Review
Medicine, General & Internal
Elena Prisciandaro, Giulia Sedda, Andrea Cara, Cristina Diotti, Lorenzo Spaggiari, Luca Bertolaccini
Summary: Artificial neural networks are statistical methods that simulate the learning dynamics of the human brain. They have shown excellent aptitude in learning the relationships between input/output mappings without prior assumptions about the data distribution. They can provide valuable support for both basic research and clinical decision-making in lung cancer.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Oncology
Yuexin Liu, Barrett C. Lawson, Xuelin Huang, Bradley M. Broom, John N. Weinstein
Summary: This study developed a deep learning neural network framework to predict the sensitivity of ovarian cancer to chemotherapy. The trained model achieved a high accuracy in distinguishing sensitive from resistant cancers based on histopathological images. This analysis has the potential to improve the prediction of response to therapy and contribute to our understanding of histopathological variables.
Article
Computer Science, Information Systems
M. Senthil Sivakumar, L. Megalan Leo, T. Gurumekala, V. Sindhu, A. Saraswathi Priyadharshini
Summary: This study proposes an automated high-precision diagnostic model with a convolutional neural network (CNN) for identifying Malignant Melanoma Cancer. By employing deep learning techniques to analyze data on skin lesions, such as rashes, boils, and cancer growth, the model achieves improved accuracy through preprocessing, feature extraction, classification, and malignant melanoma identification. Experimental results demonstrate significant improvement over traditional methods, with an accuracy of 94% and an F1-score of 93.9% on the International Skin Image Collaboration (ISIC) dataset. Additionally, the developed web application accelerates precise diagnosis and provides accurate information compared to other practical methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Luca Brunese, Francesco Mercaldo, Alfonso Reginelli, Antonella Santone
Summary: This paper proposes an automatic method to analyze respiratory sounds and demonstrates the effectiveness of machine learning techniques in detecting and characterizing lung diseases. The experimental analysis shows promising results, with the neural network model achieving the best performance.
APPLIED SCIENCES-BASEL
(2022)
Article
Oncology
Huan Gao, Zhi-yi He, Xing-li Du, Zheng-gang Wang, Li Xiang
Summary: This study developed a two-step artificial neural network model for predicting synchronous organ-specific metastasis in lung cancer patients, with higher accuracy in predicting distant metastasis and organ-specific metastasis compared to the random forest model.
FRONTIERS IN ONCOLOGY
(2022)
Article
Computer Science, Information Systems
Santisudha Panigrahi, Jayshankar Das, Tripti Swarnkar
Summary: Oral cancer is a common malignancy affecting the oral cavity. This paper presents a new approach for classifying oral cancer using a deep learning technique known as the capsule network. The network demonstrates high accuracy and sensitivity in classifying early-stage pathological images of oral cancer.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Biology
Han Li, Peishu Wu, Zidong Wang, Jingfeng Mao, Fuad E. Alsaadi, Nianyin Zeng
Summary: In this paper, a feature learning enhanced convolutional neural network (FLE-CNN) is proposed for cancer detection from histopathology images. Experimental results demonstrate the merits of the proposed FLE-CNN in terms of feature extraction, achieving improved performance compared to other advanced deep learning models.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Engineering, Biomedical
Arezoo Karimizadeh, Mansour Vali, Mohammadreza Modaresi
Summary: Multichannel lung sound analysis was successful in discriminating different severity levels of CF lung disease. Features from upper airways and peripheral airways were more effective in distinguishing normal from mild (91.1%) and moderate from severe (92.8%) respiratory sound samples, respectively. The neural network classifier showed the best performance in discriminating among all severity groups with an average accuracy of 89.05%.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Chemistry, Multidisciplinary
Nelson Faria, Sofia Campelos, Vitor Carvalho
Summary: Lung cancer is a leading cause of cancer-related deaths worldwide, and developing computer-aided diagnosis systems can improve accuracy and reduce workload. This study developed a learning algorithm (CancerDetecNN) to evaluate tumor presence in lung whole-slide images (WSIs) with reduced computational cost.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Interdisciplinary Applications
Shih-Hui Huang, Chao-Yu Chu, Yu-Chia Hsu, San-Yuan Wang, Li-Na Kuo, Kuan-Jen Bai, Ming-Chih Yu, Jer-Hwa Chang, Eugene H. Liu, Hsiang-Yin Chen
Summary: Machine learning models with clinical and genomic features can be used as a preliminary tool for predicting platinum-induced nephrotoxicity in non-small cell lung cancer patients and providing preventive strategies in advance.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
S. Pitchumani Angayarkanni
Summary: Breast cancer is the most common form of cancer among women in India. To improve the diagnosis of breast cancer, researchers have adopted a hybrid deep learning model for automatic analysis and detection of breast cancer using histopathology images. By utilizing convolution neural networks, the model achieves efficient feature extraction and classification, resulting in high accuracy.
JOURNAL OF DIGITAL IMAGING
(2022)
Article
Multidisciplinary Sciences
Congcong Yan, Ke Li, Fanling Meng, Lu Chen, Jingting Zhao, Zicheng Zhang, Dandan Xu, Jie Sun, Meng Zhou
Summary: Increasing evidence shows that the activation and diversity of macrophage subtypes in the tumor microenvironment are dynamically heterogeneous and play a critical role in various cancers. This study investigated the heterogeneity and homeostasis of macrophage subtypes and their impact on ovarian cancer. The results revealed that the abundance of M0 and M1 macrophages was associated with better outcome and therapeutic efficacy, while M2 macrophages showed the opposite effect. Consensus clustering analysis identified two ovarian cancer subgroups with distinct clinical and immunological behaviors based on the balance between M0, M1, and M2 macrophages. Additionally, an artificial neural network model based on macrophage polarization was proposed to predict clinical outcomes and treatment efficacy in ovarian cancer patients.
JOURNAL OF ADVANCED RESEARCH
(2023)
Review
Health Care Sciences & Services
Peng Xue, Jiaxu Wang, Dongxu Qin, Huijiao Yan, Yimin Qu, Samuel Seery, Yu Jiang, Youlin Qiao
Summary: This study conducted a meta-analysis to evaluate the diagnostic performance of deep learning algorithms for early breast and cervical cancer identification. The results showed that these algorithms performed acceptably well across all subgroups, comparable to human clinicians. However, the relatively poor design and reporting of the included studies may have caused bias in the results.
NPJ DIGITAL MEDICINE
(2022)
Article
Engineering, Multidisciplinary
Ibham Veza, Asif Afzal, M. A. Mujtaba, Anh Tuan Hoang, Dhinesh Balasubramanian, Manigandan Sekar, I. M. R. Fattah, M. E. M. Soudagar, Ahmed EL-Seesy, D. W. Djamari, A. L. Hananto, N. R. Putra, Noreffendy Tamaldin
Summary: Artificial Neural Network (ANN) is considered as a beneficial prediction tool in automotive applications, especially when the system is complicated and costly to model using simulation programs. However, further examination and improvement are required for the use of ANN in engine applications.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Review
Oncology
Athena Davri, Effrosyni Birbas, Theofilos Kanavos, Georgios Ntritsos, Nikolaos Giannakeas, Alexandros T. Tzallas, Anna Batistatou
Summary: Lung cancer is a common and deadly malignancy, and traditional methods of histological and cytological examination are challenging and time-consuming. Artificial intelligence-based methods, particularly Deep Learning, show great potential in assisting with lung cancer diagnosis, classification, prognosis prediction, mutational status characterization, and PD-L1 expression estimation. This systematic review provides an overview of the current advances in Deep Learning-based methods on lung cancer using histological and cytological images.
Article
Medicine, Research & Experimental
Marijn A. Scheijde-Vermeulen, Lennart A. Kester, Liset Westera, Bastiaan B. J. Tops, Friederike A. G. Meyer-Wentrup
Summary: This study aimed to evaluate the feasibility of integrating state-of-the-art sequencing techniques and flow cytometry into the diagnostic workup of pediatric lymphoma. The results showed that this integration is not only feasible but also provides additional diagnostic information.
LABORATORY INVESTIGATION
(2024)
Article
Medicine, Research & Experimental
Enrico Berrino, Sara Erika Bellomo, Anita Chesta, Paolo Detillo, Alberto Bragoni, Amedeo Gagliardi, Alessio Naccarati, Matteo Cereda, Gianluca Witel, Anna Sapino, Benedetta Bussolati, Gianni Bussolati, Caterina Marchi
Summary: Formalin-fixed paraffin-embedded (FFPE) samples are crucial for tissue-based analysis in precision medicine, but the quality of these samples can affect the reliability of sequencing data. The use of acid-deprived fixatives guarantees the highest DNA preservation and sequencing performance, enabling more complex molecular profiling of tissue samples.
LABORATORY INVESTIGATION
(2024)
Article
Medicine, Research & Experimental
Roope A. Kallionpaa, Sirkku Peltonen, Kim My Le, Eija Martikkala, Mira Jaaskelainen, Elnaz Fazeli, Pilvi Riihila, Pekka Haapaniemi, Anne Rokka, Marko Salmi, Ilmo Leivo, Juha Peltonen
Summary: This study investigated the immune microenvironment of cutaneous neurofibromas (cNFs) in patients with neurofibromatosis 1 (NF1). The results showed that cNFs have substantial populations of T cells and macrophages, which may be tumor-specific. T cell populations in cNFs were found to be different from those in the skin, and cNFs exhibited lower expression of proteins related to T cell-mediated immunity compared to the skin.
LABORATORY INVESTIGATION
(2024)