Cancer is a leading cause of death in many countries. An early diagnosis of cancer based on biomedical imaging ensures effective treatment and a better prognosis. However, biomedical imaging presents challenges to both clinical institutions and researchers. Physiological anomalies are often characterized by slight abnormalities in individual cells or tissues, making them difficult to detect visually. Traditionally, anomalies are diagnosed by radiologists and pathologists with extensive training. This procedure, however, demands the participation of professionals and incurs a substantial cost. The cost makes large-scale biological image classification impractical. In this study, we provide unique deep neural network designs for multiclass classification of medical images, in particular cancer images. We incorporated transformers into a multiclass framework to take advantage of data-gathering capability and perform more accurate classifications. We evaluated models on publicly accessible datasets using various measures to ensure the reliability of the models. Extensive assessment metrics suggest this method can be used for a multitude of classification tasks.
GasHisSDB: A New Gastric Histopathology Image Dataset for Computer Aided Diagnosis of Gastric Cancer
Northeastern University(东北大学);Cancer Hospital, China Medical University(中国医科大学肿瘤医院);Liaoning Cancer Hospital and Institute(辽宁省肿瘤医院和研究所);Heilongjiang University(黑龙江大学);Stevens Institute of Technology(斯蒂文斯理工学院);Shengjing Hospital, China Medical University(中国医科大学盛京医院);University of Luebeck(吕贝克大学)
Segmentation Strategies in Deep Learning for Prostate Cancer Diagnosis: A Comparative Study of Mamba, SAM, and YOLO
School of Electrical Engineering, Iran University of Science and Technology(伊朗科学技术大学电气工程学院);School of Computer Engineering, Iran University of Science and Technology(伊朗科学技术大学计算机工程学院);School of Electrical Engineering, Shahrood Branch, Islamic Azad University(伊斯兰阿扎德大学沙赫鲁德分校电气工程学院);Medical Sciences and Technologies Department, Science and Research Branch, Islamic Azad University(伊斯兰阿扎德大学科学研究分支医学与技术系);Biomedical Engineering Department, School of Electrical Engineering, Iran University of Science and Technology(伊朗科学技术大学电气工程学院生物医学工程系)
CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans
DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Johns Hopkins University(约翰斯·霍普金斯大学);Hupan Lab(湖畔实验室);Sun Yat-sen University Cancer Center(中山大学肿瘤防治中心);Sichuan Cancer Hospital(四川省肿瘤医院);The First Affiliated Hospital of Zhejiang University(浙江大学医学院附属第一医院);Shengjing Hospital of China Medical University(中国医科大学附属盛京医院);Guangdong Provincial People’s Hospital(广东省人民医院)
A 3D Probabilistic Deep Learning System for Detection and Diagnosis of Lung Cancer Using Low-Dose CT Scans
Draper(德雷珀实验室);Google(谷歌)
我们介绍了一种新的计算机辅助检测和诊断系统,肺癌筛查与低剂量CT扫描,产生有意义的概率评估。我们的系统完全基于3D卷积神经网络,并在公开的LUNA16和Kaggle Data Science Bowl挑战赛上实现了肺结节检测和恶性肿瘤分类任务的最新性能。虽然结节检测系统通常是自行设计和优化的,但我们发现,考虑检测和诊断组件之间的耦合是很重要的。利用这种耦合使我们能够开发一种端到端系统,该系统具有更高和更强大的性能,并消除了对结节检测假阳性减少阶段的需要。此外,我们在我们的深度学习系统中描述了模型的不确定性,这是肺部CT分析的第一个,并表明我们可以使用它来为结节检测和患者恶性肿瘤诊断提供校准良好的分类概率。这些由模型不确定性提供信息的校准概率可用于后续基于风险的诊断干预或疾病治疗决策,正如我们使用基于概率的患者转诊策略进一步改善我们的结果所证明的那样。
DepViT-CAD: Deployable Vision Transformer-Based Cancer Diagnosis in Histopathology
University of Padova, Italy(意大利帕多瓦大学);Unit of Surgical Pathology and Cytopathology, Ospedale dell’Angelo, Italy(意大利奥斯佩达莱-安吉洛外科病理学与细胞病理学单位);Pathological Anatomy Unit, Padova University-Hospital, Italy(意大利帕多瓦大学医院病理学解剖单位);Department of Medicine, University of Padova, Italy(意大利帕多瓦大学医学系);Department of Integrated Diagnostics, Azienda Ospedale-Università Padova, Italy(意大利帕多瓦医院-大学整合诊断系)
Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach
Tyris Tech S.L.(泰瑞斯科技公司);Universitat Politècnica de València(瓦伦西亚理工大学);ValgrAI – Valencian Graduate School and Research Network for Artificial Intelligence(瓦伦西亚人工智能研究生院与研究网络)
Histopathological Imaging Classification of Breast Tissue for Cancer Diagnosis Support Using Deep Learning Models
Vietnam Aviation Academy(越南航空学院);Ho Chi Minh City Open University(胡志明市开放大学);University of Information Technology, VNU-HCM(胡志明市国家大学信息技术大学)
根据一些医学成像技术,称为苏木精和伊红的乳腺组织病理学图像被认为是癌症诊断的金标准。基于将病理图像(WSI)划分为多个补丁的想法,我们使用窗口[512,512]从左到右滑动,从上到下滑动,每个滑动步骤重叠50%,以增强从ICIAR 2018 Grand Challenge收集的400张图像数据集上的数据。然后利用EfficientNet模型对乳腺癌组织病理图像进行分类识别,将其分为正常、良性、癌、浸润癌四种类型。EfficientNet模型是最近开发的一种模型,它使用一组固定的缩放因子统一缩放网络的宽度,深度和分辨率,这些缩放因子非常适合训练高分辨率的图像。实验结果表明,该模型在训练集和评价集上的分类准确率分别达到98%和93%,具有较强的竞争力。
Deep Doubly Supervised Transfer Network for Diagnosis of Breast Cancer with Imbalanced Ultrasound Imaging Modalities
Shanghai Institute for Advanced Communication and Data Science(上海先进通信与数据科学研究院);The First Affiliated Hospital of Anhui Medical University(安徽医科大学第一附属医院);Fudan University Shanghai Cancer Center(复旦大学附属肿瘤医院);Shanghai Medical College, Fudan University(复旦大学上海医学院);School of Science, Shanghai University(上海大学理学院)
Interpretative Computer-aided Lung Cancer Diagnosis: from Radiology Analysis to Malignancy Evaluation
College of Physics and Information Engineering, Fuzhou University(福州大学物理与信息工程学院);Thoracic Department, Fujian Medical University Union Hospital(福建医科大学附属协和医院胸外科)
Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence Assisted Cancer Diagnosis
Karolinska Institutet(卡罗林斯卡学院);FFEI Ltd(FFEI有限公司);University of Turku(图尔库大学);Stavanger University Hospital(斯塔万格大学医院);University of Stavanger(斯塔万格大学);Aarhus University Hospital(奥胡斯大学医院);Aarhus University(奥胡斯大学);Tampere University(坦佩雷大学)
Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);College of Biomedical Engineering, Sichuan University(四川大学生物医学工程学院);AI Lab, Tencent(腾讯AI实验室);The Fourth Hospital of Hebei Medical University(河北医科大学第四医院);Massachusetts General Hospital(麻省总医院);Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Harvard Medical School(哈佛医学院);Children’s Hospital of Chongqing Medical University(重庆医科大学附属儿童医院);The Affiliated Yantai Yuhuangding Hospital of Qingdao University(青岛大学附属烟台毓璜顶医院)
UGGNet: Bridging U-Net and VGG for Advanced Breast Cancer Diagnosis
School of Engineering, Tokyo Institute of Technology(东京技术大学工学院);Faculty of Information Technology Nguyen Tat Thanh University(Nguyen Tat Thanh大学信息科技学院)
RamanSeg: Interpretability-driven Deep Learning on Raman Spectra for Cancer Diagnosis
Department of Computer Science and Technology(计算机科学与技术系);University of Cambridge(剑桥大学);Department of Physics(物理系);Department of Otorhinolaryngology(耳鼻喉科系);Jena University Hospital(耶拿大学医院);Section Pathology of the Institute of Forensic Medicine(法医学研究所病理学部);Cambridge Raman Imaging Srl(剑桥拉曼成像有限公司)
Can Domain Experts Rely on AI Appropriately? A Case Study on AI-Assisted Prostate Cancer MRI Diagnosis
University of Chicago(芝加哥大学);Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);University of Michigan(密歇根大学);Bagcilar Training and Research Hospital(巴格奇拉尔培训与研究医院);Hospital of Bolzano (SABES-ASDAA)(博尔扎诺医院(SABES-ASDAA));Radiology Associates of North Texas(北德克萨斯放射协会);İstanbul Medipol University Hospital(伊斯坦布尔梅迪波尔大学医院)
Extending the Horizon of Early Diagnosis: Lung Cancer Prediction with Vision Transformers
Oak Ridge National Laboratory(橡树岭国家实验室);Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院);Phoenix VA Medical Center(凤凰城退伍军人事务医疗中心);Vanderbilt University Medical Center(范德堡大学医学中心)
SDCT-AuxNet$^θ$: DCT Augmented Stain Deconvolutional CNN with Auxiliary Classifier for Cancer Diagnosis
IIIT-Delhi(德里印度理工学院信息技术学院);AIIMS(全印医学科学学院)
急性淋巴细胞白血病(ALL)是一种全球普遍存在的儿科白细胞癌症。随着卷积神经网络(CNN)的普及,癌症的计算机辅助诊断引起了人们的广泛关注。这些工具易于部署,具有成本效益。因此,这些可以使癌症诊断设施的广泛覆盖成为可能。然而,到目前为止,由于没有大型训练数据集,开发这种用于ALL癌症的工具具有挑战性。恶性细胞和正常细胞之间的视觉相似性增加了问题的复杂性。本文讨论了最近发布的一个大型数据集,并提出了一种用于ALL癌症细胞图像分类的新型深度学习架构。所提出的架构,即SDCT-CNN Net $^θ$是一个2模块框架,它利用紧凑的CNN作为一个模块中的主分类器和核SVM作为辅助分类器在另一个。虽然CNN分类器通过双线性池化来使用特征,但是辅助分类器使用频谱平均特征。此外,该CNN是在光密度域中的染色剂去卷积量图像上而不是在传统的RGB图像上训练的。提出了一种新的测试策略,利用两个分类器的决策使用的置信度分数的预测类标签。在我们最近发布的15114张ALL癌症和健康细胞图像的公共数据集上进行了详细的实验,以确定所提出的方法的有效性,该方法对受试者水平的变异性也是鲁棒的。获得的加权F1评分为94.8 $\%$,这是迄今为止在这个具有挑战性的数据集上最好的。
Computer-aided diagnosis of lung carcinoma using deep learning - a pilot study
National University of Defense Technology(中国人民解放军国防科技大学);Central South University(中南大学);Autonomous University of Barcelona(巴塞罗那自治大学);Eindhoven University of Technology(埃因霍温理工大学);The First Hospital of Changsha City(长沙市第一医院);The First People’s Hospital of Foshan(佛山市第一人民医院);Yale School of Medicine(耶鲁医学院);Radboud University Medical Center(拉德堡德大学医学中心)
Early Diagnosis of Lung Cancer Using Computer Aided Detection via Lung Segmentation Approach
NMAM Institute of Technology(NMAM理工学院);Visvesvaraya Technological University(韦斯韦斯瓦拉亚理工大学);Sahyadri College of Engineering and Management(萨亚德里工程与管理学院);JSS Academy of Technical Education(JSS技术教育学院)
Artificial Intelligence-Assisted Prostate Cancer Diagnosis for Reduced Use of Immunohistochemistry
Stavanger University Hospital(斯塔万格大学医院);University of Stavanger(斯塔万格大学);Karolinska Institutet(卡罗林斯卡学院);Synlab;University of Bergen(卑尔根大学);Griffith University(格里菲斯大学);SciLifeLab