microfluidic constriction channels for mechanical property characterization. In this study, hundreds of nuclei were characterized, producing passage times of 0.5 ± 1.2 s for SW620 nuclei in type I constriction channel (n = 153), 0.045 ± 0.047 s for SW620 nuclei in type II constriction channel (n = 215) and 0.50 ± 0.86 s for A549 nuclei in type II constriction channel. In addition, neural network based pattern recognition was used to classify the nuclei isolated from SW620 and A549 cells, producing successful classification rates of 87.2% for diameters of nuclei, 85.5% for passage times of nuclei and 89.3% for both passage times and diameters of nuclei. These results indicate that the characterization of the mechanical properties of nuclei may contribute to the classification of different tumor cells.