Chronic myeloid leukemia blast crisis presented with AML of t(9;22) and t(3;14) mimicking acute lymphocytic leukemia

Artificial intelligence performance in detecting lymphoma from medical imaging: a systematic review and meta-analysis

BACKGROUND

Accurate diagnosis and early treatment are essential in the fight against lymphatic cancer. The application of artificial intelligence (AI) in the field of medical imaging shows great potential, but the diagnostic accuracy of lymphoma is unclear. This study was done to systematically review and meta-analyse researches concerning the diagnostic performance of AI in detecting lymphoma using medical imaging for the first time.

METHODS

Searches were conducted in Medline, Embase, IEEE and Cochrane up to December 2023. Data extraction and assessment of the included study quality were independently conducted by two investigators. Studies that reported the diagnostic performance of an AI model/s for the early detection of lymphoma using medical imaging were included in the systemic review. We extracted the binary diagnostic accuracy data to obtain the outcomes of interest: sensitivity (SE), specificity (SP), and Area Under the Curve (AUC). The study was registered with the PROSPERO, CRD42022383386.

RESULTS

Thirty studies were included in the systematic review, sixteen of which were meta-analyzed with a pooled sensitivity of 87% (95%CI 83-91%), specificity of 94% (92-96%), and AUC of 97% (95-98%). Satisfactory diagnostic performance was observed in subgroup analyses based on algorithms types (machine learning versus deep learning, and whether transfer learning was applied), sample size (≤ 200 or >  200), clinicians versus AI models and geographical distribution of institutions (Asia versus non-Asia).

CONCLUSIONS

Even if possible overestimation and further studies with a better standards for application of AI algorithms in lymphoma detection are needed, we suggest the AI may be useful in lymphoma diagnosis.

Molecular Evaluation of the Impact of Polymorphic Variants in Apoptotic (Bcl-2/Bax) and Proinflammatory Cytokine (TNF-α/IL-8) Genes on the Susceptibility and Progression of Myeloproliferative Neoplasms: A Case-Control Biomarker Study

The regulation of apoptosis (the programmed cell death) is dependent on the crucial involvement of BCL2 and BAX. The Bax-248G>A and Bcl-2-938 C>A polymorphic variations in the promoter sequences of the Bax and Bcl-2 gene have been recently associated with low Bax expression, progression to advanced stages, treatment resistance, and shortened overall survival rate in some hematological malignancies, including chronic myeloid leukemia (CML) and other myeloproliferative neoplasms. Chronic inflammation has been linked to various stages of carcinogenesis wherein pro-inflammatory cytokines play diverse roles in influencing cancer microenvironment leading to cell invasion and cancer progression. Cytokines such as TNF-α and IL-8 have been implicated in cancer growth in both solid and hematological malignancies with studies showing their elevated levels in patients. Genomic approaches have in recent years provided significant knowledge with the regard to the association of certain SNPs (single nucleotide polymerphisms) either in a gene or its promoter that can influence its expression, with the risk and susceptibility to human diseases including cancer. This study has investigated the consequences of promoter SNPs in apoptosis genes Bax-248G>A (rs4645878)/Bcl-2-938C>A (rs2279115) and pro-inflammatory cytokines TNF-α rs1800629 G>A/IL-8 rs4073 T>A on the risk and susceptibility towards hematological cancers. The study design has 235 individuals both male and female enrolled as subjects that had 113 cases of MPDs (myeloproliferative disorders) and 122 healthy individuals as controls. The genotyping studies were conducted through ARMS PCR (amplification-refractory mutation system PCR). The Bcl-2-938 C>A polymorphism showed up in 22% of patients in the study, while it was observed in only 10% of normal controls. This difference in genotype and allele frequency between the two groups was significant (p = 0.025). Similarly, the Bax-248G>A polymorphism was detected in 6.48% of the patients and 4.54% of the normal controls, with a significant difference in genotype and allele frequency between the groups (p = 0.048). The results suggest that the Bcl-2-938 C>A variant is linked to an elevated risk of MPDs in the codominant, dominant, and recessive inheritance models. Moreover, the study indicated allele A as risk allele which can significantly increase the risk of MPDs unlike the C allele. In case of Bax gene covariants, these were associated with an increased risk of MPDs in the codominant inheritance model and dominant inheritance model. It was found that the allele A significantly enhanced the risk of MPDs unlike the G allele. The frequencies of IL-8 rs4073 T>A in patients was found to be TT (16.39%), AT (36.88%) and AA (46.72%), compared to controls who were more likely to have frequencies of TT (39.34%), AT (37.70%) and AA (22.95%) as such, respectively. There was a notable overrepresentation of the AA genotype and GG homozygotes among patients compared to controls in TNF-α polymorphic variants, with 6.55% of patients having the AA genotype and 84% of patients being GG homozygotes, compared to 1.63% and 69%, respectively in controls. The data from the current study provide partial but important evidence that polymorphisms in apoptotic genes Bcl-2-938C>A and Bax-248G>A and pro-inflammatory cytokines IL-8 rs4073 T>A and TNF-α G>A may help predict the clinical outcomes of patients and determine the significance of such polymorphic variations in the risk of myeloproliferative diseases and their role as prognostic markers in disease management using a case-control study approach.

Comparative Gene Expression Analysis Reveals Similarities and Differences of Chronic Myeloid Leukemia Phases

Chronic myeloid leukemia (CML) is a slowly progressing blood cancer that primarily affects elderly people. Without successful treatment, CML progressively develops from the chronic phase through the accelerated phase to the blast crisis, and ultimately to death. Nowadays, the availability of targeted tyrosine kinase inhibitor (TKI) therapies has led to long-term disease control for the vast majority of patients. Nevertheless, there are still patients that do not respond well enough to TKI therapies and available targeted therapies are also less efficient for patients in accelerated phase or blast crises. Thus, a more detailed characterization of molecular alterations that distinguish the different CML phases is still very important. We performed an in-depth bioinformatics analysis of publicly available gene expression profiles of the three CML phases. Pairwise comparisons revealed many differentially expressed genes that formed a characteristic gene expression signature, which clearly distinguished the three CML phases. Signaling pathway expression patterns were very similar between the three phases but differed strongly in the number of affected genes, which increased with the phase. Still, significant alterations of MAPK, VEGF, PI3K-Akt, adherens junction and cytokine receptor interaction signaling distinguished specific phases. Our study also suggests that one can consider the phase-wise CML development as a three rather than a two-step process. This is in accordance with the phase-specific expression behavior of 24 potential major regulators that we predicted by a network-based approach. Several of these genes are known to be involved in the accumulation of additional mutations, alterations of immune responses, deregulation of signaling pathways or may have an impact on treatment response and survival. Importantly, some of these genes have already been reported in relation to CML (e.g., AURKB, AZU1, HLA-B, HLA-DMB, PF4) and others have been found to play important roles in different leukemias (e.g., CDCA3, RPL18A, PRG3, TLX3). In addition, increased expression of BCL2 in the accelerated and blast phase indicates that venetoclax could be a potential treatment option. Moreover, a characteristic signaling pathway signature with increased expression of cytokine and ECM receptor interaction pathway genes distinguished imatinib-resistant patients from each individual CML phase. Overall, our comparative analysis contributes to an in-depth molecular characterization of similarities and differences of the CML phases and provides hints for the identification of patients that may not profit from an imatinib therapy, which could support the development of additional treatment strategies.

Chronic myeloid leukemia blast crisis presented with AML of t(9;22) and t(3;14) mimicking acute lymphocytic leukemia

BACKGROUND

Clinically, 90%-95% of cases of CML have the characteristic t(9;22) (q34.1;q11.2) translocation that leads to the Philadelphia (Ph) chromosome. Rarely, patients with CML can present directly in a blast crisis (BC). While most blast crises are of myeloid origin, myeloid BC with ALL-like morphologic features and Ph-positive acute myeloid leukemia (AML) is rare, especially at the time of CML diagnosis.

CASE PRESENTATION

A 20-year-old man presented with Ph chromosome-positive AML mimicking acute lymphocytic leukemia (ALL). Bone marrow (BM) aspiration revealed AML with ALL-like morphologic features. The results of the immunophenotypic analysis suggested AML. Cytogenetic analysis of the BM cells revealed a 46,XY,t(3;14)(q21;q32),t(9;22)(q34;q11.2)[20] karyotype. Thus, we called the condition AML mimicking ALL. The patient was diagnosed with myeloid BC based on the combination of clinical, cytologic, and cytogenetic studies.

CONCLUSION

To date, no case reports of a patient diagnosed with CML BC presented with Ph chromosome-positive AML mimicking ALL have been reported. We present the case given its rarity, easy misdiagnosis, and poor prognosis. It is important to combine clinical, cytologic, and cytogenetic analyses in distinguishing CML BC from de novo AML with the t(9;22)，and further cases should be accumulated to explore how to improve the prognosis of the patients.