Classification of Atypical White Blood Cells in Acute Myeloid Leukemia Using a Two-Stage Hybrid Model Based on Deep Convolutional Autoencoder and Deep Convolutional Neural Network.

Recent advancements in artificial intelligence (AI) have led to numerous medical discoveries. The field of computer vision (CV) for medical diagnosis has received particular attention. Using images of peripheral blood (PB) smears, CV has been utilized in hematology to detect acute leukemia (AL). Significant research has been undertaken in the area of AL diagnosis automation in order to deliver an accurate diagnosis. This study addresses the morphological classification of atypical white blood cells (WBCs), including immature WBCs and atypical lymphocytes, in acute myeloid leukemia (AML), as observed in peripheral blood (PB) smear images. The purpose of this work is to build a classification model for atypical AML WBCs based on their distinctive features. Using a hybrid model based on geometric transformation (GT) and a deep convolutional autoencoder (DCAE), this work provides a novel technique in the field of AI for resolving the issue of imbalanced distribution of WBCs in blood samples, nicknamed the "GT-DCAE WBC augmentation model". In addition, to extract context-free atypical WBC features, this study develops a stable learning paradigm by incorporating WBC segmentation into deep learning. In order to classify atypical WBCs into eight distinct subgroups, a hybrid multiclassification model termed the "two-stage DCAE-CNN atypical WBC classification model" (DCAE-CNN) was developed. The model achieved an average accuracy of 97%, a sensitivity of 97%, and a precision of 98%. Overall and by class, the model's discriminating abilities were exceptional, with an AUC of 99.7% and a class-wise range of 80% to 100%.

Preliminary Stages for COVID-19 Detection Using Image Processing.

COVID-19 was first discovered in December 2019 in Wuhan. There have been reports of thousands of illnesses and hundreds of deaths in almost every region of the world. Medical images, when combined with cutting-edge technology such as artificial intelligence, have the potential to improve the efficiency of the public health system and deliver faster and more reliable findings in the detection of COVID-19. The process of developing the COVID-19 diagnostic system begins with image accusation and proceeds via preprocessing, feature extraction, and classification. According to literature review, several attempts to develop taxonomies for COVID-19 detection using image processing methods have been introduced. However, most of these adhere to a standard category that exclusively considers classification methods. Therefore, in this study a new taxonomy for the early stages of COVID-19 detection is proposed. It attempts to offer a full grasp of image processing in COVID-19 while considering all phases required prior to classification. The survey concludes with a discussion of outstanding concerns and future directions.

High AUF1 level in stromal fibroblasts promotes carcinogenesis and chemoresistance and predicts unfavorable prognosis among locally advanced breast cancer patients.

BACKGROUND: Locally advanced breast cancer (LABC), the most aggressive form of the disease, is a serious threat for women's health worldwide. The AU-rich RNA-binding factor 1 (AUF1) promotes the formation of chemo-resistant breast cancer stem cells. Thereby, we investigated the power of AUF1 expression, in both cancer cells and their stromal fibroblasts, as predictive biomarker for LABC patients' clinical outcome following neoadjuvant treatment. METHODS: We have used immunohistochemistry to assess the level of AUF1 on formalin-fixed paraffin-embedded tissues. Immunoblotting was utilized to show the effect of AUF1 ectopic expression in breast stromal fibroblasts on the expression of various genes both in vitro and in orthotopic tumor xenografts. Cytotoxicity was evaluated using the WST1 assay, while a label-free real-time setting using the xCELLigence RTCA technology was utilized to assess the proliferative, migratory and invasive abilities of cells. RESULTS: We have shown that high AUF1 immunostaining (≥ 10%) in both cancer cells and their adjacent cancer-associated fibroblasts (CAFs) was significantly associated with higher tumor grade. Kaplan-Meier univariate analysis revealed a strong correlation between high AUF1 level in CAFs and poor patient's survival. This correlation was highly significant in patients with triple negative breast cancer, who showed poor disease-free survival (DFS) and overall survival (OS). High expression of AUF1 in CAFs was also associated with poor OS of ER+/Her2- patients. Similarly, AUF1-positive malignant cells tended to be associated with shorter DFS and OS of ER+/Her2+ patients. Interestingly, neoadjuvant therapy downregulated AUF1 to a level lower than 10% in malignant cells in a significant number of patients, which improved both DFS and OS. In addition, ectopic expression of AUF1 in breast fibroblasts activated these cells and enhanced their capacity to promote, in an IL-6-dependent manner, the epithelial-to-mesenchymal transition and stemness processes. Furthermore, these AUF1-expressing cells enhanced the chemoresistance of breast cancer cells and their growth in orthotopic tumor xenografts. CONCLUSIONS: The present findings show that the CAF-activating factor AUF1 has prognostic/predictive value for breast cancer patients and could represent a great therapeutic target in order to improve the precision of cancer treatment.

Clinical course and outcomes of COVID-19 in hematopoietic cell transplant patients, a regional report from the Middle East.

The coronavirus disease-2019 (COVID-19) caused by SARS Coronavirus 2 (SARS-CoV-2) is a potentially lethal infection. Cancer patients, and specifically hematopoietic cell transplant (HCT) recipients are severely immunocompromised and may be at a higher risk of a complicated course with this infection. We aimed to study the COVID-19 outcomes and severity in post HCT patients. We retrospectively reviewed post-HCT patients diagnosed with COVID-19 between March 15, 2020, and December 1, 2020 at 10 transplant centers across the Middle East. We identified 91 patients with confirmed SARS-CoV-2 infection across 10 transplant centers. The median age upon presentation with COVID-19 was 35. Fifty two patients were post allo-HCT while the remaining 39 patients were post auto-HCT. The median time from transplant was 14.9 months. Mortality rate was 4.4%. Hospital admission rate was 53%. ICU admission rate was 14%. Mechanical ventilation rate was 10%. Oxygen supplementation rate was 18%. Time from HCT to COVID-19 >6 months was associated with lower admission rates and lower rates of the "severity" composite endpoint. Antibody responses was seen 67% of evaluable patients. In this series of HCT recipients, we report overall favorable clinical outcomes for patients with COVID-19 and provide preliminary insights into the clinical course of this disease in this specific population.

Comparison of closed system transfer devices for turnaround time and ease of use.

OBJECTIVE/PURPOSE: The primary purpose of this study was to compare three closed-system transfer devices with differing mechanical interfaces for their suitability for adoption into our daily practice. The secondary purpose was to use the results of this study to support the selection of one of the closed-system transfer devices, which would suit both the pharmacy and nursing staff at our institution, furthermore promoting the enculturation of international recommendations into our clinical practice. STUDY DESIGN/METHODS: The hazardous drug preparation process was observed and timed continuously from the moment the technician started compounding until the finished product was handed to the designated checker by raising hands. A self-administered, structured questionnaire was used for data collection looking at ease of use of each of the devices from the perspective of pharmacy technicians and nurses. The questionnaire contained an open-ended 10-point Likert-type scale of eight domains. RESULTS/KEY FINDINGS: An improvement in the compounding efficiency of hazardous drugs using PhaSeal™ ( n = 46), ChemoLock™ ( n = 45), and EquaShield® II ( n = 45), when compared respectively against the historical control ( n = 86), was statistically significant ( p < 0.001). However, no statistically significant difference among the different closed-system transfer devices for preparation of hazardous drugs was observed in our study ( p = 0.1). In terms of ease of use, there was no difference in preference for ChemoLock™ and Equashield®II among the pharmacy technicians with both scoring a mean score of 10 with regard to implementation. While PhaSeal™ scored a mean score of 7.2. Among the nursing staff there was a slight preference for ChemoLock™ over Equashield®II with a mean score of 9.2 and 9, respectively with regard to the recommended product, while PhaSeal™ scored a mean score of 7.4. Both nursing staff and pharmacy technicians had a preference ChemoLock™, with a mean score of 10 and 9.6, respectively in terms of on how easy was each device/system to use and overall impression for pharmacy technicians. This was followed by Equashield®II with a mean score of 9.8 and 8.6, respectively and then PhaSeal™ with a mean score of 7.2 and 6.6, respectively. Pharmacy technicians felt there were more steps, packaging and clutter when using PhaSeal® in comparison to the other devices. With Equashield® II, the estimation of clutter was higher than that of ChemoLock™ despite the number of packages being within a similar range. CONCLUSION/RECOMMENDATIONS: Our study found that with experienced staff, compounding of hazardous drugs with closed-system transfer devices can be as efficient as or even more so than with the traditional needle and syringe method. With the lack of statistically significant difference among the different closed-system transfer devices studied, in addition to the cost, ease of use was one of the factors that decided the products applicability in our institution.

Survival analysis of patients with Hodgkin lymphoma who failed high dose chemotherapy and autologous stem cell transplant.

Hodgkin lymphoma (HL) patients failing after high dose chemotherapy (HDC) and auto-SCT have a poor outcome. Some patients may still benefit from further treatments. From 1996 to 2016, 137 HL patients (39.5%) out of 347 transplanted experienced post auto-SCT failure. Males/female 61%:39%, median age at auto-SCT 23.4 years and median follow-up 55.6 months (9-153). Type of failure was progressive (46%), relapsed (35%) or persistent disease/refractory disease (19%). Median overall survival (OS) from the time of failure is 20 months; 35 patients (25.5%) are alive. One hundred and four patients received treatment; the response rate was 45%; complete remission in 41 (30%) and partial remission in 21 (15%) patients. 1st interventions post auto-SCT were chemotherapy (39%), radiation therapy (35%) or best supportive care (24%). Twenty-seven patients with 2nd-SCT (allogeneic (15), auto-SCT (2)) and/or brentuximab (18 patients) had superior OS (50.6 months) vs other treatments (22.5 months, P value 0.037). COX regression multivariate analysis identified post auto-SCT treatment failure before 12 months (hazard ratio (HR) 3.37, CI 1.7-6.6, P value < 0.001), presence of B symptoms (HR 2.55, CI 1.4-4.6, P value 0.002), stages III-IV (HR 2.7, CI 1.5-4.9, P value 0.001), albumin < 4 g/dl (HR 1.76, CI 1.1-2.9, P value 0.027) and tumor > 5 cm (HR 1.1.9, CI 1.13-3.25, P value 0.015) as significant risk factors; P value < 0.001. KM OS with 0-1 factor (148.6 months): 2 factors (23.6 months) and 3-5 factors (9.4 months) (P value < 0.001). OS was 63%:25%:7% respectively with 0-1:2:3-5 factors respectively (P value < 0.001). Despite high-risk factors, 2nd-SCT/brentuximab use post HDC auto-SCT failure may result in durable survival.

Outcome analysis of high-dose chemotherapy and autologous stem cell transplantation in adolescent and young adults with relapsed or refractory Hodgkin lymphoma.

High-dose chemotherapy (HDC) and autologous stem cell transplantation (auto-SCT) can salvage many patients with relapsed or refractory Hodgkin's lymphoma (HL). We are reporting the outcome of HDC auto-SCT and the impact of 21 prognostic factors in relapsed and refractory adolescent (14-21 years) and young adult (>21-30 years) (AYA) HL patients. We used Fine and Gray's competing risk analysis method and regression model for outcome analysis. From 1996 to 2013, 290 consecutive patients with biopsy-proven HL underwent HDC auto-SCT for relapsed/refractory HL; 216 patients (74.5 %) were AYA at the time of auto-SCT. Male/female were equal, median age at auto-SCT was 22.4 years, and there were 94 adolescent (43.5 %) and 122 young adults (56.5 %). There was refractory disease in 121 (56 %) patients, relapsed in 95 (44 %). Median follow-up was 72.6 months. The Kaplan-Meier method estimated that 5-year overall survival is 62.7 % (adolescents (63.5 %), young adults (62 %)) and event-free survival was 51.3 %. Five-year cumulative incidence of disease-specific death (DS-death) is 33 % and that of DS-event is 45 %. For DS-death, the multivariate analysis identified complete remission (CR) duration of <12 months (hazard ratio (HR) 3.61, P = 0.0009), no CR after salvage (HR: 3.93, P = 0.0002), and nodular sclerosis pathology (HR 3.3, P = 0.016) and positive B symptoms (HR 2, P = 0.028) as negative factors. For DS-event, CR duration of <12 months (HR 1.88, P = 0.02), no CR after salvage (HR 3.47, P = 0.000005) and nodular sclerosis pathology (HR 1.88, P = 0.02) were found significant. The Kaplan-Meier method estimated overall survival (OS) at 36 months with 0-2:3:4 factors being 93.6:54:21 %, respectively (P value <0.001). Kaplan-Meier estimated event-free survival (EFS) at 36 months with 0-1:2:3 factors being 84.6:65:31 %, respectively (P value <0.001). Clinically, adolescents have similar outcomes as young adults.