A semi-supervised multi-task learning framework for cancer classification with weak annotation in whole-slide images

Cancer region detection (CRD) and subtyping are two fundamental tasks in digital pathology image analysis. The development of data-driven models for CRD and subtyping on whole-slide images (WSIs) would mitigate the burden of pathologists and improve their accuracy in diagnosis. However, the existing models are facing two major limitations. Firstly, they typically require large-scale datasets with precise annotations, which contradicts with the original intention of reducing labor effort. Secondly, for the subtyping task, the non-cancerous regions are treated as the same as cancerous regions within a WSI, which confuses a subtyping model in its training process. To tackle the latter limitation, the previous research proposed to perform CRD first for ruling out the non-cancerous region, then train a subtyping model based on the remaining cancerous patches. However, separately training ignores the interaction of these two tasks, also leads to propagating the error of the CRD task to the subtyping task. To address these issues and concurrently improve the performance on both CRD and subtyping tasks, we propose a semi-supervised multi-task learning (MTL) framework for cancer classification. Our framework consists of a backbone feature extractor, two task-specific classifiers, and a weight control mechanism. The backbone feature extractor is shared by two task-specific classifiers, such that the interaction of CRD and subtyping tasks can be captured. The weight control mechanism preserves the sequential relationship of these two tasks and guarantees the error back-propagation from the subtyping task to the CRD task under the MTL framework. We train the overall framework in a semi-supervised setting, where datasets only involve small quantities of annotations produced by our minimal point-based (min-point) annotation strategy. Extensive experiments on four large datasets with different cancer types demonstrate the effectiveness of the proposed framework in both accuracy and generalization.     

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.     

Caspase activation is required for gemcitabine activity in multiple myeloma cell lines

The objective of this study was to determine potential mechanisms of apoptotic activity of gemcitabine, a pyrimidine nucleoside analogue, in the MM1.S multiple myeloma (MM) cell line. A MM cell line that is sensitive to glucocorticoids (MM1.S) was used for this study. Immunoblotting analysis, cell cycle assays, and annexin V staining were performed to determine whether gemcitabine induced apoptosis in this model. Furthermore, we attempted to delineate the apoptotic pathway by measuring caspase-8 and -9 activity using fluorometric assays. Loss of mitochondrial membrane potential was measured by flow cytometry. Gemcitabine treatment caused apoptosis in MM cell lines as measured by an increase in DNA cleavage, an increase in annexin V binding, a decrease in the mitochondrial membrane potential, and activation of caspase activity. Furthermore, cleavage of the caspase substrate poly(ADP-ribose) polymerase and caspase-3 activation were documented as early as 8 h after treatment with gemcitabine. Caspase-8 and -9 were activated by gemcitabine treatment in this cell line, suggesting several mechanisms of action including death receptor pathway and mitochondrial damage. The addition of interleukin 6 to MM1.S cells treated with gemcitabine offered no protection against gemcitabine-induced cell death. Gemcitabine induced apoptosis in the MM1.S cell line, and its activity required caspase activation. There is a suggestion that mitochondrial integrity is being affected with gemcitabine in this system. Gemcitabine acts independently of interleukin 6, suggesting potential important therapeutic implications in MM patients.     

Diana-5全自动血液分析仪白细胞分类与镜检的相关性研究

目的 对Diana-5全自动血液分析仪白细胞五分类与镜检的相关性进行研究与评价。方法 系统研究Diana-5全自动血液分析仪白细胞分类测定的精密度、总变异、镜检率、敏感性、特异性和过筛符合率，并分析比较与镜检结果的相关性。结果仪器分类测定中性粒细胞（Neu）、淋巴细胞（Lym）、单核细胞（Mon）、嗜酸性粒细胞（Eos）和嗜碱性粒细胞（Bas）的精密度分别为1.25％、1.53％、5．96％、7．58％和15．85％，总变异分别为1．82％、2．86％、7．84％、9．32％和17．32％。与镜检结果的相关系数分别为0．982、0．956、0．842、0．536和0．328。分类镜检率为20．2％，敏感性98．0％，特异性87．2％，过筛符合率88．1％。该仪器可提示异常白细胞的检测信息，其中非成熟细胞占异常提示信息的51.5％。结论 Diana-5血液分析仪白细胞分类测定的自动化程度高，结果 重复性好，具有良好的相关性，能有效发挥仪器的过筛作用，非常适合血常规的快速检测。     

Diana-5全自动血液分析仪白细胞分类与镜检的相关性研究

目的对Diana-5全自动血液分析仪白细胞五分类与镜检的相关性进行研究与评价。方法系统研究Diana-5全自动血液分析仪白细胞分类测定的精密度、总变异、镜检率、敏感性、特异性和过筛符合率,并分析比较与镜检结果的相关性。结果仪器分类测定中性粒细胞(Neu)、淋巴细胞(Lym)、单核细胞(Mon)、嗜酸性粒细胞(Eos)和嗜碱性粒细胞(Bas)的精密度分别为1.25%、1.53%、5.96%、7.58%和15.85%,总变异分别为1.82%、2.86%、7.84%、9.32%和17.32%。与镜检结果的相关系数分别为0.982、0.956、0.842、0.536和0.328。分类镜检率为20.2%,敏感性98.0%,特异性87.2%,过筛符合率88.1%。该仪器可提示异常白细胞的检测信息,其中非成熟细胞占异常提示信息的51.5%。结论Diana-5血液分析仪白细胞分类测定的自动化程度高,结果重复性好,具有良好的相关性,能有效发挥仪器的过筛作用,非常适合血常规的快速检测。     

Computer-aided diagnosis for the classification of breast masses in automated whole breast ultrasound images

New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student’s t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw)     

黄芩素对多发性骨髓瘤细胞株RPMI8226和U266细胞增殖和迁移的影响

目的 探讨黄芩素对多发性骨髓瘤(MM)细胞增殖和迁移能力的影响及分子机制.方法 以不同浓度黄芩素处理MM细胞株RPMI 8226和U266细胞不同时间后,应用四甲基偶氮唑盐(MTT)比色实验检测黄芩素对MM细胞增殖的影响;用黄芩素和(或)IL-6处理RPMI 8226、U266细胞,激光共聚焦及Western blot检测处理前后细胞中β连环素(β-catenin)蛋白表达;Transwell小室实验检测不同浓度黄芩素处理前后RPMI 8226和U266细胞的迁移能力;RT-PCR检测不同浓度黄芩素处理前后细胞内β-catenin、c-myc、细胞周期素D1(Cyclin D1)和细胞迁移相关基因整联蛋白β7(integrin β7)基因mRNA表达.结果 黄芩素呈浓度和时间依赖性抑制RPMI 8226和U266细胞的增殖;激光共聚焦及Westem blot结果显示黄芩素能够抑制β-catenin的表达从而抵抗IL-6对MM细胞的促增殖作用;RT-PCR检测显示黄芩素能够抑制β-catenin、c-myc、cyclin D1和integrin β7的mRNA表达;Transwell小室迁移实验表明,在基质细胞衍生因子(SDF-1)的趋化下,黄芩素以浓度依赖的方式降低MM细胞的迁移能力.结论 黄芩素具有抑制MM细胞增殖和迁移的作用,其分子机制与抑制增殖相关基因β-catenin、c-myc、cyclin D1和integrin β7的表达有关.     

霍奇金病R—S细胞分型诊断意义的探讨

目的 探讨Ｒ－Ｓ细胞谱系对霍奇金病（ＨＤ）的诊断意义。方法 观察并分析了７１例ＨＤ的Ｒ－Ｓ细胞分类。结果 未见单一类型Ｒ－Ｓ细胞出现,其中出现２种类型为７．１％,３种１８。３％,４种３５．２％,５种３３．８％,６种５．６％。以单核型Ｒ－Ｓ细胞最为多见（９３．０％）,其次为多形型（８６．０％）。结论 以诊断型Ｒ－Ｓ细胞为代表系列Ｒ－Ｓ细胞的出现是ＨＤ诊断要点。     

Retinal signal transmission in Duchenne muscular dystrophy: evidence for dysfunction in the photoreceptor/depolarizing bipolar cell pathway.

There have been reports of abnormal retinal neurotransmission determined by electroretinography in boys with Duchenne and Becker muscular dystrophy. Dystrophin may play a role in transmitting signals between photoreceptors and the excitatory synapse of the ON-bipolar cell. These electroretinographic changes appeared to be limited to the rod ON-pathway but we felt there was also similar abnormality in the cone ON-pathway. We used long-duration stimuli to separate ON-(depolarizing bipolar cell) and OFF (hyperpolarizing bipolar cell) contributions to the cone-dominated ERG to better understand how the retina functions in boys with Duchenne muscular dystrophy. We recorded the electroretinograms of 11 boys with Duchenne muscular dystrophy and found abnormal signal transmission at the level of the photoreceptor and ON-bipolar cell in both the rod and cone generated responses. The OFF-bipolar cell that responds to the offset of the stimulus continues to function normally. The results support our hypothesis that retinal dystrophin plays a role in receptor function or controlling ion channels at the level of the photoreceptor and depolarizing bipolar cell.     

自动识别技术在乳腺结节超声图像良恶性分类中的可行性研究

正在中国,乳腺癌已成为女性最常见的恶性肿瘤之一,其死亡率已经超过宫颈癌,位居癌症病死率的前5名[1]。美国癌症协会发表的2016美国癌症统计数据也表明,乳腺癌是女性最常见的癌症,预计乳腺癌将独占女性全部新发病例的29%[2]。早期发现乳腺癌可以增加患者治疗的机会和提高患者的生存率[3-4];因此,乳腺癌的筛査及早期诊断十分必要。近年来,随着超声技术的不断发展,其在乳腺癌的早期诊断、乳腺良恶性病变的鉴别方面起着越来越     

K562细胞及其耐药细胞株K562/A02细胞白血病耐药相关microRNA筛选

目的 通过检测慢性粒细胞白血病急变细胞系K562及其阿霉素耐药株K562/A02的微小RNA(microRNA、miR)表达差异,探讨microRNA与白血病化疗耐药的关系.方法 MTT法检测K562/A02及其亲本细胞系K562的耐药性能;流式细胞术检测K562与K562/A02细胞的P-gp表达;运用microRNA芯片技术筛查K562与K562/A02细胞之间差异表达的microRNA,随后用实时荧光定量RT-PCR方法进一步证实.结果 阿霉素耐药株K562/A02相对于其亲本细胞系K562对阿霉素的耐药倍数为180倍;K562细胞P-gp的表达率为0.2%,K562/A02细胞P-gp的表达率为86%;microRNA芯片结果显示K562/A02与K562细胞之间有22种microRNA表达存在显著的差异(P<0.01),表达差异在2倍以上的有9种,其中miR-221、miR-155、miR-451在K562/A02细胞表达上调,而miR-98、miR-181a、let-7f、miR-424、let-7g和miR-563则表达下调.实时荧光定量RT-PCR进一步证实了上述结果,并显示miR-451、miR-155、miR-221、let-7f、miR-424在两种细胞中表达差异显著.结论 K562/A02与K562细胞存在microRNA表达差异,其中miR-451、miR-155和miR-221在K562/A02中表达显著上调,而let-7f、miR-424则显著下调,提示microRNA可能参与白血病耐药形成,差异表达的microRNA可能为逆转白血病耐药提供新的作用靶点.     

K562细胞及其耐药细胞株K562/A02细胞白血病耐药相关microRNA筛选

目的 通过检测慢性粒细胞白血病急变细胞系K562及其阿霉素耐药株K562/A02的微小RNA(microRNA、miR)表达差异,探讨microRNA与白血病化疗耐药的关系.方法 MTT法检测K562/A02及其亲本细胞系K562的耐药性能;流式细胞术检测K562与K562/A02细胞的P-gp表达;运用microRNA芯片技术筛查K562与K562/A02细胞之间差异表达的microRNA,随后用实时荧光定量RT-PCR方法进一步证实.结果 阿霉素耐药株K562/A02相对于其亲本细胞系K562对阿霉素的耐药倍数为180倍;K562细胞P-gp的表达率为0.2%,K562/A02细胞P-gp的表达率为86%;microRNA芯片结果显示K562/A02与K562细胞之间有22种microRNA表达存在显著的差异(P<0.01),表达差异在2倍以上的有9种,其中miR-221、miR-155、miR-451在K562/A02细胞表达上调,而miR-98、miR-181a、let-7f、miR-424、let-7g和miR-563则表达下调.实时荧光定量RT-PCR进一步证实了上述结果,并显示miR-451、miR-155、miR-221、let-7f、miR-424在两种细胞中表达差异显著.结论 K562/A02与K562细胞存在microRNA表达差异,其中miR-451、miR-155和miR-221在K562/A02中表达显著上调,而let-7f、miR-424则显著下调,提示microRNA可能参与白血病耐药形成,差异表达的microRNA可能为逆转白血病耐药提供新的作用靶点.     

K562细胞及其耐药细胞株K562/A02细胞白血病耐药相关microRNA筛选

目的 通过检测慢性粒细胞白血病急变细胞系K562及其阿霉素耐药株K562/A02的微小RNA(microRNA、miR)表达差异,探讨microRNA与白血病化疗耐药的关系.方法 MTT法检测K562/A02及其亲本细胞系K562的耐药性能;流式细胞术检测K562与K562/A02细胞的P-gp表达;运用microRNA芯片技术筛查K562与K562/A02细胞之间差异表达的microRNA,随后用实时荧光定量RT-PCR方法进一步证实.结果 阿霉素耐药株K562/A02相对于其亲本细胞系K562对阿霉素的耐药倍数为180倍;K562细胞P-gp的表达率为0.2%,K562/A02细胞P-gp的表达率为86%;microRNA芯片结果显示K562/A02与K562细胞之间有22种microRNA表达存在显著的差异(P<0.01),表达差异在2倍以上的有9种,其中miR-221、miR-155、miR-451在K562/A02细胞表达上调,而miR-98、miR-181a、let-7f、miR-424、let-7g和miR-563则表达下调.实时荧光定量RT-PCR进一步证实了上述结果,并显示miR-451、miR-155、miR-221、let-7f、miR-424在两种细胞中表达差异显著.结论 K562/A02与K562细胞存在microRNA表达差异,其中miR-451、miR-155和miR-221在K562/A02中表达显著上调,而let-7f、miR-424则显著下调,提示microRNA可能参与白血病耐药形成,差异表达的microRNA可能为逆转白血病耐药提供新的作用靶点.     

DLGNet: A dual-branch lesion-aware network with the supervised Gaussian Mixture model for colon lesions classification in colonoscopy images

Colorectal cancer is one of the malignant tumors with the highest mortality due to the lack of obvious early symptoms. It is usually in the advanced stage when it is discovered. Thus the automatic and accurate classification of early colon lesions is of great significance for clinically estimating the status of colon lesions and formulating appropriate diagnostic programs. However, it is challenging to classify full-stage colon lesions due to the large inter-class similarities and intra-class differences of the images. In this work, we propose a novel dual-branch lesion-aware neural network (DLGNet) to classify intestinal lesions by exploring the intrinsic relationship between diseases, composed of four modules: lesion location module, dual-branch classification module, attention guidance module, and inter-class Gaussian loss function. Specifically, the elaborate dual-branch module integrates the original image and the lesion patch obtained by the lesion localization module to explore and interact with lesion-specific features from a global and local perspective. Also, the feature-guided module guides the model to pay attention to the disease-specific features by learning remote dependencies through spatial and channel attention after network feature learning. Finally, the inter-class Gaussian loss function is proposed, which assumes that each feature extracted by the network is an independent Gaussian distribution, and the inter-class clustering is more compact, thereby improving the discriminative ability of the network. The extensive experiments on the collected 2568 colonoscopy images have an average accuracy of 91.50%, and the proposed method surpasses the state-of-the-art methods. This study is the first time that colon lesions are classified at each stage and achieves promising colon disease classification performance. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/DLGNet.     

Evidence that the T cell antigen receptor may not be involved in cytotoxicity mediated by gamma/delta and alpha/beta thymic cell lines

After culture in IL-2, thymocytes expressing either TCR-alpha/beta or - gamma/delta acquired the ability to lyse hematopoietic and solid tumor cell targets without deliberate immunization or apparent restriction by the MHC. Moreover, TCR-alpha/beta- and TCR-gamma/delta-bearing thymic cell lines demonstrated an essentially identical spectrum of cytolysis against several tumor cell targets. Cytotoxicity was not inhibited by antibodies against CD3 or CD2 and modulation of the CD3/TCR complex also failed to affect cytotoxicity. Thus, non-MHC-restricted cytotoxicity can be mediated by thymocytes with either TCR-alpha/beta or TCR-gamma/delta, but the TCR may not be responsible for target recognition.     

肿瘤坏死因子α对人肺腺癌细胞耐顺铂的影响

目的研究肿瘤坏死因子OL（TNF-α）对人肺腺癌细胞系A549／顺铂（DDP）耐DDP的逆转作用,探讨其与肺耐药相关蛋白（LRP）表达之间的关系。方法以MTT法检0n,0TNF-α与顺铂联用对A549／DDP细胞的细胞毒性作用,以免疫细胞化学方法检测A549／DDP细胞LRP的表达情况。结果250、1000U／mlTNF-α可使顺铂对A549／DDP细胞的IC50从7．12ng／L分别降至5．02、4．41ng／L,能够逆转A549／DDP对顺铂的耐药,逆转倍数分别为1．42、1．62。A549／DDP细胞LRP呈强阳性表达,250、1000U／mlTN-α与顺铂联用可以下调LRP表达,LRP阳性表达率分别为（60．14-4-6．54）％、（57．234-5．98）％,同无药组和顺铂组LRP表达率（79．63±4．78）％、（75．97±5．32）％比较,差异具有统计学意义（P均〈0．01）。结论TNF-α能够逆转A549／DDP对顺铂的耐药,其机制可能与下调LRP表达有关。     

PI3K抑制剂LY294002对弥漫大B细胞性淋巴瘤细胞株化疗增敏作用的研究

目的 研究PI3K抑制剂LY294002对弥漫大B细胞淋巴瘤(DLBCL)细胞株ly1、ly8、ly10的化疗增敏作用.方法 采用LY294002、阿霉素及两者联合、序贯使用分别作用于ly1、ly8、ly10细胞;采用Western blot法观察LY294002处理后ly1、ly8、ly10细胞中磷酸化AKT/PKB(pAKT)的改变;采用流式细胞术结合Brdu法分析LY294002对细胞增殖和细胞周期分布的影响,采用流式细胞术结合AnnexinV-FITC染色检测各组细胞凋亡率.结果 LY294002可显著降低DLBCL细胞中磷酸化AKT的表达水平;并导致S期细胞比例显著降低(P＜0.05);LY294002预处理序贯使用阿霉素组中细胞凋亡的发生率比单独使用LY294002、阿霉素或同时联合使用LY294002、阿霉素组均明显提高,在24、48、72 h(ly1)或48、72 h(ly8)或24 h(ly10)差异均有统计学意义(P值均＜0.05).结论 PI3K抑制剂LY294002对阿霉素诱导DLBCL细胞凋亡的促进作用提示其可能是DLBCL治疗中潜在的具有较好化疗增敏作用的分子靶向药物.