Deep Multiple Instance Learning Model to Predict Outcome of Pancreatic Cancer Following Surgery.

: Pancreatic ductal adenocarcinoma (PDAC) is a cancer with very poor prognosis despite early surgical management. To date, only clinical variables are used to predict outcome for decision-making about adjuvant therapy. We sought to generate a deep learning approach based on hematoxylin and eosin (H&E) or hematoxylin, eosin and saffron (HES) whole slides to predict patients' outcome, compare these new entities with known molecular subtypes and question their biological significance; : We used as a training set a retrospective private cohort of 206 patients treated by surgery for PDAC cancer and a validation cohort of 166 non-metastatic patients from The Cancer Genome Atlas (TCGA) PDAC project.

Case report: Immune response characterization of a pseudoprogression in a PD-L1-negative, TMB-low, co-mutated metastatic NSCLC.

A patient with a PD-L1-negative, TMB-low, co-mutated metastatic non-small cell lung cancer (NSCLC) experienced a multisite radiological progression at 3 months after initiation of chemoimmunotherapy as first-line treatment for metastatic disease. After the radiological progression, while she was not undergoing treatment, the patient had spontaneous lesions shrinkage and further achieved a prolonged complete response. Genomic and transcriptomic data collected at baseline and at the time of pseudoprogression allowed us to biologically characterize this rare response pattern.

Respective contribution of baseline clinical data, tumour metabolism and tumour blood-flow in predicting pCR after neoadjuvant chemotherapy in HER2 and Triple Negative breast cancer.

Background: The aim of this study is to investigate the added value of combining tumour blood flow (BF) and metabolism parameters, including texture features, with clinical parameters to predict, at baseline, the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in patients with newly diagnosed breast cancer (BC).

Methods: One hundred and twenty-eight BC patients underwent a F-FDG PET/CT before any treatment. Tumour BF and metabolism parameters were extracted from first-pass dynamic and delayed PET images, respectively.

HER2-Low Luminal Breast Carcinoma Is Not a Homogenous Clinicopathological and Molecular Entity.

Background: With the development of some new antibody-drug conjugates, the HER2 classification of breast carcinomas now includes the HER2-low (H2L) category: IHC 1+, 2+ non-amplified by ISH, and double-equivocal carcinomas, mostly luminal, expressing hormone receptors (HR+).

Methods: We analyzed mutational status and transcriptomic activities of three HER2 effector pathways: PI3K-AKT, MAPK, and JAK-STAT, in association with clinicopathologic features, in 62 H2L carcinomas compared to 43 HER2-positive and 20 HER2-negative carcinomas, all HR+.

Results: H2L carcinomas had significantly lower histoprognostic grades and mitotic and Ki67 proliferation indexes than HER2-positive carcinomas.