[Results of the Massive Open Online Course (MOOC) on cancer diagnosis and evaluation of its impact on the perception of the pathology specialty]. / Massive open online course (MOOC) sur le diagnostic des cancers : bilan et évaluation de l'impact sur la perception de l'anatomie et cytologie pathologiques.

The Massive Open Online Course (or MOOC) "Diagnostic Strategies Cancers", was hosted in autumn 2016 on the platform "France Université Numérique" and had two levels of learners: students in the field of health and biology and the general public. Of the 5285 learners in 81 different countries, 1237 (23%) were successfully certified. This MOOC was also integrated into the teaching program of medical students of Paris Diderot University and Paris 13 University. Using anonymous questionnaires before and after MOOC, it has been shown that pathology is less known than other medical specialties. Participation in this MOOC led to a marked improvement in participants' knowledge of the place and role of the pathologist in the diagnosis of cancers. Regarding the students who have followed the MOOC as part of their university course, their comments were very positive, but it is necessary to make substantial adjustments in the amounts and contents of the campus-based courses.

[Backstage of a massive open online course (MOOC) on cancer diagnosis]. / Les coulisses d'un Massive Open Online Course (MOOC) sur le diagnostic des cancers.

Massive open online course (or MOOC) is a new online and open access teaching approach aimed at unlimited participation and providing interactions among students and teaching staff. These academic courses, often still free, lead to the delivery of a certificate of attendance and could soon also deliver a diploma. The MOOC "Stratégies diagnostiques des cancers" will be hosted in autumn 2016 on the platform "France Université Numérique" and will have two levels of learners: students in the field of health and biology and the general public. This MOOC will also be integrated into the teaching program of medical students of Paris Diderot University and Paris 13 University. The educational objective of this MOOC is to convey to all participants an overview of the diagnostic steps of cancers and of the various medical specialties involved in this diagnosis. The second week of the MOOC, entitled "tumor samples, macroscopic and microscopic analysis", presents the pathology specialty with the technical treatment of tissue or cell samples and the basic elements of the tissue section analysis to get a diagnosis of benign or malignant tumor. After this MOOC, it is planned to assess the impact of this new modality of teaching the pathology specialty or pathology, especially by the general public.

Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology.

Purpose: Generalization is one of the main challenges of computational pathology. Slide preparation heterogeneity and the diversity of scanners lead to poor model performance when used on data from medical centers not seen during training. In order to achieve stain invariance in breast invasive carcinoma patch classification, we implement a stain translation strategy using cycleGANs for unsupervised image-to-image translation. Those models often suffer from a lack of proper metrics to monitor and stop the training at a particular point. We also introduce a method to solve this issue. Approach: We compare three CycleGAN-based approaches to a baseline classification model obtained without any stain invariance strategy. Two of the proposed approaches use CycleGAN's translations at inference or training to build stain-specific classification models. The last method uses them for stain data augmentation during training. This constrains the classification model to learn stain-invariant features. Regarding CycleGANs' training monitoring, we leverage Fréchet inception distance between generated and real samples and use it as a stopping criterion. We compare CycleGANs' models stopped using this criterion and models stopped at a fixed number of epochs. Results: Baseline metrics are set by training and testing the baseline classification model on a reference stain. We assessed performances using three medical centers with H&E and H&E&S staining. Every approach tested in this study improves baseline metrics without needing labels on target stains. The stain augmentation-based approach produced the best results on every stain. Each method's pros and cons are studied and discussed. Moreover, FID stopping criterion proves superiority to methods using a predefined number of training epoch and has the benefit of not requiring any visual inspection of CycleGAN results. Conclusion: We introduce a method to attain stain invariance for breast invasive carcinoma classification by leveraging CycleGAN's abilities to produce realistic translations between various stains. Moreover, we propose a systematical method for scheduling CycleGANs' trainings by using FID as a stopping criterion and prove its superiority to other methods. Finally, we give an insight on the minimal amount of data required for CycleGAN training in a digital histopathology setting.

Multicenter automatic detection of invasive carcinoma on breast whole slide images.

Breast cancer is one of the most prevalent cancers worldwide and pathologists are closely involved in establishing a diagnosis. Tools to assist in making a diagnosis are required to manage the increasing workload. In this context, artificial intelligence (AI) and deep-learning based tools may be used in daily pathology practice. However, it is challenging to develop fast and reliable algorithms that can be trusted by practitioners, whatever the medical center. We describe a patch-based algorithm that incorporates a convolutional neural network to detect and locate invasive carcinoma on breast whole-slide images. The network was trained on a dataset extracted from a reference acquisition center. We then performed a calibration step based on transfer learning to maintain the performance when translating on a new target acquisition center by using a limited amount of additional training data. Performance was evaluated using classical binary measures (accuracy, recall, precision) for both centers (referred to as "test reference dataset" and "test target dataset") and at two levels: patch and slide level. At patch level, accuracy, recall, and precision of the model on the reference and target test sets were 92.1% and 96.3%, 95% and 87.8%, and 73.9% and 70.6%, respectively. At slide level, accuracy, recall, and precision were 97.6% and 92.0%, 90.9% and 100%, and 100% and 70.8% for test sets 1 and 2, respectively. The high performance of the algorithm at both centers shows that the calibration process is efficient. This is performed using limited training data from the new target acquisition center and requires that the model is trained beforehand on a large database from a reference center. This methodology allows the implementation of AI diagnostic tools to help in routine pathology practice.

Nosocomial nasal myiasis owing to Cochliomyia hominivorax: a case in French Guiana.

Abstract The larval stages of the fly Cochliomyia hominivorax are responsible for myiasis, which primarily affects wounds. We report the case of a bed-ridden patient with dementia who developed right nasal myiasis during his stay at Cayenne Hospital. Progression was favorable, but the nasal pyramid was partially destroyed. In zones where this fly is endemic, particular attention should be given to hospitalized patients with wounds and consciousness problems.