[The first data challenge of the french society of pathology: An international competition in 2020, a research tool in A.I. for the future?] / Le premier data challenge organisé par la Société Française de Pathologie : une compétition internationale en 2020, un outil de recherche en intelligence artificielle pour l'avenir ?

The french society of pathology (SFP) organized in 2020 its first data challenge with the help of Health Data Hub (HDH). The organisation of this event first consisted in recruiting almost 5000 slides of uterus cervical biopsies obtained in 20 pathology centers. After having made sure that patients did not refuse to include their slides in the project, the slides were anonymised, digitized and annotated by expert pathologists, and were finally uploaded on a data challenge platform for competitors all around the world. Competitors teams had to develop algorithms that could distinguish among four diagnostic classes in epithelial lesions of uterine cervix. Among many submissions by competitors, the best algorithms obtained an overall score close to 95%. The best 3 teams shared 25k€ prizes during a special session organised during the national congress of the SFP. The final part of the competition lasted only 6 weeks and the goal of SFP and HDH is now to allow for the collection to be published in open access. This final step will allow data scientists and pathologists to further develop artificial intelligence algorithms in this medical area.

Skin amyloid deposits and nerve fiber loss as markers of neuropathy onset and progression in hereditary transthyretin amyloidosis.

BACKGROUND AND PURPOSE: This study was undertaken to assess skin biopsy as a marker of disease onset and severity in hereditary transthyretin amyloidosis with polyneuropathy (ATTRv-PN), a treatable disease. METHODS: In this single center retrospective study, skin Congo red staining and intraepidermal nerve fiber density (IENFD) were evaluated in symptomatic ATTRv-PN patients and asymptomatic TTR gene mutation carriers between 2012 and 2019. Non-ATTRv subjects with suspected small fiber neuropathy who underwent skin biopsy during the same timespan were used as controls. RESULTS: One hundred eighty-three symptomatic ATTRv-PN patients, 36 asymptomatic carriers, and 537 non-ATTRv patients were included. Skin biopsy demonstrated amyloid depositions in 80% of the 183 symptomatic cases. Skin amyloid deposits were found in 75% of early stage ATTRv-PN patients, and in 14% of asymptomatic carriers. All 183 symptomatic and 34 of 36 asymptomatic patients displayed decreased ankle IENFD with a proximal-distal gradient distribution, and reduced IEFND correlated with disease severity and duration. CONCLUSIONS: Our study demonstrates skin amyloid deposits are a marker of ATTRv-PN disease onset, and decreased IENFD a marker of disease progression. These results are of major importance for the early identification of ATTRv-PN patients in need of disease-modifying treatments.

Four-Year Experience of Digital Slide Telepathology for Intraoperative Frozen Section Consultations in a Two-Site French Academic Department of Pathology.

OBJECTIVES: To share our experience with digital slide telepathology for intraoperative frozen section consultations (IOCs) and to describe its evolution over time by reporting performance metrics and addressing organizational and economic aspects. METHODS: Since 2013, a technician has been alone at the surgical site. At the other site, the pathologist opens the digital slide from a local server via the intranet. Three periods were compared: a 6-month period of conventional IOC (period 1), a 24-month period of telepathology at 6 months after implementation (period 2), and a 12-month period of telepathology at 3.5 years after implementation (period 3). RESULTS: In total, 87 conventional IOCs and 464 and 313 IOCs on digital slides were performed respectively during periods 1, 2, and 3; mean turnaround time was 27, 36, and 38 minutes, respectively, and there were a mean number of 1.1, 1.1, and 1.3 slides, respectively, per IOC. Diagnostic accuracy was achieved in 95.4%, 92.7%, and 93.9%, respectively, of IOCs (not significant). The additional cost is in the same range as the cost of urgent transport by courier. CONCLUSIONS: Developing IOC with digital slides is a challenge but is necessary to optimize medical time in the current context of pathologist shortage and budget restrictions.

Improving Hepatocyte Engraftment Following Hepatocyte Transplantation Using Repeated Reversible Portal Vein Embolization in Rats.

Hepatocyte transplantation (HT) has emerged as a promising alternative to orthotopic liver transplantation, yet liver preconditioning is needed to promote hepatocyte engraftment. A method of temporary occlusion of the portal flow called reversible portal vein embolization (RPVE) has been demonstrated to be an efficient method of liver preconditioning. By providing an additional regenerative stimulus, repeated reversible portal vein embolization (RRPVE) could further boost liver engraftment. The aim of this study was to determine the efficiency of liver engraftment of transplanted hepatocytes after RPVE and RRPVE in a rat model. Green fluorescent protein-expressing hepatocytes were isolated from transgenic rats and transplanted into 3 groups of syngeneic recipient rats. HT was associated with RPVE in group 1, with RRPVE in group 2, and with sham embolization in the sham group. Liver engraftment was assessed at day 28 after HT on liver samples after immunostaining. Procedures were well tolerated in all groups. RRPVE resulted in increased engraftment rate in total liver parenchyma compared with RPVE (3.4% ± 0.81% versus 1.4% ± 0.34%; P < 0.001). In conclusion, RRPVE successfully enhanced hepatocyte engraftment after HT and could be helpful in the frame of failure of HT due to low cell engraftment.

High-throughput ovarian follicle counting by an innovative deep learning approach.

The evaluation of the number of mouse ovarian primordial follicles (PMF) can provide important information about ovarian function, regulation of folliculogenesis or the impact of chemotherapy on fertility. This counting, usually performed by specialized operators, is a tedious, time-consuming but indispensable procedure.The development and increasing use of deep machine learning algorithms promise to speed up and improve this process. Here, we present a new methodology of automatically detecting and counting PMF, using convolutional neural networks driven by labelled datasets and a sliding window algorithm to select test data. Trained from a database of 9 millions of images extracted from mouse ovaries, and tested over two ovaries (3 millions of images to classify and 2 000 follicles to detect), the algorithm processes the digitized histological slides of a completed ovary in less than one minute, dividing the usual processing time by a factor of about 30. It also outperforms the measurements made by a pathologist through optical detection. Its ability to correct label errors enables conducting an active learning process with the operator, improving the overall counting iteratively. These results could be suitable to adapt the methodology to the human ovarian follicles by transfer learning.

Volumetric Portal Embolization: A New Concept to Improve Liver Regeneration and Hepatocyte Engraftment.

BACKGROUND: Hepatocyte transplantation has been proposed as an alternative to orthotopic liver transplantation to treat metabolic liver diseases. This approach requires preconditioning of the host liver to enhance engraftment of transplanted hepatocytes. Different methods are currently used in preclinical models: partial hepatectomy, portal ligature or embolization, and radiotherapy or chemotherapeutic drugs. However, these methods carry high risks of complications and are problematic for use in clinical practice. Here, we developed an innovative method called volumetric (distal, partial, and random) portal embolization (VPE), which preserves total liver volume. METHODS: Embolization was performed in the portal trunk of C57BL6 adult mice with polyester microspheres, to ensure a bilateral and distal distribution. The repartition of microspheres was studied by angiographic and histological analyses. Liver regeneration was evaluated by Ki67 labeling. Optimal conditions for VPE were determined, and the resulting regeneration was compared with that after partial hepatectomy (70%). Labeled adult hepatocytes were then transplanted, and engraftment was compared between embolized (n = 19) and nonembolized mice (n = 8). Engraftment was assessed in vivo and histologically by tracking labeled cells at day 5. RESULTS: The best volumetric embolization conditions, which resulted in the regeneration of 5% of total liver, were 8 × 10 ten-micron microspheres infused with a 29 G needle directly into the portal trunk at 3.3 µL/s. In these conditions, transplanted hepatocytes engraftment was significantly higher than that in control conditions (3 vs 0.65%). CONCLUSIONS: The VPE is a new, minimally invasive, and efficient technique to prepare the host liver for cell transplantation.