Search

Summary: In sub‐Saharan Africa, acute‐onset severe malaria anaemia (SMA) is a critical challenge, particularly affecting children under five. The acute drop in haematocrit in SMA is thought to be driven by an increased phagocytotic pathological process in the spleen, leading to the presence of distinct red blood cells (RBCs) with altered morphological characteristics. We hypothesized that these RBCs could be detected systematically and at scale in peripheral blood films (PBFs) by harnessing the capabilities of deep learning models. Assessment of PBFs by a microscopist does not scale for this task and is subject to variability. Here we introduce a deep learning model, leveraging a weakly supervised Multiple Instance Learning framework, to Identify SMA (MILISMA) through the presence of morphologically changed RBCs. MILISMA achieved a classification accuracy of 83% (receiver operating characteristic area under the curve [AUC] of 87%; precision‐recall AUC of 76%). More importantly, MILISMA's capabilities extend to identifying statistically significant morphological distinctions (p < 0.01) in RBCs descriptors. Our findings are enriched by visual analyses, which underscore the unique morphological features of SMA‐affected RBCs when compared to non‐SMA cells. This model aided detection and characterization of RBC alterations could enhance the understanding of SMA's pathology and refine SMA diagnostic and prognostic evaluation processes at scale. [ABSTRACT FROM AUTHOR]

Automated image‐based assessment of blood films has tremendous potential to support clinical haematology within overstretched healthcare systems. To achieve this, efficient and reliable digital capture of the rich diagnostic information contained within a blood film is a critical first step. However, this is often challenging, and in many cases entirely unfeasible, with the microscopes typically used in haematology due to the fundamental trade‐off between magnification and spatial resolution. To address this, we investigated three state‐of‐the‐art approaches to microscopic imaging of blood films which leverage recent advances in optical and computational imaging and analysis to increase the information capture capacity of the optical microscope: optical mesoscopy, which uses a giant microscope objective (Mesolens) to enable high‐resolution imaging at low magnification; Fourier ptychographic microscopy, a computational imaging method which relies on oblique illumination with a series of LEDs to capture high‐resolution information; and deep neural networks which can be trained to increase the quality of low magnification, low resolution images. We compare and contrast the performance of these techniques for blood film imaging for the exemplar case of Giemsa‐stained peripheral blood smears. Using computational image analysis and shape‐based object classification, we demonstrate their use for automated analysis of red blood cell morphology and visualization and detection of small blood‐borne parasites such as the malarial parasite Plasmodium falciparum. Our results demonstrate that these new methods greatly increase the information capturing capacity of the light microscope, with transformative potential for haematology and more generally across digital pathology. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland. [ABSTRACT FROM AUTHOR]

Aim: To describe the pattern of paediatric Rhabdomyosarcomas (RMS) and Non-Rhabdomyosarcomas (NRMS) with emphasis on the indices that affect survival outcomes.Methods: We reviewed all patients with histologically confirmed RMS and NRMS in the Departments of Pathology and Paediatrics, University College Hospital (UCH), Ibadan, Nigeria; in children aged 0-14 years. The study period was January 1991 to December 2016. Information obtained included age, gender, morphology and site of the tumours. The tumour grade and pathologic/clinical staging of all patients were also obtained and verified by the clinical records. Tumour grading was carried out using the Fédération Nationale des Centres de Lutte Contre le Cancer (FNCLCC) Sarcoma group grading system and staging was done using TNM. Follow up, survival information and final outcome were retrieved.Results: The 104 patients included in the study had almost equal male-to-female ratio, age ranged between 5 months and 14 years (median 8.2 years). Rhabdomyosarcoma had mean age of 5.6 (±3.8) years while that of NRMS was 9.2(±4.1) years. Overall, the modal age group was 5-9 years. Rhabdomyosarcoma was the commonest histological type (76%), undifferentiated sarcomas (6.7%), fibrosarcoma (3.8%) and 2.9% each for synovial sarcoma and dermatofibrosarcoma protuberans. The common primary sites were the head and neck (including the orbit) 49 (47.1%), and the abdominopelvic 26 (25%) regions. Majority (89%) had histologic grade 3 at presentation. Seventy per cent and 64% of patients with RMS and NRMS, respectively, had high stage tumour at presentation. Median survival for all patients with Rhabdomyosarcoma was 45 weeks with a 1-year survival of 43% and 2-year survival of 25%. Non-RMS (Dermatofibrosarcoma protuberans and Solitary fibrous tumours) had survival of over 4 year's duration.Conclusion: Majority of our patients presented at a late stage with histologic high grade which confers poor prognosis and reduced chances for good overall survival outcome. [ABSTRACT FROM AUTHOR]

Prior to the introduction of the International Network for Cancer Treatment and Research ( INCTR) protocol INCTR 03-06, survival of patients with Burkitt lymphoma at four tertiary care centres in equatorial Africa was probably no more than 10-20%. The results reported here for 356 patients have demonstrated marked improvement in survival through the use of a uniform treatment protocol consisting of cyclophosphamide, methotrexate, vincristine, and intrathecal therapy, and the introduction of non-cross resistant second-line (salvage) therapy, consisting of ifosfamide, mesna, etoposide and cytarabine, when patients failed to achieve a complete response to first-line therapy or relapsed early. Overall survival rates of 67% and 62% were observed at 1 and 2 years (relapse is rare after 1 year of remission). Of interest was the small impact of cerebrospinal fluid ( CSF) and bone marrow involvement on outcome. However, the presence or absence of abdominal involvement clearly defined two prognostic groups. An additional finding was the association between CSF pleocytosis and orbital tumours, suggesting that spread of tumour cells to the central nervous system may sometimes occur via direct involvement of cranial nerves in the orbit. Survival rates may be increased in patients with abdominal involvement by combining first- and second-line therapy, but verification will require a further clinical study. [ABSTRACT FROM AUTHOR]