Multi-class Segmentation of Organ at Risk from Abdominal CT Images: A Deep Learning Approach

Khalil, Muhammad Ibrahim; Humayun, Mamoona; Jhanjhi, N. Z.; Talib, Mohammad; Tabbakh, Thamer

doi:10.1007/978-981-16-3153-5_45

Cited by 41 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the Dropout DBN algorithm with BWOA, RFNM, FM-DNN and other common drug identification algorithms were compared. During the training process, the loss values of several algorithms [26,27,28] change as shown in Figure 4.1.…”

Section: Training Effect Analysis Of Dropout Dbn Modelmentioning

confidence: 99%

Construction of an Intelligent Identification Model for Drugs in Near Infrared Spectroscopy and Research on Drog Classification based on Improved Deep Algorithm

Xia

2024

SCPE

View full text Add to dashboard Cite

Near-infrared spectroscopy has important applications in drug and food identification. Combining machine learning with near-infrared spectroscopy to achieve intelligent identification of drugs has become a research hotspot in recent years. To solve the problem of machine learning’s inefficiency in classifying small-scale data, a drug identification model based on near-infrared spectroscopy combined with a random fading depth belief network is proposed. Aiming at the problem that the training time of the machine learning algorithm is too long, the extreme learning machine is used to replace the back propagation algorithm to optimize the stack sparse auto-encoder network. Additionally, the stack sparse auto-encoder algorithm based on extreme learning machine algorithm is constructed. The study found that the precision of the Dropout Deep Belief Network model was 99.12%, which was higher than the other three models. Additionally, the area under the curve value of the Dropout Deep Belief Network model was 0.87, which was 0.04 higher than the binary whale optimization algorithm model, 0.26 higher than the factor decomposition machine and depth neural network model, and 0.05 higher than the random forest network model. The sparse auto-encoder algorithm based on the extreme learning machine algorithm achieved a precision of 99.72%. The study proposes two algorithm models that can effectively identify drugs using near-infrared spectroscopy. This has a positive impact on the medical industry and the safety of patients' lives and health.

show abstract

Section: Training Effect Analysis Of Dropout Dbn Modelmentioning

confidence: 99%

Construction of an Intelligent Identification Model for Drugs in Near Infrared Spectroscopy and Research on Drog Classification based on Improved Deep Algorithm

Xia

2024

SCPE

View full text Add to dashboard Cite

show abstract

“…In general, unbalanced voxel distribution is common in medical images, such as brain MR and abdominal CT images. 38,39 Therefore, in future studies, researchers can use DLS-Net to evaluate its segmentation performance for other unbalanced medical images.…”

Section: Limitationsmentioning

confidence: 99%

A Lightweight Convolutional Neural Network Based on Dynamic Level‐Set Loss Function for Spine MR Image Segmentation

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundSpine MR image segmentation is important foundation for computer‐aided diagnostic (CAD) algorithms of spine disorders. Convolutional neural networks segment effectively, but require high computational costs.PurposeTo design a lightweight model based on dynamic level‐set loss function for high segmentation performance.Study TypeRetrospective.PopulationFour hundred forty‐eight subjects (3163 images) from two separate datasets. Dataset‐1: 276 subjects/994 images (53.26% female, mean age 49.02 ± 14.09), all for disc degeneration screening, 188 had disc degeneration, 67 had herniated disc. Dataset‐2: public dataset with 172 subjects/2169 images, 142 patients with vertebral degeneration, 163 patients with disc degeneration.Field Strength/SequenceT2 weighted turbo spin echo sequences at 3T.AssessmentDynamic Level‐set Net (DLS‐Net) was compared with four mainstream (including U‐net++) and four lightweight models, and manual label made by five radiologists (vertebrae, discs, spinal fluid) used as segmentation evaluation standard. Five‐fold cross‐validation are used for all experiments. Based on segmentation, a CAD algorithm of lumbar disc was designed for assessing DLS‐Net's practicality, and the text annotation (normal, bulging, or herniated) from medical history data were used as evaluation standard.Statistical TestsAll segmentation models were evaluated with DSC, accuracy, precision, and AUC. The pixel numbers of segmented results were compared with manual label using paired t‐tests, with P < 0.05 indicating significance. The CAD algorithm was evaluated with accuracy of lumbar disc diagnosis.ResultsWith only 1.48% parameters of U‐net++, DLS‐Net achieved similar accuracy in both datasets (Dataset‐1: DSC 0.88 vs. 0.89, AUC 0.94 vs. 0.94; Dataset‐2: DSC 0.86 vs. 0.86, AUC 0.93 vs. 0.93). The segmentation results of DLS‐Net showed no significant differences with manual labels in pixel numbers for discs (Dataset‐1: 1603.30 vs. 1588.77, P = 0.22; Dataset‐2: 863.61 vs. 886.4, P = 0.14) and vertebrae (Dataset‐1: 3984.28 vs. 3961.94, P = 0.38; Dataset‐2: 4806.91 vs. 4732.85, P = 0.21). Based on DLS‐Net's segmentation results, the CAD algorithm achieved higher accuracy than using non‐cropped MR images (87.47% vs. 61.82%).Data ConclusionThe proposed DLS‐Net has fewer parameters but achieves similar accuracy to U‐net++, helps CAD algorithm achieve higher accuracy, which facilitates wider application.Evidence Level2Technical EfficacyStage 1

show abstract

“…Accuracy is an ideal classification metric and is easy to understand [ 21 , 22 ]. It is the proportion of true results to total number of results.…”

Section: Workflow Architecturementioning

confidence: 99%

A Transfer Learning Approach with a Convolutional Neural Network for the Classification of Lung Carcinoma

et al. 2022

Self Cite

View full text Add to dashboard Cite

Lung cancer is among the most hazardous types of cancer in humans. The correct diagnosis of pathogenic lung disease is critical for medication. Traditionally, determining the pathological form of lung cancer involves an expensive and time-consuming process investigation. Lung cancer is a leading cause of mortality worldwide, with lung tissue nodules being the most prevalent way for doctors to identify it. The proposed model is based on robust deep-learning-based lung cancer detection and recognition. This study uses a deep neural network as an extraction of features approach in a computer-aided diagnosing (CAD) system to assist in detecting lung illnesses at high definition. The proposed model is categorized into three phases: first, data augmentation is performed, classification is then performed using the pretrained CNN model, and lastly, localization is completed. The amount of obtained data in medical image assessment is occasionally inadequate to train the learning network. We train the classifier using a technique known as transfer learning (TL) to solve the issue introduced into the process. The proposed methodology offers a non-invasive diagnostic tool for use in the clinical assessment that is effective. The proposed model has a lower number of parameters that are much smaller compared to the state-of-the-art models. We also examined the desired dataset’s robustness depending on its size. The standard performance metrics are used to assess the effectiveness of the proposed architecture. In this dataset, all TL techniques perform well, and VGG 16, VGG 19, and Xception for 20 epoch structure are compared. Preprocessing functions as a wonderful bridge to build a dependable model and eventually helps to forecast future scenarios by including the interface at a faster phase for any model. At the 20th epoch, the accuracy of VGG 16, VGG 19, and Xception is 98.83 percent, 98.05 percent, and 97.4 percent.

show abstract

Multi-class Segmentation of Organ at Risk from Abdominal CT Images: A Deep Learning Approach

Cited by 41 publications

References 9 publications

Construction of an Intelligent Identification Model for Drugs in Near Infrared Spectroscopy and Research on Drog Classification based on Improved Deep Algorithm

Construction of an Intelligent Identification Model for Drugs in Near Infrared Spectroscopy and Research on Drog Classification based on Improved Deep Algorithm

A Lightweight Convolutional Neural Network Based on Dynamic Level‐Set Loss Function for Spine MR Image Segmentation

A Transfer Learning Approach with a Convolutional Neural Network for the Classification of Lung Carcinoma

Contact Info

Product

Resources

About