Composite pin-fin heat sink for effective hotspot reduction

This current work aims to decrease temperature nonuniformity in a microprocessor. The proposed composite pin-fin heat sink design is analyzed computationally, and its functioning is compared with the conventional heat sink design. According to the heat rate, the composite heat sink is divided into two sections: the hotspot and the background section. Aluminum, copper, and graphene are chosen for the background and hotspot sections. Both noncomposite and composite heat sinks are designed with similar geometrical dimensions. DI water is used as the working fluid. They are studied for heterogeneous hotspot heat flux varying from 200 to 600 kW/m² by keeping constant background heat flux as 100 kW/m² with the inlet mass flow rate of 0.05 kg/s. Further simulations are performed for various Reynolds numbers (Re = 150, 225, 300) with a constant background and hotspot heat flux of 100 and 600 kW/m², respectively, for different inlet temperatures of 15°C, 20°C, and 25°C. The simulations are also carried out for other working fluids, such as TiO₂ and Fe₂O₃ based nanofluids with the constant volume concentration of 0.65% and 3%, respectively in the DI water, at the constant background and hotspot heat flux of 100 and 600 kW/m², respectively. The results are shown for all the above studies planned. The results suggest that composite heat sinks with graphene as a composite material and Fe₂O₃ based nanofluid yields higher heat dissipation.     

SABOS-Net: Self-supervised attention based network for automatic organ segmentation of head and neck CT images

The segmentation of Organs At Risk (OAR) in Computed Tomography (CT) images is an essential part of the planning phase of radiation treatment to avoid the adverse effects of cancer radiotherapy treatment. Accurate segmentation is a tedious task in the head and neck region due to a large number of small and sensitive organs and the low contrast of CT images. Deep learning-based automatic contouring algorithms can ease this task even when the organs have irregular shapes and size variations. This paper proposes a fully automatic deep learning-based self-supervised 3D Residual UNet architecture with CBAM(Convolution Block Attention Mechanism) for the organ segmentation in head and neck CT images. The Model Genesis structure and image context restoration techniques are used for self-supervision, which can help the network learn image features from unlabeled data, hence solving the annotated medical data scarcity problem in deep networks. A new loss function is applied for training by integrating Focal loss, Tversky loss, and Cross-entropy loss. The proposed model outperforms the state-of-the-art methods in terms of dice similarity coefficient in segmenting the organs. Our self-supervised model could achieve a 4% increase in the dice score of Chiasm, which is a small organ that is present only in a very few CT slices. The proposed model exhibited better accuracy for 5 out of 7 OARs than the recent state-of-the-art models. The proposed model could simultaneously segment all seven organs in an average time of 0.02 s. The source code of this work is made available at https://github.com/seeniafrancis/SABOSNet .