CW-NET for multitype cell detection and classification in bone marrow examination and mitotic figure examination.

MOTIVATION: Bone marrow (BM) examination is one of the most important indicators in diagnosing hematologic disorders and is typically performed under the microscope via oil-immersion objective lens with a total 100× objective magnification. On the other hand, mitotic detection and identification is critical not only for accurate cancer diagnosis and grading but also for predicting therapy success and survival. Fully automated BM examination and mitotic figure examination from whole-slide images is highly demanded but challenging and poorly explored. First, the complexity and poor reproducibility of microscopic image examination are due to the cell type diversity, delicate intralineage discrepancy within the multitype cell maturation process, cells overlapping, lipid interference and stain variation. Second, manual annotation on whole-slide images is tedious, laborious and subject to intraobserver variability, which causes the supervised information restricted to limited, easily identifiable and scattered cells annotated by humans. Third, when the training data are sparsely labeled, many unlabeled objects of interest are wrongly defined as background, which severely confuses AI learners. RESULTS: This article presents an efficient and fully automatic CW-Net approach to address the three issues mentioned above and demonstrates its superior performance on both BM examination and mitotic figure examination. The experimental results demonstrate the robustness and generalizability of the proposed CW-Net on a large BM WSI dataset with 16 456 annotated cells of 19 BM cell types and a large-scale WSI dataset for mitotic figure assessment with 262 481 annotated cells of five cell types. AVAILABILITY AND IMPLEMENTATION: An online web-based system of the proposed method has been created for demonstration (see https://youtu.be/MRMR25Mls1A).

Distinct clinico-biological features in AML patients with low allelic ratio FLT3-ITD: role of allogeneic stem cell transplantation in first remission.

The mutant burden of FLT3-ITD modulates its prognostic impact on patients with acute myeloid leukemia (AML). However, for patients with low allelic ratio (AR) FLT3-ITD (FLT3-ITDlow, AR < 0.5), clinical features, as well as genomic and transcriptomic profiles remain unclear, and evidence supporting allogeneic hematopoietic stem cell transplantation (allo-HSCT) in first complete remission (CR1) remains controversial. This study aimed to elucidate the genomic features, prognosis, and transplantation outcome of FLT3-ITDIow in AML patients with intermediate-risk cytogenetics. FLT3-ITDlow was associated with a negative enrichment of the leukemic stem cell signature, a marked enrichment of the RAS pathway, and with higher frequencies of RAS pathway mutations, different from those with FLT3-ITDhigh. Concurrent CEBPA double mutations were favorable prognostic factors, whereas MLL-PTD, and mutations in splicing factors were unfavorable prognostic factors in FLT3-ITDlow patients. Patients with FLT3-ITDlow had a shorter overall survival (OS) and event-free survival (EFS) than those with FLT3wt. Allo-HSCT in CR1 was associated with a significantly longer OS and EFS compared with postremission chemotherapy in patients with FLT3-ITDlow. In conclusion, FLT3-ITDlow is associated with different mutational and transcriptomic profiles compared with FLT3-ITDhigh. The presence of concomitant poor-risk mutations exert negative prognostic impacts in patients with FLT3-ITDlow, who markedly benefit from allo-HSCT in CR1.

Deep learning for bone marrow cell detection and classification on whole-slide images.

Bone marrow (BM) examination is an essential step in both diagnosing and managing numerous hematologic disorders. BM nucleated differential count (NDC) analysis, as part of BM examination, holds the most fundamental and crucial information. However, there are many challenges to perform automated BM NDC analysis on whole-slide images (WSIs), including large dimensions of data to process, complicated cell types with subtle differences. To the authors best knowledge, this is the first study on fully automatic BM NDC using WSIs with 40x objective magnification, which can replace traditional manual counting relying on light microscopy via oil-immersion 100x objective lens with a total 1000x magnification. In this study, we develop an efficient and fully automatic hierarchical deep learning framework for BM NDC WSI analysis in seconds. The proposed hierarchical framework consists of (1) a deep learning model for rapid localization of BM particles and cellular trails generating regions of interest (ROI) for further analysis, (2) a patch-based deep learning model for cell identification of 16 cell types, including megakaryocytes, mitotic cells, and four stages of erythroblasts which have not been demonstrated in previous studies before, and (3) a fast stitching model for integrating patch-based results and producing final outputs. In evaluation, the proposed method is firstly tested on a dataset with a total of 12,426 annotated cells using cross validation, achieving high recall and accuracy of 0.905 ± 0.078 and 0.989 ± 0.006, respectively, and taking only 44 seconds to perform BM NDC analysis for a WSI. To further examine the generalizability of our model, we conduct an evaluation on the second independent dataset with a total of 3005 cells, and the results show that the proposed method also obtains high recall and accuracy of 0.842 and 0.988, respectively. In comparison with the existing small-image-based benchmark methods, the proposed method demonstrates superior performance in recall, accuracy and computational time.

Hepatitis B Surface Antigen Positivity Is an Independent Unfavorable Prognostic Factor in Diffuse Large B-Cell Lymphoma in the Rituximab Era.

BACKGROUND: Patients with diffuse large B-cell lymphoma (DLBCL) with concurrent hepatitis B surface antigen (HBsAg)-positive hepatitis B virus (HBV) infection have distinct clinical features. Nevertheless, the prognostic value of HBsAg in DLBCL in the rituximab era remains unclear. MATERIALS AND METHODS: We conducted a retrospective cohort study to investigate the clinical relevance of HBsAg in immunocompetent patients with DLBCL treated with homogeneous rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone between 2002 and 2016. RESULTS: Among 416 analyzed patients, 98 (23.6%) were HBsAg positive. HBsAg positivity was associated with a younger age and more advanced stage at diagnosis, more frequent hepatic impairment during perichemotherapy, and a trend of higher National Comprehensive Cancer Network-International Prognostic Index (NCCN-IPI) score at diagnosis. Compared with the HBsAg-negative patients, the HBsAg-positive patients had a lower overall response rate (76.5% vs. 85.5%, p = .043), poorer 5-year overall survival (OS) rate (57.2% vs. 73.5%, p < .001), and shorter 5-year progression-free survival (PFS) rate (47.2% vs. 60.7%, p = .013). Multivariate analyses showed that HBsAg positivity was an independent unfavorable prognostic indicator for OS and PFS. A scoring system incorporating HBsAg positivity, the NCCN-IPI score, and serum albumin levels proved to be useful for stratifying prognostically relevant subgroups of patients with DLBCL. CONCLUSION: This study demonstrated that HBV infection is uniquely relevant to DLBCL. HBsAg might serve as a novel biomarker to improve clinical risk stratification of patients with DLBCL in areas with high prevalence of HBV infection. Further research investigating the etiopathogenesis of HBV infection in DLBCL is imperative. IMPLICATIONS FOR PRACTICE: A considerable disparity exists regarding the prognostic relevance of hepatitis B surface antigen (HBsAg)-positive hepatitis B virus (HBV) infection in patients with diffuse large B-cell lymphoma (DLBCL). In this large, retrospective cohort study from an area with high prevalence of HBV infection, the authors demonstrated that HBsAg was an independent unfavorable factor significantly associated with survival, highlighting its potential as a novel prognostic indicator to improve the risk stratification of patients with DLBCL in the rituximab era.

Diagnostic value of high-frequency color Doppler ultrasonography examination in combination with anti-cyclic citrullinated peptide antibody testing in rheumatoid arthritis patients.

We studied the diagnostic value of high-frequency color Doppler ultrasonography (HCDU) examination in combination with anti-cyclic citrullinated peptide (anti-CCP) antibody testing in rheumatoid arthritis (RA) patients with finger joint damage. From January 2015 to December 2015, 80 patients diagnosed with RA with finger joints damage were enrolled in this study. Patients were examined with HCDU. Serum anti-CCP antibody level was tested using ELISA, and results were compared with the healthy control group. Results obtained by ELISA demonstrated that the positive rate of anti-CCP antibodies was 73.8% in the study group, and 10% in the control group. The negative rate was 26.2% in the study group, and 90% in the control group. HCDU examination suggested that the predominantly affected joint by bone erosion of RA with finger joint damage was MCP3 (16.7%), followed by PIP3 (14.1%), MCP2 (13.5%) and PIP2 (12.8%). The slightest affected joint was thumb metacarpophalangeal joint, followed by thumb, little finger metacarpophalangeal joint and proximal interphalangeal joint. The sensitivity of diagnosis of RA with finger joints damage with both HCDU and CCP antibody examination showed a significantly lower level compared with examination with each one of the methods alone, while specificity showed a significantly higher level. Thus, a combination of HCDU examination and anti-CCP antibody testing can be considered useful to improve the early diagnostic rate of RA. HCDU examination is a sensitive, secure, atraumatic and easily-operated diagnostic method for early RA patients with finger joint damage. When combined with anti-CCP antibody testing, it will provide a better chance for RA patients, and give them hope for a better treatment and improved prognosis.

Diagnostic value of high-frequency ultrasound and magnetic resonance imaging in early rheumatoid arthritis.

Early diagnosis and management improve the outcome of patients with rheumatoid arthritis (RA). The present study explored the application of high-frequency ultrasound (US) and magnetic resonance imaging (MRI) in the detection of early RA. Thirty-nine patients (20 males and 19 females) diagnosed with early RA were enrolled in the study. A total of 1,248 positions, including 858 hand joints and 390 tendons, were examined by high-frequency US and MRI to evaluate the presence of bone erosion, bone marrow edema (BME), synovial proliferation, joint effusion, tendinitis and tendon sheath edema. The imaging results of the above abnormalities, detected by US, were compared with those identified using MRI. No statistically significant overall changes were observed between high-frequency US and MRI in detecting bone erosion [44 (5.1%) vs. 35 (4.1%), respectively; P>0.05], tendinitis [18 (4.6%) vs. 14 (1.5%), respectively; P>0.05] and tendon sheath edema [37 (9.5%) vs. 30 (7.7%), respectively; P>0.05]. Significant differences were observed between high-frequency US and MRI with regards to the detection of synovial proliferation [132 (15.4%) vs. 66 (7.7%), respectively; P<0.05] and joint effusion [89 (10.4%) vs. 52 (6.1%), respectively; P<0.05]. In addition, significant differences were identified between the detection of BME using MRI compared with high-frequency US (5.5 vs. 0%, respectively; P<0.05). MRI and high-frequency US of the dominant hand and wrist joints were comparably sensitive to bone erosion, tendinitis and tendon sheath edema. However, MRI was more sensitive in detecting bone marrow edema in early RA, while US was more sensitive in the evaluation of joint effusion and synovial proliferation. In conclusion, US and MRI are promising for the detection and diagnosis of inflammatory activity in patients with RA.