Hyperparameter Optimization of Deep Neural Network in Multimodality Fused Medical Image Classification for Medical and Industrial IoT

Velmurugan, S.; Sivakumar, P.; Sampson, Jenyfal

doi:10.1007/978-3-030-52624-5_9

“…At one stage, each had its extended matrix mark combined. Three data points, Database, Coil100 and CIFAR‐10, were used to evaluate this methodology (Parvathy et al, 2021).…”

Section: Background Ovarian Cancer Area Using Internet Of Medical Thingsmentioning

confidence: 99%

“…At one stage, each had its extended matrix mark combined. Three data points, Database, Coil100 and CIFAR-10, were used to evaluate this methodology (Parvathy et al, 2021). Qin et al developed a new method for identifying Ovarian cancer with SOMICS and the Genetics Evolution Neural Networks (GENN) (Chidambaranathan et al, 2021).…”

Section: Background Ovarian Cancer Area Using Internet Of Medical Thingsmentioning

confidence: 99%

Feature optimization and identification of ovarian cancer using internet of medical things

Ghazal

¹

,

Taleb

²

2022

View full text Add to dashboard Cite

Ovarian cancer (OC) is one kind of tumour that impacts women's ovaries and is hard to diagnose in the initial phase as a primary cause of cancer death. The ovarian cancer information generated by the Clinical Network has been used, and the Self Organizing Map (SOM) and Optimized Neural Networks have suggested a new method for the distinction between ovarian cancer and remaining cancer. Feature optimization and identification of the ovarian cancer (FOI-OV) framework are proposed in this research. The SOM algorithm has also been used separately to improve the functional subset, with understandable and intriguing information from participants' health information steps. The SOM-based collection appears to be tolerable in guided learning strategies due to the lack of different classifiers, which would direct the quest for knowledge specific to the classification algorithm. The classification technique will classify data from ovarian cancer as benign/malignant. By optimizing Neural Network configuration, Advanced Harmony Searching Optimization (AHSO) can enhance the ovarian cancer detection method compared with other methods. This research's suggested model can also diagnose cancer with high precision, and low root means square error (RMSE) early. With 94% precision and 0.029%, RMSE, SOM, and NN techniques have shown identification and precision in ovarian cancer. Optimization (AHSO) has provided an efficient classification approach with a better failure rate.

show abstract

“…It is also well known, that it is a tedious and slow process, for that reason several studies on distributing it and thus increase its performance have been carried out [27], [28]. Furthermore, it has also been proposed on medical image diagnosis [29], [30], [31], but in these studies their focus is not on efficiency. In our work we propose an easy to use distributed hyperparameter tuning, which leads to a dramatically improvement on performance and more simple usability.…”

Section: State Of the Artmentioning

confidence: 99%

Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation

Berral

¹

,

Oriol

²

,

Domínguez

³

et al. 2022

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)

3

0

View full text Add to dashboard Cite

Most research on novel techniques for 3D Medical Image Segmentation (MIS) is currently done using Deep Learning with GPU accelerators. The principal challenge of such technique is that a single input can easily cope computing resources, and require prohibitive amounts of time to be processed. Distribution of deep learning and scalability over computing devices is an actual need for progressing on such research field. Conventional distribution of neural networks consist in "data parallelism", where data is scattered over resources (e.g., GPUs) to parallelize the training of the model. However, "experiment parallelism" is also an option, where different training processes (i.e., on a hyper-parameter search) are parallelized across resources. While the first option is much more common on 3D image segmentation, the second provides a pipeline design with less dependence among parallelized processes, allowing overhead reduction and more potential scalability. In this work we present a design for distributed deep learning training pipelines, focusing on multinode and multi-GPU environments, where the two different distribution approaches are deployed and benchmarked. We take as proof of concept the 3D U-Net architecture, using the MSD Brain Tumor Segmentation dataset, a state-of-art problem in medical image segmentation with high computing and space requirements. Using the BSC MareNostrum supercomputer as benchmarking environment, we use TensorFlow and Ray as neural network training and experiment distribution platforms. We evaluate the experiment speed-up when parallelizing, showing the potential for scaling out on GPUs and nodes. Also comparing the different parallelism techniques, showing how experiment distribution leverages better such resources through scaling, e.g. by a speed-up factor from x12 to x14 using 32 GPUs. Finally, we provide the implementation of the design open to the community, and the non-trivial steps and methodology for adapting and deploying a MIS case as the here presented.

show abstract

“…It is also well known, that it is a tedious and slow process, for that reason several studies on distributing it and thus increase its performance have been carried out [21], [22]. Furthermore, it has also been proposed on medical image diagnosis [23], [24], [25], but in these studies their focus is not on efficiency. In our work we propose an easy to use distributed hyperparameter tuning, which leads to a dramatically improvement on performance and more simple usability.…”

Section: State Of the Artmentioning

confidence: 99%

Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation

Berral¹,

Oriol²,

Domínguez³

et al. 2021

Preprint

View full text Add to dashboard Cite

Most research on novel techniques for 3D Medical Image Segmentation (MIS) is currently done using Deep Learning with GPU accelerators. The principal challenge of such technique is that a single input can easily cope computing resources, and require prohibitive amounts of time to be processed. Distribution of deep learning and scalability over computing devices is an actual need for progressing on such research field. Conventional distribution of neural networks consist in "data parallelism", where data is scattered over resources (e.g., GPUs) to parallelize the training of the model. However, "experiment parallelism" is also an option, where different training processes (i.e., on a hyper-parameter search) are parallelized across resources. While the first option is much more common on 3D image segmentation, the second provides a pipeline design with less dependence among parallelized processes, allowing overhead reduction and more potential scalability. In this work we present a design for distributed deep learning training pipelines, focusing on multinode and multi-GPU environments, where the two different distribution approaches are deployed and benchmarked. We take as proof of concept the 3D U-Net architecture, using the MSD Brain Tumor Segmentation dataset, a state-of-art problem in medical image segmentation with high computing and space requirements. Using the BSC MareNostrum supercomputer as benchmarking environment, we use TensorFlow and Ray as neural network training and experiment distribution platforms. We evaluate the experiment speed-up when parallelizing, showing the potential for scaling out on GPUs and nodes. Also comparing the different parallelism techniques, showing how experiment distribution leverages better such resources through scaling, e.g. by a speed-up factor from x12 to x14 using 32 GPUs. Finally, we provide the implementation of the design open to the community, and the non-trivial steps and methodology for adapting and deploying a MIS case as the here presented.

show abstract

Hyperparameter Optimization of Deep Neural Network in Multimodality Fused Medical Image Classification for Medical and Industrial IoT

Cited by 4 publications

References 30 publications

Feature optimization and identification of ovarian cancer using internet of medical things

Feature optimization and identification of ovarian cancer using internet of medical things

Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation

Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation

Contact Info

Product

Resources

About