Article
Computer Science, Information Systems
Maad M. Mijwil
Summary: Skin cancer is a dangerous disease, and early detection is crucial for increasing survival rates. Deep learning models applied to computerized skin cancer detection have become a standard practice, providing valuable assistance to doctors in making accurate diagnoses and improving classification accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Oncology
Xiaobo Zhang, Wei Ba, Xiaoya Zhao, Chen Wang, Qiting Li, Yinli Zhang, Shanshan Lu, Lang Wang, Shuhao Wang, Zhigang Song, Danhua Shen
Summary: This study aims to develop a deep learning system for endometrial cancer detection using whole-slide images (WSIs). The model achieved a high degree of accuracy in identifying EC, serving as an assisted diagnostic tool to improve working efficiency for pathologists.
FRONTIERS IN ONCOLOGY
(2022)
Article
Multidisciplinary Sciences
Yoshiko Bamba, Shimpei Ogawa, Michio Itabashi, Shingo Kameoka, Takahiro Okamoto, Masakazu Yamamoto
Summary: This study utilized convolutional neural networks to recognize and evaluate the accuracy of forceps types in surgical videos obtained during colorectal surgeries, demonstrating the potential for achieving high accuracy in forceps recognition.
SCIENTIFIC REPORTS
(2021)
Review
Computer Science, Interdisciplinary Applications
Apeksha Koul, Rajesh K. Bawa, Yogesh Kumar
Summary: This paper presents a system for predicting and classifying multiple respiratory diseases using various deep transfer learning models. The models analyze pulmonary images, such as CT scans and chest x-rays of lung cancer, pulmonary embolism, COVID, and pneumoconiosis, along with healthy lungs. The proposed hybrid model achieves high accuracy, precision, recall, and F1 score, with the lowest loss value. The research suggests that the hybrid deep transfer learning model can help doctors and experts make better predictions and improve the classification of respiratory diseases.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Shengping Cai, Yang Chen, Shixuan Zhao, Dehuai He, Yongjie Li, Nian Xiong, Zhidan Li, Shaoping Hu
Summary: This study developed a dynamic 3D radiomics analysis method using artificial intelligence to automatically assess the disease stages of COVID-19 patients based on CT images. The method showed high accuracy and good diagnostic performance.
EUROPEAN RADIOLOGY
(2022)
Article
Pathology
Eric Erak, Lia DePaula Oliveira, Adrianna A. Mendes, Oluwademilade Dairo, Onur Ertunc, Ibrahim Kulac, Javier A. Baena-Del Valle, Tracy Jones, Jessica L. Hicks, Stephanie Glavaris, Gunes Guner, Igor Damasceno Vidal, Mark Markowski, Claire de la Calle, Bruce J. Trock, Avaneesh Meena, Uttara Joshi, Chaith Kondragunta, Saikiran Bonthu, Nitin Singhal, Angelo M. De Marzo, Tamara L. Lotan
Summary: Microscopic examination of prostate cancer has not found a consistent association between molecular and morphologic features. However, deep-learning algorithms trained on hematoxylin and eosin (H & E)-stained whole slide images may be better than human eyes at screening for clinically-relevant genomic alterations. These algorithms can identify prostate tumors with ETS-related gene (ERG) fusions or PTEN deletions.
Article
Multidisciplinary Sciences
Lei Jin, Tianyang Sun, Xi Liu, Zehong Cao, Yan Liu, Hong Chen, Yixin Ma, Jun Zhang, Yaping Zou, Yingchao Liu, Feng Shi, Dinggang Shen, Jinsong Wu
Summary: Accurate pathological classification and grading of gliomas is crucial in clinical diagnosis and treatment. In this study, deep learning techniques were used for automated histological pathology diagnosis of gliomas. The model showed high accuracy in both internal validation and multi-center testing.
Review
Oncology
Katherine Sanchez, Kanika Kamal, Priya Manjaly, Sophia Ly, Arash Mostaghimi
Summary: The development and implementation of artificial intelligence (AI) in dermatology is impacting patient care. AI has mainly been applied in clinical settings for melanoma, but it is also critically important for non-melanoma skin cancers such as basal cell and squamous cell cancers. AI can help improve diagnosis time and accuracy, predict therapeutic response, and aid in designing new therapies. However, realistic expectations and transparent guidelines are necessary to promote confidence in AI systems. Dermatologists play a crucial role in curating diverse and high-quality datasets for training AI algorithms. AI should be seen as a tool to complement dermatologists' expertise rather than a replacement.
CURRENT TREATMENT OPTIONS IN ONCOLOGY
(2023)
Article
Gastroenterology & Hepatology
Daiki Nemoto, Zhe Guo, Shinichi Katsuki, Takahito Takezawa, Ryo Maemoto, Keisuke Kawasaki, Ken Inoue, Takashi Akutagawa, Hirohito Tanaka, Koichiro Sato, Teppei Omori, Kunihiro Takanashi, Yoshikazu Hayashi, Yuki Nakajima, Yasuyuki Miyakura, Takayuki Matsumoto, Naohisa Yoshida, Motohiro Esaki, Toshio Uraoka, Hiroyuki Kato, Yuji Inoue, Boyuan Peng, Ruiyao Zhang, Takashi Hisabe, Tomoki Matsuda, Hironori Yamamoto, Noriko Tanaka, Alan Kawarai Lefor, Xin Zhu, Kazutomo Togashi
Summary: This study aimed to develop a computer-aided diagnosis (CADx) system using nonmagnified endoscopic white-light images to diagnose early-stage colorectal cancers (CRCs). The CADx system showed high specificity and accuracy for diagnosing T1b lesions, surpassing trainees and comparable to experts. The CADx system has promising potential for clinical application.
GASTROINTESTINAL ENDOSCOPY
(2023)
Article
Oncology
Md Mohaimenul Islam, Tahmina Nasrin Poly, Bruno Andreas Walther, Ming-Chin Lin, Yu-Chuan (Jack) Li
Summary: Gastric cancer is a newly diagnosed cancer and is the fifth leading cause of death globally. Recognition of early gastric cancer can ensure prompt treatment and reduce mortality rates significantly. This study evaluated the performance of the CNN model in detecting EGC and found that the CNN model performed comparably to expert endoscopists in diagnosing EGC using digital endoscopy images.
Review
Biology
Fatimah Abdulazim Altuhaifa, Khin Than Win, Guoxin Su
Summary: This review examines studies utilizing machine learning and data-mining techniques to predict lung cancer survival using clinical data. It finds that the application of machine learning models based on clinical data for lung cancer survival prediction has increased over time. However, there are still challenges to be addressed, such as handling missing data and data preprocessing.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Gastroenterology & Hepatology
Joon Yeul Nam, Hyung Jin Chung, Kyu Sung Choi, Hyuk Lee, Tae Jun Kim, Hosim Soh, Eun Ae Kang, Soo-Jeong Cho, Jong Chul Ye, Jong Pil Im, Sang Gyun Kim, Joo Sung Kim, Hyunsoo Chung, Jeong-Hoon Lee
Summary: This study developed and validated convolutional neural network-based artificial intelligence models for the differential diagnosis of gastric mucosal lesions, showing good performance in lesion detection, differential diagnosis, and evaluation of invasion depth when compared with visual diagnoses by endoscopists and EUS results. The AI models were comparable with experts and outperformed novice and intermediate endoscopists in the differential diagnosis, while the AI model for invasion depth assessment performed better than EUS.
GASTROINTESTINAL ENDOSCOPY
(2022)
Review
Biochemistry & Molecular Biology
Kyle Swanson, Eric Wu, Angela Zhang, Ash A. Alizadeh, James Zou
Summary: Machine learning is increasingly used in clinical oncology to diagnose cancers, predict patient outcomes, and inform treatment planning. This review focuses on recent applications of machine learning across the clinical oncology workflow, including medical imaging and molecular data obtained from liquid and solid tumor biopsies for cancer diagnosis, prognosis, and treatment design. Key considerations in developing machine learning for the distinct challenges posed by imaging and molecular data are discussed. The review also examines machine learning models approved for cancer-related patient usage by regulatory agencies and discusses approaches to improve the clinical usefulness of machine learning.
Article
Energy & Fuels
Marko Turek, Manuel Meusel
Summary: The quality control in solar cell production is improved by analyzing the correlation between quantitative performance data and imaging diagnostics. A reliable and automated classification of EL-images is achieved using an artificial intelligence approach. The correlation between cell I-V-data and AI-predicted EL-image classes allows for early detection of performance issues.
SOLAR ENERGY MATERIALS AND SOLAR CELLS
(2023)
Article
Gastroenterology & Hepatology
Jun Ohara, Tetsuo Nemoto, Yasuharu Maeda, Noriyuki Ogata, Shin-Ei Kudo, Toshiko Yamochi
Summary: This study demonstrates that an automated quantitative method using a deep learning-based model is useful in predicting the prognosis of patients with ulcerative colitis by evaluating mucin depletion.
JOURNAL OF GASTROENTEROLOGY
(2022)