| 121. |
- Nie, Yali
(författare)
-
Deep Learning Approaches towards Skin Lesion Classification with Dermoscopic Images
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Melanoma is a skin cancer that tends to be deadly. The incidence of melanoma is currently at the highest level ever recorded in Europe, North America and Oceania. The survival rate can be significantly increased if skin lesions are identified in dermoscopic images at an early stage. In the other hand, the classification of skin lesions is incredibly challenging. Skin lesion classification using deep learning approaches has provided better results in classifying skin diseases than those of dermatologist, which is lifesaving in terms of diagnosis.This thesis presents a review of our research articles on classifying skin lesions using deep learning. Regarding the research, I have four goals concerning research frontier work, small datasets, data imbalance, and improving accuracy. In this thesis, I discuss how deep learning can classify skin diseases, summarizing the problems that remain at this stage and the outlook for the future.For the above goals, I first studied and summarized more than 200 highguality articles published over five years. I then used three versions of You only look once (Yolo) to detect skin lesions. Although there were only 200 pictures, the test was very effective for detection. I applied the five-fold algorithm to Vgg_16, trained five models, and fused them so solve the small data problem. To improve the accuracy, I also tried to combine the traditional machine learning method, i.e., the seven-point checklist, with three different backbones. Since the learning rate. Then, I also tried to use the hybrid model, combining convolutional neural networks (CNN) and transformer to train the dataset, and applied focal loss to balance the extremely unbalanced weight of the data.In addition to high-quality data sets and high-performance computers being extremely important in the research and application of deep learning, the optimization of machine learning algorithms for skin lesions can be endless
|
|
| 122. |
- Nie, Yali, et al.
(författare)
-
Deep Melanoma classification with K-Fold Cross-Validation for Process optimization
- 2020
-
Ingår i: 2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA). - : IEEE. - 9781728153865
-
Konferensbidrag (refereegranskat)abstract
- Deep convolution neural networks (DCNNs) enable effective methods to predict the melanoma classes otherwise found with ultrasonic extraction. However, gathering large datasets in local hospitals in Sweden can take years. Small datasets will result in models with poor accuracy and insufficient generalization ability, which has a great impact on the result. This paper proposes to use a K-Fold cross validation approach based on a DCNN algorithm working on a small sample dataset. The performance of the model is verified via a Vgg16 extracting the features. The experimental results reveal that the model built by the approach proposed in this paper can effectively achieve a better prediction and enhance the accuracy of the model, which proves that K-Fold can achieve better performance on a small skin cancer dataset.
|
|
| 123. |
- Nie, Yali, et al.
(författare)
-
Multi-Path Interference Denoising of LiDAR Data Using a Deep Learning Based on U-Net Model
- 2024
-
Ingår i: 2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). - : IEEE conference proceedings. - 9798350380903
-
Konferensbidrag (refereegranskat)abstract
- Eliminating Multi-Path Interference (MPI) stands as a significant unresolved challenge in the domain of depth estimation using Time-of-Flight (ToF) cameras. ToF data is typically influenced by significant noise and artifacts stemming from MPI. Although a variety of conventional methods have been suggested to enhance ToF data quality, the application of machine learning techniques has been infrequent, primarily due to the scarcity of authentic training data with accurate depth information. This paper introduces an approach that eliminates the dependency on labeled real-world data within the learning framework. We employ a U-Net trained on the data with ground truth in a supervised manner, enabling it to leverage multi-frequency ToF data for MPI correction. Concurrently, we compare three channels as input with one channel and two channels. Our experimental results convincingly showcase the effectiveness of this approach in reducing noise in real-world data.
|
|
| 124. |
- Nie, Yali, et al.
(författare)
-
Recent Advances in Diagnosis of Skin Lesions using Dermoscopic Images based on Deep Learning
- 2022
-
Ingår i: IEEE Access. - 2169-3536. ; 10, s. 95716-95747
-
Tidskriftsartikel (refereegranskat)abstract
- Skin cancer is one of the most threatening cancers, which spreads to the other parts of the body if not caught and treated early. During the last few years, the integration of deep learning into skin cancer has been a milestone in health care, and dermoscopic images are right at the center of this revolution. This review study focuses on the state-of-the-art automatic diagnosis of skin cancer from dermoscopic images based on deep learning. This work thoroughly explores the existing deep learning and its application in diagnosing dermoscopic images. This study aims to present and summarize the latest methodology in melanoma classification and the techniques to improve this. We discuss advancements in deep learning-based solutions to diagnose skin cancer, along with some challenges and future opportunities to strengthen these automatic systems to support dermatologists and enhance their ability to diagnose skin cancer. Author
|
|
| 125. |
- Nie, Yali, et al.
(författare)
-
Skin Cancer Classification based on Cosine Cyclical Learning Rate with Deep Learning
- 2022
-
Ingår i: Conference Record - IEEE Instrumentation and Measurement Technology Conference. - : IEEE. - 9781665483605
-
Konferensbidrag (refereegranskat)abstract
- Since early-stage skin cancer identification can improve melanoma prognosis and significantly reduce treatment costs, AI-based diagnosis systems might greatly benefit patients suffering from suspicious skin lesions. The study proposes a cosine cyclical learning rate with a skin cancer classification model to improve melanoma prediction. The contributions of models involve three critical CNNs, which are standard deep feature extraction modules for the skin cancer classification in this study (Vgg19, ResNet101 and InceptionV3). Each CNN model applies three different learning rates: fixed learning rate(LR), Cosine Annealing LR, and Cosine Annealing with WarmRestarts. HAM10000 is a large collection of publicly available dermoscopic images dataset used for our experiments. The performance of the proposed approach was appraised through comparative experiments. The outcome has indicated that the proposed method has high efficiency in diagnosing skin lesions with a cosine cyclical learning rate.
|
|
| 126. |
- Nordin, Lisa, 1981-, et al.
(författare)
-
Analysis of the quality of optical fibre and fines measurement for prediction of dewatering characteristics for mechanical pulps
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- The quality of the optical fibre and fines measurement has been investigated. Fibres and fines of different quality were mixed in defined proportions and the mixtures were characterized by means of optical fibre measurements and dewatering behaviour. The results show that the same measured fines amounts show different dewatering behaviour, depending on the quality of the fines used. The difference in fines quality was, however, not reflected in the optical measurement. We conclude that this is caused by too low resolution in the optical measurement, so there is a large need for higher resolution of the measurement equipments in order to make it possible to measure the shape of the fines.
|
|
| 127. |
|
|
| 128. |
- Nordin, Lisa, 1981-, et al.
(författare)
-
Measurement and prediction of dewatering characteristics for mechanical pulps using optical fibre analyzers
- 2009
-
Ingår i: Proceedings - 2009 International Mechanical Pulping Conference, IMPC 2009. ; , s. 309-316
-
Konferensbidrag (refereegranskat)abstract
- The aim of this work was to obtain an on-line measurement for dewatering behaviour in the wire section based on fibre and fines characteristics. Four laboratory dewatering equipments were compared and the fibre characteristics were measured by means of optical fibre analyzers. The results show that rough correlations do appear to exist between the dewatering equipments; however they rank the pulps differently depending on the raw wood material used and whether the refining conditions are mild or harsh. The prediction models based on fibre characteristics showed a high degree of statistical accuracy. The descriptions, however, proved not to be sufficiently good with regards to the dewatering behaviour for them to be used in relation to on-line applications. This might have been because consideration was not given to some important variables which do, in fact, have a significant impact on the drainability. These variables could include physical fibre properties or others that are not measured, or properties that, at present, are unable to be measured at a sufficient resolution.
|
|
| 129. |
- Norell, Håkan, et al.
(författare)
-
A Generalized Architecture for Hardware Synthesis of Spatio-Temporal Memory Models for Image Processing Systems
- 2005
-
Ingår i: IWSSIP 2005 - Proceedings of the 12th International Worshop on Systems, Signals & Image Processing. - : InderScience Publishers. - 0907776205 ; , s. 361-365
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a generalized architecture for the synthesis of application specific memory architectures for real-time image processing systems. The memory generation presented in this paper can handle both spatial and spatio-temporal memory models. The results show that the architecture efficiently solves the problems related to memory accesses for most of the available video image processing filters available at present.
|
|
| 130. |
- Norell, Håkan, et al.
(författare)
-
Automatic Generation of Spatial and Temporal Memory Architectures for Embedded Video Processing Systems
- 2007
-
Ingår i: EURASIP Journal on Embedded Systems. - : Springer Science and Business Media LLC. - 1687-3955 .- 1687-3963. ; 2007
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a tool for automatic generation of the memory management implementation for spatial and temporal real-time video processing systems targeting field programmable gate arrays (FPGAs). The generator creates all the necessary memory and control functionality for a functional spatio-temporal video processing system. The required memory architecture is automatically optimized and mapped to the FPGAs' memory resources thus producing an efficient implementation in terms of used internal resources. The results in this paper show that the tool is able to efficiently and automatically generate all required memory management modules for both spatial and temporal real-time video processing systems.
|
|
