Abstract: A cell image segmentation method using scribble labels includes iteratively pre-training via an image segmentation network (U-Net) using a cell image and scribble labels indicating a cell region and a background region as training data, calculating an exponential moving average (EMA) of image segmentation prediction probabilities at a predetermined interval during the pre-training, self-training by assigning the cell region and the background region for which the EMA of image segmentation prediction probabilities is over a preset threshold to be a pseudo-label, and iteratively refining the image segmentation prediction probability based on a scribbled loss (Lsp) obtained through a result of the training and an unscribbled loss (Lup). Accordingly, it is possible to achieve cell image segmentation with high reliability using only scribble labels.

Abstract: Provided is a method of operating an apparatus for prostate cancer analysis operated by at least one processor, the method including: receiving digital slide images prepared from serial sections of a prostatectomy specimen, and a gross image of the serial sections; acquiring prostate cancer-related histological information of each received digital slide image using an artificial neural network model trained to infer histological information from the digital slide images; generating digital pathology images by displaying the prostate cancer-related histological information inferred from the artificial neural network model on each digital slide image; and providing a histological mapping image in which a tumor region extracted from each digital pathology image is mapped to a gross image of the corresponding section.

Abstract: A cell image segmentation method using scribble labels includes iteratively pre-training via an image segmentation network (U-Net) using a cell image and scribble labels indicating a cell region and a background region as training data, calculating an exponential moving average (EMA) of image segmentation prediction probabilities at a predetermined interval during the pre-training, self-training by assigning the cell region and the background region for which the EMA of image segmentation prediction probabilities is over a preset threshold to be a pseudo-label, and iteratively refining the image segmentation prediction probability based on a scribbled loss (Lsp) obtained through a result of the training and an unscribbled loss (Lup). Accordingly, it is possible to achieve cell image segmentation with high reliability using only scribble labels.

Abstract: Provided is a substrate processing apparatus in which parts are selectively lifted according to the purpose or subject of maintenance/repair during a maintenance/repair operation. The substrate processing apparatus includes: a chamber; a first cover and a second cover on the chamber; a lifting device connected to the first cover and configured to raise and lower the first cover; and a connection region. When the lifting device and the second cover are connected to each other via the connection region or the first and second covers are connected to each other via the connection region, the first and second covers are raised and lowered by the lifting device.

Abstract: Provided is a cooling device capable of controlling the temperature of an upper portion of a reactor, or more particularly, a gas supply device, for example, a shower head. The cooling device includes a separator configured to uniformly and efficiently cool the gas supply device.

Abstract: Provided is a substrate processing apparatus in which parts are selectively lifted according to the purpose or subject of maintenance/repair during a maintenance/repair operation. The substrate processing apparatus includes: a chamber; a first cover and a second cover on the chamber; a lifting device connected to the first cover and configured to raise and lower the first cover; and a connection region. When the lifting device and the second cover are connected to each other via the connection region or the first and second covers are connected to each other via the connection region, the first and second covers are raised and lowered by the lifting device.

Abstract: A system and method are provided for a parallel processing of the Hamilton-Jacobi equation. A numerical method is provided to solve the Hamilton-Jacobi equation that can be used with various parallel architectures and an improved Godunov Hamiltonian computation.

Abstract: A system and method are provided for a parallel processing of the Hamilton-Jacobi equation. A numerical method is provided to solve the Hamilton-Jacobi equation that can be used with various parallel architectures and an improved Godunov Hamiltonian computation.

Abstract: A lift pin driving device and a manufacturing apparatus having the device are provided. The device includes drive unit including a single drive motor that drives a pin plate, a plurality of timing belts and a plurality of pulleys. The pin plate, which supports a plurality of lift pins thereon, is moved by the pulleys, operated in conjunction with the motor through the timing belts. A tensioner controls a tension of the timing belts. The tensioner may be controlled to provide precise rectilinear movement without leaning, and to prevent the timing belts from sagging. The device efficiently controls the tension of the timing belts and allows the lift pins to be precisely moved upwards or downwards such that a substrate positioned thereon may maintain a horizontal position while being moved upwards or downwards.

Abstract: A substrate processing apparatus includes first and second transfer chambers, first and second load lock chambers for exchanging one or more substrates with respective ones of first and the second transfer chambers, and a substrate transfer unit, located between the first and second load lock chambers, for transferring the one or more substrates to the first and second load lock chambers.

Abstract: A system and method are provided for a parallel processing of the Hamilton-Jacobi equation.

Abstract: A substrate processing apparatus includes a chamber having a process space, a support plate in the chamber to support a substrate, a shower head above the support plate and having a body with an opened lower part, and a spray plate connected to the lower part of the body to supply source gas above the support plate. The apparatus further includes a sensing unit having a sensor and an elastic member. One end of the sensor is in contact with an upper surface of the spray plate. The elastic member provides elastic force to the sensor in a direction toward the spray plate.

Abstract: A substrate processing apparatus includes first and second transfer chambers, first and second load lock chambers for exchanging one or more substrates with respective ones of first and the second transfer chambers, and a substrate transfer unit, located between the first and second load lock chambers, for transferring the one or more substrates to the first and second load lock chambers.

Abstract: A lift pin driving device and a manufacturing apparatus having the device are provided. The device includes drive unit including a single drive motor that drives a pin plate, a plurality of timing belts and a plurality of pulleys. The pin plate, which supports a plurality of lift pins thereon, is moved by the pulleys, operated in conjunction with the motor through the timing belts. A tensioner controls a tension of the timing belts. The tensioner may be controlled to provide precise rectilinear movement without leaning, and to prevent the timing belts from sagging. The device efficiently controls the tension of the timing belts and allows the lift pins to be precisely moved upwards or downwards such that a substrate positioned thereon may maintain a horizontal position while being moved upwards or downwards.