Real-time diabetic foot ulcer classification based on deep learning & parallel hardware computational tools

  1. Fadhel, Mohammed A.
  2. Alzubaidi, Laith
  3. Gu, Yuantong
  4. Santamaría, Jose
  5. Duan, Ye
Aldizkaria:
Multimedia Tools and Applications

ISSN: 1573-7721

Argitalpen urtea: 2024

Mota: Artikulua

DOI: 10.1007/S11042-024-18304-X GOOGLE SCHOLAR lock_openSarbide irekia editor

Beste argitalpen batzuk: Multimedia Tools and Applications

Garapen Iraunkorreko Helburuak

Laburpena

Meeting the rising global demand for healthcare diagnostic tools is crucial, especially with a shortage of medical professionals. This issue has increased interest in utilizing deep learning (DL) and telemedicine technologies. DL, a branch of artificial intelligence, has progressed due to advancements in digital technology and data availability and has proven to be effective in solving previously challenging learning problems. Convolutional neural networks (CNNs) show potential in image detection and recognition, particularly in healthcare applications. However, due to their resource-intensiveness, they surpass the capabilities of general-purpose CPUs. Therefore, hardware accelerators such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and graphics processing units (GPUs) have been developed. With their parallelism efficiency and energy-saving capabilities, FPGAs have gained popularity for DL networks. This research aims to automate the classification of normal and abnormal (specifically Diabetic Foot Ulcer—DFU) classes using various parallel hardware accelerators. The study introduces two CNN models, namely DFU_FNet and DFU_TFNet. DFU_FNet is a simple model that extracts features used to train classifiers like SVM and KNN. On the other hand, DFU_TFNet is a deeper model that employs transfer learning to test hardware efficiency on both shallow and deep models. DFU_TFNet has outperformed AlexNet, VGG16, and GoogleNet benchmarks with an accuracy 99.81%, precision 99.38% and F1-Score 99.25%. In addition, the study evaluated two high-performance computing platforms, GPUs and FPGAs, for real-time system requirements. The comparison of processing time and power consumption revealed that while GPUs outpace FPGAs in processing speed, FPGAs exhibit significantly lower power consumption than GPUs.

€ Ikusi finantzaketa

Finantzaketari buruzko informazioa

Finantzatzaile

Erreferentzia bibliografikoak

  • Alzubaidi L, Bai J, Al-Sabaawi A, Santamaría J, Albahri AS, Al-dabbagh BSN, Fadhel MA et al. (2023) A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. J Big Data 10, (1): 46
  • Albahri AS, Duhaim AM, Fadhel MA, Alnoor A, Baqer NS, Alzubaidi L, Albahri OS et al (2023) A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion. Information Fusion
  • Nozawa T, Uchiyama M, Honda K, Nakano T, Miyake Y (2020) Speech Discrimination in Real-World Group Communication Using Audio-Motion Multimodal Sensing. Sensors 20(10):2948
  • Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamaría J, Fadhel MA, Al-Amidie M, Farhan L (2021) Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, (1): 1–74
  • Seritan S, Bannwarth C, Fales BS, Hohenstein EG, Isborn CM, Kokkila‐Schumacher SIL, Li X et al. (2021) TeraChem: A graphical processing unit‐accelerated electronic structure package for large‐scale ab initio molecular dynamics. Wiley Interdisciplinary Reviews: Computational Molecular Science 11, (2): e1494
  • Coates A, Huval B, Wang T, Wu D, Catanzaro B, Andrew N (2013) Deep learning with cots HPC systems. In Proceedings of the 30th International Conference on Machine Learning, 1337–1345
  • Fowers J, Brown G, Cooke P, Stitt G (2012) A performance and energy comparison of FPGAs, GPUs, and multicores for sliding-window applications. In Proceedings of the ACM/SIGDA International Symposium on Field Programmable Gate Arrays, 47–56
  • Seng KP, Lee PJ, Ang LM (2021) Embedded Intelligence on FPGA: Survey, Applications and Challenges. Electronics 10, no. 8: 895
  • Cox CE, Ekkehard Blanz W (1992) GANGLION-a fast field-programmable gate array implementation of a connectionist classifier. IEEE J Solid-State Circuits 27, (3): 288–299
  • Cloutier J, Cosatto E, Pigeon S, Boyer FR, Simard PY (1996) Vip: An fpga-based processor for image processing and neural networks. In Proceedings of the Fifth International Conference on Microelectronics for Neural Networks, pp. 330–336. IEEE
  • Ovtcharov K, Ruwase O, Kim J-Y, Fowers J, Strauss K, Chung ES (2015) Accelerating deep convolutional neural networks using specialized hardware. Microsoft Research Whitepaper 2(11):1–4
  • Zhang C, Li P, Sun G, Guan Y, Xiao B, Cong J (2015) Optimizing fpga-based accelerator design for deep convolutional neural networks. In Proceedings of the 2015 ACM/SIGDA international symposium on field-programmable gate arrays, pp. 161–170
  • Baba A, Bonny T (2023) FPGA-based parallel implementation to classify Hyperspectral images by using a Convolutional Neural Network. Integration 92:15–23
  • Parizotto R, Coelho BL, Nunes DC, Haque I, Schaeffer-Filho A (2023) Offloading Machine Learning to Programmable Data Planes: A Systematic Survey. ACM Computing Surveys
  • Almomany A, Ayyad WR, Jarrah A (2022) Optimized implementation of an improved KNN classification algorithm using Intel FPGA platform: Covid-19 case study. Journal of King Saud University-Computer and Information Sciences 34(6):3815–3827
  • Mohamed NA, Cavallaro JR (2023) A Unified Parallel CORDIC-based Hardware Architecture for LSTM Network Acceleration. IEEE Transactions on Computers
  • Heartlin MH, Kayalvizhi R, Malarvizhi S, Venkatraman R, Patil S, Senthil Kumar A (2023) Real-time deployment of BI-RADS breast cancer classifier using deep-learning and FPGA techniques. J Real-Time Image Process 20, no. 4: 80
  • Paul K and Rajopadhye S (2006) Back-propagation algorithm achieving 5 gops on the virtex-e. In FPGA Implementations of Neural Networks, pp. 137–165. Springer: Boston
  • Thotad PN, Bharamagoudar GR, Anami BS (2023) Diabetic foot ulcer detection using deep learning approaches. Sensors International 4:100210
  • Ahsan M, Naz S, Ahmad R, Ehsan H, Sikandar A (2023) A deep learning approach for diabetic foot ulcer classification and recognition. Information 14(1):36
  • Khandakar A, Chowdhury MEH, Reaz MBI, Md Ali SH, Abbas TO, Alam T, Ayari MA et al. (2022) Thermal change index-based diabetic foot thermogram image classification using machine learning techniques. Sensors 22, no. 5: 1793
  • Wang S, Wang J, Zhu MX, Tan Q (2022) Machine learning for the prediction of minor amputation in University of Texas grade 3 diabetic foot ulcers. Plos one 17, no. 12: e0278445
  • Alzubaidi L, Fadhel MA, Oleiwi SR, Al-Shamma O, Zhang J (2020) DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network. Multimed Tools Appl 79(21):15655–15677
  • Sarvamangala DR, Kulkarni RV (2022) Convolutional neural networks in medical image understanding: a survey. Evolutionary intelligence 15, no. 1: 1–22
  • Pattanayak S (2023) Pro Deep Learning with TensorFlow 2.0: A Mathematical Approach to Advanced Artificial Intelligence in Python. Apress
  • Goyal M, Reeves ND, Davison AK, Rajbhandari S, Spragg J, Yap MH (2020) DFUNet: Convolutional Neural Networks for Diabetic Foot Ulcer Classification." IEEE Transactions on Emerging Topics in Computational Intelligence 4, no. 5: 728–739
  • Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
  • Iman M, Arabnia HR, Rasheed K (2023) A review of deep transfer learning and recent advancements. Technologies 11, no. 2: 40
  • Wang X, Chen G, Qian G, Gao P, Wei X-Y, Wang Y, Tian Y, Gao W (2023) Large-scale multi-modal pre-trained models: A comprehensive survey. Machine Intelligence Research: 1–36
  • Dermnetnz Online Medical Resources | Home. Available online: https://www.dermnetnz.org/ (accessed on 5 March 2022)
  • Lim WX, Chen ZY, Ahmed A (2022) The adoption of deep learning interpretability techniques on diabetic retinopathy analysis: a review. Med Biol Eng Comput 60, no. 3: 633–642
  • Kazim M, Hong JG, Kim M-G, Kim K-KK (2023) Recent Advances in Path Integral Control for Trajectory Optimization: An Overview in Theoretical and Algorithmic Perspectives. arXiv preprint arXiv:2309.12566
  • Manual, DE1-SoC User. "Terasic Inc." Hsinchu, Taiwan, Feb (2014)
  • Akesson B, Nasri M, Nelissen G, Altmeyer S, Davis RI (2022) A comprehensive survey of industry practice in real-time systems. Real-Time Systems 58(3):358–398
  • Kashani S, Beuchat R (2020) Soc-fpga design guide de1-soc edition