The effectiveness of the developed Bi-LSTM-based modified genetic was tested on an online benchmark database. The undertaken database has 25,272 images with 870,301 brain slices, and the acquired images were then labeled by the annotators as five classes: subdural, intraparenchymal, subarachnoid, epidural, and intraventricular. In the acquired database, the annotators did not have details about the patient’s medical history, the acuity of their symptoms, prior examinations, OR the patient’s age. The brain images of the acquired database are shown in Figure 2.

After the acquisition of the brain images, region segmentation was performed by employing Otsu’s thresholding, which helped determine the maximum separability of the classes such as subdural, intraparenchymal, subarachnoid, epidural, and intraventricular (Feng et al., 2017). In this technique, the selected pixel intensity value of the image is related to the average pixel intensity value to improve the segmentation results. First, the acquired 3D brain scans were portioned into two binary regions, i.e., dark T 1 and light T 0 regions, which were mathematically represented in Eqs 1, 2, with l being represented as histogram bins.

In this scenario, the threshold value was set as t = 0.5 , where it effectively discriminated between the overlapping intracranial hemorrhage classes (Al-Rahlawee and Rahebi, 2021; Tan et al., 2021; Dutta et al., 2022). The optimal threshold value t = 0.5 was found by minimizing the weight group variance based on the distinct group’s p ( i ) probability, and it was mathematically represented in Eq. 3.

In the 3D brain images, the variance σ b 2 ( t ) a n d σ f 2 ( t ) , mean μ b ( t ) a n d μ f ( t ) , and weight w b ( t ) a n d w f ( t ) of the light and dark regions T 0 and T 1 were computed using Eqs 4, 5.

The optimal threshold was found with lower class variance σ w 2 , and was mathematically represented in Eq. 6. After the segmentation of the intracranial hemorrhage regions, feature extraction was performed using GLTP descriptors and Tamura features.

After region segmentation, the discriminative vectors were extracted by implementing the GLTP descriptor and Tamura features. In this manuscript, three Tamura features f T a m u r a like directionality, contrast, and coarseness were implemented for the extraction of discriminative vectors from the segmented regions. First, directionality generated the edge probability of the image histograms by quantizing the edge angles, with this procedure helping to sharpen the image edges. Second, contrast-enhanced the gray level in the segmented regions by distributing the pixel intensity value. Third, coarseness mainly relied on the texture scale and repetition rates in the brain images to find patterns with different structures. A total of 3,492 vectors were extracted from the segmented region utilizing the Tamura features (Karmakar et al., 2017; Tao and Lu, 2018; Das et al., 2019; Yu et al., 2020).

In addition to this, GLTP is a texture descriptor that encodes the local texture of the segmented images by quantizing the pixel intensity value into three discrimination levels and by estimating the gradient magnitude. The GLTP ensures the texture patterns even under conditions of illumination variations and random noise. First, the horizontal and vertical approximations ( G i , G j ) of the segmented images were obtained using the Sobel Feldman operator. Then, the gradient magnitude G i , j of each brain image was obtained by integrating G i and G j – this was mathematically represented in Eq. 7.

A threshold value t was used around the Center Gradient G c value of 3 × 3 neighborhood image pixels to distinguish both smooth and highly textured regions from G i , j , − this was mathematically specified in Eq. 8 (Holder and Tapamo, 2017; Fekri-Ershad, 2020).

Where S G L T P is the quantized value of the neighborhood image pixels. The gradient values below G c − t were quantized to −1, gradient values above G c + t were quantized to 1 and then the gradient values falling between G c + t and G c − t were quantized to zero. The obtained three-level discrimination coding was high-dimensional, and further, S G L T P was categorized into –ve N G L T P and + ve P G L T P decimal codes, which were mathematically given in Eqs 9, 10.

In the next step, the GLTP histogram values were computed from N G L T P and P G L T P for each brain image m × n , as mentioned in Eqs 11, 12.

Where ( r , c ) denote rows and columns in the GLTP-encoded images, ( M , N ) specify the width and height of the images, and α = τ represents the GLTP code, which ranges between zero and 255. Finally, H N G L T P and H P G L T P values were integrated to generate the final vectors F G L T P . A total of 1,926 vectors were extracted using the GLTP texture descriptor. By using the feature level fusion technique, the extracted vectors of the GLTP descriptor and Tamura features were integrated, and further dimensionality reduction was carried out by employing a modified genetic algorithm.

After extracting 5,418 discriminative vectors, optimization was carried out by implementing a modified genetic algorithm. In the existing research studies, a conventional genetic algorithm was used to determine the relevant vectors for disease classification. In recent decades, many variations of genetic operations have been used to further improve optimization performance. An extensively utilized method in the traditional genetic algorithm is entropy, which measures the database homogeneities to identify the mutual information among the extracted vectors, which helps in determining the active vectors.

However, a modified genetic algorithm uses a simple entropy function to find the active vectors. In the proposed algorithm, the conditional entropy value was determined for both the output vectors and the regularized vectors based on an infinite feature selection technique. The implemented algorithm aims at identifying the maximum relevance between the output vectors and the regularized vectors, which reduces the redundancy within the regularized vectors. In a modified genetic algorithm, the initial population is equal to the subset of the regularized vectors that are assumed to be the active vectors of the pre-defined outputs. In addition, the fitness function is determined based on the entropy measure by improving the mutual state of the conditional entropy function between the output and the regularized vectors, as mentioned in Eq. 13.

The modified genetic algorithm stops when it reaches the maximum number of generations, which is 100. γ indicates the classification accuracy, α ϵ [ 0 , 1 ] , β = 1 − α , T f indicate the extracted vectors, and l c represents the chromosome length. In addition, the crossover operations improved the diversity of genetics to identify the active regularized vectors (Mirjalili, 2019; Mirjalili et al., 2020; Katoch et al., 2021). The flow diagram of the modified genetic algorithm is specified in Figure 3.

In a modified genetic algorithm, the selection operations performed for identifying the active vectors are performed by reducing the redundancy based on the fitness function. The assumed parameters of the modified genetic algorithm are: mutation function is 0.1, population type is bit string, generation is 100, fitness function is entropy, elite count is 2, crossover function is 0.80, and population size is equal to the extracted vector length. From the extracted 5,418 vectors, a total of 2,932 vectors were selected for classification. The fitness comparison between the genetic algorithm and the modified genetic algorithm is shown in Figure 4.

In the final phase, the 2,932 selected vectors were fed to the Bi-LSTM network to categorize the subtypes of intracranial hemorrhage: subdural, intraparenchymal, subarachnoid, epidural, and intraventricular. The LSTM is an updated version of the RNN, and it uses memory cells to control three gates: input, output, and forget gates. This helps store the temporal state. In a conventional LSTM network, the input and output gates are utilized to handle the input and output flows of the memory cells. Further, the forget gate is connected to the memory cells to transmit the output information from the current neuron to the subsequent neurons. The information is stored in the memory cells, while the input has higher activation. Additionally, the information is transferred to the next neuron while the output has higher activation. The LSTM gates input i t , forget f t , cell c t , and output gate o t are mathematically represented in Equations (14–17). The architecture of the Bi-LSTM network is shown in Figure 5 (Alhussein et al., 2020; Shahid et al., 2020).

Where, ⊙ denotes pointwise multiplication, W and b are work coefficient values, a t = A [ t , . ] ∈ ℝ F denote quasi-periodic vectors, h t − 1 is the output of the previous LSTM unit, tanh ( . ) denotes a hyperbolic tangent function, and σ ( . ) indicates a sigmoid function. The output of the LSTM h t is mathematically expressed in Eq. 18.

The element h t contains information about the previous time steps of an output gate and a cell state. The cell state c t | t = 1 , 2 , .. T learns memory information of a t = A [ t , . ] ∈ ℝ F for a longer and shorter period based on dependency relations. In this work, the Bi-LSTM was implemented to address the concerns of the conventional LSTM, where it perfectly works on the previous content, but failed to use future content. In the Bi-LSTM network, the input flows in both forward and backward directions that helps in preserving the future and past information. The parameters considered in the Bi-LSTM network are as follows: maximum epochs are 100, execution environment is graphics processing units, gradient threshold is one, learning rate is 0.001, and batch size is 27. Hence, the extensive experimental investigation of the Bi-LSTM-based modified genetic algorithm is presented in the next section.

The segmentation outcomes of the proposed framework are specified in Table 1. The adopted segmentation model;Otsu’s thresholding effectiveness was compared with three existing models: FCM, K-means, and kernel-based FCM. According to Table 1, Otsu’s thresholding model obtained 88.42% of the Dice coefficient and 82.03% of the Jaccard coefficient, where the obtained results were the maximum with respect to the existing models. Otsu’s thresholding considers the maximum inter-class variance between the target images and the background region based on the threshold selection rule. The graphical representation of the segmentation results is shown in Figure 6.

The classification results of the proposed model are specified in Tables 2, 3. Particularly, the classification results of different classifiers with and without feature optimization techniques are given in Table 2. As specified there, the experimental results of different classifiers: Naïve Bayes, Random Forest, SVM, RNN, LSTM, and Bi-LSTM are given with and without utilizing a feature optimization technique called the modified genetic algorithm. After feature extraction, the direct feeding of vectors to the Bi-LSTM model obtained 98.76% of the F1 score, 97.72% of the MCC, 98.21% of sensitivity, 97.69% of classification accuracy, and 97.77% of specificity, which are all higher compared to other classifiers.

In addition, feeding optimal vectors selected by the modified genetic algorithm to the Bi-LSTM model achieved 99.30% of the F1 score, 99.12% of the MCC, 99.40% of sensitivity, 99.80% of accuracy, and 99.48% of specificity. The obtained experimental results are higher compared to the existing machine learning classifiers: Naïve Bayes, Random Forest, SVM, RNN, and LSTM network in intracranial hemorrhage detection. The graphical representation of the classification results by varying the classifiers is shown in Figure 7. In Bi-LSTM, the input flowed in two directions, which preserved the past and future feature information, helping to achieve better classification results.

Additionally, the classification results obtained by varying the optimizers are represented in Table 3. In this scenario, the Bi-LSTM network is evaluated with different optimizers such as Particle Swarm Optimizer (PSO), Artificial Bee Colony (ABC), Firefly Optimizer, Genetic Algorithm, Grasshopper Optimization Algorithm (GOA), and Modified Genetic Algorithm. By looking at Table 3, the Bi-LSTM network with a modified genetic algorithm has obtained higher outcomes: 99.30% of the F1 Score, 99.12% of the MCC, 99.40% of sensitivity, 99.80% of accuracy, and 99.48% of specificity. In this research, the modified genetic algorithm effectively selected optimal vectors from the total extracted vectors, which reduced the computational complexity to linear based on the input size and order of magnitude. On the other hand, the computational time was 54.28 s, which is lower compared to the existing models. A graphical representation of the classification results by varying the optimizers is shown in Figure 8.

The experimental outcomes of the Bi-LSTM-based modified genetic algorithm for different cross-fold validations are indicated in Table 4. As shown there, the developed Bi-LSTM-based modified genetic algorithm was tested by different k-fold cross-validations, such as 3-fold, 5-fold, 8-fold, and 10-fold. According to Table 4, the Bi-LSTM-based modified genetic algorithm achieved better classification results 5-fold with respect to other cross-fold validations. In this research, the cross-fold validations improved the computational time and decreased the variance and bias of the Bi-LSTM-based modified genetic algorithm. The graphical representation of the Bi-LSTM-based modified genetic algorithm for different cross-fold validations is shown in Figure 9.

The numerical investigation between existing algorithms and the proposed Bi-LSTM based modified genetic algorithm is indicated in Table 5. Burduja et al. (2020) integrated both ResNeXt-101 and Bi-LSTM for intracranial hemorrhage detection in 3D-CT brain images. In the resulting phase, the developed deep learning model obtained 72.86% sensitivity, 97.83% accuracy, and 99% specificity. Wang et al. (2021) implemented a 2D CNN model for better detection of intracranial hemorrhage diseases. The extensive experiments confirmed that the implemented model had 95.84% sensitivity, 95% accuracy, and 94.85% specificity. Anupama et al. (2022) introduced a synergistic deep-learning model that achieved 95.73% accuracy, 97.78% specificity, and 94.01% sensitivity. Sengupta and Alzbutas (2022) combined the Optimized Gated Recurrent Unit (OGRU) with the Cuckoo Search Algorithm (CSA) for the effective detection of intracranial hemorrhage in the 3D-CT brain images. The simulation outcomes demonstrated that the ORGU-CSO model obtained 99.25% sensitivity, 99.36% accuracy, and 99.40% specificity. Asif et al. (2023) initially used the ResNet101-V2 model to extract potential vectors from the slices. Then, the Inception-V4 model was used to capture the spatial information from the second path. Finally, the outputs of the ResNet101-V2 and Inception-V4 models were fed to the light gradient boosting machine for intracranial hemorrhage detection, and the presented model achieved 96.50% sensitivity and 97.70% accuracy on the RSNA 2019 database. Regarding the comparative works, the Bi-LSTM-based modified genetic algorithm achieved high classification results in intracranial hemorrhage detection with 99.40% sensitivity, 99.80% accuracy, and 99.48% specificity.

As mentioned earlier, feature optimization and classification are integral parts of this manuscript. The proposed modified genetic algorithm used a simple entropy function to find the active vectors from the total extracted vectors. The conditional entropy value was calculated for the output vectors and the regularized vectors in the modified genetic algorithm based on an infinite feature selection technique. The modified genetic algorithm found the maximum relevance between the output vectors and the regularized vectors, which reduced the redundancy of the regularized vectors and the computation time. The computation time of the proposed model was 54.28 s, which is limited compared to the existing models. The selected vectors were fed to the Bi-LSTM model for disease-type classification. The effectiveness of the proposed framework is depicted in Tables 1–5.