Deep Learning for Detecting BRCA Mutations in High-Grade Ovarian Cancer Based on an Innovative Tumor Segmentation Method From Whole Slide Images.

BRCA1 and BRCA2 genes play a crucial role in repairing DNA double-strand breaks through homologous recombination. Their mutations represent a significant proportion of homologous recombination deficiency and are a reliable effective predictor of sensitivity of high-grade ovarian cancer (HGOC) to poly(ADP-ribose) polymerase inhibitors. However, their testing by next-generation sequencing is costly and time-consuming and can be affected by various preanalytical factors. In this study, we present a deep learning classifier for BRCA mutational status prediction from hematoxylin-eosin-safran-stained whole slide images (WSI) of HGOC. We constituted the OvarIA cohort composed of 867 patients with HGOC with known BRCA somatic mutational status from 2 different pathology departments. We first developed a tumor segmentation model according to dynamic sampling and then trained a visual representation encoder with momentum contrastive learning on the predicted tumor tiles. We finally trained a BRCA classifier on more than a million tumor tiles in multiple instance learning with an attention-based mechanism. The tumor segmentation model trained on 8 WSI obtained a dice score of 0.915 and an intersection-over-union score of 0.847 on a test set of 50 WSI, while the BRCA classifier achieved the state-of-the-art area under the receiver operating characteristic curve of 0.739 in 5-fold cross-validation and 0.681 on the testing set. An additional multiscale approach indicates that the relevant information for predicting BRCA mutations is located more in the tumor context than in the cell morphology. Our results suggest that BRCA somatic mutations have a discernible phenotypic effect that could be detected by deep learning and could be used as a prescreening tool in the future.

Deep Learning Methodologies Applied to Digital Pathology in Prostate Cancer: A Systematic Review.

Deep learning (DL), often called artificial intelligence (AI), has been increasingly used in Pathology thanks to the use of scanners to digitize slides which allow us to visualize them on monitors and process them with AI algorithms. Many articles have focused on DL applied to prostate cancer (PCa). This systematic review explains the DL applications and their performances for PCa in digital pathology. Article research was performed using PubMed and Embase to collect relevant articles. A Risk of Bias (RoB) was assessed with an adaptation of the QUADAS-2 tool. Out of the 77 included studies, eight focused on pre-processing tasks such as quality assessment or staining normalization. Most articles (n = 53) focused on diagnosis tasks like cancer detection or Gleason grading. Fifteen articles focused on prediction tasks, such as recurrence prediction or genomic correlations. Best performances were reached for cancer detection with an Area Under the Curve (AUC) up to 0.99 with algorithms already available for routine diagnosis. A few biases outlined by the RoB analysis are often found in these articles, such as the lack of external validation. This review was registered on PROSPERO under CRD42023418661.

Spatial Distribution of Immune Cells in Primary and Recurrent Glioblastoma: A Small Case Study.

Only a minority of patients with glioblastoma (GBM) respond to immunotherapy, and always only partially. There is a lack of knowledge on immune distribution in GBM and in its tumor microenvironment (TME). To address the question, we used paired primary and recurrent tumors from GBM patients to study the composition and the evolution of the immune landscape upon treatment. We studied the expression of a handful of immune markers (CD3, CD8, CD68, PD-L1 and PD-1) in GBM tissues in 15 paired primary and recurrent GBM. In five selected patients, we used Nanostring Digital Spatial Profiling (DSP) to obtain simultaneous assessments of multiple biomarkers both within the tumor and the microenvironment in paired primary and recurrent GBM. Our results suggest that the evolution of the immune landscape between paired primary and recurrent GBM tumors is highly heterogeneous. However, our study identifies B3-H7 and HLA-DR as potential targets in primary and recurrent GBM. Spatial profiling of immune markers from matched primary and recurrent GBM shows a nonlinear complex evolution during the progression of cancer. Nonetheless, our study demonstrated a global increase in macrophages, and revealed differential localization of some markers, such as B7-H3 and HLA-DR, between GBM and its TME.

[Takayasu's arteritis]. / Artérite de Takayasu.

TAKAYASU'S ARTERITIS. Takayasu's arteritis is an inflammatory panarteritis of the large vessels, preferentially affecting the aorta, its main branches, and the pulmonary arteries. Its incidence is estimated at 1.11 cases per million person-years, with a female predominance. The disease is classically characterized by the succession of two phases: a pre-occlusive inflammatory phase that may go unnoticed and an occlusive phase characterized by ischemic vascular symptoms because of parietal arterial lesions such as stenosis, occlusion or aneurysm. The diagnosis is based on clinical, biological and morphological findings. When available, pathological examination reveals a predominantly medial-adventitial, segmental and focal granulomatous panarteritis. Treatment consists of administering corticosteroid therapy and often immunosuppressants, or even biotherapies, managing cardiovascular risk factors, and managing vascular complications.

ARTÉRITE DE TAKAYASU. L'artérite de Takayasu est une panartérite inflammatoire des gros vaisseaux touchant préférentiellement l'aorte et ses branches principales ainsi que les artères pulmonaires. On estime son incidence annuelle à 1,11 cas par million de personnes, avec une prédominance féminine. Il est classiquement observé deux phases successives : une phase inflammatoire préocclusive pouvant passer inaperçue, puis une phase occlusive, caractérisée par des symptômes vasculaires ischémiques, conséquence des lésions artérielles pariétales à type de sténose, occlusion ou anévrisme. Le diagnostic repose sur un faisceau d'arguments cliniques, biologiques et morphologiques. Lorsqu'il est accessible, l'examen anatomopathologique retrouve un aspect de panartérite granulomateuse à prédominance médio-adventitielle, segmentaire et focale. Le traitement consiste en l'administration d'une corticothérapie et souvent d'immunosuppresseurs, ainsi qu'en la prise en charge des facteurs de risque cardiovasculaire afin de prévenir les complications vasculaires à plus long terme.

Impact on outcomes of mixed chimerism of bone marrow CD34+ sorted cells after matched or haploidentical allogeneic stem cell transplantation for myeloid malignancies.

Allogeneic hematopoietic stem cell transplantation (Allo-HSCT), proposed to patients with high-risk myeloid malignancies, may ultimately fail because of disease relapse. Bone marrow (BM) CD34+ cells in Allo-HSCT recipients can be either re-emerging recipient malignant cells or donor cells attesting of hematopoietic reconstitution. In this context, investigating donor/recipient chimerism in the population of BM CD34+ sorted cells (BM-CD34+SC) was performed in 261 Allo-HSCT recipients (matched n = 145, haploidentical n = 65, matched unrelated n = 51) with myeloid malignancies. BM-CD34+SC chimerism was compared to that of whole peripheral blood (PB) cells as well as other Allo-HSCT-related parameters, and impact on relapse and survival was assessed. Thresholds of 98% donor cells for PB and 90% for BM-CD34+SC were found to allow relapse prediction. This was completed by the application of machine learning tools to explore the predictive value of these parameters in multidimensional models with repeated iterations. BM-CD34+SC mixed chimerism stood out with all these methods as the most robust predictor of relapse with a significant impact on disease-free and overall survivals even after haploidentical Allo-HSCT and/or PTCY administration. This marker therefore appears to be of great interest for the decision of preemptive treatment to avoid post-transplant relapse.

Effect of Parathyroidectomy on Metabolic Homeostasis in Primary Hyperparathyroidism.

Background: The benefits of parathyroidectomy on cardiovascular risk in primary hyperparathyroidism (PHPT) are controversial. This monocentric, observational, prospective study aimed to assess the effects of parathyroidectomy on glucose and lipid metabolism in classic or mild PHPT. Methods: Patients who underwent parathyroidectomy for classic (calcemia >2.85 mmol/L) or mild PHPT (calcemia ≤2.85 mmol/L) between 2016 and 2019 were included. A metabolic assessment was performed before and 1 year after parathyroidectomy. Patients with a history of diabetes were excluded. Results: Nineteen patients had classic and 120 had mild PHPT. Ninety-five percent were normocalcemic 6 months after surgery. Fasting plasma glucose and insulin levels decreased after parathyroidectomy in patients with mild PHPT (p < 0.001). HOMA-IR decreased after surgery in the overall population (p < 0.001), while plasma adiponectin concentrations increased in patients with both classic (p = 0.005) and mild PHPT (p < 0.001). Plasma triglyceride levels decreased significantly only in patients with classic PHPT (p = 0.021). Plasma PCSK9 levels decreased in patients with mild PHPT (p < 0.001). Conclusions: Parathyroidectomy for PHPT improves insulin resistance and decreases plasma triglyceride levels in classic PHPT and plasma PCSK9 levels in mild PHPT. Further studies are needed to better characterize the consequences of such metabolic risk factors' improvements on cardiovascular events.

[Inflammatory cardiomyopathies: Diagnosis, correlations with imaging, interest of myocardial biopsy and place of molecular biology]. / Cardiomyopathies inflammatoires : diagnostic, corrélations avec l'imagerie, intérêt de la biopsie myocardique et place de la biologie moléculaire.

Inflammatory cardiomyopathies, also known as "myocarditis" are inflammatory pathologies affecting the myocardium and characterized by vast etiological and clinical heterogeneity. They can be asymptomatic, particularly in viral forms, or be responsible for sudden death, particularly in subjects under 35 years olds. Due to insufficient sensitivity and specificity of imaging and biology, the gold standard is histopathological and is performed on an endomyocardial biopsy or on explanted heart samples in a transplant context. Their classification has considerably evolved and is now based on the identification of a predominant cell pattern such as lymphocytic, neutrophilic or eosinophilic polynuclear, giant cell or granulomatous myocarditis. These different patterns will guide the etiological diagnosis, prognosis and the therapies to be implemented. Due to the importance of viral etiologies, this morphological analysis must be complemented by a virological analysis based on PCR with viral load quantification. In addition, some authors have been able to demonstrate the occurrence of myocarditis in patients with arrhythmogenic cardiomyopathy of genetic origin. The aim of this chapter is to review the current state of knowledge on inflammatory cardiomyopathies and their management.