Enhanced Watershed Segmentation Algorithm-Based Modified ResNet50 Model for Brain Tumor Detection

Sharma, Arpit; Nandal, Amita; Koundal, Deepika; Bogatinoska, Dijana Capeska; Alyami, Hashem

doi:10.1155/2022/7348344

Cited by 50 publications

(23 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among MLMs, convolutional neural networks with deep learning approaches have been previously reported for medical images [20]. One approach, ResNet50, emerged as superior in image classi cation tasks [21,22] while SVM classi cation was judged useful for discriminating between two classes by making a decision boundary with one or more feature vectors [23].…”

Section: Discussionmentioning

confidence: 99%

A machine learning model to predict the histology of retroperitoneal lymph node dissection specimens

Nitta

Kojima

Gido

et al. 2023

Preprint

View full text Add to dashboard Cite

Background While post-chemotherapy retroperitoneal lymph node dissection (PC-RPLND) benefits patients with teratoma or viable germ cell tumors (GCT), it becomes overtreatment if necrosis is detected in PC-RPLND specimens. Serum microRNA-371a-3p correctly predicts residual viable GCT with 100% sensitivity but residual teratoma in PC-RPLND specimens using current modalities remains difficult. Therefore, we developed a machine learning model using CT imaging and clinical variables to predict the presence of residual teratoma in PC-RPLND specimens. Methods We included 58 patients who underwent PC-RPLND between 2005 and 2019 at the University of Tsukuba Hospital. On CT imaging, 155 lymph nodes were identified as regions of interest (ROIs). The ResNet50 algorithm and/or Support Vector Machine (SVM) classification were applied and a nested, 3-fold cross-validation protocol was used to determine classifier accuracy. Results PC-RPLND specimen analysis revealed 35 patients with necrosis and 23 patients with residual teratoma while histology of 155 total ROIs showed necrosis in 84 ROIs and teratoma in 71 ROIs. The ResNet50 algorithm, using CT imaging, achieved a diagnostic accuracy of 80.0%, corresponding to a sensitivity of 67.3%, a specificity of 90.5%, and an AUC of 0.84 while SVM classification using clinical variables achieved a diagnostic accuracy of 74.8%, corresponding to a sensitivity of 59.0%, a specificity of 88.1%, and an AUC of 0.84. Conclusions Our machine learning models reliably distinguish between necrosis and residual teratoma in clinical PC-RPLND specimens.

show abstract

Section: Discussionmentioning

confidence: 99%

A machine learning model to predict the histology of retroperitoneal lymph node dissection specimens

Nitta

Kojima

Gido

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The residual module is innovatively proposed in ResNet50, which effectively solves the problem of deep network degradation with deepening layers in convolutional neural networks 3 . It has been widely used in recent years, see 1,[4][5][6]8,[10][11][12][13] . Therefore, ResNet50 is chosen as the basic network in this paper.…”

Section: Model Building 21 Dual Channel Resnet50 Networkmentioning

confidence: 99%

Satellite pose estimation network based on dual-channel ResNet50

Wang

Zhang

et al. 2023

Second Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022)

View full text Add to dashboard Cite

In the satellite pose estimation problem, the deep learning method is used to train the network. The satellite pose needs to estimate the rotation (R) and translation (T), which are difficult to be well estimated simultaneously due to the internal coupling interaction. To solve the above problems, a dual-channel satellite pose estimation network based on ResNet50 is proposed to decouple the rotation and translation of satellite, effectively avoid the interaction, and estimate the translation and rotation of satellite respectively through the constructed network, which improves the recognition effect of satellite attitude. Through experimental verification, the network model constructed in this paper has better effect on the estimation of rotation and translation compared with other methods.

show abstract

“…In the literature section, different published research works have been discussed with their implementation details and limitations. Most of the researchers used complex architecture 7,10 . with achieving less accuracy, while some research work 12 applied smaller versions of models to find out their desired output, the rest of all the other articles used fewer images for their implementation.…”

Section: Related Workmentioning

confidence: 99%

“…Most of the researchers used complex architecture. 7,10 with achieving less accuracy, while some research work 12 applied smaller versions of models to find out their desired output, the rest of all the other articles used fewer images for their implementation.…”

Section: Related Workmentioning

confidence: 99%

“…For training, modified 2D‐U‐NET and 3D‐U‐Net architectures were applied by choosing different optimisers (Adam, SGDM and RMSprop) with different learning rates of 200 epochs and the system was evaluated on the basis of MSE and peak signal‐to‐noise ratio (PSNR) values. The authors of 10 presented a hybrid feature extraction model for the detection of tumours using a modified ResNet50 model. The proposed RestNet50 model used a layer architecture modified by including five different convolutional layers with three fully connected layers with high‐dimensional deep features, while the enhanced watershed segmentation (EWS) algorithm consisted of a few steps, including filtering for morphological restoration of the object surface, in the second step markup extraction used to mark least worthy features on images and in the final mark‐based transformation applied to show accurate images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance analysis of state‐of‐the‐art CNN architectures for brain tumour detection

Khushi,

Masood,

Jaffar

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Deep learning models, such as convolutional neural network (CNN), are popular now a day to solve various complex problems in medical and other fields, such as image classification, object detection, recommendation of images, processing of natural languages and video and image analysis. So, the idea of studying the architecture of CNNs has gotten a lot of attention and become popular. This study analysed and contrasted the performance of many different CNN models trained on the publicly accessible Br35h dataset for the detection of brain tumours. These models included the LeNet, AlexNet, VGG16, VGG19 and ResNet50. Several optimisers were used in this research to fine‐tune the performance of the CNN model. These included Adam (adaptive moment estimation), SGD (stochastic gradient descent) and RMSprop (root‐mean‐square propagation). Accuracy, miss‐classification rate, sensitivity, specificity, NPV (negative predictive value), PPV (positive predictive value), F1‐score and false omission rate (FOR) were used to assess the efficacy of five different CNN architectures trained using three different optimisers. The experimental results showed that AlexNet architecture with SGD optimiser performed better than other CNN architecture with different optimisers and achieved the highest accuracy of 98.79% with a miss classification rate of 1.20%. It also achieved 98.98% sensitivity, 98.58% specificity, 98.93% NPV, 98.65% PPV, 98.82% F1‐score and 1.06% FOR.

show abstract

Enhanced Watershed Segmentation Algorithm-Based Modified ResNet50 Model for Brain Tumor Detection

Cited by 50 publications

References 29 publications

A machine learning model to predict the histology of retroperitoneal lymph node dissection specimens

A machine learning model to predict the histology of retroperitoneal lymph node dissection specimens

Satellite pose estimation network based on dual-channel ResNet50

Performance analysis of state‐of‐the‐art CNN architectures for brain tumour detection

Contact Info

Product

Resources

About