Cellular Morphological Features Research Articles

MCRANet: MTSL-based connectivity region attention network for PD-L1 status segmentation in H&E stained images

The quantitative analysis of Programmed death-ligand 1 (PD-L1) via Immunohistochemical (IHC) plays a crucial role in guiding immunotherapy. However, IHC faces challenges, including high costs, time consumption and result variability. Conversely, Hematoxylin-Eosin (H&E) staining offers cost-effectiveness, speed, and stable results. Nonetheless, H&E staining, which solely visualizes cellular morphological features, lacks clinical applicability in detecting biomarker expressions like PD-L1. Substituting H&E staining for IHC in determining PD-L1 status is a clinically significant and challenging task. Motivated by above observations, we propose a Multi-Task supervised learning (MTSL)-based connectivity region attention network (MCRANet) for PD-L1 status segmentation in H&E stained images. To reduce interference from non-tumor areas, the MTSL-based region attention is proposed to enhances the network's capability to distinguish between tumor and non-tumor regions. Consequently, this augmentation further improves the network's segmentation efficacy for PD-L1 positive and negative regions. Furthermore, the PD-L1 expression regions demonstrate interconnection throughout the tissue section. Leveraging this topological prior knowledge, we integrate a connectivity modeling module (CM module) within the MTSL-based region attention module (MRA module) to enhance the precision of MTSL-based region attention localization. This integration further improves the structural similarity between the segmentation results and the ground truth. Extensive visual and quantitative results demonstrate that our supervised-learning-guided MRA module produces more interpretable attention and the introduced CM module provides accurate positional attention to the MRA module. Compared to other state-of-the-art networks, MCRANet exhibits superior segmentation performance with a dice similarity coefficient (DSC) of 79.6 % on the lung squamous cell carcinoma (LUSC) PD-L1 status dataset.

PARP inhibitors enhance antitumor immune responses by triggering pyroptosis via TNF–caspase 8–GSDMD/E axis in ovarian cancer

BackgroundIn addition to their established action of synthetic lethality in tumor cells, poly(ADP-ribose) polymerase inhibitors (PARPis) also orchestrate tumor immune microenvironment (TIME) that contributes to suppressing tumor growth. However, it...

Magnetic 3D bioprinting of skeletal muscle spheroid for a spheroid-based screening assay

Over the past decade, there has been a rapid development in the use of magnetic three dimensional (3D) based cell culture systems. Concerning the skeletal muscle, 3D culture systems can provide biological insights for translational clinical research in the fields of muscle physiology and metabolism. These systems can enhance the cell culture environment by improving spatially-oriented cellular assemblies and morphological features closely mimicking the in vivo tissues/organs, since they promote strong interactions between cells and the extracellular matrix (ECM). However, the time-consuming and complex nature of 3D traditional culture techniques pose a challenge to the widespread adoption of 3D systems. Herein, a bench protocol is presented for creating an innovative, promptly assembled and user-friendly culture platform for the magnetic 3D bioprinting of skeletal muscle spheroids. Our protocol findings revealed consistent morphological outcomes and the functional development of skeletal muscle tissue, as evidenced by the expression of muscle-specific contractile proteins and myotubes and the responsiveness to stimulation with cholinergic neurotransmitters. This proof-of-concept protocol confirmed the future potential for further validation and application of spheroid-based assays in human skeletal muscle research.

Efficacy of Follicular Cell Pattern Analysis in Thyroid Fine-needle Aspiration Cytology Evaluation.

Fine-needle aspiration cytology (FNAC) is widely utilized for thyroid lesion diagnosis but faces challenges such as sample inadequacy and overlapping cytological features. This study examines how accurately these patterns correlate with histopathological diagnoses, shedding light on FNAC's limitations and diagnostic potential. To study the application of the architectural pattern of follicular cells in the interpretation of thyroid lesions and to demonstrate the diagnostic accuracy (DA) of FNAC. Cross-sectional study carried over 1 year. A total of 110 cases were reviewed by the cytopathologists. The prominent follicular cell architecture, namely macrofollicular, microfollicular, papillary, trabecular, three-dimensional clusters, and dispersed cells, was described in each case. In addition to these patterns, cellular morphology and background features were also noted, and a final cytological diagnosis was established. The cytology diagnosis was correlated with the histopathological diagnosis. Sensitivity, specificity, positive predictive value, negative predictive value, DA of FNAC in diagnosing nonneoplastic and neoplastic lesions. Macrofollicular pattern was seen in 80.26% of colloid goiter cases. Microfollicular pattern was observed in 72.2% of follicular neoplasm. About 62.5% of papillary thyroid carcinomas showed a papillary pattern. The trabecular pattern was seen in 42.86% of chronic lymphocytic thyroiditis and 16.67% of follicular neoplasms. The sensitivity and specificity of FNAC in diagnosing neoplastic lesions was 92.59% and 97.59%, respectively. FNAC is a simple, rapid, definite, and cost-effective primary diagnostic tool for thyroid evaluation. Cell architecture pattern is a simple and appropriate approach that complements cell morphology and background details in arriving at the final cytological diagnosis of thyroid lesions.

Deep in situ microscopy for real-time analysis of mammalian cell populations in bioreactors

An in situ microscope based on pulsed transmitted light illumination via optical fiber was combined to artificial-intelligence to enable for the first time an online cell classification according to well-known cellular morphological features. A 848 192-image database generated during a lab-scale production process of antibodies was processed using a convolutional neural network approach chosen for its accurate real-time object detection capabilities. In order to induce different cell death routes, hybridomas were grown in normal or suboptimal conditions in a stirred tank reactor, in the presence of substrate limitation, medium addition, pH regulation problem or oxygen depletion. Using such an optical system made it possible to monitor real-time the evolution of different classes of animal cells, among which viable, necrotic and apoptotic cells. A class of viable cells displaying bulges in feast or famine conditions was also revealed. Considered as a breakthrough in the catalogue of process analytical tools, in situ microscopy powered by artificial-intelligence is also of great interest for research.

Malignant Mesothelioma subtyping via sampling driven multiple instance prediction on tissue image and cell morphology data

Malignant Mesothelioma is a difficult to diagnose and highly lethal cancer usually associated with asbestos exposure. It can be broadly classified into three subtypes: Epithelioid, Sarcomatoid, and a hybrid Biphasic subtype in which significant components of both of the previous subtypes are present. Early diagnosis and identification of the subtype informs treatment and can help improve patient outcome. However, the subtyping of malignant mesothelioma, and specifically the recognition of transitional features from routine histology slides has a high level of inter-observer variability.In this work, we propose an end-to-end multiple instance learning (MIL) approach for malignant mesothelioma subtyping. This uses an adaptive instance-based sampling scheme for training deep convolutional neural networks on bags of image patches that allows learning on a wider range of relevant instances compared to max or top-N based MIL approaches. We also investigate augmenting the instance representation to include aggregate cellular morphology features from cell segmentation. The proposed MIL approach enables identification of malignant mesothelial subtypes of specific tissue regions. From this a continuous characterisation of a sample according to predominance of sarcomatoid vs epithelioid regions is possible, thus avoiding the arbitrary and highly subjective categorisation by currently used subtypes. Instance scoring also enables studying tumor heterogeneity and identifying patterns associated with different subtypes. We have evaluated the proposed method on a dataset of 234 tissue micro-array cores with an AUROC of 0.89±0.05 for this task. The dataset and developed methodology is available for the community at: https://github.com/measty/PINS.

Acute ischemic stroke: how to investigate the association between disease etiology and gene expression profiles

Background: Acute ischemic stroke (AIS) represents one of the principal causes of neurological morbidity and mortality worldwide. For a prompt and efficient cerebral blood restoration, intravenous treatment with rt-PA is often combined with mechanical thrombectomy (MT) which provides cerebral thrombi (CT) as study material, allowing the investigation of its cellular composition, morphological and histopathological features. Indeed, the determination of stroke etiology, typically defined by the TOAST classification, is paramount for prognostic factors, outcome, and management of the event. Aim of the study is therefore to highlight and analyze gene expression profiles in thrombotic tissue and peripheral blood (PB) in the comparison between strokes of cardioembolic (CE) and atherosclerotic (LAA) origin. Methods: We performed gene expression profiles of 92 patients. CT were stored in RNA later and RNA was extracted by PAX gene blood miRNA kit. The global gene expression profile was assessed by Affymetrix technology using GeneChip Human Transcriptome Array 2.0 combined with Affymetrix Transcriptome Analysis Console (TAC) Software. Results: Currently, we focused our attention on CT data analysis. The analysis revealed a significant difference (p-value<0.05 and FoldChange=2 as threshold) in gene expression when comparing LAA and CE stroke. In particular, from CT of atherosclerotic origin emerges an overexpression of 1766 genes. Prominent among them are genes such as MMP-9, TGFB, TGFBR and CXCL1, primarily involved in neutrophil-mediated immunity, Blood-Brain Barrier (BBB) disruption processes, and associated with atherosclerotic plaque instability and related to poor neurological outcome, suggesting a deleterious role in human brain injury. As concerns CE patients, 57 genes mainly involved in transcriptional regulatory processes turn out to be significantly overexpressed. Conclusions: Transcriptome profiling is a powerful weapon for revealing expression patterns associated with complex disorders. The variation of gene expression profiles confirmed and extended several known pathophysiological mechanisms and may be one way of delineating different stroke etiology.

High-speed reflectance confocal microscopy of human skin at 1251-1342 nm.

Reflectance confocal microscopy (RCM) is an imaging method that can noninvasively visualize microscopic features of the human skin. The utility of RCM can be further improved by increasing imaging speed. In this paper, we report high-speed RCM imaging of human skin with a frame rate that is over 10 times faster and an area imaging rate that is 6-9 times faster than those of commercially available RCM devices. The higher imaging speed was achieved using a high-speed RCM technique, termed spectrally encoded confocal microscopy (SECM). SECM uses a diffraction grating and a high-speed, wavelength-swept source to conduct confocal imaging at a very high rate. We developed a handheld SECM probe using a scanned-grating approach. The SECM probe was used in conjunction with a wavelength-swept source with a spectral band of 1251-1342 nm. The SECM probe achieved high lateral resolution of 1.3-1.6 µm and an axial resolution of 3.5 µm. SECM images of the human skin (image size = 439 × 439 µm2 ) obtained at 100 frames/s clearly show previously reported RCM features of the human skin in vivo with adequate image quality. The fast imaging speed allowed for the rapid acquisiton of volumetric SECM image data (200 frames covering a depth range of 200 µm) within 2 s. The use of 1251-1342 nm provided sufficient signal level and contrast required to visualize key cellular morphologic features. These preliminary results demonstrate that high-speed SECM imaging of the human skin at 1251-1342 nm is feasible.

MorphoFeatures for unsupervised exploration of cell types, tissues, and organs in volume electron microscopy.

Electron microscopy (EM) provides a uniquely detailed view of cellular morphology, including organelles and fine subcellular ultrastructure. While the acquisition and (semi-)automatic segmentation of multicellular EM volumes are now becoming routine, large-scale analysis remains severely limited by the lack of generally applicable pipelines for automatic extraction of comprehensive morphological descriptors. Here, we present a novel unsupervised method for learning cellular morphology features directly from 3D EM data: a neural network delivers a representation of cells by shape and ultrastructure. Applied to the full volume of an entire three-segmented worm of the annelid Platynereis dumerilii, it yields a visually consistent grouping of cells supported by specific gene expression profiles. Integration of features across spatial neighbours can retrieve tissues and organs, revealing, for example, a detailed organisation of the animal foregut. We envision that the unbiased nature of the proposed morphological descriptors will enable rapid exploration of very different biological questions in large EM volumes, greatly increasing the impact of these invaluable, but costly resources.

641. ALPORT SYNDROME WITH ESOPHAGEAL LEIOMYOMA TREATED WITH CONSERVATIVE DISTAL ROBOTIC MYOTOMY: AVOIDING ESOPHAGECTOMY?

Abstract Alport Syndrome manifests as dysmorphic hematuria associated or not with nephrotic syndrome, renal failure and visual and auditory impairment, in addition to family history. Leiomyoma is the most common benign neoplasm of the esophagus, but it is rare in childhood, and controversies persist as to the best option for its surgical treatment. We report the case of an 8-year-old female patient diagnosed with Alport syndrome and association with esophageal leiomyoma. An 8-year-old female had 3 episodes of pneumonia related to bronchoaspiration. During childhood, he presented pictures of retrosternal pain related to dysphagia, which had worsened in intensity in the last 2 years. She had a hypothesis of achalasia, she underwent an Endoscopic Poem Myotomy. During the procedure, a mass was observed in the distal esophagus and a biopsy showed that it was an esophageal leiomyoma. Given the close association of this tumor with Alport Syndrome, biopsy confirmed the diagnosis. She was then submitted to robotic surgery for possible esophagectomy, however, only partial resection of the Leiomyoma was performed avoiding esophagectomy. Due to young age and the morbidity of esophageactomy, only partial resection of the Leiomyoma was performed, with significant improvement in esophageal emptying for liquids and solids in the postoperative period and hospital discharge after 5 days. Considering leiomyomatosis a benign disease, partial resection was permitted since the histological aspects such as high rates of Ki67% and cellular morphological features were not found. The case in question presented a diagnosis due to the severe manifestations that were provided by the esophageal leiomyoma in a patient with atypical epidemiological characteristics, such as age group and sex. The conservative surgical strategy was chosen due to the patient's age and the surgical result was satisfactory, being suggested in similar cases.

Myeloid neoplasm with ETV6::ACSl6 fusion: landscape of molecular and clinical features

ABSTRACT Objectives Since the publication of the third edition, the WHO classification of tumors of hematopoietic and lymphoid disorders has introduced the disease entity of ‘myeloid/lymphoid neoplasms with eosinophilia and PDGFRB rearrangement’, in which the most common chromosomal abnormality is t(5;12) (q32;p13.2), and this abnormality generates the ETV6::PDGFRB fusion gene. However, there have been patients with hematologic features and chromosomal abnormalities that are extremely similar to those carrying ETV6::PDGFRB fusion. These rare disorders harbor ETV6::ACSL6 fusion, and only sporadic cases have been reported at present. Methods We report a patient with chronic eosinophilic leukemia (CEL) carrying chromosome translocation t(5;12)(q32;p13.2), and we present the clinical features. In addition, we conducted a literature review to collect all reported cases and summarized the genetic and clinical profiling as well as the treatments and outcomes. Result In addition to our patient, a total of 19 cases have been previously reported, including 6 variants of ETV6::ACSL6 and 3 reciprocals. We identified a novel variant of the ETV6::ACSL6 transcript in our patient, and the breakpoint was flanked by exon 2 of ETV6 and exon 2 of ACSL6. The cellular morphology features consisted of myeloproliferative neoplasm (MPN); myelodysplastic/myeloproliferative neoplasm (MDS/MPN), specifically CEL; and acute myelocytic leukemia (AML). The treatments and outcomes varied greatly depending on the type of disease, although tyrosine kinase inhibitors (TKIs) were not effective. Conclusion In contrast to neoplasms with ETV6::PDGFRB fusion, myeloid neoplasms with ETV6::ACSL6 fusion have unique characteristics.

Abstract 1218: HOPE2Net: Integrating histological features and position embeddings in spatially resolved transcriptomics to predict gene expression and pathway activities from histology images in tumors

Abstract Recent developments in spatially resolved transcriptomics (SRT) technologies have enabled the profiling of transcriptome-wide gene expression while retaining spatial location information of each measured spot within a tissue. Meanwhile, the corresponding histopathology images of tissue sections are readily available and can be aligned to the measured spots. Given that the histology images are practically more convenient and affordable to obtain, we designed HOPE2Net, a multi-layer perceptron architecture, that leverages information provided by SRT data to predict gene expression and pathway activities from histology images. Through systematic evaluations of different approaches for extracting deep image features and cellular morphology features, HOPE2Net performs feature selections from a pre-trained Vision Transformer, which is the state-of-art deep learning model for image recognition. After extracting histological image features, HOPE2Net further integrates with position embeddings, to optimize the gene expression and pathway activity prediction tasks. Through analyzing breast cancer and prostate cancer SRT datasets obtained from numerous tissue sections in multiple patients, we demonstrate that HOPE2Net can accurately predict the gene expression patterns for highly variable genes and the activities for significantly enriched domain-specific pathways. We further show that the predicted gene expression and pathway activities can help detect cancer subtypes and aid in treatment decision-makings. Given the growing interest in applying SRT in cancer genomics, we believe HOPE2Net holds the potential in identifying biomarkers from direct screenings of tissue histology images, which may be implemented in clinical studies for cancer diagnoses and decision-making processes. Citation Format: Kenong Su, Minxing Pang, Mingyao Li. HOPE2Net: Integrating histological features and position embeddings in spatially resolved transcriptomics to predict gene expression and pathway activities from histology images in tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1218.

Synchrotron Based X-ray Microtomography Reveals Cellular Morphological Features of Developing Wheat Grain

Wheat is one of the most important crops in the world, mainly used for human consumption and animal feed. To overcome the increasing demand in wheat production, it is necessary to better understand the mechanisms involved in the growth of the wheat grain. X-ray computed tomography is an efficient method for the non-destructive investigation of the 3D architecture of biological specimens, which does not require staining, sectioning, or inclusion. In particular, phase-contrast tomography results in images with better contrast and an increased resolution compared to that obtained with laboratory tomography devices. The aim of this study was to investigate the potential of phase-contrast tomography for the study of the anatomy of the wheat grain at early stages of development. We provided 3D images of entire grains at various development stages. The image analysis allowed identifying a large number of tissues, and to visualize individual cells. Using a high-resolution setup, finer details were obtained, making it possible to identify additional tissues. Three-dimensional rendering of the grain also revealed the pattern resulting from the epidermis cells. X-ray phase-contrast tomography appears as a promising imaging method for the study of the 3D anatomy of plant organs and tissues.

Immune alveolitis in interstitial lung disease: an attractive cytological profile in immunocompromised patients

BackgroundBronchoalveolar lavage (BAL) is a major diagnostic tool in interstitial lung disease (ILD). Its use remains largely quantitative, usually focused on cell differential ratio. However, cellular morphological features provide additional valuable information. The significance of the “immune alveolitis” cytological profile, characterized by lymphocytic alveolitis with activated lymphocytes and macrophages in epithelioid transformation or foamy macrophages desquamating in cohesive clusters with lymphocytes, remains unknown in ILD. Our objective was to describe patients’ characteristics and diagnoses associated with an immune alveolitis profile in undiagnosed ILD.MethodsWe performed a monocentric retrospective observational study. Eligible patients were adults undergoing diagnostic exploration for ILD and whose BAL fluid displayed an immune alveolitis profile. For each patient, we collected clinical, radiological and biological findings as well as the final etiology of ILD.ResultsBetween January 2012 and December 2018, 249 patients were included. Mean age was 57 ± 16 years, 140 patients (56%) were men, and 65% of patients were immunocompromised. The main etiological diagnosis was Pneumocystis pneumonia (PCP) (24%), followed by drug-induced lung disease (DILD) (20%), viral pneumonia (14%) and hypersensitivity pneumonitis (HP) (10%). All PCP were diagnosed in immunocompromised patients while HP was found in only 8% of this subgroup. DILD and viral pneumonia were also commonly diagnosed in immunocompromised patients (94% and 80%, respectively).ConclusionOur study highlights the additional value of BAL qualitative description in ILD. We suggest incorporating the immune alveolitis profile for the diagnosis and management of ILD, especially in immunocompromised patients, since it guides towards specific diagnoses.

Dance and Science: an analysis of the creative process behind "Transitions", a show by Contemporary Dance Company of UFRJ

This study proposes an esthetic reflection on the influence of the biological sciences on dance as a variety of contemporary art. The relationship between science and art in this study is grounded on François Dagognet’s hyperphenomenology, particularly his representation of the major role played by the image-symbol as essential base of present-day scientific activity [1]. Contemporary dance creators and companies such as Wayne Mac Gregor, Phylobolus Dance Company and Liz Lerman Dance Exchange are analyzed, in order to highlight how some biosciences themes are explored as creative potentials in their dance performances [2,3,4]. We aim at relating biological shapes and patterns existing in the cellular and molecular universe with the fundamentals of dance described by Helenita Sá Earp. Earp’s conception posits dance as wide-scoped knowledge, including a “science of dance” where intuition works as basic foundation and its epistemology is made of an open type of knowledge named “dance parameters”, namely motion, space, shape, dynamics and time. These parameters allow establishing access points for multiple connections within the realm of dance. This approach tends to generate a kind of access to body actions stimulating interdisciplinarity between several areas of knowledge [4]. As study-case, we focus methodologically on the processes of esthetic creation involved in the production of a multimedia show entitled “Transitions” by appealing to biochemical notions, especially some features of cytology and cellular morphology, cell proliferation and processes of cellular transportation [5].

Mechanistic Insight into Apoptotic Induction in Human Rhabdomyosarcoma and Breast Adenocarcinoma Cells by Chnoospora minima: A Sri Lankan Brown Seaweed.

The current study determined the cytotoxic and apoptotic potential of the polyphenol-rich methanol extract of Chnoospora minima (C. minima) and its fractions against human breast adenocarcinoma (MCF-7) and rhabdomyosarcoma (RMS) cells. MTT and neutral red assays were used to determine cytotoxicity. The clonogenic assay evaluated the antineoplastic activity, while the apoptotic activity was determined by cellular morphological changes, caspase 3/7 activity, and DNA fragmentation. Morphological alterations in apoptosis were observed by an inverted phase-contrast microscope and Hoechst 33342 staining methods. The total phenolic, flavonoids, alkaloids, and antioxidant activity in the hexane and chloroform fractions were determined, based on their cytotoxic activity. The hexane fraction of C. minima effectively reduced the cell growth that is concentration-dependent in human RMS and MCF-7 cell lines. It also exhibited low cytotoxicity on Vero cells. The characteristic cellular and nuclear apoptotic morphological features were observed. A noticeable caspase 3/7 activation and the fragmented DNA were detected only in the hexane fraction treated RMS cells, whereas MCF-7 cells showed low caspase 3/7 activation due to a lack of caspase 3 and no evidence of having a typical ladder pattern of apoptosis. Further analysis revealed that the hexane fraction-treated RMS cells upregulated the p53 gene twofold (2.72) compared to the p21 (0.77) gene, whereas in the MCF-7 cells, a 2.21-fold upregulation of p53 was observed compared to the p21 (0.64) gene. The hexane fraction exhibited moderate total phenolics, flavonoids, alkaloids content, and antioxidant activity. According to the different antioxidant mechanisms, hexane and chloroform fractions showed the highest antioxidant activities by FRAP and ORAC assays, respectively. GC-MS analysis of hexane fraction revealed the presence of methyl tetradecanoate (38.314%) as the most abundant compound. The study’s findings highlighted that the non-polar compounds present in the hexane fraction of C. minima suppressed cell proliferation and induced apoptosis-mediated cell death in RMS and MCF-7 cells, mainly via the activation of the p53 gene. Hence, the isolation of compounds is warranted. However, more studies are required to understand the mechanistic insights of these observations.

PLURIPOTENT STEM CELL EXOSOMES: EFFECTIVE STRATEGIES FOR CELLULAR SENESCENCE PREVENTION AND REVERSION

<h3>Introduction</h3> Aging is a natural process, which is closely linked to the loss of homeostasis. When the dynamic balance of a functional organism is disturbed, unfavorable impacts over health are soon noticed. It has been shown that cellular senescence can be induced in a paracrine fashion. In the present study, we assessed whether cellular senescence could also be prevented or reverted in a paracrine fashion by treating senescent cells with iPSC-derived extracellular vesicles (iPSC-EVs). <h3>Methodology</h3> Human fibroblasts were induced to senescence using doxorubicin. iPSC-EVs were separated by an ultrafiltration process. The iPSC-EVs obtained were characterized by TRPS method and transmission electron microscopy. Total iPSC-EVs protein was isolated for quantification. Ten ug of iPSC-EVs was used to treat senescent fibroblasts for 4 days, and 3 experimental groups were investigated: non-senescent fibroblasts (1), doxorubicin-treated senescent fibroblasts (2), and doxorubicin-induced senescent fibroblasts treated with iPSC-EVs (3). Cells were analyzed according to the senescence-associated beta galactosidase staining and proliferation capacity, determined according to the colony formation assay and the calculation of population doubling time (PDT). <h3>Results</h3> The isolated iPSC-EVs presented a diameter mode of 94 nm, which was confirmed by TEM analysis. After iPSC-EVs treatment, cells from group 3 had lower beta galactosidase staining and higher proliferation capacity than group 2 cells. While group 1 had negligible amount of senescent cells, group 2 had an average of 60% SA beta galactosidase-positive cells, and group 3 had an average of 40% senescent cells. PDT was reduced from >110hs in group 2 to 80hs in group 1. Total RNA was collected from experimental groups iPSC-EVs for RNASeq. The analysis of iPSC-EVs uptake, cellular morphological features, and gene expression are in progress. <h3>Conclusions</h3> iPSC-EVs were isolated and possibly contain exosomes, requiring further characterization. The treatment of senescent cells with iPSC-EVs supported increased cell proliferation and attenuation of SA beta galactosidase staining. The mRNA composition of iPSC-EVs, as well as of iPSC-EVs-treated cells are under investigation, as well as the morphological features of treated cells. So far, it is possible to suggest that iPSC-EVs might constitute an effective strategy for delaying / reversing cellular senescence.

Deep Learning for Distinguishing Morphological Features of Acute Promyelocytic Leukemia

Acute Promyelocytic Leukemia (APL) is a subtype of Acute Myeloid Leukemia (AML), classified by a translocation between chromosomes 15 and 17 [t(15;17)], that is notably distinguished clinically by a rapidly progressive and fatal course. Due to the acute nature of its presentation, prompt and accurate diagnosis is required to initiate appropriate therapy that can be curative. However, the gold standard genetic tests can take days to confirm a diagnosis and thus therapy is often initiated on high clinical suspicion based on both clinical presentation as well as direct visualization of the peripheral smear. While there are described cellular morphological features that distinguish APL, there is still considerable difficulty in diagnosing APL from direct visualization of a peripheral smear by a hematopathologist. We hypothesized that deep learning pattern recognition would have greater discriminatory power and consistency compared to humans to distinguish t(15;17) translocation positive APL from t(15;17) translocation negative AML. To best tackle the problem of diagnosing APL rapidly from a peripheral smear, study patients with APL and AML were identified via retrospective chart review from a list of confirmed FISH t(15;17)-positive (n = 34) and -negative (n = 72) patients presenting at The Johns Hopkins Hospital (JHH). Additional inclusion criteria included new disease diagnosis, no prior treatment, and availability of peripheral blood smear image uploaded to CellaVision. Patients were separated into a discovery cohort presenting prior to 1/2019 (APL, n = 22; AML, n=60) and a validation cohort presenting on or after 1/2019 (APL, n = 12; AML, n = 12). A multiple-instance deep learning model employing convolutional layers at the per-cell level (Figure 1A) was trained on the discovery cohort and then tested on the independent prospective validation cohort to assess generalizability of the model. When compared to 10 academic clinicians (denoted with red +) who consisted of leukemia-treating hematologists, oncologists, and hematopathologists, the deep learning model was equivalent or outperformed 9/10 readers (Figure 1B) with an AUC of 0.861. We further looked at the performance of using proportion of promyelocytes (per CellaVision classification) as a biomarker of APL which had an AUC of 0.611. Finally, we applied integrated gradients, a method by which to extract per-pixel importance to the classification probability to identify and understand the morphological features the model was learning and using to distinguish APL (Figure 1C). We noted that the appearance of the chromatin in the non-APL leukemias was more dispersed and focused at the edge of the cell whereas in APL, the chromatin was more condensed and focused at the center of the cell. These morphological features, taught to us by the model, have not been previously reported in the literature as being useful for distinguishing APL from non-APL. Our work presents a deep learning model capable of rapid and accurate diagnosis of APL from universally available peripheral smears. In addition, explainable artificial intelligence is provided for biological insights to facilitate clinical management and reveal morphological concepts previously unappreciated in APL. The deep learning framework we have delineated is applicable to any diagnostic pipeline that can leverage a peripheral blood smear, potentially allowing for efficient diagnosis and early treatment of disease. Figure 1. Disclosures Streiff: Bayer: Consultancy, Speakers Bureau; Dispersol: Consultancy; BristolMyersSquibb: Consultancy; Janssen: Consultancy, Research Funding; Pfizer: Consultancy, Speakers Bureau; Portola: Consultancy; Boehringer-Ingelheim: Research Funding; NHLBI: Research Funding; PCORI: Research Funding; NovoNordisk: Research Funding; Sanofi: Research Funding. Moliterno:Pharmessentia: Consultancy; MPNRF: Research Funding. DeZern:MEI: Consultancy; Abbvie: Consultancy; Astex: Research Funding; Celgene: Consultancy, Honoraria. Levis:Astellas: Honoraria, Research Funding; Menarini: Honoraria; Amgen: Honoraria; FujiFilm: Honoraria, Research Funding; Daiichi-Sankyo: Honoraria.

Cellular morphological features are predictive markers of cancer cell state

Even genetically identical cells have heterogeneous properties because of stochasticity in gene or protein expression. Single cell techniques that assay heterogeneous properties would be valuable for basic science and diseases like cancer, where accurate estimates of tumor properties is critical for accurate diagnosis and grading. Cell morphology is an emergent outcome of many cellular processes, potentially carrying information about cell properties at the single cell level. Here we study whether morphological parameters are sufficient for classification of single cells, using a set of 15 cell lines, representing three processes: (i) the transformation of normal cells using specific genetic mutations; (ii) metastasis in breast cancer and (iii) metastasis in osteosarcomas. Cellular morphology is defined as quantitative measures of the shape of the cell and the structure of the actin. We use a toolbox that calculates quantitative morphological parameters of cell images and apply it to hundreds of images of cells belonging to different cell lines. Using a combination of dimensional reduction and machine learning, we test whether these different processes have specific morphological signatures and whether single cells can be classified based on morphology alone. Using morphological parameters we could accurately classify cells as belonging to the correct class with high accuracy. Morphological signatures could distinguish between cells that were different only because of a different mutation on a parental line. Furthermore, both oncogenesis and metastasis appear to be characterized by stereotypical morphology changes. Thus, cellular morphology is a signature of cell phenotype, or state, at the single cell level.

Reproducible production and image-based quality evaluation of retinal pigment epithelium sheets from human induced pluripotent stem cells

Transplantation of retinal pigment epithelial (RPE) sheets derived from human induced pluripotent cells (hiPSC) is a promising cell therapy for RPE degeneration, such as in age-related macular degeneration. Current RPE replacement therapies, however, face major challenges. They require a tedious manual process of selecting differentiated RPE from hiPSC-derived cells, and despite wide variation in quality of RPE sheets, there exists no efficient process for distinguishing functional RPE sheets from those unsuitable for transplantation. To overcome these issues, we developed methods for the generation of RPE sheets from hiPSC, and image-based evaluation. We found that stepwise treatment with six signaling pathway inhibitors along with nicotinamide increased RPE differentiation efficiency (RPE6iN), enabling the RPE sheet generation at high purity without manual selection. Machine learning models were developed based on cellular morphological features of F-actin-labeled RPE images for predicting transepithelial electrical resistance values, an indicator of RPE sheet function. Our model was effective at identifying low-quality RPE sheets for elimination, even when using label-free images. The RPE6iN-based RPE sheet generation combined with the non-destructive image-based prediction offers a comprehensive new solution for the large-scale production of pure RPE sheets with lot-to-lot variations and should facilitate the further development of RPE replacement therapies.