Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation

Sanam Nagendram; Arunendra Singh; Gade Harish Babu; Rahul Joshi; Sandeep Dwarkanath Pande; S K Hasane Ahammad; Dharmesh Dhabliya; Aadarsh Bisht

doi:10.1515/biol-2022-0665

Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation

Open Life Sci. 2023 Aug 8;18(1):20220665. doi: 10.1515/biol-2022-0665. eCollection 2023.

Authors

Sanam Nagendram¹, Arunendra Singh², Gade Harish Babu³, Rahul Joshi⁴, Sandeep Dwarkanath Pande⁵, S K Hasane Ahammad⁶, Dharmesh Dhabliya⁷, Aadarsh Bisht⁸

Affiliations

¹ Department of Artificial Intelligence, KKR & KSR Institute of Technology and Sciences, Guntur, India.
² Department of Information Technology, Pranveer Singh Institute of Technology, Kanpur, 209305, Uttar Pradesh, India.
³ Department of E.C.E, CVR College of Engineering, Hyderabad, India.
⁴ CSE Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India.
⁵ MIT, Academy of Engineering, Alandi, Pune, India.
⁶ Department of E.C.E., Koneru Lakshmaiah Education Foundation, Vaddeswaram, 522302, India.
⁷ Department of Information Technology, Vishwakarma Institute of Information Technology, Pune, India.
⁸ University Institute of Engineering, Chandigarh University, Mohali, India.

Abstract

In accordance with the inability of various hair artefacts subjected to dermoscopic medical images, undergoing illumination challenges that include chest-Xray featuring conditions of imaging acquisi-tion situations built with clinical segmentation. The study proposed a novel deep-convolutional neural network (CNN)-integrated methodology for applying medical image segmentation upon chest-Xray and dermoscopic clinical images. The study develops a novel technique of segmenting medical images merged with CNNs with an architectural comparison that incorporates neural networks of U-net and fully convolutional networks (FCN) schemas with loss functions associated with Jaccard distance and Binary-cross entropy under optimised stochastic gradient descent + Nesterov practices. Digital image over clinical approach significantly built the diagnosis and determination of the best treatment for a patient's condition. Even though medical digital images are subjected to varied components clarified with the effect of noise, quality, disturbance, and precision depending on the enhanced version of images segmented with the optimised process. Ultimately, the threshold technique has been employed for the output reached under the pre- and post-processing stages to contrast the image technically being developed. The data source applied is well-known in PH² Database for Melanoma lesion segmentation and chest X-ray images since it has variations in hair artefacts and illumination. Experiment outcomes outperform other U-net and FCN architectures of CNNs. The predictions produced from the model on test images were post-processed using the threshold technique to remove the blurry boundaries around the predicted lesions. Experimental results proved that the present model has better efficiency than the existing one, such as U-net and FCN, based on the image segmented in terms of sensitivity = 0.9913, accuracy = 0.9883, and dice coefficient = 0.0246.

Keywords: SGD; convolutional neural networks; machine learning; medical chest-X-ray images.