在同一数据集上训练的不同神经网络通常学习具有非常不同权重的相似输入 - 输出映射。这些神经网络解决方案之间是否有一些对应?对于线性网络,已经表明相同网络体系结构的不同实例编码相同的代表性相似性矩阵,并且它们的神经活动模式通过正交变换连接。但是,目前还不清楚这是否适用于非线性网络。使用共享响应模型,我们表明不同的神经网络编码相同的输入示例作为底层共享表示的不同正交变换。我们使用标准卷积神经网络和CIFAR10和CIFAR100上的残余网络来测试这种说法。
translated by 谷歌翻译
*These authors contributed equally to this work. The brightfield microscope is instrumental in the visual examination of both biological and physical samples at sub-millimeter scales. One key clinical application has been in cancer histopathology, where the microscopic assessment of the tissue samples is used for the diagnosis and staging of cancer and thus guides clinical therapy​ ​ 1​. However, the interpretation of these samples is inherently subjective, resulting in significant diagnostic variability​ ​ 2,3​. Moreover, in many regions of the world, access to pathologists is severely limited due to lack of trained personnel​ ​ 4​. In this regard, Artificial Intelligence (AI) based tools promise to improve the access and quality of healthcare​ ​ 5-7​. However, despite significant advances in AI research, integration of these tools into real-world cancer diagnosis workflows remains challenging because of the costs of image digitization and difficulties in deploying AI solutions​ ​ 8​ ,​ 9​. Here we propose a cost-effective solution to the integration of AI: the Augmented Reality Microscope (ARM). The ARM overlays AI-based information onto the current view of the sample through the optical pathway in real-time, enabling seamless integration of AI into the regular microscopy workflow. We demonstrate the utility of ARM in the detection of lymph node metastases in breast cancer and the identification of prostate cancer with a latency that supports real-time workflows. We anticipate that ARM will remove barriers towards the use of AI in microscopic analysis and thus improve the accuracy and efficiency of cancer diagnosis. This approach is applicable to other microscopy tasks and AI algorithms in the life sciences​ ​ 10​ and beyond​ ​ 11,12​. Microscopic examination of samples is the gold standard for the diagnosis of cancer, autoimmune diseases, infectious diseases, and more. In cancer, the microscopic examination of stained tissue sections is critical for diagnosing and staging the patient's tumor, which informs treatment decisions and prognosis. In cancer, microscopy analysis faces three major challenges. As a form of image interpretation, these examinations are inherently subjective, exhibiting considerable inter-observer and intra-observer variability​ 2,3​. Moreover, clinical guidelines​ 1​ and studies​ 13​ have begun to require quantitative assessments as part of the effort towards better patient risk stratification​ 1​. For example, breast cancer staging requires counting mitotic cells and quantification of the tumor burden in lymph nodes by measuring the largest tumor focus. However, despite being helpful in treatment planning, quantification is laborious and error-prone. Lastly, access to disease experts can be limited in both developed and developing countries​ 4​ , exacerbating the problem. As a potential solution, recent advances in AI, specifically deep learning​ 14​ , have demonstrated automated medical image analysis with performance c
translated by 谷歌翻译
对于前列腺癌患者,Gleason评分是最重要的预后因素之一,可能决定独立于分期的治疗。然而,Gleason评分基于肿瘤形态的主观显微镜检查并且具有较差的再现性。在这里,我们提出了一个深度学习系统(DLS),用于Gleason评分前列腺切除术的全幻灯片图像。我们的系统是使用来自1,226张幻灯片的1.12亿个病理学家注释的图像片段开发的,并在331个幻灯片的独立验证数据集上进行评估,其中参考标准由泌尿生殖专家病理学家建立。在验证数据集中,29名一般病理学家的平均准确度为0.61。 DLS的诊断准确率显着提高0.70(p = 0.002),并且与临床随访数据的相关性趋向于更好的患者风险分层。我们的方法可以提高格里森评分的准确性和随后的治疗决策,特别是在专业知识不可用的情况下。 DLS还超越了当前的格里森系统,以更精细地表征和定量肿瘤形态,为格里森系统本身的细化提供了机会。
translated by 谷歌翻译