Detection of Metastatic Tumor Cells in the Bone Marrow Aspirate Smears by Artificial Intelligence (AI)-Based Morphogo System

IntroductionMetastatic carcinomas of bone marrow (MCBM) are characterized as tumors of non-hematopoietic origin spreading to the bone marrow through blood or lymphatic circulation. The diagnosis is critical for tumor staging, treatment selection and prognostic risk stratification. However, the identification of metastatic carcinoma cells on bone marrow aspiration smears is technically challenging by conventional microscopic screening.ObjectiveThe aim of this study is to develop an automatic recognition system using deep learning algorithms applied to bone marrow cells image analysis. The system takes advantage of an artificial intelligence (AI)-based method in recognizing metastatic atypical cancer clusters and promoting rapid diagnosis.MethodsWe retrospectively reviewed metastatic non-hematopoietic malignancies in bone marrow aspirate smears collected from 60 cases of patients admitted to Zhongshan Hospital. High resolution digital bone marrow aspirate smear images were generated and automatically analyzed by Morphogo AI based system. Morphogo system was trained and validated using 20748 cell cluster images from randomly selected 50 MCBM patients. 5469 pre-classified cell cluster images from the remaining 10 MCBM patients were used to test the recognition performance between Morphogo and experienced pathologists.ResultsMorphogo exhibited a sensitivity of 56.6%, a specificity of 91.3%, and an accuracy of 82.2% in the recognition of metastatic cancer cells. Morphogo’s classification result was in general agreement with the conventional standard in the diagnosis of metastatic cancer clusters, with a Kappa value of 0.513. The test results between Morphogo and pathologists H1, H2 and H3 agreement demonstrated a reliability coefficient of 0.827. The area under the curve (AUC) for Morphogo to diagnose the cancer cell clusters was 0.865.ConclusionIn patients with clinical history of cancer, the Morphogo system was validated as a useful screening tool in the identification of metastatic cancer cells in the bone marrow aspirate smears. It has potential clinical application in the diagnostic assessment of metastatic cancers for staging and in screening MCBM during morphology examination when the symptoms of the primary site are indolent.

Download Full-text

Naturally occurring resistance of bone marrow mononuclear and metastatic cancer cells to anticancer agents

Clinical & Experimental Metastasis ◽

10.1007/s10585-006-9034-x ◽

2006 ◽

Vol 23 (5-6) ◽

pp. 249-258

Author(s):

Christina Richard ◽

Jonathan Yau ◽

John P. H. Th’ng ◽

Wilhelmina C. M. Duivenvoorden

Keyword(s):

Bone Marrow ◽

Cancer Cells ◽

Anticancer Agents ◽

Metastatic Cancer ◽

Naturally Occurring ◽

Metastatic Cancer Cells

Download Full-text

Metastatic Cancer Cells in Bone Marrow

A M A Archives of Surgery ◽

10.1001/archsurg.1957.01280160100013 ◽

1957 ◽

Vol 75 (4) ◽

pp. 590

Author(s):

GEORGE J. ANDAY

Keyword(s):

Bone Marrow ◽

Cancer Cells ◽

Metastatic Cancer ◽

Metastatic Cancer Cells

Download Full-text

Normal cells repel WWOX-negative or -dysfunctional cancer cells via WWOX cell surface epitope 286-299

Communications Biology ◽

10.1038/s42003-021-02271-2 ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Yu-An Chen ◽

Yong-Da Sie ◽

Tsung-Yun Liu ◽

Hsiang-Ling Kuo ◽

Pei-Yi Chou ◽

...

Keyword(s):

Cell Surface ◽

Cancer Cells ◽

Room Temperature ◽

Metastatic Cancer ◽

Normal Cells ◽

Tgfβ Receptor ◽

Membrane Type ◽

Cell Invasiveness ◽

And Control ◽

Metastatic Cancer Cells

AbstractMetastatic cancer cells are frequently deficient in WWOX protein or express dysfunctional WWOX (designated WWOXd). Here, we determined that functional WWOX-expressing (WWOXf) cells migrate collectively and expel the individually migrating WWOXd cells. For return, WWOXd cells induces apoptosis of WWOXf cells from a remote distance. Survival of WWOXd from the cell-to-cell encounter is due to activation of the survival IκBα/ERK/WWOX signaling. Mechanistically, cell surface epitope WWOX286-299 (repl) in WWOXf repels the invading WWOXd to undergo retrograde migration. However, when epitope WWOX7-21 (gre) is exposed, WWOXf greets WWOXd to migrate forward for merge. WWOX binds membrane type II TGFβ receptor (TβRII), and TβRII IgG-pretreated WWOXf greet WWOXd to migrate forward and merge with each other. In contrast, TβRII IgG-pretreated WWOXd loses recognition by WWOXf, and WWOXf mediates apoptosis of WWOXd. The observatons suggest that normal cells can be activated to attack metastatic cancer cells. WWOXd cells are less efficient in generating Ca2+ influx and undergo non-apoptotic explosion in response to UV irradiation in room temperature. WWOXf cells exhibit bubbling cell death and Ca2+ influx effectively caused by UV or apoptotic stress. Together, membrane WWOX/TβRII complex is needed for cell-to-cell recognition, maintaining the efficacy of Ca2+ influx, and control of cell invasiveness.

Download Full-text

Amoebic Foraging Model of Metastatic Cancer Cells

Symmetry ◽

10.3390/sym13071140 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1140

Author(s):

Daiki Andoh ◽

Yukio-Pegio Gunji

Keyword(s):

Bayesian Inference ◽

Cancer Cells ◽

Metastatic Cancer ◽

Gait Patterns ◽

Lévy Walk ◽

Levy Walk ◽

Unicellular Organisms ◽

Living Organisms ◽

Walk Algorithm ◽

Metastatic Cancer Cells

The Lévy walk is a pattern that is often seen in the movement of living organisms; it has both ballistic and random features and is a behavior that has been recognized in various animals and unicellular organisms, such as amoebae, in recent years. We proposed an amoeba locomotion model that implements Bayesian and inverse Bayesian inference as a Lévy walk algorithm that balances exploration and exploitation, and through a comparison with general random walks, we confirmed its effectiveness. While Bayesian inference is expressed only by P(h) = P(h|d), we introduce inverse Bayesian inference expressed as P(d|h) = P(d) in a symmetry fashion. That symmetry contributes to balancing contracting and expanding the probability space. Additionally, the conditions of various environments were set, and experimental results were obtained that corresponded to changes in gait patterns with respect to changes in the conditions of actual metastatic cancer cells.

Download Full-text

Light- and Melanin Nanoparticle-Induced Cytotoxicity in Metastatic Cancer Cells

Pharmaceutics ◽

10.3390/pharmaceutics13070965 ◽

2021 ◽

Vol 13 (7) ◽

pp. 965

Author(s):

Victoria R. Gabriele ◽

Robabeh M. Mazhabi ◽

Natalie Alexander ◽

Purna Mukherjee ◽

Thomas N. Seyfried ◽

...

Keyword(s):

Cancer Cells ◽

Metastatic Cancer ◽

Energy Levels ◽

Nanoparticle Concentration ◽

Visible Radiation ◽

Laser Illumination ◽

Wide Range ◽

Low Glucose ◽

Melanin Nanoparticles ◽

Metastatic Cancer Cells

Melanin nanoparticles are known to be biologically benign to human cells for a wide range of concentrations in a high glucose culture nutrition. Here, we show cytotoxic behavior at high nanoparticle and low glucose concentrations, as well as at low nanoparticle concentration under exposure to (nonionizing) visible radiation. To study these effects in detail, we developed highly monodispersed melanin nanoparticles (both uncoated and glucose-coated). In order to study the effect of significant cellular uptake of these nanoparticles, we employed three cancer cell lines: VM-M3, A375 (derived from melanoma), and HeLa, all known to exhibit strong macrophagic character, i.e., strong nanoparticle uptake through phagocytic ingestion. Our main observations are: (i) metastatic VM-M3 cancer cells massively ingest melanin nanoparticles (mNPs); (ii) the observed ingestion is enhanced by coating mNPs with glucose; (iii) after a certain level of mNP ingestion, the metastatic cancer cells studied here are observed to die—glucose coating appears to slow that process; (iv) cells that accumulate mNPs are much more susceptible to killing by laser illumination than cells that do not accumulate mNPs; and (v) non-metastatic VM-NM1 cancer cells also studied in this work do not ingest the mNPs, and remain unaffected after receiving identical optical energy levels and doses. Results of this study could lead to the development of a therapy for control of metastatic stages of cancer.

Download Full-text

The In Vivo Selection Method in Breast Cancer Metastasis

International Journal of Molecular Sciences ◽

10.3390/ijms22041886 ◽

2021 ◽

Vol 22 (4) ◽

pp. 1886

Author(s):

Jun Nakayama ◽

Yuxuan Han ◽

Yuka Kuroiwa ◽

Kazushi Azuma ◽

Yusuke Yamamoto ◽

...

Keyword(s):

Cancer Cells ◽

Cell Lines ◽

Cancer Metastasis ◽

Metastatic Cancer ◽

Expression Patterns ◽

Selection Method ◽

Gene Signatures ◽

In Vivo Selection ◽

Metastatic Cancer Cells

Metastasis is a complex event in cancer progression and causes most deaths from cancer. Repeated transplantation of metastatic cancer cells derived from transplanted murine organs can be used to select the population of highly metastatic cancer cells; this method is called as in vivo selection. The in vivo selection method and highly metastatic cancer cell lines have contributed to reveal the molecular mechanisms of cancer metastasis. Here, we present an overview of the methodology for the in vivo selection method. Recent comparative analysis of the transplantation methods for metastasis have revealed the divergence of metastasis gene signatures. Even cancer cells that metastasize to the same organ show various metastatic cascades and gene expression patterns by changing the transplantation method for the in vivo selection. These findings suggest that the selection of metastasis models for the study of metastasis gene signatures has the potential to influence research results. The study of novel gene signatures that are identified from novel highly metastatic cell lines and patient-derived xenografts (PDXs) will be helpful for understanding the novel mechanisms of metastasis.

Download Full-text