OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning

Breast cancer cells promote osteoclast differentiation in an MRTF-dependent paracrine manner

Bone is a frequent site for breast cancer metastasis. The vast majority of breast cancer-associated metastasis is osteolytic in nature, and RANKL (receptor activator for nuclear factor κB)-induced differentiation of bone marrow-derived macrophages to osteoclasts (OCLs) is a key requirement for osteolytic metastatic growth of cancer cells. In this study, we demonstrate that Myocardin-related transcription factor (MRTF) in breast cancer cells plays an important role in paracrine modulation of RANKL-induced OCL differentiation. This is partly attributed to MRTFs' critical role in maintaining the basal cellular expression of connective tissue growth factor (CTGF), findings that align with a strong positive correlation between CTGF expression and MRTF-A gene signature in the human disease context. Luminex analyses reveal that MRTF depletion in breast cancer cells has a broad impact on OCL-regulatory cell-secreted factors that extend beyond CTGF. Experimental metastasis studies demonstrate that MRTF depletion diminishes OCL abundance and bone colonization of breast cancer cells in vivo, suggesting that MRTF inhibition could be an effective strategy to diminish OCL formation and skeletal involvement in breast cancer. In summary, this study highlights a novel tumor-extrinsic function of MRTF relevant to breast cancer metastasis.

Breast cancer cells promote osteoclast differentiation in an MRTF-dependent paracrine manner

Bone is a frequent site for breast cancer metastasis. The vast majority of breast cancer-associated metastasis is osteolytic in nature, and RANKL (receptor activator for nuclear factor κB)-induced differentiation of bone marrow-derived macrophages (BMDMs) to osteoclasts (OCLs) is a key requirement for osteolytic metastatic growth of cancer cells. In this study, we demonstrate that Myocardin-related transcription factor (MRTF) in breast cancer cells plays an important role in paracrine modulation of RANKL-induced osteoclast differentiation. This is partly attributed to MRTF's critical role in maintaining the basal cellular expression of connective tissue growth factor (CTGF), findings that align with a strong positive correlation between CTGF expression and MRTF-A gene signature in the human disease context. Luminex analyses reveal that MRTF depletion in breast cancer cells has a broad impact on OCL-regulatory cell-secreted factors that extend beyond CTGF. Experimental metastasis studies demonstrate that MRTF depletion diminishes OCL abundance and bone colonization breast cancer cells in vivo , suggesting that MRTF inhibition could be an effective strategy to diminish OCL formation and skeletal involvement in breast cancer. In summary, this study highlights a novel tumor-extrinsic function of MRTF relevant to breast cancer metastasis.

SIGNIFICANCE STATEMENT

MRTF, a transcriptional coactivator of SRF, is known to promote breast cancer progression through its tumor-cell-intrinsic function. Whether and how MRTF activity in tumor cells modulates other types of cells in the tumor microenvironment are not clearly understood.This study uncovers a novel tumor-cell-extrinsic function of MRTF in breast cancer cells in promoting osteoclast differentiation partly through CTGF regulation, and further demonstrates MRTF's requirement for bone colonization of breast cancer cells in vivo.Our studies suggest that MRTF inhibition could be an effective strategy to diminish osteoclast formation and skeletal involvement in metastatic breast cancer.

Loss-of-function OGFRL1 variants identified in autosomal recessive cherubism families

Cherubism (OMIM 118400) is a rare craniofacial disorder in children characterized by destructive jawbone expansion due to the growth of inflammatory fibrous lesions. Our previous studies have shown that gain-of-function mutations in SH3 domain-binding protein 2 (SH3BP2) are responsible for cherubism and that a knock-in mouse model for cherubism recapitulates the features of cherubism, such as increased osteoclast formation and jawbone destruction. To date, SH3BP2 is the only gene identified to be responsible for cherubism. Since not all patients clinically diagnosed with cherubism had mutations in SH3BP2, we hypothesized that there may be novel cherubism genes and that these genes may play a role in jawbone homeostasis. Here, using whole exome sequencing, we identified homozygous loss-of-function variants in the opioid growth factor receptor like 1 (OGFRL1) gene in 2 independent autosomal recessive cherubism families from Syria and India. The newly identified pathogenic homozygous variants were not reported in any variant databases, suggesting that OGFRL1 is a novel gene responsible for cherubism. Single cell analysis of mouse jawbone tissue revealed that Ogfrl1 is highly expressed in myeloid lineage cells. We generated OGFRL1 knockout mice and mice carrying the Syrian frameshift mutation to understand the in vivo role of OGFRL1. However, neither mouse model recapitulated human cherubism or the phenotypes exhibited by SH3BP2 cherubism mice under physiological and periodontitis conditions. Unlike bone marrow-derived M-CSF-dependent macrophages (BMMs) carrying the SH3BP2 cherubism mutation, BMMs lacking OGFRL1 or carrying the Syrian mutation showed no difference in TNF-ɑ mRNA induction by LPS or TNF-ɑ compared to WT BMMs. Osteoclast formation induced by RANKL was also comparable. These results suggest that the loss-of-function effects of OGFRL1 in humans differ from those in mice and highlight the fact that mice are not always an ideal model for studying rare craniofacial bone disorders.

NOISe: Nuclei-Aware Osteoclast Instance Segmentation for Mouse-to-Human Domain Transfer

Osteoclast cell image analysis plays a key role in osteoporosis research, but it typically involves extensive manual image processing and hand annotations by a trained expert. In the last few years, a handful of machine learning approaches for osteoclast image analysis have been developed, but none have addressed the full instance segmentation task required to produce the same output as that of the human expert led process. Furthermore, none of the prior, fully automated algorithms have publicly available code, pretrained models, or annotated datasets, inhibiting reproduction and extension of their work. We present a new dataset with ~2 × 105 expert annotated mouse osteoclast masks, together with a deep learning instance segmentation method which works for both in vitro mouse osteoclast cells on plastic tissue culture plates and human osteoclast cells on bone chips. To our knowledge, this is the first work to automate the full osteoclast instance segmentation task. Our method achieves a performance of 0.82 mAP0.5 (mean average precision at intersection-over-union threshold of 0.5) in cross validation for mouse osteoclasts. We present a novel nuclei-aware osteoclast instance segmentation training strategy (NOISe) based on the unique biology of osteoclasts, to improve the model's generalizability and boost the mAP0.5 from 0.60 to 0.82 on human osteoclasts. We publish our annotated mouse osteoclast image dataset, instance segmentation models, and code at github.com/michaelwwan/noise to enable reproducibility and to provide a public tool to accelerate osteoporosis research.

A Machine Learning-Based Image Segmentation Method to Quantify In Vitro Osteoclast Culture Endpoints

Quantification of in vitro osteoclast cultures (e.g. cell number) often relies on manual counting methods. These approaches are labour intensive, time consuming and result in substantial inter- and intra-user variability. This study aimed to develop and validate an automated workflow to robustly quantify in vitro osteoclast cultures. Using ilastik, a machine learning-based image analysis software, images of tartrate resistant acid phosphatase-stained mouse osteoclasts cultured on dentine discs were used to train the ilastik-based algorithm. Assessment of algorithm training showed that osteoclast numbers strongly correlated between manual- and automatically quantified values (r = 0.87). Osteoclasts were consistently faithfully segmented by the model when visually compared to the original reflective light images. The ability of this method to detect changes in osteoclast number in response to different treatments was validated using zoledronate, ticagrelor, and co-culture with MCF7 breast cancer cells. Manual and automated counting methods detected a 70% reduction (p < 0.05) in osteoclast number, when cultured with 10 nM zoledronate and a dose-dependent decrease with 1-10 μM ticagrelor (p < 0.05). Co-culture with MCF7 cells increased osteoclast number by ≥ 50% irrespective of quantification method. Overall, an automated image segmentation and analysis workflow, which consistently and sensitively identified in vitro osteoclasts, was developed. Advantages of this workflow are (1) significantly reduction in user variability of endpoint measurements (93%) and analysis time (80%); (2) detection of osteoclasts cultured on different substrates from different species; and (3) easy to use and freely available to use along with tutorial resources.

Automatic Segmentation of Teeth, Crown-Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

BACKGROUND

The aim of our study is to provide successful automatic segmentation of various objects on orthopantomographs (OPGs).

METHODS

8138 OPGs obtained from the archives of the Department of Dentomaxillofacial Radiology were included. OPGs were converted into PNGs and transferred to the segmentation tool's database. All teeth, crown-bridge restorations, dental implants, composite-amalgam fillings, dental caries, residual roots, and root canal fillings were manually segmented by two experts with the manual drawing semantic segmentation technique.

RESULTS

The intra-class correlation coefficient (ICC) for both inter- and intra-observers for manual segmentation was excellent (ICC > 0.75). The intra-observer ICC was found to be 0.994, while the inter-observer reliability was 0.989. No significant difference was detected amongst observers (p = 0.947). The calculated DSC and accuracy values across all OPGs were 0.85 and 0.95 for the tooth segmentation, 0.88 and 0.99 for dental caries, 0.87 and 0.99 for dental restorations, 0.93 and 0.99 for crown-bridge restorations, 0.94 and 0.99 for dental implants, 0.78 and 0.99 for root canal fillings, and 0.78 and 0.99 for residual roots, respectively.

CONCLUSIONS

Thanks to faster and automated diagnoses on 2D as well as 3D dental images, dentists will have higher diagnosis rates in a shorter time even without excluding cases.

Contemporary Advances in Computer-Assisted Bone Histomorphometry and Identification of Bone Cells in Culture

Static and dynamic bone histomorphometry and identification of bone cells in culture are labor-intensive and highly repetitive tasks. Several computer-assisted methods have been proposed to ease these tasks and to take advantage of the increased computational power available today. The present review aimed to provide an overview of contemporary methods utilizing specialized computer software to perform bone histomorphometry or identification of bone cells in culture. In addition, a brief historical perspective on bone histomorphometry is included. We identified ten publications using five different computer-assisted approaches (1) ImageJ and BoneJ; (2) Histomorph: OsteoidHisto, CalceinHisto, and TrapHisto; (3) Fiji/ImageJ2 and Trainable Weka Segmentation (TWS); (4) Visiopharm and artificial intelligence (AI); and (5) Osteoclast identification using deep learning with Single Shot Detection (SSD) architecture, Darknet and You Only Look Once (YOLO), or watershed algorithm (OC_Finder). The review also highlighted a substantial need for more validation studies that evaluate the accuracy of the new computational methods to the manual and conventional analyses of histological bone specimens and cells in culture using microscopy. However, a substantial evolution has occurred during the last decade to identify and separate bone cells and structures of interest. Most early studies have used simple image segmentation to separate structures of interest, whereas the most recent studies have utilized AI and deep learning. AI has been proposed to substantially decrease the amount of time needed for analyses and enable unbiased assessments. Despite the clear advantages of highly sophisticated computational methods, the limited nature of existing validation studies, particularly those that assess the accuracy of the third-generation methods compared to the second-generation methods, appears to be an important reason that these techniques have failed to gain wide acceptance.