> top > docs > PMC:7782580 > spans > 49852-59677 > annotations

PMC:7782580 / 49852-59677 JSONTXT

Annnotations TAB JSON ListView MergeView

LitCovid-PubTator

Id Subject Object Predicate Lexical cue tao:has_database_id
350 4563-4566 Chemical denotes ths MESH:D013910
351 4644-4647 Chemical denotes ths MESH:D013910
352 5142-5145 Chemical denotes ths MESH:D013910
353 5210-5213 Chemical denotes ths MESH:D013910
355 5680-5682 Chemical denotes BN
358 91-99 Disease denotes COVID-19 MESH:C000657245
359 254-262 Disease denotes COVID-19 MESH:C000657245
361 6782-6809 Disease denotes cross-entropy loss function MESH:C537866
363 9131-9134 Gene denotes CGB Gene:93659

LitCovid-sentences

Id Subject Object Predicate Lexical cue
T371 0-31 Sentence denotes Model architecture and training
T372 32-263 Sentence denotes In this study, we proposed a modular CNNCF to identify the COVID-19 cases in the medical images and a CNNRF to determine the relationships between the lesion areas in the medical images and the five clinical indicators of COVID-19.
T373 264-340 Sentence denotes Both proposed frameworks consisted of two units (ResBlock-A and ResBlock-B).
T374 341-443 Sentence denotes The CNNCF and CNNRF had unique units, namely the control gate block and regressor block, respectively.
T375 444-569 Sentence denotes Both frameworks were implemented using two NVIDIA GTX 1080TI graphics cards and the open-source PyTorch framework.ResBlock-A:
T376 570-590 Sentence denotes As discussed in ref.
T377 591-732 Sentence denotes 57, the residual block is a CNN-based block that allows the CNN models to reuse features, thus accelerating the training speed of the models.
T378 733-893 Sentence denotes In this study, we developed a residual block (ResBlock-A) that utilized a skip-connection for retaining features in different layers in the forward propagation.
T379 894-1106 Sentence denotes This block (Fig. 6a) consisted of a multiple-input multiple-output structure with two branches (an upper branch and a bottom branch), where input 1 and input 2 have the same size, but the values may be different.
T380 1107-1200 Sentence denotes In contrast, output 1 and output 2 had the same size, but output 1 did not have a ReLu layer.
T381 1201-1328 Sentence denotes The upper branch consisted of a max-pooling layer (Max-Pooling), a convolution layer (Conv 1 × 1), and a batch norm layer (BN).
T382 1329-1563 Sentence denotes The Max-Pooling had a kernel size of 3 × 3 and a stride of 2 to downsample the input 1 for retaining the features and ensuring the same size as the output layer before the element-wise add operation was conducted in the bottom branch.
T383 1564-1742 Sentence denotes The Conv 1 × 1 consisted of multiple 1 × 1 convolution kernels with the same number as that in the second convolution layer in the bottom branch to adjust the number of channels.
T384 1743-1892 Sentence denotes The BN used a regulation function to ensure the input in each layer of the model followed a normal distribution with a mean of 0 and a variance of 1.
T385 1893-1983 Sentence denotes The bottom branch consisted of two convolution layers, two BN layers, and two ReLu layers.
T386 1984-2192 Sentence denotes The first convolution layer in the bottom branch consisted of multiple 3 × 3 convolution kernels with a stride of 2 and a padding of 1 to reduce the size of the feature maps when local features were obtained.
T387 2193-2329 Sentence denotes The second convolution layer in the bottom branch consisted of multiple 3 × 3 convolution kernels with a stride of 1 and a padding of 1.
T388 2330-2449 Sentence denotes The ReLu function was used as the activation function to ensure a non-linear relationship between the different layers.
T389 2450-2584 Sentence denotes The output of the upper branch and the output of the bottom branch after the second BN were fused using an element-wise add operation.
T390 2585-2671 Sentence denotes The fused result was output 1, and the fused result after the ReLu layer was output 2.
T391 2672-2720 Sentence denotes Fig. 6 The four units of the proposed framework.
T392 2721-3401 Sentence denotes a ResBlock-A architecture, containing two convolution layers with 3 × 3 kernels, one convolution layer with a 1 × 1 kernel, three batch normalization layers, two ReLu layers, and one max-pooling layer with a 3 × 3 kernel. b ResBlock-B architecture; the basic unit is the same as the ResBlock-A, except for output 1. c The Control Gate Block has a synaptic-based frontend architecture that controls the direction of the feature map flow and the overall optimization direction of the framework. d The Regressor architecture is a skip-connection architecture containing one convolution layer with 3 × 3 kernels, one batch normalization layer, one ReLu layer, and three linear layers.
T393 3402-3413 Sentence denotes ResBlock-B:
T394 3414-3550 Sentence denotes The ResBlock-B (Fig. 6b) was a multiple-input single-output block that was similar to the ResBlock-A, except that there was no output 1.
T395 3551-3701 Sentence denotes The value of the stride and padding in each layer of the ResBlock-A and ResBlock-B could be adjusted using hyper-parameters based on the requirements.
T396 3702-3721 Sentence denotes Control Gate Block:
T397 3722-3975 Sentence denotes As shown in Fig. 6c, the Control Gate Block was a multiple-input single-output block consisting of a predictor module, a counter module, and a synapses module to control the optimization direction while controlling the information flow in the framework.
T398 3976-4100 Sentence denotes The pipeline of the predictor module is shown in Supplementary Fig. 19a, where the Input S1 is the output of the ResBlock-B.
T399 4101-4202 Sentence denotes The Input S1 was then flattened to a one-dimensional feature vector as the input of the linear layer.
T400 4203-4309 Sentence denotes The output of the linear layer was converted to a probability of each category using the softmax function.
T401 4310-4458 Sentence denotes A sensitivity calculator used the Vpred and Vtrue as inputs to calculate the TP, TN, FP, and false-negative (FN) rates to calculate the sensitivity.
T402 4459-4558 Sentence denotes The sensitivity calculation was followed by a step function to control the output of the predictor.
T403 4559-4705 Sentence denotes The ths was a threshold value; if the calculated sensitivity was greater or equal to ths, the step function output 1; otherwise, the output was 0.
T404 4706-4787 Sentence denotes The counter module was a conditional counter, as shown in Supplementary Fig. 19b.
T405 4788-4853 Sentence denotes If the input n was zero, the counter was cleared and set to zero.
T406 4854-4892 Sentence denotes Otherwise, the counter increased by 1.
T407 4893-4927 Sentence denotes The output of the counter was num.
T408 4928-5077 Sentence denotes The synapses block mimicked the synaptic structure, and the input variable num was similar to a neurotransmitter, as shown in Supplementary Fig. 19c.
T409 5078-5137 Sentence denotes The input num was the input parameter of the step function.
T410 5138-5266 Sentence denotes The ths was a threshold value; if the input num was greater or equal to ths, the step function output 1; otherwise, it output 0.
T411 5267-5370 Sentence denotes An element-wise multiplication was performed between the input S1 and the output of the synapses block.
T412 5371-5426 Sentence denotes The multiplied result was passed on to a discriminator.
T413 5427-5527 Sentence denotes If the sum of each element in the result was not zero, the Input S1 was passed on to the next layer.
T414 5528-5582 Sentence denotes Otherwise, the input S1 information was not passed on.
T415 5583-5599 Sentence denotes Regressor block:
T416 5600-5728 Sentence denotes The regressor block consisted of multiple linear layers, a convolution layer, a BN layer, and a ReLu layer, as shown in Fig. 6d.
T417 5729-5871 Sentence denotes A skip-connection architecture was adopted to retain the features and increase the ability of the block to represent non-linear relationships.
T418 5872-6002 Sentence denotes The convolution block in the skip-connection structure was a convolution layer with multiple numbers of 1 × 1 convolution kernels.
T419 6003-6158 Sentence denotes The number of the convolution kernels was the same as that of the output size of the second linear layer to ensure the consistency of the vector dimension.
T420 6159-6260 Sentence denotes The input size and output size of each linear layer were adjustable to be applicable to actual cases.
T421 6261-6403 Sentence denotes Based on the four blocks, two frameworks were designed for the classification task and regression task, respectively.Classification framework:
T422 6404-6469 Sentence denotes The CNNCF consisted of stage I and stage II, as shown in Fig. 3a.
T423 6470-6541 Sentence denotes Stage I was duplicated Q times in the framework (in this study, Q = 1).
T424 6542-6664 Sentence denotes It consisted of multiple ResBlock-A with a number of M (in this study, M = 2), one ResBlock-B, and one Control Gate Block.
T425 6665-6768 Sentence denotes Stage II consisted of multiple ResBlock-A with a number of N (in this study, N = 2) and one ResBlock-B.
T426 6769-6915 Sentence denotes The weighted cross-entropy loss function was used and was minimized using the SGD optimizer with a learning rate of a1 (in this study, a1 = 0.01).
T427 6916-7166 Sentence denotes A warm-up strategy58 was used in the initialization of the learning rate for a smooth training start, and a reduction factor of b1 (in this study, b1 = 0.1) was used to reduce the learning rate after every c1 (in this study, c1 = 10) training epochs.
T428 7167-7305 Sentence denotes The model was trained for d1 (in this study, d1 = 40) epochs, and the model parameters saved in the last epoch was used in the test phase.
T429 7306-7327 Sentence denotes Regression framework:
T430 7328-7400 Sentence denotes The CNNRF (Fig. 3b) consisted of two parts (stage II and the regressor).
T431 7401-7645 Sentence denotes The inputs to the regression framework were the images of the lesion areas, and the output was the corresponding vector with five dimensions, representing the five clinical indicators (all clinical indicators were normalized to a range of 0–1).
T432 7646-7750 Sentence denotes The stage II structure was the same as that in the classification framework, except for some parameters.
T433 7751-7894 Sentence denotes The loss function was the MSE loss function, which was minimized using the SGD optimizer with a learning rate of a2 (in this study, a2 = 0.01).
T434 7895-8143 Sentence denotes A warm-up strategy was used in the initialization of the learning rate for a smooth training start, and a reduction factor of b2 (in this study, b2 = 0.1) was used to reduce the learning rate after every c2 (in this study, c2 = 50) training epochs.
T435 8144-8288 Sentence denotes The framework was trained for d2 (in this study, d2 = 200) epochs, and the model parameters saved in the last epoch were used in the test phase.
T436 8289-8334 Sentence denotes The workflow of the classification framework.
T437 8335-8408 Sentence denotes The workflow of the classification framework was demonstrated in Fig. 3c.
T438 8409-8537 Sentence denotes The preprocessed images are sent to the first convolution block to expand the channels and processed as the input for the CNNCF.
T439 8538-8680 Sentence denotes Given the input Fi with a size of M × N × 64, the stage I output feature maps F′i with a size of M/8 × N/8 × 256 in the default configuration.
T440 8681-8820 Sentence denotes As we introduced above, the Control Gate Block controls the optimization direction while controlling the information flow in the framework.
T441 8821-8903 Sentence denotes If the Control Gate Block is open, the feature maps F′i are passed on to stage II.
T442 8904-9209 Sentence denotes Given the input F′i, the stage II output the feature maps F″i with a size of M/64 × N/64 × 512 which is defined as follows:1 Fi′=S1(Fi)Fi″=S2(Fi′)⊗CGB(Fi′),where S1 denotes the stage I block, S2 denotes the stage II block, and CGB is the Control Gate Block. ⊗ is the element-wise multiplication operation.
T443 9210-9366 Sentence denotes Stage II is Followed by a global average pooling layer (GAP) and a fully connect layer (FC layer) with a softmax function to generate the final predictions.
T444 9367-9457 Sentence denotes Given F″i as input, the GAP is adopted to generate a vector Vf with a size of 1 × 1 × 512.
T445 9458-9825 Sentence denotes Given Vf as input, the FC layer with the softmax function outputs a vector Vc with a size of 1 × 1 × C.2 Vf=GAPFi′Vc=SMaxFCVf,where GAP is the global average pooling layer, the FC is the fully connect layer, SMax is the softmax function, Vf is the feature vector generated by the GAP, Vc is the prediction vector, and C is the number of case types used in this study.