Artificial Intelligence to Predict the Risk of Lymph Node Metastasis in T2 Colorectal Cancer.

OBJECTIVE: To develop and externally validate an updated artificial intelligence (AI) prediction system for stratifying the risk of lymph node metastasis (LNM) in T2 colorectal cancer (CRC). SUMMARY BACKGROUND DATA: Recent technical advances allow complete local excision of T2 CRC, traditionally treated with surgical resection. Yet, the widespread adoption of this approach is hampered by the inability to stratify the risk of LNM. METHODS: Data from pT2 CRC patients undergoing surgical resection between April 2000 and May 2022 at one Japanese and one Italian center were analyzed. Primary goal was AI system development for accurate LNM prediction. Predictors encompassed seven variables: age, sex, tumor size and location, lympho-vascular invasion, histological differentiation, and carcinoembryonic antigen level. The tool's discriminating power was assessed via Area Under the Curve (AUC), sensitivity, and specificity. RESULTS: Out of 735 initial patients, 692 were eligible. Training and validation cohorts comprised of 492 and 200 patients, respectively. The AI model displayed an AUC of 0.75 in the combined validation dataset. Sensitivity for LNM prediction was 97.8% and specificity was 15.6%. The Positive and the Negative Predictive Value were 25.7% and 96% respectively. The False Negative (FN) rate was 2.2%, the False Positive was 84.4%. CONCLUSIONS: Our AI model, based on easily accessible clinical and pathological variables, moderately predicts LNM in T2 CRC. However, the risk of FN needs to be considered. The training of the model including more patients across Western and Eastern centers -differentiating between colon and rectal cancers- may improve its performance and accuracy.

Identification and validation of a tumor-infiltrating Treg transcriptional signature conserved across species and tumor types.

FoxP3+ T regulatory (Treg) cells are central elements of immunologic tolerance. They are abundant in many tumors, where they restrict potentially favorable antitumor responses. We used a three-pronged strategy to identify genes related to the presence and function of Tregs in the tumor microenvironment. Gene expression profiles were generated from tumor-infiltrating Tregs (TITRs) of both human and mouse tumors and were compared with those of Tregs of lymphoid organs or normal tissues from the same individuals. A computational deconvolution of whole-tumor datasets from the Cancer Genome Atlas (TCGA) was performed to identify transcripts specifically associated with Tregs across thousands of tumors from different stages and locations. We identified a set of TITR-differential transcripts with striking reproducibility between tumor types in mice, between mice and humans, and between different human patients spanning tumor stages. Many of the TITR-preferential transcripts were shared with "tissue Tregs" residing in nonlymphoid tissues, but a tumor-preferential segment could be identified. Many of these TITR signature transcripts were confirmed by mining of TCGA datasets, which also brought forth transcript modules likely representing the parenchymal attraction of, or response to, tumor Tregs. Importantly, the TITR signature included several genes encoding effective targets of tumor immunotherapy. A number of other targets were validated by CRISPR-based gene inactivation in mouse Tregs. These results confirm the validity of the signature, generating a wealth of leads for understanding the role of Tregs in tumor progression and identifying potential targets for cancer immunotherapy.

Hepatectomy versus Chemotherapy for Resectable Colorectal Liver Metastases in Progression after Perioperative Chemotherapy: Expanding the Boundaries of the Curative Intent.

Disease progression (PD) at neoadjuvant chemotherapy for patients with colorectal liver metastases (CLMs) is considered a contraindication to hepatic resection. Our aim was to estimate the overall survival (OS) in patients undergoing surgery compared with those treated exclusively with chemotherapy in cases of PD. Patients from a single centre with PD were analyzed and subdivided into two groups: hepatectomy (HEP) versus chemotherapy (CHT). An Inverse Probability Weighting (IPW) was run to balance the baseline differences between the two groups. A Cox regression was carried out on identifying factors predicting mortality. From 2010 to 2020, 105 patients in PD to at least one line of chemotherapy were analyzed. Of these, 27 (25.7%) underwent hepatic resection. After a median follow-up of 30 (IQR 14-46) months, 61.9% were dead. The OS values at 1 and 3 years were 54.4 and 10.6% for CHT, and 95 and 46.8% for HEP (p < 0.001). After IPW, two balanced pseudopopulations were obtained: HEP = 85 and CHT = 103. The OS values at 1 and 3 years were 54.4 and 10.6% for CHT, and 97.8 and 49.3% for HEP (HR 0.256, 95%CI: 0.08-0.78, p = 0.033). After IPW, in the multivariate model, surgery resulted in the only protective variable (HR 0.198, 95%CI: 0.08-0.48, p = 0.0016). Our results show that hepatic resection could offer a chance of a longer OS than the prosecution of chemotherapy only in originally resectable patients.

Spatiotemporal patterning of EpCAM is important for murine embryonic endo- and mesodermal differentiation.

Epithelial cell adhesion molecule EpCAM is expressed in pluripotent embryonic stem cells (ESC) in vitro, but is repressed in differentiated cells, except epithelia and carcinomas. Molecular functions of EpCAM, possibly imposing such repression, were primarily studied in malignant cells and might not apply to non-pathologic differentiation. Here, we comprehensively describe timing and rationale for EpCAM regulation in early murine gastrulation and ESC differentiation using single cell RNA-sequencing datasets, in vivo and in vitro models including CRISPR-Cas9-engineered ESC-mutants. We demonstrate expression of EpCAM in inner cell mass, epiblast, primitive/visceral endoderm, and strict repression in the most primitive, nascent Flk1+ mesoderm progenitors at E7.0. Selective expression of EpCAM was confirmed at mid-gestation and perinatal stages. The rationale for strict patterning was studied in ESC differentiation. Gain/loss-of-function demonstrated supportive functions of EpCAM in achieving full pluripotency and guided endodermal differentiation, but repressive functions in mesodermal differentiation as exemplified with cardiomyocyte formation. We further identified embryonic Ras (ERas) as novel EpCAM interactor of EpCAM and an EpCAM/ERas/AKT axis that is instrumental in differentiation regulation. Hence, spatiotemporal patterning of EpCAM at the onset of gastrulation, resulting in early segregation of interdependent EpCAM+ endodermal and EpCAM-/vimentin+ mesodermal clusters represents a novel regulatory feature during ESC differentiation.