Search results for: Nuri pyramid

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 135

Authors: M. Verde, G. Falzarano

Abstract:

The paper examines the connection between corporate social responsibility (CSR), capability approach and poverty reduction; in particular, the local employment development (LED) by way of CSR initiatives. The joint action of LED/CSR results in a win-win situation, not only for the enterprises but also for all the stakeholders involved; in this regard, subsidiarity and coordination between national and regional/local authorities are central to a socially-oriented market economy. In the first section, the CSR is analysed on the basis of its social function in the fight against poverty, as a 'capabilities deprivation'. In the central part, the attention is focused on the relationship between CSR and LED; ergo, on the role of the enterprises in fostering capabilities development (the employment). Besides, all the potential solutions are presented, stressing the possible combinations, in the last part. The benchmark is the enterprise as an economic and a social institution: the business should not be combined with profit merely, paying more attention to its sustainable impact and social contribution. In which way could it be possible? The answer is the CSR. The impact of CSR on poverty reduction is still little explored. The companies help to reduce poverty through economic contribution, human rights and social inclusion; hence, the business becomes an 'agent of development' in order to fight against 'inequality'. The starting point is the pyramid of social responsibility, where ethic and philanthropic responsibilities involve programmes and actions aimed at personal development of the individuals, improving human standard of living in all forms, including poverty, when people do not have a choice between different 'life options', ranging from level of education to employment. At this point, CSR comes into play and works on two dimensions: poverty reduction and poverty prevention, by means of a series of initiatives: first of all, job creation and precarious work reduction. Empowerment of the local actors, financial support and combination of top down and bottom up initiatives are some of CSR areas of activity. Several positive effects occur on individual levels of educations, access to capital, individual health status, empowerment of youth and woman, access to social networks and it was observed that these effects depend on the type of CSR strategy. Indeed, CSR programmes should take into account fundamental criteria, such as the transparency, the information about benefits, a coordination unit among institutions and more clear guidelines. In this way, the advantages to the corporate reputation and to the community translate into a better job matching on the labour market, inter alia. It is important to underline that the success depends on the specific measures of the areas in question, by adapting them to the local needs, in light of general principles and index; therefore, the concrete commitment of the all stakeholders involved is decisive in order to achieve the goals. The enterprise would represent a concrete contribution for the pursuit of sustainable development and for the dissemination of a social and well being awareness.

Keywords: capability approach, local employment development, poverty, social inclusion

Procedia PDF Downloads 145

Authors: Jaeyoung Lee

Abstract:

Autonomous driving systems require high reliability to provide people with a safe and comfortable driving experience. However, despite the development of a number of vehicle sensors, it is difficult to always provide high perceived performance in driving environments that vary from time to season. The image segmentation method using deep learning, which has recently evolved rapidly, provides high recognition performance in various road environments stably. However, since the system controls a vehicle in real time, a highly complex deep learning network cannot be used due to time and memory constraints. Moreover, efficient networks are optimized for GPU environments, which degrade performance in embedded processor environments equipped simple hardware accelerators. In this paper, a semantic segmentation network, matrix multiplication accelerator network (MMANet), optimized for matrix multiplication accelerator (MMA) on Texas instrument digital signal processors (TI DSP) is proposed to improve the recognition performance of autonomous driving system. The proposed method is designed to maximize the number of layers that can be performed in a limited time to provide reliable driving environment information in real time. First, the number of channels in the activation map is fixed to fit the structure of MMA. By increasing the number of parallel branches, the lack of information caused by fixing the number of channels is resolved. Second, an efficient convolution is selected depending on the size of the activation. Since MMA is a fixed, it may be more efficient for normal convolution than depthwise separable convolution depending on memory access overhead. Thus, a convolution type is decided according to output stride to increase network depth. In addition, memory access time is minimized by processing operations only in L3 cache. Lastly, reliable contexts are extracted using the extended atrous spatial pyramid pooling (ASPP). The suggested method gets stable features from an extended path by increasing the kernel size and accessing consecutive data. In addition, it consists of two ASPPs to obtain high quality contexts using the restored shape without global average pooling paths since the layer uses MMA as a simple adder. To verify the proposed method, an experiment is conducted using perfsim, a timing simulator, and the Cityscapes validation sets. The proposed network can process an image with 640 x 480 resolution for 6.67 ms, so six cameras can be used to identify the surroundings of the vehicle as 20 frame per second (FPS). In addition, it achieves 73.1% mean intersection over union (mIoU) which is the highest recognition rate among embedded networks on the Cityscapes validation set.

Keywords: edge network, embedded network, MMA, matrix multiplication accelerator, semantic segmentation network

Procedia PDF Downloads 133