Deep learning enables the automation of grading histological tissue engineered cartilage images for quality control standardization

Power, Laura; Acevedo, Lina; Yamashita, Rikiya; Rubin, Daniel L.; Martín, Iván; Barbero, Andrea

doi:10.1016/j.joca.2020.12.018

Cited by 15 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 20 , 25 - 27 On the contrary, although there have been many attempts to automatically analyze histological sections using deep learning, 28 , 29 only a few reports have analyzed musculoskeletal tissue sections, including cartilage. 30 The fact that we were able to detect anatomical locations from tissue sections of the knee joint with high accuracy might suggest a use for deep learning in histological analysis of articular cartilage.…”

Section: Discussionmentioning

confidence: 91%

Automatic Detection of Medial and Lateral Compartments from Histological Sections of Mouse Knee Joints Using the Single-Shot Multibox Detector Algorithm

et al. 2022

View full text Add to dashboard Cite

Objective Although mouse osteoarthritis (OA) models are widely used, their histological analysis may be susceptible to arbitrariness and inter-examiner variability in conventional methods. Therefore, a method for the unbiased scoring of OA histology is needed. In this study, as the first step for establishing this system, we developed a computer-vision algorithm that automatically detects the medial and lateral compartments of mouse knee sections in a rigorous and unbiased manner. Design A total of 706 images of coronal sections of mouse knee joints stained by hematoxylin and eosin, safranin O, or toluidine blue were randomly divided into training and validation images at a ratio of 80:20. A model to detect both compartments automatically was built by machine learning using a single-shot multibox detector (SSD) algorithm with training images. The model was tested to determine whether it could accurately detect both compartments by analyzing the validation images and 52 images of sections stained with Picrosirius red, a method not used for the training images. Results The trained model accurately detected both medial and lateral compartments of all 140 validation images regardless of the staining method employed, severity of articular cartilage defects, and the anatomical positions and conditions of the sections. Our model also correctly detected both compartments of 50 of 52 Picrosirius red–stained images. Conclusions By applying deep learning based on the SSD algorithm, we successfully developed a model that detects the locations of the medial and lateral compartments of tissue sections of mouse knee joints with high accuracy.

show abstract

Section: Discussionmentioning

confidence: 91%

Automatic Detection of Medial and Lateral Compartments from Histological Sections of Mouse Knee Joints Using the Single-Shot Multibox Detector Algorithm

et al. 2022

View full text Add to dashboard Cite

show abstract

“…3a). The overall chondrogenic quality of the pellets was also unchanged as determined through an automated evaluation of the modified Bern score 76 (Extended Data Fig. 3b).…”

Section: Resultsmentioning

confidence: 99%

“…Safranin-O images were adopted for tissues histological grading through the Modified Bern Score 137 . Grading was performed as previously described 76 through a deep learning based automated procedure using tiles of 224×224 pixels with a pixel dimension of 0.511 µm.…”

Section: Methodsmentioning

confidence: 99%

Modelling Osteoarthritis pathogenesis through Mechanical Loading in an Osteochondral Unit-on-Chip

Mainardi,

Börsch,

Occhetta

et al. 2023

Preprint

View full text Add to dashboard Cite

A cure for osteoarthritis (OA), the most prevalent musculoskeletal disease, remains an unmet need. Investigating the molecular and cellular processes leading to OA is challenged by the absence of human models that capture the complex interplay among different tissues in the joint under pathophysiological mechanical loading.In this study, we have engineered an OsteoChondral Unit (OCU)-on-chip system where composite hyaline cartilage - mineralized osseous microtissue analogues are exposed to controlled, tissue-specific compression regimes akin to those of the OCUin vivo. Through single-cell transcriptomic analysis, we demonstrate the critical relevance of the mineralized layer in inducing chondrocyte subpopulations implicated in the progression of OA.Upon exposure to hyperphysiological loading, the OCU-on-chip captures early phenotypic traits of OA pathogenesis, comprising alterations of subchondral mineral content and acquisition of previously described OA genetic signatures.This system enabled to identify novel upstream drivers of OA metabolic changes, including mechanically induced ribosomal alterations, as well as associated molecular targets towards the development of disease-modifying OA therapies.

show abstract

“…Although not yet integrated in the concept, first approaches to automate these controls have already been carried out. As an example, the automated visual inspection of histological tissue engineered cartilage using a modified Bern score and deep learning algorithm has already been demonstrated to be a feasible method for the prospective evaluation and graft release in a clinical manufacturing setting (31,32). However, these pivotal procedures would greatly benefit from the implementation of non-invasive in-process controls, enabling real-time quality control and monitoring of product specifications throughout the manufacturing process.…”

Section: Atmp Manufacturing 40: Facilities Of the Futurementioning

confidence: 99%

From Single Batch to Mass Production–Automated Platform Design Concept for a Phase II Clinical Trial Tissue Engineered Cartilage Product

et al. 2021

View full text Add to dashboard Cite

Advanced Therapy Medicinal Products (ATMP) provide promising treatment options particularly for unmet clinical needs, such as progressive and chronic diseases where currently no satisfying treatment exists. Especially from the ATMP subclass of Tissue Engineered Products (TEPs), only a few have yet been translated from an academic setting to clinic and beyond. A reason for low numbers of TEPs in current clinical trials and one main key hurdle for TEPs is the cost and labor-intensive manufacturing process. Manual production steps require experienced personnel, are challenging to standardize and to scale up. Automated manufacturing has the potential to overcome these challenges, toward an increasing cost-effectiveness. One major obstacle for automation is the control and risk prevention of cross contaminations, especially when handling parallel production lines of different patient material. These critical steps necessitate validated effective and efficient cleaning procedures in an automated system. In this perspective, possible technologies, concepts and solutions to existing ATMP manufacturing hurdles are discussed on the example of a late clinical phase II trial TEP. In compliance to Good Manufacturing Practice (GMP) guidelines, we propose a dual arm robot based isolator approach. Our novel concept enables complete process automation for adherent cell culture, and the translation of all manual process steps with standard laboratory equipment. Moreover, we discuss novel solutions for automated cleaning, without the need for human intervention. Consequently, our automation concept offers the unique chance to scale up production while becoming more cost-effective, which will ultimately increase TEP availability to a broader number of patients.

show abstract

Deep learning enables the automation of grading histological tissue engineered cartilage images for quality control standardization

Cited by 15 publications

References 34 publications

Automatic Detection of Medial and Lateral Compartments from Histological Sections of Mouse Knee Joints Using the Single-Shot Multibox Detector Algorithm

Automatic Detection of Medial and Lateral Compartments from Histological Sections of Mouse Knee Joints Using the Single-Shot Multibox Detector Algorithm

Modelling Osteoarthritis pathogenesis through Mechanical Loading in an Osteochondral Unit-on-Chip

From Single Batch to Mass Production–Automated Platform Design Concept for a Phase II Clinical Trial Tissue Engineered Cartilage Product

Contact Info

Product

Resources

About