Performance Analysis of Segmentation and Classification of CT-Scanned Ovarian Tumours Using U-Net and Deep Convolutional Neural Networks

Abstract

Difficulty in detecting tumours in early stages is the major cause of mortalities in patients, despite the advancements in treatment and research regarding ovarian cancer. Deep learning algorithms were applied to serve the purpose as a diagnostic tool and applied to CT scan images of the ovarian region. The images went through a series of pre-processing techniques and, further, the tumour was segmented using the UNet model. The instances were then classified into two categories—benign and malignant tumours. Classification was performed using deep learning models like CNN, ResNet, DenseNet, Inception-ResNet, VGG16 and Xception, along with machine learning models such as Random Forest, Gradient Boosting, AdaBoosting and XGBoosting. DenseNet 121 emerges as the best model on this dataset after applying optimization on the machine learning models by obtaining an accuracy of 95.7%. The current work demonstrates the comparison of multiple CNN architectures with common machine learning algorithms, with and without optimization techniques applied.

A Convolutional Neural Network-Based Auto-Segmentation Pipeline for Breast Cancer Imaging

“…[32,33]. The U-Net architecture derives its U-shape due to the sequentially arranged encoder and decoder modules [30,31,34]. The encoder consists of convolutional layers, batch normalization (BN) function, activation layers, and max pooling layers to realize the unique features in a given image.…”

“…U-Net-based architectures are one of the widely used structures in the field of medical image segmentation, such as breast tumor image segmentation, as it can work with small training data yet produce accurate results of image segmentation [32,33]. The U-Net architecture derives its U-shape due to the sequentially arranged encoder and decoder modules [30,31,34]. The encoder consists of convolutional layers, batch normalization (BN) function, activation layers, and max pooling layers to realize the unique features in a given image.…”

Semantic segmentation and classification of polycystic ovarian disease using attention UNet, Pyspark, and ensemble learning model

“…The author obtained an accuracy of 90.2% using these ML models. Kodipalli & Devi, 2023;Kodipalli, Devi, et al, 2022;Kodipalli, Guha, et al, 2022;Kodipalli, Gururaj, et al, 2023;Ruchitha et al, 2022), contributed extensively to the detection of PCOS using a questionnaire and found that Fuzzy TOPSIS outperformed the SVM algorithm (Kodipalli & Devi, 2021). Watershed and active contour random walker were used in (Ruchitha et al, 2022) for segmenting the ovarian tumour and it was found that the watershed algorithm outperformed the active contour random walker algorithm.…”

“…The novel inverted fuzzy c means architecture for the accurate detection of ovarian tumours was proposed in (Kodipalli, Fernandes, et al, 2023). The performance of UNet and Transformers was compared in (Kodipalli, Gururaj, et al, 2023) and it was observed that Transformers performed better in malignant lesion detection.…”