51
|
Bosma JS, Saha A, Hosseinzadeh M, Slootweg I, de Rooij M, Huisman H. Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning-based Prostate Cancer Detection Using Biparametric MRI. Radiol Artif Intell 2023; 5:e230031. [PMID: 37795142 PMCID: PMC10546362 DOI: 10.1148/ryai.230031] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2023] [Revised: 06/07/2023] [Accepted: 06/22/2023] [Indexed: 10/06/2023]
Abstract
Purpose To evaluate a novel method of semisupervised learning (SSL) guided by automated sparse information from diagnostic reports to leverage additional data for deep learning-based malignancy detection in patients with clinically significant prostate cancer. Materials and Methods This retrospective study included 7756 prostate MRI examinations (6380 patients) performed between January 2014 and December 2020 for model development. An SSL method, report-guided SSL (RG-SSL), was developed for detection of clinically significant prostate cancer using biparametric MRI. RG-SSL, supervised learning (SL), and state-of-the-art SSL methods were trained using 100, 300, 1000, or 3050 manually annotated examinations. Performance on detection of clinically significant prostate cancer by RG-SSL, SL, and SSL was compared on 300 unseen examinations from an external center with a histopathologically confirmed reference standard. Performance was evaluated using receiver operating characteristic (ROC) and free-response ROC analysis. P values for performance differences were generated with a permutation test. Results At 100 manually annotated examinations, mean examination-based diagnostic area under the ROC curve (AUC) values for RG-SSL, SL, and the best SSL were 0.86 ± 0.01 (SD), 0.78 ± 0.03, and 0.81 ± 0.02, respectively. Lesion-based detection partial AUCs were 0.62 ± 0.02, 0.44 ± 0.04, and 0.48 ± 0.09, respectively. Examination-based performance of SL with 3050 examinations was matched by RG-SSL with 169 manually annotated examinations, thus requiring 14 times fewer annotations. Lesion-based performance was matched with 431 manually annotated examinations, requiring six times fewer annotations. Conclusion RG-SSL outperformed SSL in clinically significant prostate cancer detection and achieved performance similar to SL even at very low annotation budgets.Keywords: Annotation Efficiency, Computer-aided Detection and Diagnosis, MRI, Prostate Cancer, Semisupervised Deep Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.
Collapse
Affiliation(s)
- Joeran S. Bosma
- From the Diagnostic Image Analysis Group, Department of Medical
Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA
Nijmegen, the Netherlands
| | - Anindo Saha
- From the Diagnostic Image Analysis Group, Department of Medical
Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA
Nijmegen, the Netherlands
| | - Matin Hosseinzadeh
- From the Diagnostic Image Analysis Group, Department of Medical
Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA
Nijmegen, the Netherlands
| | - Ivan Slootweg
- From the Diagnostic Image Analysis Group, Department of Medical
Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA
Nijmegen, the Netherlands
| | - Maarten de Rooij
- From the Diagnostic Image Analysis Group, Department of Medical
Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA
Nijmegen, the Netherlands
| | - Henkjan Huisman
- From the Diagnostic Image Analysis Group, Department of Medical
Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA
Nijmegen, the Netherlands
| |
Collapse
|
52
|
Giavina-Bianchi M, Vitor WG, Fornasiero de Paiva V, Okita AL, Sousa RM, Machado B. Explainability agreement between dermatologists and five visual explanations techniques in deep neural networks for melanoma AI classification. Front Med (Lausanne) 2023; 10:1241484. [PMID: 37746081 PMCID: PMC10513767 DOI: 10.3389/fmed.2023.1241484] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Accepted: 08/14/2023] [Indexed: 09/26/2023] Open
Abstract
Introduction The use of deep convolutional neural networks for analyzing skin lesion images has shown promising results. The identification of skin cancer by faster and less expensive means can lead to an early diagnosis, saving lives and avoiding treatment costs. However, to implement this technology in a clinical context, it is important for specialists to understand why a certain model makes a prediction; it must be explainable. Explainability techniques can be used to highlight the patterns of interest for a prediction. Methods Our goal was to test five different techniques: Grad-CAM, Grad-CAM++, Score-CAM, Eigen-CAM, and LIME, to analyze the agreement rate between features highlighted by the visual explanation maps to 3 important clinical criteria for melanoma classification: asymmetry, border irregularity, and color heterogeneity (ABC rule) in 100 melanoma images. Two dermatologists scored the visual maps and the clinical images using a semi-quantitative scale, and the results were compared. They also ranked their preferable techniques. Results We found that the techniques had different agreement rates and acceptance. In the overall analysis, Grad-CAM showed the best total+partial agreement rate (93.6%), followed by LIME (89.8%), Grad-CAM++ (88.0%), Eigen-CAM (86.4%), and Score-CAM (84.6%). Dermatologists ranked their favorite options: Grad-CAM and Grad-CAM++, followed by Score-CAM, LIME, and Eigen-CAM. Discussion Saliency maps are one of the few methods that can be used for visual explanations. The evaluation of explainability with humans is ideal to assess the understanding and applicability of these methods. Our results demonstrated that there is a significant agreement between clinical features used by dermatologists to diagnose melanomas and visual explanation techniques, especially Grad-Cam.
Collapse
|
53
|
Alammar Z, Alzubaidi L, Zhang J, Li Y, Lafta W, Gu Y. Deep Transfer Learning with Enhanced Feature Fusion for Detection of Abnormalities in X-ray Images. Cancers (Basel) 2023; 15:4007. [PMID: 37568821 PMCID: PMC10417687 DOI: 10.3390/cancers15154007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Revised: 07/29/2023] [Accepted: 08/05/2023] [Indexed: 08/13/2023] Open
Abstract
Medical image classification poses significant challenges in real-world scenarios. One major obstacle is the scarcity of labelled training data, which hampers the performance of image-classification algorithms and generalisation. Gathering sufficient labelled data is often difficult and time-consuming in the medical domain, but deep learning (DL) has shown remarkable performance, although it typically requires a large amount of labelled data to achieve optimal results. Transfer learning (TL) has played a pivotal role in reducing the time, cost, and need for a large number of labelled images. This paper presents a novel TL approach that aims to overcome the limitations and disadvantages of TL that are characteristic of an ImageNet dataset, which belongs to a different domain. Our proposed TL approach involves training DL models on numerous medical images that are similar to the target dataset. These models were then fine-tuned using a small set of annotated medical images to leverage the knowledge gained from the pre-training phase. We specifically focused on medical X-ray imaging scenarios that involve the humerus and wrist from the musculoskeletal radiographs (MURA) dataset. Both of these tasks face significant challenges regarding accurate classification. The models trained with the proposed TL were used to extract features and were subsequently fused to train several machine learning (ML) classifiers. We combined these diverse features to represent various relevant characteristics in a comprehensive way. Through extensive evaluation, our proposed TL and feature-fusion approach using ML classifiers achieved remarkable results. For the classification of the humerus, we achieved an accuracy of 87.85%, an F1-score of 87.63%, and a Cohen's Kappa coefficient of 75.69%. For wrist classification, our approach achieved an accuracy of 85.58%, an F1-score of 82.70%, and a Cohen's Kappa coefficient of 70.46%. The results demonstrated that the models trained using our proposed TL approach outperformed those trained with ImageNet TL. We employed visualisation techniques to further validate these findings, including a gradient-based class activation heat map (Grad-CAM) and locally interpretable model-independent explanations (LIME). These visualisation tools provided additional evidence to support the superior accuracy of models trained with our proposed TL approach compared to those trained with ImageNet TL. Furthermore, our proposed TL approach exhibited greater robustness in various experiments compared to ImageNet TL. Importantly, the proposed TL approach and the feature-fusion technique are not limited to specific tasks. They can be applied to various medical image applications, thus extending their utility and potential impact. To demonstrate the concept of reusability, a computed tomography (CT) case was adopted. The results obtained from the proposed method showed improvements.
Collapse
Affiliation(s)
- Zaenab Alammar
- School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia; (J.Z.); (Y.L.)
- Centre for Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Laith Alzubaidi
- Centre for Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia
- School of Mechanical, Medical and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia;
- ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Jinglan Zhang
- School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia; (J.Z.); (Y.L.)
- Centre for Data Science, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Yuefeng Li
- School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia; (J.Z.); (Y.L.)
| | | | - Yuantong Gu
- School of Mechanical, Medical and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia;
- ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia
| |
Collapse
|
54
|
Gao Y, Zhang H, Song B, Zhao C, Lu Q. Electric Double Layer Based Epidermal Electronics for Healthcare and Human-Machine Interface. BIOSENSORS 2023; 13:787. [PMID: 37622873 PMCID: PMC10452760 DOI: 10.3390/bios13080787] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/20/2023] [Revised: 07/25/2023] [Accepted: 07/31/2023] [Indexed: 08/26/2023]
Abstract
Epidermal electronics, an emerging interdisciplinary field, is advancing the development of flexible devices that can seamlessly integrate with the skin. These devices, especially Electric Double Layer (EDL)-based sensors, overcome the limitations of conventional electronic devices, offering high sensitivity, rapid response, and excellent stability. Especially, Electric Double Layer (EDL)-based epidermal sensors show great potential in the application of wearable electronics to detect biological signals due to their high sensitivity, fast response, and excellent stability. The advantages can be attributed to the biocompatibility of the materials, the flexibility of the devices, and the large capacitance due to the EDL effect. Furthermore, we discuss the potential of EDL epidermal electronics as wearable sensors for health monitoring and wound healing. These devices can analyze various biofluids, offering real-time feedback on parameters like pH, temperature, glucose, lactate, and oxygen levels, which aids in accurate diagnosis and effective treatment. Beyond healthcare, we explore the role of EDL epidermal electronics in human-machine interaction, particularly their application in prosthetics and pressure-sensing robots. By mimicking the flexibility and sensitivity of human skin, these devices enhance the functionality and user experience of these systems. This review summarizes the latest advancements in EDL-based epidermal electronic devices, offering a perspective for future research in this rapidly evolving field.
Collapse
Affiliation(s)
- Yuan Gao
- School of CHIPS, XJTLU Entrepreneur College (Taicang), Xi’an Jiaotong-Liverpool University, 111 Taicang Avenue, Taicang 215488, China; (Y.G.); (H.Z.); (B.S.)
| | - Hanchu Zhang
- School of CHIPS, XJTLU Entrepreneur College (Taicang), Xi’an Jiaotong-Liverpool University, 111 Taicang Avenue, Taicang 215488, China; (Y.G.); (H.Z.); (B.S.)
| | - Bowen Song
- School of CHIPS, XJTLU Entrepreneur College (Taicang), Xi’an Jiaotong-Liverpool University, 111 Taicang Avenue, Taicang 215488, China; (Y.G.); (H.Z.); (B.S.)
| | - Chun Zhao
- School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou 215123, China;
| | - Qifeng Lu
- School of CHIPS, XJTLU Entrepreneur College (Taicang), Xi’an Jiaotong-Liverpool University, 111 Taicang Avenue, Taicang 215488, China; (Y.G.); (H.Z.); (B.S.)
| |
Collapse
|
55
|
Sitaru S, Oueslati T, Schielein MC, Weis J, Kaczmarczyk R, Rueckert D, Biedermann T, Zink A. Automatische Körperteil-Identifikation in dermatologischen klinischen Bildern durch maschinelles Lernen. J Dtsch Dermatol Ges 2023; 21:863-871. [PMID: 37574684 DOI: 10.1111/ddg.15113_g] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Accepted: 03/30/2023] [Indexed: 08/15/2023]
Abstract
ZusammenfassungHintergrundDermatologische Erkrankungen sind in allen Bevölkerungsgruppen weit verbreitet. Das betroffene Körperteil ist für ihre Diagnose, Therapie und Forschung von Bedeutung. Die automatische Identifizierung der abgebildeten Körperteile in dermatologischen Krankheitsbildern könnte daher die klinische Versorgung verbessern, indem sie zusätzliche Informationen für klinische Entscheidungsalgorithmen liefert, schwer zu behandelnde Bereiche aufdeckt und die Forschung durch die Identifizierung neuer Krankheitsmuster unterstützt.Patienten und MethodikIn dieser Studie wurden 6219 annotierte dermatologische Bilder aus unserer klinischen Datenbank verwendet, womit ein neuronales Netz trainiert und validiert wurde. Als Anwendung wurden mit diesem System qualitative Heatmaps für die Verteilung von Körperteilen bei häufigen dermatologischen Erkrankungen erstellt.ErgebnisseDer Algorithmus erreichte eine mittlere balancierte Genauigkeit (Accuracy) von 89% (74,8%–96,5%). Die Fotos von nichtmelanozytärem Hautkrebs betrafen vor allem das Gesicht und den Oberkörper, während die größte Häufigkeit der Ekzem‐ und Psoriasis‐Bildverteilung den Oberkörper, die Beine und die Hände umfassten.SchlussfolgerungenDie Genauigkeit dieses Systems ist vergleichbar mit den besten bisher veröffentlichten Algorithmen für Bildklassifizierungsaufgaben, was darauf hindeutet, dass dieser Algorithmus die Diagnose, Therapie und Forschung bei dermatologischen Erkrankungen verbessern könnte.
Collapse
Affiliation(s)
- Sebastian Sitaru
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
| | - Talel Oueslati
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
| | - Maximilian C Schielein
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
| | - Johanna Weis
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
| | - Robert Kaczmarczyk
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
| | - Daniel Rueckert
- Institut für künstliche Intelligenz und Informatik in der Medizin Fakultät, Technische Universität München, München, Deutschland
- Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, Großbritannien
| | - Tilo Biedermann
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
| | - Alexander Zink
- Klinik für Dermatologie und Allergologie, Technische Universität München, Medizinische Fakultät, München, Deutschland
- Abteilung für Dermatologie und Venerologie, Medizinische Fakultät Solna, Karolinska Institutet, Stockholm, Schweden
| |
Collapse
|
56
|
Sitaru S, Oueslati T, Schielein MC, Weis J, Kaczmarczyk R, Rueckert D, Biedermann T, Zink A. Automatic body part identification in real-world clinical dermatological images using machine learning. J Dtsch Dermatol Ges 2023; 21:863-869. [PMID: 37306036 DOI: 10.1111/ddg.15113] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Accepted: 03/30/2023] [Indexed: 06/13/2023]
Abstract
BACKGROUND Dermatological conditions are prevalent across all population sub-groups. The affected body part is of importance to their diagnosis, therapy, and research. The automatic identification of body parts in dermatological clinical pictures could therefore improve clinical care by providing additional information for clinical decision-making algorithms, discovering hard-to-treat areas, and research by identifying new patterns of disease. PATIENTS AND METHODS In this study, we used 6,219 labelled dermatological images from our clinical database, which were used to train and validate a convolutional neural network. As a use case, qualitative heatmaps for the body part distribution in common dermatological conditions was generated using this system. RESULTS The algorithm reached a mean balanced accuracy of 89% (range 74.8%-96.5%). Non-melanoma skin cancer photos were mostly of the face and torso, while hotspots of eczema and psoriasis image distribution included the torso, legs, and hands. CONCLUSIONS The accuracy of this system is comparable to the best to-date published algorithms for image classification challenges, suggesting this algorithm could boost diagnosis, therapy, and research of dermatological conditions.
Collapse
Affiliation(s)
- Sebastian Sitaru
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
| | - Talel Oueslati
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
| | - Maximilian C Schielein
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
| | - Johanna Weis
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
| | - Robert Kaczmarczyk
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
| | - Daniel Rueckert
- Technical University of Munich, School of Medicine, Institute of AI and Informatics in Medicine, Munich, Germany
- Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, UK
| | - Tilo Biedermann
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
| | - Alexander Zink
- Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany
- Division of Dermatology and Venereology, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
57
|
Kaneda Y, Takahashi R, Kaneda U, Akashima S, Okita H, Misaki S, Yamashiro A, Ozaki A, Tanimoto T. Assessing the Performance of GPT-3.5 and GPT-4 on the 2023 Japanese Nursing Examination. Cureus 2023; 15:e42924. [PMID: 37667724 PMCID: PMC10475149 DOI: 10.7759/cureus.42924] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/03/2023] [Indexed: 09/06/2023] Open
Abstract
Purpose The purpose of this study was to evaluate the changes in capabilities between the Generative Pre-trained Transformer (GPT)-3.5 and GPT-4 versions of the large-scale language model ChatGPT within a Japanese medical context. Methods The study involved ChatGPT versions 3.5 and 4 responding to questions from the 112th Japanese National Nursing Examination (JNNE). The study comprised three analyses: correct answer rate and score rate calculations, comparisons between GPT-3.5 and GPT-4, and comparisons of correct answer rates for conversation questions. Results ChatGPT versions 3.5 and 4 responded to 237 out of 238 Japanese questions from the 112th JNNE. While GPT-3.5 achieved an overall accuracy rate of 59.9%, failing to meet the passing standards in compulsory and general/scenario-based questions, scoring 58.0% and 58.3%, respectively, GPT-4 had an accuracy rate of 79.7%, satisfying the passing standards by scoring 90.0% and 77.7%, respectively. For each problem type, GPT-4 showed a higher accuracy rate than GPT-3.5. Specifically, the accuracy rates for compulsory questions improved from 58.0% with GPT-3.5 to 90.0% with GPT-4. For general questions, the rates went from 64.6% with GPT-3.5 to 75.6% with GPT-4. In scenario-based questions, the accuracy rates improved substantially from 51.7% with GPT-3.5 to 80.0% with GPT-4. For conversation questions, GPT-3.5 had an accuracy rate of 73.3% and GPT-4 had an accuracy rate of 93.3%. Conclusions The GPT-4 version of ChatGPT displayed performance sufficient to pass the JNNE, significantly improving from GPT-3.5. This suggests specialized medical training could make such models beneficial in Japanese clinical settings, aiding decision-making. However, user awareness and training are crucial, given potential inaccuracies in ChatGPT's responses. Hence, responsible usage with an understanding of its capabilities and limitations is vital to best support healthcare professionals and patients.
Collapse
Affiliation(s)
- Yudai Kaneda
- College of Medicine, Hokkaido University, Hokkaido, JPN
| | - Ryo Takahashi
- Department of Rehabilitation Medicine, Sonodakai Joint Replacement Center Hospital, Tokyo, JPN
| | - Uiri Kaneda
- Department of Foreign Languages, Dokkyo University, Saitama, JPN
| | - Shiori Akashima
- Department of Obstetrics and Gynecology, Shonan Kamakura General Hospital, Kanagawa, JPN
| | - Haruna Okita
- College of Medicine, Tokyo Women's Medical University, Tokyo, JPN
| | - Sadaya Misaki
- Department of Rehabilitation Medicine, Sonoda Daiichi Hospital, Tokyo, JPN
| | - Akimi Yamashiro
- Department of Nutrition Science, Shokei Gakuin University, Miyagi, JPN
| | - Akihiko Ozaki
- Department of Breast and Thyroid Surgery, Jyoban Hospital of Tokiwa Foundation, Fukushima, JPN
| | | |
Collapse
|
58
|
AlSuwaidan L. Deep Learning Based Classification of Dermatological Disorders. Biomed Eng Comput Biol 2023; 14:11795972221138470. [PMID: 37533697 PMCID: PMC10392223 DOI: 10.1177/11795972221138470] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Accepted: 07/01/2023] [Indexed: 08/04/2023] Open
Abstract
Automated medical diagnosis has become crucial and significantly supports medical doctors. Thus, there is a demand for inventing deep learning (DL) and convolutional networks for analyzing medical images. Dermatology, in particular, is one of the domains that was recently targeted by AI specialists to introduce new DL algorithms or enhance convolutional neural network (CNN) architectures. A significantly high proportion of studies in the field are concerned with skin cancer, whereas other dermatological disorders are still limited. In this work, we examined the performance of 6 CNN architectures named VGG16, EfficientNet, InceptionV3, MobileNet, NasNet, and ResNet50 for the top 3 dermatological disorders that frequently appear in the Middle East. An Image filtering and denoising were imposed in this work to enhance image quality and increase architecture performance. Experimental results revealed that MobileNet achieved the highest performance and accuracy among the CNN architectures and can classify disorder with high performance (95.7% accuracy). Future scope will focus more on proposing a new methodology for deep-based classification. In addition, we will expand the dataset for more images that consider new disorders and variations.
Collapse
Affiliation(s)
- Lulwah AlSuwaidan
- Lulwah AlSuwaidan, Innovation and Emerging Technologies Center, Digital Government Authority, PO Box 11112, Riyadh, Saudi Arabia.
| |
Collapse
|
59
|
Brown A, Tomasev N, Freyberg J, Liu Y, Karthikesalingam A, Schrouff J. Detecting shortcut learning for fair medical AI using shortcut testing. Nat Commun 2023; 14:4314. [PMID: 37463884 DOI: 10.1038/s41467-023-39902-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 06/26/2023] [Indexed: 07/20/2023] Open
Abstract
Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. An important step is to characterize the (un)fairness of ML models-their tendency to perform differently across subgroups of the population-and to understand its underlying mechanisms. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. Diagnosing this phenomenon is difficult as sensitive attributes may be causally linked with disease. Using multitask learning, we propose a method to directly test for the presence of shortcut learning in clinical ML systems and demonstrate its application to clinical tasks in radiology and dermatology. Finally, our approach reveals instances when shortcutting is not responsible for unfairness, highlighting the need for a holistic approach to fairness mitigation in medical AI.
Collapse
Affiliation(s)
| | | | | | - Yuan Liu
- Google Research, Palo Alto, CA, USA
| | | | | |
Collapse
|
60
|
Ding Y, Yang F, Han M, Li C, Wang Y, Xu X, Zhao M, Zhao M, Yue M, Deng H, Yang H, Yao J, Liu Y. Multi-center study on predicting breast cancer lymph node status from core needle biopsy specimens using multi-modal and multi-instance deep learning. NPJ Breast Cancer 2023; 9:58. [PMID: 37443117 DOI: 10.1038/s41523-023-00562-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2022] [Accepted: 06/26/2023] [Indexed: 07/15/2023] Open
Abstract
The objective of our study is to develop a deep learning model based on clinicopathological data and digital pathological image of core needle biopsy specimens for predicting breast cancer lymph node metastasis. We collected 3701 patients from the Fourth Hospital of Hebei Medical University and 190 patients from four medical centers in Hebei Province. Integrating clinicopathological data and image features build multi-modal and multi-instance (MMMI) deep learning model to obtain the final prediction. For predicting with or without lymph node metastasis, the AUC was 0.770, 0.709, 0.809 based on the clinicopathological features, WSI and MMMI, respectively. For predicting four classification of lymph node status (no metastasis, isolated tumor cells (ITCs), micrometastasis, and macrometastasis), the prediction based on clinicopathological features, WSI and MMMI were compared. The AUC for no metastasis was 0.770, 0.709, 0.809, respectively; ITCs were 0.619, 0.531, 0.634, respectively; micrometastasis were 0.636, 0.617, 0.691, respectively; and macrometastasis were 0.748, 0.691, 0.758, respectively. The MMMI model achieved the highest prediction accuracy. For prediction of different molecular types of breast cancer, MMMI demonstrated a better prediction accuracy for any type of lymph node status, especially in the molecular type of triple negative breast cancer (TNBC). In the external validation sets, MMMI also showed better prediction accuracy in the four classification, with AUC of 0.725, 0.757, 0.525, and 0.708, respectively. Finally, we developed a breast cancer lymph node metastasis prediction model based on a MMMI model. Through all cases tests, the results showed that the overall prediction ability was high.
Collapse
Affiliation(s)
- Yan Ding
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China
| | - Fan Yang
- AI Lab, Tencent, 518057, Shenzhen, China
| | - Mengxue Han
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China
| | - Chunhui Li
- Department of Pathology, Chengde Medical University Affiliated Hospital, 067000, Chengde, Hebei, China
| | - Yanan Wang
- Department of Pathology, Affiliated Hospital of Hebei University, 071000, Baoding, Hebei, China
| | - Xin Xu
- Department of Pathology, Xingtai People's Hospital, 054000, Xingtai, Hebei, China
| | - Min Zhao
- Department of Pathology, First Hospital of Qinhuangdao, 066000, Qinhuangdao, Hebei, China
| | - Meng Zhao
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China
| | - Meng Yue
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China
| | - Huiyan Deng
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China
| | - Huichai Yang
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China
| | | | - Yueping Liu
- Department of Pathology, The Fourth Hospital of Hebei Medical University, 050011, Shijiazhuang, Hebei, China.
| |
Collapse
|
61
|
Reynolds M, Chaudhary T, Eshaghzadeh Torbati M, Tudorascu DL, Batmanghelich K. ComBat Harmonization: Empirical Bayes versus fully Bayes approaches. Neuroimage Clin 2023; 39:103472. [PMID: 37506457 PMCID: PMC10412957 DOI: 10.1016/j.nicl.2023.103472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Revised: 07/05/2023] [Accepted: 07/06/2023] [Indexed: 07/30/2023]
Abstract
Studying small effects or subtle neuroanatomical variation requires large-scale sample size data. As a result, combining neuroimaging data from multiple datasets is necessary. Variation in acquisition protocols, magnetic field strength, scanner build, and many other non-biologically related factors can introduce undesirable bias into studies. Hence, harmonization is required to remove the bias-inducing factors from the data. ComBat is one of the most common methods applied to features from structural images. ComBat models the data using a hierarchical Bayesian model and uses the empirical Bayes approach to infer the distribution of the unknown factors. The empirical Bayes harmonization method is computationally efficient and provides valid point estimates. However, it tends to underestimate uncertainty. This paper investigates a new approach, fully Bayesian ComBat, where Monte Carlo sampling is used for statistical inference. When comparing fully Bayesian and empirical Bayesian ComBat, we found Empirical Bayesian ComBat more effectively removed scanner strength information and was much more computationally efficient. Conversely, fully Bayesian ComBat better preserved biological disease and age-related information while performing more accurate harmonization on traveling subjects. The fully Bayesian approach generates a rich posterior distribution, which is useful for generating simulated imaging features for improving classifier performance in a limited data setting. We show the generative capacity of our model for augmenting and improving the detection of patients with Alzheimer's disease. Posterior distributions for harmonized imaging measures can also be used for brain-wide uncertainty comparison and more principled downstream statistical analysis.Code for our new fully Bayesian ComBat extension is available at https://github.com/batmanlab/BayesComBat.
Collapse
Affiliation(s)
- Maxwell Reynolds
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, 5607 Baum Blvd. Suite 500, Pittsburgh, PA 15206, USA.
| | - Tigmanshu Chaudhary
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, 5607 Baum Blvd. Suite 500, Pittsburgh, PA 15206, USA.
| | - Mahbaneh Eshaghzadeh Torbati
- Intelligent System Program, University of Pittsburgh School of Computing and Information, 210 South Bouquet Street, Pittsburgh, PA 15260, USA.
| | - Dana L Tudorascu
- Department of Psychiatry, University of Pittsburgh School of Medicine, 3811 O'Hara Street, Pittsburgh, PA 15213, USA; Department of Biostatistics, University of Pittsburgh, 130 De Soto Street, Pittsburgh, PA 15213, USA.
| | - Kayhan Batmanghelich
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, 5607 Baum Blvd. Suite 500, Pittsburgh, PA 15206, USA.
| |
Collapse
|
62
|
Malvehy J, Dreno B, Barba E, Dirshka T, Fumero E, Greis C, Gupta G, Lacarrubba F, Micali G, Moreno D, Pellacani G, Sampietro-Colom L, Stratigos A, Puig S. Smart e-Skin Cancer Care in Europe During and after the Covid-19 Pandemic: a Multidisciplinary Expert Consensus. Dermatol Pract Concept 2023; 13:e2023181. [PMID: 37557116 PMCID: PMC10412091 DOI: 10.5826/dpc.1303a181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/27/2023] [Indexed: 08/11/2023] Open
Abstract
INTRODUCTION Melanoma is the deadliest of all the skin cancers and its incidence is increasing every year in Europe. Patients with melanoma often present late to the specialist and treatment is delayed for many reasons (delay in patient consultation, misdiagnosis by general practitioners, and/or limited access to dermatologists). Beyond this, there are significant inequalities in skin cancer between population groups within the same country and between countries across Europe. The emergence of the COVID-19 pandemic only aggravated these health deficiencies. OBJECTIVES The aim was to create an expert opinion about the challenges in skin cancer management in Europe during the post COVID-19 acute pandemic and to identify and discuss the implementation of new technologies (including e-health and artificial intelligence defined as "Smart Skin Cancer Care") to overcome them. METHODS For this purpose, an ad-hoc questionnaire with items addressing topics of skin cancer care was developed, answered independently and discussed by a multidisciplinary European panel of experts comprising dermatologists, dermato-oncologists, patient advocacy representatives, digital health technology experts, and health technology assessment experts. RESULTS After all panel of experts discussions, a multidisciplinary expert opinion was created. CONCLUSIONS As a conclusion, the access to dermatologists is difficult and will be aggravated in the near future. This fact, together with important differences in Skin Cancer Care in Europe, suggest the need of a new approach to skin health, prevention and disease management paradigm (focused on integration of new technologies) to minimize the impact of skin cancer and to ensure optimal quality and equity.
Collapse
Affiliation(s)
- Josep Malvehy
- Dermatology Department. Hospital Clinic of Barcelona, Spain
- University of Barcelona, Barcelona, Spain. Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain. Biomedical Research Networking Centre on Rare Diseases (CIBERER), ISCIII, Barcelona, Spain
| | - Brigitte Dreno
- Department of Dermatolo-Cancerology, CHU Nantes, CIC 1413, CRCINA, University Nantes, Nantes, France
| | - Enric Barba
- Spanish Melanoma Association, Barcelona, Spain
| | - Thomas Dirshka
- Centroderm Clinic, Wuppertal, and Faculty of Health, University Witten-Herdecke, Witten, Germany
| | | | - Christian Greis
- Department Dermatology, University Hospital of Zurich, Zurich, Switzerland
| | - Girish Gupta
- University Department of Dermatology, Edinburgh Royal Infirmary, Lauriston Building, Edinburgh, UK
| | | | | | - David Moreno
- Dermatology Department, University Hospital Virgen Macarena, Seville, Spain
| | - Giovanni Pellacani
- Dermatology Department. Università degli Studi di Roma La Sapienza. Roma, Italy
| | - Laura Sampietro-Colom
- Assessment of Innovations and New Technologies Unit, Hospital Clínic of Barcelona, University of Barcelona, Barcelona, Spain
| | - Alexander Stratigos
- Department of Dermatology-Venereology, Andreas Sygros Hospital, National and Kapodestrian University of Athens, Athens, Greece
| | - Susanna Puig
- Dermatology Department. Hospital Clinic of Barcelona, Spain
- University of Barcelona, Barcelona, Spain. Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain. Biomedical Research Networking Centre on Rare Diseases (CIBERER), ISCIII, Barcelona, Spain
| |
Collapse
|
63
|
Yu YC, Zhang W, O'Gara D, Li JS, Chang SH. A moment kernel machine for clinical data mining to inform medical decision making. Sci Rep 2023; 13:10459. [PMID: 37380721 DOI: 10.1038/s41598-023-36752-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Accepted: 06/09/2023] [Indexed: 06/30/2023] Open
Abstract
Machine learning-aided medical decision making presents three major challenges: achieving model parsimony, ensuring credible predictions, and providing real-time recommendations with high computational efficiency. In this paper, we formulate medical decision making as a classification problem and develop a moment kernel machine (MKM) to tackle these challenges. The main idea of our approach is to treat the clinical data of each patient as a probability distribution and leverage moment representations of these distributions to build the MKM, which transforms the high-dimensional clinical data to low-dimensional representations while retaining essential information. We then apply this machine to various pre-surgical clinical datasets to predict surgical outcomes and inform medical decision making, which requires significantly less computational power and time for classification while yielding favorable performance compared to existing methods. Moreover, we utilize synthetic datasets to demonstrate that the developed moment-based data mining framework is robust to noise and missing data, and achieves model parsimony giving an efficient way to generate satisfactory predictions to aid personalized medical decision making.
Collapse
Affiliation(s)
- Yao-Chi Yu
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, 63130, USA
| | - Wei Zhang
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, 63130, USA
| | - David O'Gara
- Division of Computational and Data Sciences, Washington University in St. Louis, St. Louis, MO, 63130, USA
| | - Jr-Shin Li
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, 63130, USA.
- Division of Computational and Data Sciences, Washington University in St. Louis, St. Louis, MO, 63130, USA.
- Division of Biology and Biomedical Sciences, Washington University in St. Louis, St. Louis, MO, 63130, USA.
| | - Su-Hsin Chang
- Division of Public Health Sciences, Department of Surgery, Washington University School of Medicine, St. Louis, MO, 63110, USA.
| |
Collapse
|
64
|
Viriyasaranon T, Chun JW, Koh YH, Cho JH, Jung MK, Kim SH, Kim HJ, Lee WJ, Choi JH, Woo SM. Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study. Cancers (Basel) 2023; 15:3392. [PMID: 37444502 DOI: 10.3390/cancers15133392] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Revised: 06/26/2023] [Accepted: 06/26/2023] [Indexed: 07/15/2023] Open
Abstract
The aim of this study was to develop a novel deep learning (DL) model without requiring large-annotated training datasets for detecting pancreatic cancer (PC) using computed tomography (CT) images. This retrospective diagnostic study was conducted using CT images collected from 2004 and 2019 from 4287 patients diagnosed with PC. We proposed a self-supervised learning algorithm (pseudo-lesion segmentation (PS)) for PC classification, which was trained with and without PS and validated on randomly divided training and validation sets. We further performed cross-racial external validation using open-access CT images from 361 patients. For internal validation, the accuracy and sensitivity for PC classification were 94.3% (92.8-95.4%) and 92.5% (90.0-94.4%), and 95.7% (94.5-96.7%) and 99.3 (98.4-99.7%) for the convolutional neural network (CNN) and transformer-based DL models (both with PS), respectively. Implementing PS on a small-sized training dataset (randomly sampled 10%) increased accuracy by 20.5% and sensitivity by 37.0%. For external validation, the accuracy and sensitivity were 82.5% (78.3-86.1%) and 81.7% (77.3-85.4%) and 87.8% (84.0-90.8%) and 86.5% (82.3-89.8%) for the CNN and transformer-based DL models (both with PS), respectively. PS self-supervised learning can increase DL-based PC classification performance, reliability, and robustness of the model for unseen, and even small, datasets. The proposed DL model is potentially useful for PC diagnosis.
Collapse
Affiliation(s)
- Thanaporn Viriyasaranon
- Graduate Program in System Health Science and Engineering, Division of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Republic of Korea
| | - Jung Won Chun
- Center for Liver and Pancreatobiliary Cancer, National Cancer Center, Goyang 10408, Republic of Korea
| | - Young Hwan Koh
- Center for Liver and Pancreatobiliary Cancer, National Cancer Center, Goyang 10408, Republic of Korea
| | - Jae Hee Cho
- Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 03722, Republic of Korea
| | - Min Kyu Jung
- Department of Internal Medicine, Kyungpook National University Hospital, Daegu 41944, Republic of Korea
| | - Seong-Hun Kim
- Department of Internal Medicine, Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonju 54907, Republic of Korea
| | - Hyo Jung Kim
- Department of Gastroenterology, Korea University Guro Hospital, Seoul 10408, Republic of Korea
| | - Woo Jin Lee
- Center for Liver and Pancreatobiliary Cancer, National Cancer Center, Goyang 10408, Republic of Korea
| | - Jang-Hwan Choi
- Graduate Program in System Health Science and Engineering, Division of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Republic of Korea
| | - Sang Myung Woo
- Center for Liver and Pancreatobiliary Cancer, National Cancer Center, Goyang 10408, Republic of Korea
| |
Collapse
|
65
|
Azizi S, Culp L, Freyberg J, Mustafa B, Baur S, Kornblith S, Chen T, Tomasev N, Mitrović J, Strachan P, Mahdavi SS, Wulczyn E, Babenko B, Walker M, Loh A, Chen PHC, Liu Y, Bavishi P, McKinney SM, Winkens J, Roy AG, Beaver Z, Ryan F, Krogue J, Etemadi M, Telang U, Liu Y, Peng L, Corrado GS, Webster DR, Fleet D, Hinton G, Houlsby N, Karthikesalingam A, Norouzi M, Natarajan V. Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging. Nat Biomed Eng 2023:10.1038/s41551-023-01049-7. [PMID: 37291435 DOI: 10.1038/s41551-023-01049-7] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2022] [Accepted: 05/02/2023] [Indexed: 06/10/2023]
Abstract
Machine-learning models for medical tasks can match or surpass the performance of clinical experts. However, in settings differing from those of the training dataset, the performance of a model can deteriorate substantially. Here we report a representation-learning strategy for machine-learning models applied to medical-imaging tasks that mitigates such 'out of distribution' performance problem and that improves model robustness and training efficiency. The strategy, which we named REMEDIS (for 'Robust and Efficient Medical Imaging with Self-supervision'), combines large-scale supervised transfer learning on natural images and intermediate contrastive self-supervised learning on medical images and requires minimal task-specific customization. We show the utility of REMEDIS in a range of diagnostic-imaging tasks covering six imaging domains and 15 test datasets, and by simulating three realistic out-of-distribution scenarios. REMEDIS improved in-distribution diagnostic accuracies up to 11.5% with respect to strong supervised baseline models, and in out-of-distribution settings required only 1-33% of the data for retraining to match the performance of supervised models retrained using all available data. REMEDIS may accelerate the development lifecycle of machine-learning models for medical imaging.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Ting Chen
- Google Research, Mountain View, CA, USA
| | | | | | | | | | | | | | | | - Aaron Loh
- Google Research, Mountain View, CA, USA
| | | | - Yuan Liu
- Google Research, Mountain View, CA, USA
| | | | | | | | | | | | - Fiona Ryan
- Georgia Institute of Technology, Computer Science, Atlanta, GA, USA
| | | | - Mozziyar Etemadi
- School of Medicine/School of Engineering, Northwestern University, Chicago, IL, USA
| | | | - Yun Liu
- Google Research, Mountain View, CA, USA
| | - Lily Peng
- Google Research, Mountain View, CA, USA
| | | | | | | | | | | | | | | | | |
Collapse
|
66
|
Stafford H, Buell J, Chiang E, Ramesh U, Migden M, Nagarajan P, Amit M, Yaniv D. Non-Melanoma Skin Cancer Detection in the Age of Advanced Technology: A Review. Cancers (Basel) 2023; 15:3094. [PMID: 37370703 PMCID: PMC10295857 DOI: 10.3390/cancers15123094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 06/02/2023] [Accepted: 06/02/2023] [Indexed: 06/29/2023] Open
Abstract
Skin cancer is the most common cancer diagnosis in the United States, with approximately one in five Americans expected to be diagnosed within their lifetime. Non-melanoma skin cancer is the most prevalent type of skin cancer, and as cases rise globally, physicians need reliable tools for early detection. Artificial intelligence has gained substantial interest as a decision support tool in medicine, particularly in image analysis, where deep learning has proven to be an effective tool. Because specialties such as dermatology rely primarily on visual diagnoses, deep learning could have many diagnostic applications, including the diagnosis of skin cancer. Furthermore, with the advancement of mobile smartphones and their increasingly powerful cameras, deep learning technology could also be utilized in remote skin cancer screening applications. Ultimately, the available data for the detection and diagnosis of skin cancer using deep learning technology are promising, revealing sensitivity and specificity that are not inferior to those of trained dermatologists. Work is still needed to increase the clinical use of AI-based tools, but based on the current data and the attitudes of patients and physicians, deep learning technology could be used effectively as a clinical decision-making tool in collaboration with physicians to improve diagnostic efficiency and accuracy.
Collapse
Affiliation(s)
- Haleigh Stafford
- School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA
| | - Jane Buell
- School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA
| | - Elizabeth Chiang
- School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA
| | - Uma Ramesh
- School of Medicine, Baylor College of Medicine, Houston, TX 77030, USA
| | - Michael Migden
- Division of Internal Medicine, Department of Dermatology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Priyadharsini Nagarajan
- Department of Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Moran Amit
- Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA;
- Department of Head and Neck Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA;
| | - Dan Yaniv
- Department of Head and Neck Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA;
| |
Collapse
|
67
|
Gomes RFT, Schuch LF, Martins MD, Honório EF, de Figueiredo RM, Schmith J, Machado GN, Carrard VC. Use of Deep Neural Networks in the Detection and Automated Classification of Lesions Using Clinical Images in Ophthalmology, Dermatology, and Oral Medicine-A Systematic Review. J Digit Imaging 2023; 36:1060-1070. [PMID: 36650299 PMCID: PMC10287602 DOI: 10.1007/s10278-023-00775-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2022] [Revised: 01/03/2023] [Accepted: 01/04/2023] [Indexed: 01/19/2023] Open
Abstract
Artificial neural networks (ANN) are artificial intelligence (AI) techniques used in the automated recognition and classification of pathological changes from clinical images in areas such as ophthalmology, dermatology, and oral medicine. The combination of enterprise imaging and AI is gaining notoriety for its potential benefits in healthcare areas such as cardiology, dermatology, ophthalmology, pathology, physiatry, radiation oncology, radiology, and endoscopic. The present study aimed to analyze, through a systematic literature review, the application of performance of ANN and deep learning in the recognition and automated classification of lesions from clinical images, when comparing to the human performance. The PRISMA 2020 approach (Preferred Reporting Items for Systematic Reviews and Meta-analyses) was used by searching four databases of studies that reference the use of IA to define the diagnosis of lesions in ophthalmology, dermatology, and oral medicine areas. A quantitative and qualitative analyses of the articles that met the inclusion criteria were performed. The search yielded the inclusion of 60 studies. It was found that the interest in the topic has increased, especially in the last 3 years. We observed that the performance of IA models is promising, with high accuracy, sensitivity, and specificity, most of them had outcomes equivalent to human comparators. The reproducibility of the performance of models in real-life practice has been reported as a critical point. Study designs and results have been progressively improved. IA resources have the potential to contribute to several areas of health. In the coming years, it is likely to be incorporated into everyday life, contributing to the precision and reducing the time required by the diagnostic process.
Collapse
Affiliation(s)
- Rita Fabiane Teixeira Gomes
- Graduate Program in Dentistry, School of Dentistry, Federal University of Rio Grande Do Sul, Barcelos 2492/503, Bairro Santana, Porto Alegre, RS, CEP 90035-003, Brazil.
| | - Lauren Frenzel Schuch
- Department of Oral Diagnosis, Piracicaba Dental School, University of Campinas, Piracicaba, Brazil
| | - Manoela Domingues Martins
- Graduate Program in Dentistry, School of Dentistry, Federal University of Rio Grande Do Sul, Barcelos 2492/503, Bairro Santana, Porto Alegre, RS, CEP 90035-003, Brazil
- Department of Oral Diagnosis, Piracicaba Dental School, University of Campinas, Piracicaba, Brazil
| | | | - Rodrigo Marques de Figueiredo
- Technology in Automation and Electronics Laboratory - TECAE Lab, University of Vale Do Rio Dos Sinos - UNISINOS, São Leopoldo, Brazil
| | - Jean Schmith
- Technology in Automation and Electronics Laboratory - TECAE Lab, University of Vale Do Rio Dos Sinos - UNISINOS, São Leopoldo, Brazil
| | - Giovanna Nunes Machado
- Technology in Automation and Electronics Laboratory - TECAE Lab, University of Vale Do Rio Dos Sinos - UNISINOS, São Leopoldo, Brazil
| | - Vinicius Coelho Carrard
- Graduate Program in Dentistry, School of Dentistry, Federal University of Rio Grande Do Sul, Barcelos 2492/503, Bairro Santana, Porto Alegre, RS, CEP 90035-003, Brazil
- Department of Epidemiology, School of Medicine, TelessaúdeRS-UFRGS, Federal University of Rio Grande Do Sul, Porto Alegre, RS, Brazil
- Department of Oral Medicine, Otorhinolaryngology Service, Hospital de Clínicas de Porto Alegre (HCPA), Porto Alegre, RS, Brazil
| |
Collapse
|
68
|
Smak Gregoor AM, Sangers TE, Eekhof JAH, Howe S, Revelman J, Litjens RJM, Sarac M, Bindels PJE, Bonten T, Wehrens R, Wakkee M. Artificial intelligence in mobile health for skin cancer diagnostics at home (AIM HIGH): a pilot feasibility study. EClinicalMedicine 2023; 60:102019. [PMID: 37261324 PMCID: PMC10227364 DOI: 10.1016/j.eclinm.2023.102019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/13/2023] [Revised: 05/05/2023] [Accepted: 05/09/2023] [Indexed: 06/02/2023] Open
Abstract
Background Artificial intelligence (AI)-based mobile phone apps (mHealth) have the potential to streamline care for suspicious skin lesions in primary care. This study aims to investigate the conditions and feasibility of a study that incorporates an AI-based app in primary care and evaluates its potential impact. Methods We conducted a pilot feasibility study from November 22nd, 2021 to June 9th, 2022 with a mixed-methods design on implementation of an AI-based mHealth app for skin cancer detection in three primary care practices in the Netherlands (Rotterdam, Leiden and Katwijk). The primary outcome was the inclusion and successful participation rate of patients and general practitioners (GPs). Secondary outcomes were the reasons, facilitators and barriers for successful participation and the potential impact in both pathways for future sample size calculations. Patients were offered use of an AI-based mHealth app before consulting their GP. GPs assessed the patients blinded and then unblinded to the app. Qualitative data included observations and audio-diaries from patients and GPs and focus-groups and interviews with GPs and GP assistants. Findings Fifty patients were included with a median age of 52 years (IQR 33.5-60.3), 64% were female, and 90% had a light skin type. The average patient inclusion rate was 4-6 per GP practice per month and 84% (n = 42) successfully participated. Similarly, in 90% (n = 45 patients) the GPs also successfully completed the study. GPs never changed their working diagnosis, but did change their treatment plan (n = 5) based on the app's assessments. Notably, 54% of patients with a benign skin lesion and low risk rating, indicated that they would be reassured and cancel their GP visit with these results (p < 0.001). Interpretation Our findings suggest that studying implementation of an AI-based mHealth app for detection of skin cancer in the hands of patients or as a diagnostic tool used by GPs in primary care appears feasible. Preliminary results indicate potential to further investigate both intended use settings. Funding SkinVision B.V.
Collapse
Affiliation(s)
- Anna M. Smak Gregoor
- Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, the Netherlands
| | - Tobias E. Sangers
- Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, the Netherlands
| | - Just AH. Eekhof
- Department of Public Health and Primary Care, Leiden University Medical Centre, Leiden, the Netherlands
| | - Sydney Howe
- School of Health Policy and Management, Erasmus University, Rotterdam, the Netherlands
| | - Jeroen Revelman
- Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, the Netherlands
| | - Romy JM. Litjens
- Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, the Netherlands
| | - Mohammed Sarac
- Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, the Netherlands
| | | | - Tobias Bonten
- Department of Public Health and Primary Care, Leiden University Medical Centre, Leiden, the Netherlands
| | - Rik Wehrens
- School of Health Policy and Management, Erasmus University, Rotterdam, the Netherlands
| | - Marlies Wakkee
- Department of Dermatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, the Netherlands
| |
Collapse
|
69
|
Xu W, Chen L, Cai G, Gao M, Chen Y, Pu J, Chen X, Liu N, Ye Q, Qian K. Diagnosis of Parkinson's Disease via the Metabolic Fingerprint in Saliva by Deep Learning. SMALL METHODS 2023:e2300285. [PMID: 37236160 DOI: 10.1002/smtd.202300285] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/03/2023] [Revised: 04/17/2023] [Indexed: 05/28/2023]
Abstract
Parkinson's disease (PD) is the second cause of the neurodegenerative disorder, affecting over 6 million people worldwide. The World Health Organization estimated that population aging will cause global PD prevalence to double in the coming 30 years. Optimal management of PD shall start at diagnosis and requires both a timely and accurate method. Conventional PD diagnosis needs observations and clinical signs assessment, which are time-consuming and low-throughput. A lack of body fluid diagnostic biomarkers for PD has been a significant challenge, although substantial progress has been made in genetic and imaging marker development. Herein, a platform that noninvasively collects saliva metabolic fingerprinting (SMF) by nanoparticle-enhanced laser desorption-ionization mass spectrometry with high-reproducibility and high-throughput, using ultra-small sample volume (down to 10 nL), is developed. Further, excellent diagnostic performance is achieved with an area-under-the-curve of 0.8496 (95% CI: 0.7393-0.8625) by constructing deep learning model from 312 participants. In conclusion, an alternative solution is provided for the molecular diagnostics of PD with SMF and metabolic biomarker screening for therapeutic intervention.
Collapse
Affiliation(s)
- Wei Xu
- State Key Laboratory of Systems Medicine for Cancer, Division of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, P. R. China
| | - Lina Chen
- Department of Neurology, Fujian Medical University Union Hospital, Fujian Key Laboratory of Molecular Neurology and Institute of Neuroscience, Fujian Medical University, Fuzhou, 350001, P. R. China
| | - Guoen Cai
- Department of Neurology, Fujian Medical University Union Hospital, Fujian Key Laboratory of Molecular Neurology and Institute of Neuroscience, Fujian Medical University, Fuzhou, 350001, P. R. China
| | - Ming Gao
- School of Management Science and Engineering, Key Laboratory of Big Data Management Optimization and Decision of Liaoning Province, Dongbei University of Finance of Economics, Dongbei, 116025, P. R. China
| | - Yifan Chen
- State Key Laboratory of Systems Medicine for Cancer, Division of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, P. R. China
| | - Jun Pu
- State Key Laboratory of Systems Medicine for Cancer, Division of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, P. R. China
| | - Xiaochun Chen
- Department of Neurology, Fujian Medical University Union Hospital, Fujian Key Laboratory of Molecular Neurology and Institute of Neuroscience, Fujian Medical University, Fuzhou, 350001, P. R. China
| | - Ning Liu
- School of Electronics Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China
| | - Qinyong Ye
- Department of Neurology, Fujian Medical University Union Hospital, Fujian Key Laboratory of Molecular Neurology and Institute of Neuroscience, Fujian Medical University, Fuzhou, 350001, P. R. China
| | - Kun Qian
- State Key Laboratory of Systems Medicine for Cancer, Division of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, P. R. China
- School of Biomedical Engineering, Institute of Medical Robotics and Med-X Research Institute, Shanghai Jiao Tong University, Shanghai, 200030, P. R. China
| |
Collapse
|
70
|
DeGrave AJ, Cai ZR, Janizek JD, Daneshjou R, Lee SI. Dissection of medical AI reasoning processes via physician and generative-AI collaboration. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.05.12.23289878. [PMID: 37292705 PMCID: PMC10246034 DOI: 10.1101/2023.05.12.23289878] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Despite the proliferation and clinical deployment of artificial intelligence (AI)-based medical software devices, most remain black boxes that are uninterpretable to key stakeholders including patients, physicians, and even the developers of the devices. Here, we present a general model auditing framework that combines insights from medical experts with a highly expressive form of explainable AI that leverages generative models, to understand the reasoning processes of AI devices. We then apply this framework to generate the first thorough, medically interpretable picture of the reasoning processes of machine-learning-based medical image AI. In our synergistic framework, a generative model first renders "counterfactual" medical images, which in essence visually represent the reasoning process of a medical AI device, and then physicians translate these counterfactual images to medically meaningful features. As our use case, we audit five high-profile AI devices in dermatology, an area of particular interest since dermatology AI devices are beginning to achieve deployment globally. We reveal how dermatology AI devices rely both on features used by human dermatologists, such as lesional pigmentation patterns, as well as multiple, previously unreported, potentially undesirable features, such as background skin texture and image color balance. Our study also sets a precedent for the rigorous application of explainable AI to understand AI in any specialized domain and provides a means for practitioners, clinicians, and regulators to uncloak AI's powerful but previously enigmatic reasoning processes in a medically understandable way.
Collapse
Affiliation(s)
- Alex J DeGrave
- Paul G. Allen School of Computer Science and Engineering, University of Washington
- Medical Scientist Training Program, University of Washington
| | - Zhuo Ran Cai
- Program for Clinical Research and Technology, Stanford University
| | - Joseph D Janizek
- Paul G. Allen School of Computer Science and Engineering, University of Washington
- Medical Scientist Training Program, University of Washington
| | - Roxana Daneshjou
- Department of Dermatology, Stanford School of Medicine
- Department of Biomedical Data Science, Stanford School of Medicine
| | - Su-In Lee
- Paul G. Allen School of Computer Science and Engineering, University of Washington
| |
Collapse
|
71
|
MacMath D, Chen M, Khoury P. Artificial Intelligence: Exploring the Future of Innovation in Allergy Immunology. Curr Allergy Asthma Rep 2023:10.1007/s11882-023-01084-z. [PMID: 37160554 PMCID: PMC10169188 DOI: 10.1007/s11882-023-01084-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/21/2023] [Indexed: 05/11/2023]
Abstract
PURPOSE OF REVIEW Artificial intelligence (AI) has increasingly been used in healthcare. Given the capacity of AI to handle large data and complex relationships between variables, AI is well suited for applications in healthcare. Recently, AI has been applied to allergy research. RECENT FINDINGS In this article, we review how AI technologies have been utilized in basic science and clinical allergy research for asthma, atopic dermatitis, rhinology, adverse reactions to drugs and vaccines, food allergy, anaphylaxis, urticaria, and eosinophilic gastrointestinal disorders. We discuss barriers for AI adoption to improve the care of patients with atopic diseases. These studies demonstrate the utility of applying AI to the field of allergy to help investigators expand their understanding of disease pathogenesis, improve diagnostic accuracy, enable prediction for treatments and outcomes, and for drug discovery.
Collapse
Affiliation(s)
- Derek MacMath
- Department of Medicine, Department of Pediatrics, Baylor College of Medicine, Houston, TX, USA
| | - Meng Chen
- Division of Pulmonary, Allergy & Critical Care Medicine, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA
| | - Paneez Khoury
- National Institutes of Allergic and Infectious Diseases, National Institutes of Health, 9000 Rockville Pike, Bethesda, MD, USA.
| |
Collapse
|
72
|
Kim DH, Sun S, Cho SI, Kong HJ, Lee JW, Lee JH, Suh DH. Automated Facial Acne Lesion Detecting and Counting Algorithm for Acne Severity Evaluation and Its Utility in Assisting Dermatologists. Am J Clin Dermatol 2023:10.1007/s40257-023-00777-5. [PMID: 37160644 DOI: 10.1007/s40257-023-00777-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/27/2023] [Indexed: 05/11/2023]
Abstract
BACKGROUND Although lesion counting is an evaluation method that effectively analyzes facial acne severity, its usage is limited because of difficult implementation. OBJECTIVES We aimed to develop and validate an automated algorithm that detects and counts acne lesions by type, and to evaluate its clinical applicability as an assistance tool through a reader test. METHODS A total of 20,699 lesions (closed and open comedones, papules, nodules/cysts, and pustules) were manually labeled on 1213 facial images of 398 facial acne photography sets (frontal and both lateral views) acquired from 258 patients and used for training and validating algorithms based on a convolutional neural network for classifying five classes of acne lesions or for binary classification into noninflammatory and inflammatory lesions. RESULTS In the validation dataset, the highest mean average precision was 28.48 for the binary classification algorithm. Pearson's correlation of lesion counts between algorithm and ground-truth was 0.72 (noninflammatory) and 0.90 (inflammatory), respectively. In the reader test, eight readers (100.0%) detected and counted lesions more accurately using the algorithm compared with the reader-alone evaluation. CONCLUSIONS Overall, our algorithm demonstrated clinically applicable performance in detecting and counting facial acne lesions by type and its utility as an assistance tool for evaluating acne severity.
Collapse
Affiliation(s)
- Dong Hyo Kim
- Department of Dermatology, Seoul National University College of Medicine, Seoul, South Korea
- Acne, Rosacea, Seborrheic Dermatitis and Hidradenitis Suppurativa Research Laboratory, Seoul National University Hospital, Seoul, South Korea
| | - Sukkyu Sun
- Biomedical Research Institute, Seoul National University Hospital, Seoul, South Korea
| | - Soo Ick Cho
- Department of Dermatology, Seoul National University College of Medicine, Seoul, South Korea
| | - Hyoun-Joong Kong
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, South Korea
- Department of Medicine, Seoul National University College of Medicine, Seoul, South Korea
| | - Ji Won Lee
- Department of Dermatology, Seoul National University College of Medicine, Seoul, South Korea
| | - Jun Hyo Lee
- Department of Dermatology, Seoul National University College of Medicine, Seoul, South Korea
- Acne, Rosacea, Seborrheic Dermatitis and Hidradenitis Suppurativa Research Laboratory, Seoul National University Hospital, Seoul, South Korea
| | - Dae Hun Suh
- Department of Dermatology, Seoul National University College of Medicine, Seoul, South Korea.
- Acne, Rosacea, Seborrheic Dermatitis and Hidradenitis Suppurativa Research Laboratory, Seoul National University Hospital, Seoul, South Korea.
| |
Collapse
|
73
|
Lim SY, Yoon HM, Kook MC, Jang JI, So PTC, Kang JW, Kim HM. Stomach tissue classification using autofluorescence spectroscopy and machine learning. Surg Endosc 2023:10.1007/s00464-023-10053-6. [PMID: 37055665 DOI: 10.1007/s00464-023-10053-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2022] [Accepted: 03/26/2023] [Indexed: 04/15/2023]
Abstract
BACKGROUND AND OBJECTIVES Determination of stomach tumor location and invasion depth requires delineation of gastric histological structure, which has hitherto been widely accomplished by histochemical staining. In recent years, alternative histochemical evaluation methods have been pursued to accelerate intraoperative diagnosis, often by bypassing the time-consuming step of dyeing. Owing to strong endogenous signals from coenzymes, metabolites, and proteins, autofluorescence spectroscopy is a favorable candidate technique to achieve this aim. MATERIALS AND METHODS We investigated stomach tissue slices and block specimens using a fast fluorescence imaging scanner. To obtain histological information from broad and structureless fluorescence spectra, we analyzed tens of thousands of spectra with multiple machine-learning algorithms and built a tissue classification model trained with dissected gastric tissues. RESULTS A machine-learning-based spectro-histological model was built based on the autofluorescence spectra measured from stomach tissue samples with delineated and validated histological structures. The scores from a principal components analysis were employed as input features, and prediction accuracy was confirmed to be 92.0%, 90.1%, and 91.4% for mucosa, submucosa, and muscularis propria, respectively. We investigated the tissue samples in both sliced and block forms using a fast fluorescence imaging scanner. CONCLUSION We successfully demonstrated differentiation of multiple tissue layers of well-defined specimens with the guidance of a histologist. Our spectro-histology classification model is applicable to histological prediction for both tissue blocks and slices, even though only sliced samples were trained.
Collapse
Affiliation(s)
- Soo Yeong Lim
- Department of Chemistry, Kookmin University, 77, Jeongneung-ro, Seongbuk-gu, Seoul, 02707, Republic of Korea
| | - Hong Man Yoon
- Division of Convergence Technology, National Cancer Center, 323 Ilsan-ro, Ilsandong-gu, Goyang-si, Gyeonggi-do, 10408, Republic of Korea
| | - Myeong-Cherl Kook
- Division of Convergence Technology, National Cancer Center, 323 Ilsan-ro, Ilsandong-gu, Goyang-si, Gyeonggi-do, 10408, Republic of Korea
| | - Jin Il Jang
- Department of Chemistry, Kookmin University, 77, Jeongneung-ro, Seongbuk-gu, Seoul, 02707, Republic of Korea
| | - Peter T C So
- Laser Biomedical Research Center, G. R. Harrison Spectroscopy Laboratory, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA
| | - Jeon Woong Kang
- Laser Biomedical Research Center, G. R. Harrison Spectroscopy Laboratory, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA.
| | - Hyung Min Kim
- Department of Chemistry, Kookmin University, 77, Jeongneung-ro, Seongbuk-gu, Seoul, 02707, Republic of Korea.
| |
Collapse
|
74
|
Del Amor R, Silva-Rodríguez J, Naranjo V. Labeling confidence for uncertainty-aware histology image classification. Comput Med Imaging Graph 2023; 107:102231. [PMID: 37087899 DOI: 10.1016/j.compmedimag.2023.102231] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2022] [Revised: 02/23/2023] [Accepted: 03/27/2023] [Indexed: 04/25/2023]
Abstract
Deep learning-based models applied to digital pathology require large, curated datasets with high-quality (HQ) annotations to perform correctly. In many cases, recruiting expert pathologists to annotate large databases is not feasible, and it is necessary to collect additional labeled data with varying label qualities, e.g., pathologists-in-training (henceforth, non-expert annotators). Learning from datasets with noisy labels is more challenging in medical applications since medical imaging datasets tend to have instance-dependent noise and suffer from high inter/intra-observer variability. In this paper, we design an uncertainty-driven labeling strategy with which we generate soft labels from 10 non-expert annotators for multi-class skin cancer classification. Based on this soft annotation, we propose an uncertainty estimation-based framework to handle these noisy labels. This framework is based on a novel formulation using a dual-branch min-max entropy calibration to penalize inexact labels during the training. Comprehensive experiments demonstrate the promising performance of our labeling strategy. Results show a consistent improvement by using soft labels with standard cross-entropy loss during training (∼4.0% F1-score) and increases when calibrating the model with the proposed min-max entropy calibration (∼6.6% F1-score). These improvements are produced at negligible cost, both in terms of annotation and calculation.
Collapse
Affiliation(s)
- Rocío Del Amor
- Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València, Valencia, Spain.
| | | | - Valery Naranjo
- Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València, Valencia, Spain.
| |
Collapse
|
75
|
Diaz-Ramón JL, Gardeazabal J, Izu RM, Garrote E, Rasero J, Apraiz A, Penas C, Seijo S, Lopez-Saratxaga C, De la Peña PM, Sanchez-Diaz A, Cancho-Galan G, Velasco V, Sevilla A, Fernandez D, Cuenca I, Cortes JM, Alonso S, Asumendi A, Boyano MD. Melanoma Clinical Decision Support System: An Artificial Intelligence-Based Tool to Diagnose and Predict Disease Outcome in Early-Stage Melanoma Patients. Cancers (Basel) 2023; 15:cancers15072174. [PMID: 37046835 PMCID: PMC10093614 DOI: 10.3390/cancers15072174] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 03/17/2023] [Accepted: 04/03/2023] [Indexed: 04/08/2023] Open
Abstract
This study set out to assess the performance of an artificial intelligence (AI) algorithm based on clinical data and dermatoscopic imaging for the early diagnosis of melanoma, and its capacity to define the metastatic progression of melanoma through serological and histopathological biomarkers, enabling dermatologists to make more informed decisions about patient management. Integrated analysis of demographic data, images of the skin lesions, and serum and histopathological markers were analyzed in a group of 196 patients with melanoma. The interleukins (ILs) IL-4, IL-6, IL-10, and IL-17A as well as IFNγ (interferon), GM-CSF (granulocyte and macrophage colony-stimulating factor), TGFβ (transforming growth factor), and the protein DCD (dermcidin) were quantified in the serum of melanoma patients at the time of diagnosis, and the expression of the RKIP, PIRIN, BCL2, BCL3, MITF, and ANXA5 proteins was detected by immunohistochemistry (IHC) in melanoma biopsies. An AI algorithm was used to improve the early diagnosis of melanoma and to predict the risk of metastasis and of disease-free survival. Two models were obtained to predict metastasis (including “all patients” or only patients “at early stages of melanoma”), and a series of attributes were seen to predict the progression of metastasis: Breslow thickness, infiltrating BCL-2 expressing lymphocytes, and IL-4 and IL-6 serum levels. Importantly, a decrease in serum GM-CSF seems to be a marker of poor prognosis in patients with early-stage melanomas.
Collapse
Affiliation(s)
- Jose Luis Diaz-Ramón
- Dermatology Service, Cruces University Hospital, 48903 Barakaldo, Spain
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
| | - Jesus Gardeazabal
- Dermatology Service, Cruces University Hospital, 48903 Barakaldo, Spain
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
| | - Rosa Maria Izu
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Dermatology Service, Basurto University Hospital, 48013 Bilbao, Spain
| | - Estibaliz Garrote
- TECNALIA, Basque Research and Technology Alliance (BRTA), 20850 Gipuzkoa, Spain
- Department of Cell Biology and Histology, University of the Basque Country/EHU, 48940 Leioa, Spain
| | - Javier Rasero
- Department of Psychology, Carnegie Mellon University, Pittsburgh, PA 15213, USA
| | - Aintzane Apraiz
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Department of Cell Biology and Histology, University of the Basque Country/EHU, 48940 Leioa, Spain
| | - Cristina Penas
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Department of Cell Biology and Histology, University of the Basque Country/EHU, 48940 Leioa, Spain
| | - Sandra Seijo
- Ibermática Innovation Institute, 48170 Zamudio, Spain
| | | | | | - Ana Sanchez-Diaz
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Dermatology Service, Basurto University Hospital, 48013 Bilbao, Spain
| | - Goikoane Cancho-Galan
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Pathology Service, Basurto University Hospital, 48013 Bilbao, Spain
| | - Veronica Velasco
- Dermatology Service, Cruces University Hospital, 48903 Barakaldo, Spain
- Pathology Service, Cruces University Hospital, 48903 Barakaldo, Spain
| | - Arrate Sevilla
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Department of Genetics, Physical Anthropology and Animal Physiology, University of the Basque Country/EHU, 48940 Leioa, Spain
| | | | - Iciar Cuenca
- Ibermática Innovation Institute, 48170 Zamudio, Spain
| | - Jesus María Cortes
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Department of Cell Biology and Histology, University of the Basque Country/EHU, 48940 Leioa, Spain
- IKERBASQUE, The Basque Foundation for Science, 48009 Bilbao, Spain
| | - Santos Alonso
- Department of Genetics, Physical Anthropology and Animal Physiology, University of the Basque Country/EHU, 48940 Leioa, Spain
| | - Aintzane Asumendi
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Department of Cell Biology and Histology, University of the Basque Country/EHU, 48940 Leioa, Spain
| | - María Dolores Boyano
- Biocruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
- Department of Cell Biology and Histology, University of the Basque Country/EHU, 48940 Leioa, Spain
| |
Collapse
|
76
|
Steele L, Tan XL, Olabi B, Gao JM, Tanaka RJ, Williams HC. Determining the clinical applicability of machine learning models through assessment of reporting across skin phototypes and rarer skin cancer types: A systematic review. J Eur Acad Dermatol Venereol 2023; 37:657-665. [PMID: 36514990 DOI: 10.1111/jdv.18814] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Accepted: 11/09/2022] [Indexed: 12/15/2022]
Abstract
Machine learning (ML) models for skin cancer recognition may have variable performance across different skin phototypes and skin cancer types. Overall performance metrics alone are insufficient to detect poor subgroup performance. We aimed (1) to assess whether studies of ML models reported results separately for different skin phototypes and rarer skin cancers, and (2) to graphically represent the skin cancer training datasets used by current ML models. In this systematic review, we searched PubMed, Embase and CENTRAL. We included all studies in medical journals assessing an ML technique for skin cancer diagnosis that used clinical or dermoscopic images from 1 January 2012 to 22 September 2021. No language restrictions were applied. We considered rarer skin cancers to be skin cancers other than pigmented melanoma, basal cell carcinoma and squamous cell carcinoma. We identified 114 studies for inclusion. Rarer skin cancers were included by 8/114 studies (7.0%), and results for a rarer skin cancer were reported separately in 1/114 studies (0.9%). Performance was reported across all skin phototypes in 1/114 studies (0.9%), but performance was uncertain in skin phototypes I and VI from minimal representation of the skin phototypes in the test dataset (9/3756 and 1/3756, respectively). For training datasets, although public datasets were most frequently used, with the most widely used being the International Skin Imaging Collaboration (ISIC) archive (65/114 studies, 57.0%), the largest datasets were private. Our review identified that most ML models did not report performance separately for rarer skin cancers and different skin phototypes. A degree of variability in ML model performance across subgroups is expected, but the current lack of transparency is not justifiable and risks models being used inappropriately in populations in whom accuracy is low.
Collapse
Affiliation(s)
- Lloyd Steele
- Department of Dermatology, The Royal London Hospital, London, UK.,Centre for Cell Biology and Cutaneous Research, Blizard Institute, Queen Mary University of London, London, UK
| | - Xiang Li Tan
- St George's University Hospitals NHS Foundation Trust, London, UK
| | - Bayanne Olabi
- Biosciences Institute, Newcastle University, Newcastle, UK
| | - Jing Mia Gao
- Department of Dermatology, The Royal London Hospital, London, UK
| | - Reiko J Tanaka
- Department of Bioengineering, Imperial College London, London, UK
| | - Hywel C Williams
- Centre of Evidence-Based Dermatology, School of Medicine, University of Nottingham, Nottingham, UK
| |
Collapse
|
77
|
Flament F, Jiang R, Houghton J, Cassier M, Amar D, Delaunay C, Balooch G, Bouhadana E, Aarabi P, Passeron T. Objective and automatic grading system of facial signs from smartphones' pictures in South African men: Validation versus dermatologists and characterization of changes with age. Skin Res Technol 2023; 29:e13257. [PMID: 37113093 PMCID: PMC10234158 DOI: 10.1111/srt.13257] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2022] [Accepted: 12/02/2022] [Indexed: 04/29/2023]
Abstract
OBJECTIVE To evaluate the capacity of the automatic detection system to accurately grade, from selfie pictures, the severity of eight facial signs in South African men. METHODS Selfie pictures (obtained from frontal and back cameras) of 281 South African men differently aged (20-70 years) were obtained and analyzed by an automatic artificial intelligence (AI)-based automatic grading system. Data were compared with the clinical gradings made by experts and dermatologists. RESULTS In all facial signs, both series of gradings were found highly correlated with, however, different coefficients (0.59-0.95), those of marionette lines and cheek pores being of lower values. No differences were observed between data obtained by frontal and back cameras. With age, in most cases, gradings show up to the 50-59 year age-class, linear-like changes. When compared to men of other ancestries, South African men present lower wrinkles/texture, pigmentation, and ptosis/sagging scores till 50-59 years, albeit not much different in the cheek pores sign. The early onset (mean age) of visibility of wrinkles/texture for South African men were (i.e., reaching grade >1) 39 and 45 years for ptosis/sagging. CONCLUSION This study completes and enlarges the previous works conducted on men of other ancestries by showing some South African specificities and slight differences with men of comparable phototypes (Afro American).
Collapse
Affiliation(s)
| | - Ruowei Jiang
- ModiFace ‐ A L'Oréal Group CompanyTorontoOntarioCanada
| | - Jeff Houghton
- ModiFace ‐ A L'Oréal Group CompanyTorontoOntarioCanada
| | | | - David Amar
- L'Oréal Research and InnovationClichyFrance
| | | | | | | | - Parham Aarabi
- ModiFace ‐ A L'Oréal Group CompanyTorontoOntarioCanada
| | - Thierry Passeron
- Department of Dermatology, Université Côte d'AzurCHU NiceNiceFrance
- Université Côte d'AzurINSERM, U1065, C3MNiceFrance
| |
Collapse
|
78
|
Sun J, Fu L, Zhang W, Li D, Zhang M, Xu Z, Bai H, Ding P. Convolutional neural network models for automatic diagnosis and graduation in skin frostbite. Int Wound J 2023; 20:910-916. [PMID: 36054618 PMCID: PMC10031220 DOI: 10.1111/iwj.13937] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2022] [Accepted: 08/09/2022] [Indexed: 10/14/2022] Open
Abstract
The study aimed to develop and validate a convolutional neural network (CNN)-based deep learning method for automatic diagnosis and graduation of skin frostbite. A dataset of 71 annotated images was used for the training, the validation, and the testing based on ResNet-50 model. The performances were evaluated with the test set. The diagnosis and graduation performance of our approach was compared with two residents from burns department. The approach correctly identified all the frostbite of IV (18/18, 100%), but with respectively 1 mistake in the diagnosis of degree I (29/30, 96.67%), II (28/29, 96.55%) and III (37/38, 97.37%). The accuracy of the approach on the whole test set was 97.39% (112/115). The accuracy of the two residents were respectively 77.39% and 73.04%. Weighted Kappa of 0.583 indicates good reliability between the two residents (P = .445). Kendall's coefficient of concordance is 0.326 (P = .548), indicating differences in accuracy between the approach and the two residents. Our approach based on CNNs demonstrated an encouraging performance for the automatic diagnosis and graduation of skin frostbite, with higher accuracy and efficiency.
Collapse
Affiliation(s)
- Jiachen Sun
- Department of Burns and Plastic SurgeryThe Fourth Medical Center of Chinese PLA General HospitalBeijingChina
| | - Lin Fu
- Plastic Surgery Hospital of Chinese Academy of Medical SciencesPeking Union Medical CollegeBeijingChina
| | - Wen Zhang
- Department of Burns and Plastic SurgeryThe Fourth Medical Center of Chinese PLA General HospitalBeijingChina
| | - Dongjie Li
- Department of Burns and Plastic SurgeryThe Fourth Medical Center of Chinese PLA General HospitalBeijingChina
| | - Ming Zhang
- Department of Burns and Plastic SurgeryThe Fourth Medical Center of Chinese PLA General HospitalBeijingChina
| | - Zineng Xu
- R&D DepartmentDeepcare Inc.BeijingChina
| | | | - Peng Ding
- R&D DepartmentDeepcare Inc.BeijingChina
| |
Collapse
|
79
|
Yu Y, Christensen S, Ouyang J, Scalzo F, Liebeskind DS, Lansberg MG, Albers GW, Zaharchuk G. Predicting Hypoperfusion Lesion and Target Mismatch in Stroke from Diffusion-weighted MRI Using Deep Learning. Radiology 2023; 307:e220882. [PMID: 36472536 PMCID: PMC10068889 DOI: 10.1148/radiol.220882] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2022] [Revised: 09/08/2022] [Accepted: 10/13/2022] [Indexed: 12/12/2022]
Abstract
Background Perfusion imaging is important to identify a target mismatch in stroke but requires contrast agents and postprocessing software. Purpose To use a deep learning model to predict the hypoperfusion lesion in stroke and identify patients with a target mismatch profile from diffusion-weighted imaging (DWI) and clinical information alone, using perfusion MRI as the reference standard. Materials and Methods Imaging data sets of patients with acute ischemic stroke with baseline perfusion MRI and DWI were retrospectively reviewed from multicenter data available from 2008 to 2019 (Imaging Collaterals in Acute Stroke, Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution 2, and University of California, Los Angeles stroke registry). For perfusion MRI, rapid processing of perfusion and diffusion software automatically segmented the hypoperfusion lesion (time to maximum, ≥6 seconds) and ischemic core (apparent diffusion coefficient [ADC], ≤620 × 10-6 mm2/sec). A three-dimensional U-Net deep learning model was trained using baseline DWI, ADC, National Institutes of Health Stroke Scale score, and stroke symptom sidedness as inputs, with the union of hypoperfusion and ischemic core segmentation serving as the ground truth. Model performance was evaluated using the Dice score coefficient (DSC). Target mismatch classification based on the model was compared with that of the clinical-DWI mismatch approach defined by the DAWN trial by using the McNemar test. Results Overall, 413 patients (mean age, 67 years ± 15 [SD]; 207 men) were included for model development and primary analysis using fivefold cross-validation (247, 83, and 83 patients in the training, validation, and test sets, respectively, for each fold). The model predicted the hypoperfusion lesion with a median DSC of 0.61 (IQR, 0.45-0.71). The model identified patients with target mismatch with a sensitivity of 90% (254 of 283; 95% CI: 86, 93) and specificity of 77% (100 of 130; 95% CI: 69, 83) compared with the clinical-DWI mismatch sensitivity of 50% (140 of 281; 95% CI: 44, 56) and specificity of 89% (116 of 130; 95% CI: 83, 94) (P < .001 for all). Conclusion A three-dimensional U-Net deep learning model predicted the hypoperfusion lesion from diffusion-weighted imaging (DWI) and clinical information and identified patients with a target mismatch profile with higher sensitivity than the clinical-DWI mismatch approach. ClinicalTrials.gov registration nos. NCT02225730, NCT01349946, NCT02586415 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Kallmes and Rabinstein in this issue.
Collapse
Affiliation(s)
- Yannan Yu
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - Soren Christensen
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - Jiahong Ouyang
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - Fabien Scalzo
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - David S. Liebeskind
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - Maarten G. Lansberg
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - Gregory W. Albers
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| | - Greg Zaharchuk
- From the Departments of Radiology (Y.Y., G.Z.), Neurology (S.C.,
M.G.L., G.W.A.), and Electrical Engineering (J.O.), Stanford University, 1201
Welch Rd, PS-04, Mailcode 5488, Stanford, CA 94305-5488; and Department of
Neurology, University of California, Los Angeles, Los Angeles, Calif (F.S.,
D.S.L.)
| |
Collapse
|
80
|
Exploring the potential of artificial intelligence in improving skin lesion diagnosis in primary care. Sci Rep 2023; 13:4293. [PMID: 36922556 PMCID: PMC10015524 DOI: 10.1038/s41598-023-31340-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2023] [Accepted: 03/10/2023] [Indexed: 03/18/2023] Open
Abstract
Dermatological conditions are a relevant health problem. Machine learning (ML) models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and disease classification. The objective of this study was to perform a prospective validation of an image analysis ML model, which is capable of screening 44 skin diseases, comparing its diagnostic accuracy with that of General Practitioners (GPs) and teledermatology (TD) dermatologists in a real-life setting. Prospective, diagnostic accuracy study including 100 consecutive patients with a skin problem who visited a participating GP in central Catalonia, Spain, between June 2021 and October 2021. The skin issue was first assessed by the GPs. Then an anonymised skin disease picture was taken and uploaded to the ML application, which returned a list with the Top-5 possible diagnosis in order of probability. The same image was then sent to a dermatologist via TD for diagnosis, as per clinical practice. The GPs Top-3, ML model's Top-5 and dermatologist's Top-3 assessments were compared to calculate the accuracy, sensitivity, specificity and diagnostic accuracy of the ML models. The overall Top-1 accuracy of the ML model (39%) was lower than that of GPs (64%) and dermatologists (72%). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained (n = 82), the balanced Top-1 accuracy of the ML model increased (48%) and in the Top-3 (75%) was comparable to the GPs Top-3 accuracy (76%). The Top-5 accuracy of the ML model (89%) was comparable to the dermatologist Top-3 accuracy (90%). For the different diseases, the sensitivity of the model (Top-3 87% and Top-5 96%) is higher than that of the clinicians (Top-3 GPs 76% and Top-3 dermatologists 84%) only in the benign tumour pathology group, being on the other hand the most prevalent category (n = 53). About the satisfaction of professionals, 92% of the GPs considered it as a useful diagnostic support tool (DST) for the differential diagnosis and in 60% of the cases as an aid in the final diagnosis of the skin lesion. The overall diagnostic accuracy of the model in this study, under real-life conditions, is lower than that of both GPs and dermatologists. This result aligns with the findings of few existing prospective studies conducted under real-life conditions. The outcomes emphasize the significance of involving clinicians in the training of the model and the capability of ML models to assist GPs, particularly in differential diagnosis. Nevertheless, external testing in real-life conditions is crucial for data validation and regulation of these AI diagnostic models before they can be used in primary care.
Collapse
|
81
|
Differentiating malignant and benign eyelid lesions using deep learning. Sci Rep 2023; 13:4103. [PMID: 36914694 PMCID: PMC10011394 DOI: 10.1038/s41598-023-30699-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Accepted: 02/28/2023] [Indexed: 03/16/2023] Open
Abstract
Artificial intelligence as a screening tool for eyelid lesions will be helpful for early diagnosis of eyelid malignancies and proper decision-making. This study aimed to evaluate the performance of a deep learning model in differentiating eyelid lesions using clinical eyelid photographs in comparison with human ophthalmologists. We included 4954 photographs from 928 patients in this retrospective cross-sectional study. Images were classified into three categories: malignant lesion, benign lesion, and no lesion. Two pre-trained convolutional neural network (CNN) models, DenseNet-161 and EfficientNetV2-M architectures, were fine-tuned to classify images into three or two (malignant versus benign) categories. For a ternary classification, the mean diagnostic accuracies of the CNNs were 82.1% and 83.0% using DenseNet-161 and EfficientNetV2-M, respectively, which were inferior to those of the nine clinicians (87.0-89.5%). For the binary classification, the mean accuracies were 87.5% and 92.5% using DenseNet-161 and EfficientNetV2-M models, which was similar to that of the clinicians (85.8-90.0%). The mean AUC of the two CNN models was 0.908 and 0.950, respectively. Gradient-weighted class activation map successfully highlighted the eyelid tumors on clinical photographs. Deep learning models showed a promising performance in discriminating malignant versus benign eyelid lesions on clinical photographs, reaching the level of human observers.
Collapse
|
82
|
Anomaly Detection in Chest X-rays Based on Dual-Attention Mechanism and Multi-Scale Feature Fusion. Symmetry (Basel) 2023. [DOI: 10.3390/sym15030668] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/09/2023] Open
Abstract
The efficient and automatic detection of chest abnormalities is vital for the auxiliary diagnosis of medical images. Many studies utilize computer vision and deep learning approaches involving symmetry and asymmetry concepts to detect chest abnormalities, and achieve promising findings. However, an accurate instance-level and multi-label detection of abnormalities in chest X-rays remains a significant challenge. Here, a novel anomaly detection method for symmetric chest X-rays using dual-attention and multi-scale feature fusion is proposed. Three aspects of our method should be noted in comparison with the previous approaches. We improved the deep neural network with channel-dimensional and spatial-dimensional attention to capture the abundant contextual features. We then used an optimized multi-scale learning framework for feature fusion to adapt to the scale variation in the abnormalities. Considering the influence of the data imbalance and other factors, we introduced a seesaw loss function to flexibly adjust the sample weights and enhance the model learning efficiency. The rigorous experimental evaluation of a public chest X-ray dataset with fourteen different types of abnormalities demonstrates that our model has a mean average precision of 0.362 and outperforms existing methods.
Collapse
|
83
|
Li D, Li X, Li S, Qi M, Sun X, Hu G. Relationship between the deep features of the full-scan pathological map of mucinous gastric carcinoma and related genes based on deep learning. Heliyon 2023; 9:e14374. [PMID: 36942252 PMCID: PMC10023952 DOI: 10.1016/j.heliyon.2023.e14374] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Revised: 02/28/2023] [Accepted: 03/02/2023] [Indexed: 03/11/2023] Open
Abstract
Background Long-term differential expression of disease-associated genes is a crucial driver of pathological changes in mucinous gastric carcinoma. Therefore, there should be a correlation between depth features extracted from pathology-based full-scan images using deep learning and disease-associated gene expression. This study tried to provides preliminary evidence that long-term differentially expressed (disease-associated) genes lead to subtle changes in disease pathology by exploring their correlation, and offer a new ideas for precise analysis of pathomics and combined analysis of pathomics and genomics. Methods Full pathological scans, gene sequencing data, and clinical data of patients with mucinous gastric carcinoma were downloaded from TCGA data. The VGG-16 network architecture was used to construct a binary classification model to explore the potential of VGG-16 applications and extract the deep features of the pathology-based full-scan map. Differential gene expression analysis was performed and a protein-protein interaction network was constructed to screen disease-related core genes. Differential, Lasso regression, and extensive correlation analyses were used to screen for valuable deep features. Finally, a correlation analysis was used to determine whether there was a correlation between valuable deep features and disease-related core genes. Result The accuracy of the binary classification model was 0.775 ± 0.129. A total of 24 disease-related core genes were screened, including ASPM, AURKA, AURKB, BUB1, BUB1B, CCNA2, CCNB1, CCNB2, CDCA8, CDK1, CENPF, DLGAP5, KIF11, KIF20A, KIF2C, KIF4A, MELK, PBK, RRM2, TOP2A, TPX2, TTK, UBE2C, and ZWINT. In addition, differential, Lasso regression, and extensive correlation analyses were used to screen eight valuable deep features, including features 51, 106, 109, 118, 257, 282, 326, and 487. Finally, the results of the correlation analysis suggested that valuable deep features were either positively or negatively correlated with core gene expression. Conclusion The preliminary results of this study support our hypotheses. Deep learning may be an important bridge for the joint analysis of pathomics and genomics and provides preliminary evidence for long-term abnormal expression of genes leading to subtle changes in pathology.
Collapse
Affiliation(s)
- Ding Li
- Department of Traditional Chinese Medicine, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Xiaoyuan Li
- Department of Traditional Chinese Medicine, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Shifang Li
- Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Mengmeng Qi
- Department of Endocrinology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Xiaowei Sun
- Department of Traditional Chinese Medicine, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Guojie Hu
- Department of Traditional Chinese Medicine, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
- Corresponding author.
| |
Collapse
|
84
|
Thieme AH, Zheng Y, Machiraju G, Sadee C, Mittermaier M, Gertler M, Salinas JL, Srinivasan K, Gyawali P, Carrillo-Perez F, Capodici A, Uhlig M, Habenicht D, Löser A, Kohler M, Schuessler M, Kaul D, Gollrad J, Ma J, Lippert C, Billick K, Bogoch I, Hernandez-Boussard T, Geldsetzer P, Gevaert O. A deep-learning algorithm to classify skin lesions from mpox virus infection. Nat Med 2023; 29:738-747. [PMID: 36864252 PMCID: PMC10033450 DOI: 10.1038/s41591-023-02225-7] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Accepted: 01/19/2023] [Indexed: 03/04/2023]
Abstract
Undetected infection and delayed isolation of infected individuals are key factors driving the monkeypox virus (now termed mpox virus or MPXV) outbreak. To enable earlier detection of MPXV infection, we developed an image-based deep convolutional neural network (named MPXV-CNN) for the identification of the characteristic skin lesions caused by MPXV. We assembled a dataset of 139,198 skin lesion images, split into training/validation and testing cohorts, comprising non-MPXV images (n = 138,522) from eight dermatological repositories and MPXV images (n = 676) from the scientific literature, news articles, social media and a prospective cohort of the Stanford University Medical Center (n = 63 images from 12 patients, all male). In the validation and testing cohorts, the sensitivity of the MPXV-CNN was 0.83 and 0.91, the specificity was 0.965 and 0.898 and the area under the curve was 0.967 and 0.966, respectively. In the prospective cohort, the sensitivity was 0.89. The classification performance of the MPXV-CNN was robust across various skin tones and body regions. To facilitate the usage of the algorithm, we developed a web-based app by which the MPXV-CNN can be accessed for patient guidance. The capability of the MPXV-CNN for identifying MPXV lesions has the potential to aid in MPXV outbreak mitigation.
Collapse
Affiliation(s)
- Alexander H Thieme
- Department of Medicine, Stanford University, Stanford, CA, USA.
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA.
- Department of Radiation Oncology, Charité-Universitätsmedizin Berlin, Berlin, Germany.
- Berlin Institute of Health at Charité-Universitätsmedizin Berlin, BIH Biomedical Innovation Academy, BIH Charité Digital Clinician Scientist Program, Berlin, Berlin, Germany.
| | - Yuanning Zheng
- Department of Medicine, Stanford University, Stanford, CA, USA
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA
| | - Gautam Machiraju
- Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
| | - Chris Sadee
- Department of Medicine, Stanford University, Stanford, CA, USA
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA
| | - Mirja Mittermaier
- Berlin Institute of Health at Charité-Universitätsmedizin Berlin, BIH Biomedical Innovation Academy, BIH Charité Digital Clinician Scientist Program, Berlin, Berlin, Germany
- Department of Infectious Diseases and Respiratory Medicine, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Maximilian Gertler
- Institute of Tropical Medicine and International Health, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Jorge L Salinas
- Division of Infectious Diseases and Geographic Medicine, Department of Medicine, Stanford University, Stanford, CA, USA
| | - Krithika Srinivasan
- Division of Infectious Diseases and Geographic Medicine, Department of Medicine, Stanford University, Stanford, CA, USA
| | | | - Francisco Carrillo-Perez
- Department of Medicine, Stanford University, Stanford, CA, USA
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA
- Department of Architecture and Computer Technology (ATC), University of Granada, Granada, Spain
| | - Angelo Capodici
- Department of Medicine, Stanford University, Stanford, CA, USA
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA
- Department of Biomedical and Neuromotor Science, Alma Mater Studiorum-University of Bologna, Bologna, Italy
| | - Maximilian Uhlig
- Department of Medicine, Justus-Liebig-Universität Gießen, Gießen, Germany
| | | | - Anastassia Löser
- Department of Radiotherapy, University Medical Center Schleswig-Holstein, Lübeck, Germany
| | - Maja Kohler
- Heidelberg Institute of Global Health, Heidelberg University Hospital, Heidelberg, Germany
- University Basel, Department of Psychology, Center for Cognitive and Decision Sciences, Basel, Switzerland
| | | | - David Kaul
- Department of Radiation Oncology, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Johannes Gollrad
- Department of Radiation Oncology, Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Jackie Ma
- Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany
| | - Christoph Lippert
- Digital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, Potsdam, Germany
- Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Kendall Billick
- Division of Dermatology, Toronto Western Hospital, University Health Network, Toronto, Ontario, Canada
| | - Isaac Bogoch
- Division of Infectious Diseases, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Tina Hernandez-Boussard
- Department of Medicine, Stanford University, Stanford, CA, USA
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA
- Department of Surgery, Stanford University, Stanford, CA, USA
| | - Pascal Geldsetzer
- Division of Primary Care and Population Health, Department of Medicine, Stanford University, Stanford, CA, USA
- Chan Zuckerberg Biohub, San Francisco, CA, USA
| | - Olivier Gevaert
- Department of Medicine, Stanford University, Stanford, CA, USA
- Stanford Center for Biomedical Informatics Research (BMIR), Department of Biomedical Data Science, Stanford University, Stanford, USA
| |
Collapse
|
85
|
Rezk E, Eltorki M, El-Dakhakhni W. Interpretable Skin Cancer Classification based on Incremental Domain Knowledge Learning. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2023; 7:59-83. [PMID: 36910915 PMCID: PMC9995827 DOI: 10.1007/s41666-023-00127-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Revised: 01/02/2023] [Accepted: 02/03/2023] [Indexed: 02/17/2023]
Abstract
The recent advances in artificial intelligence have led to the rapid development of computer-aided skin cancer diagnosis applications that perform on par with dermatologists. However, the black-box nature of such applications makes it difficult for physicians to trust the predicted decisions, subsequently preventing the proliferation of such applications in the clinical workflow. In this work, we aim to address this challenge by developing an interpretable skin cancer diagnosis approach using clinical images. Accordingly, a skin cancer diagnosis model consolidated with two interpretability methods is developed. The first interpretability method integrates skin cancer diagnosis domain knowledge, characterized by a skin lesion taxonomy, into model development, whereas the other method focuses on visualizing the decision-making process by highlighting the dominant of interest regions of skin lesion images. The proposed model is trained and validated on clinical images since the latter are easily obtainable by non-specialist healthcare providers. The results demonstrate the effectiveness of incorporating lesion taxonomy in improving model classification accuracy, where our model can predict the skin lesion origin as melanocytic or non-melanocytic with an accuracy of 87%, predict lesion malignancy with 77% accuracy, and provide disease diagnosis with an accuracy of 71%. In addition, the implemented interpretability methods assist understand the model's decision-making process and detecting misdiagnoses. This work is a step toward achieving interpretability in skin cancer diagnosis using clinical images. The developed approach can assist general practitioners to make an early diagnosis, thus reducing the redundant referrals that expert dermatologists receive for further investigations.
Collapse
Affiliation(s)
- Eman Rezk
- School of Computational Science and Engineering, McMaster University, Hamilton, ON Canada
| | - Mohamed Eltorki
- Faculty of Health Sciences, McMaster University, Hamilton, ON Canada
| | - Wael El-Dakhakhni
- School of Computational Science and Engineering, McMaster University, Hamilton, ON Canada
| |
Collapse
|
86
|
Eminaga O, Abbas M, Shen J, Laurie M, Brooks JD, Liao JC, Rubin DL. PlexusNet: A neural network architectural concept for medical image classification. Comput Biol Med 2023; 154:106594. [PMID: 36753979 DOI: 10.1016/j.compbiomed.2023.106594] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2022] [Revised: 01/12/2023] [Accepted: 01/22/2023] [Indexed: 01/27/2023]
Abstract
State-of-the-art (SOTA) convolutional neural network models have been widely adapted in medical imaging and applied to address different clinical problems. However, the complexity and scale of such models may not be justified in medical imaging and subject to the available resource budget. Further increasing the number of representative feature maps for the classification task decreases the model explainability. The current data normalization practice is fixed prior to model development and discounting the specification of the data domain. Acknowledging these issues, the current work proposed a new scalable model family called PlexusNet; the block architecture and model scaling by the network's depth, width, and branch regulate PlexusNet's architecture. The efficient computation costs outlined the dimensions of PlexusNet scaling and design. PlexusNet includes a new learnable data normalization algorithm for better data generalization. We applied a simple yet effective neural architecture search to design PlexusNet tailored to five clinical classification problems that achieve a performance noninferior to the SOTA models ResNet-18 and EfficientNet B0/1. It also does so with lower parameter capacity and representative feature maps in ten-fold ranges than the smallest SOTA models with comparable performance. The visualization of representative features revealed distinguishable clusters associated with categories based on latent features generated by PlexusNet. The package and source code are at https://github.com/oeminaga/PlexusNet.git.
Collapse
Affiliation(s)
- Okyaz Eminaga
- Center for Artificial Intelligence in Medicine & Imaging and Department of Urology, Stanford School of Medicine, Stanford, CA, 94305, USA; Department of Urology, Stanford School of Medicine, Stanford, CA, 94305, USA
| | - Mahmoud Abbas
- Department of Pathology, University of Muenster, Muenster, Germany.
| | - Jeanne Shen
- Department of Pathology, Stanford School of Medicine, Stanford, CA, 94305, USA.
| | - Mark Laurie
- Department of Computer Science, Stanford University, Stanford, CA, 94305, USA.
| | - James D Brooks
- Department of Urology, Stanford School of Medicine, Stanford, CA, 94305, USA.
| | - Joseph C Liao
- Department of Urology, Stanford School of Medicine, Stanford, CA, 94305, USA.
| | - Daniel L Rubin
- Department of Biomedical Data Science, Stanford School of Medicine, Stanford, CA, 94305, USA.
| |
Collapse
|
87
|
Kung TH, Cheatham M, Medenilla A, Sillos C, De Leon L, Elepaño C, Madriaga M, Aggabao R, Diaz-Candido G, Maningo J, Tseng V. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS DIGITAL HEALTH 2023; 2:e0000198. [PMID: 36812645 PMCID: PMC9931230 DOI: 10.1371/journal.pdig.0000198] [Citation(s) in RCA: 731] [Impact Index Per Article: 731.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Accepted: 01/23/2023] [Indexed: 02/11/2023]
Abstract
We evaluated the performance of a large language model called ChatGPT on the United States Medical Licensing Exam (USMLE), which consists of three exams: Step 1, Step 2CK, and Step 3. ChatGPT performed at or near the passing threshold for all three exams without any specialized training or reinforcement. Additionally, ChatGPT demonstrated a high level of concordance and insight in its explanations. These results suggest that large language models may have the potential to assist with medical education, and potentially, clinical decision-making.
Collapse
Affiliation(s)
- Tiffany H. Kung
- AnsibleHealth, Inc Mountain View, California, United States of America
- Department of Anesthesiology, Massachusetts General Hospital, Harvard School of Medicine Boston, Massachusetts, United States of America
| | - Morgan Cheatham
- Warren Alpert Medical School; Brown University Providence, Rhode Island, United States of America
| | - Arielle Medenilla
- AnsibleHealth, Inc Mountain View, California, United States of America
| | - Czarina Sillos
- AnsibleHealth, Inc Mountain View, California, United States of America
| | - Lorie De Leon
- AnsibleHealth, Inc Mountain View, California, United States of America
| | - Camille Elepaño
- AnsibleHealth, Inc Mountain View, California, United States of America
| | - Maria Madriaga
- AnsibleHealth, Inc Mountain View, California, United States of America
| | - Rimel Aggabao
- AnsibleHealth, Inc Mountain View, California, United States of America
| | | | - James Maningo
- AnsibleHealth, Inc Mountain View, California, United States of America
| | - Victor Tseng
- AnsibleHealth, Inc Mountain View, California, United States of America
- Department of Medical Education, UWorld, LLC Dallas, Texas, United States of America
- * E-mail:
| |
Collapse
|
88
|
Schuhmacher A, Haefner N, Honsberg K, Goldhahn J, Gassmann O. The dominant logic of Big Tech in healthcare and pharma. Drug Discov Today 2023; 28:103457. [PMID: 36427777 DOI: 10.1016/j.drudis.2022.103457] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Revised: 09/19/2022] [Accepted: 11/17/2022] [Indexed: 11/25/2022]
Abstract
Digital health and digital pharma are considered supportive tools for patients and healthcare providers (HCPs), making the market highly attractive for industry players. Not surprisingly, Tech Giants have started to move into this area. We utilized established management models and publicly available information sources, such as annual company reports, and performed a thorough analysis to uncover the underlying business models of Alphabet, Amazon, Apple, IBM, and Microsoft in order to better understand their intention and course of entering the healthcare and pharma industries. Our results indicate that Big Tech or Tech Giants do address the needs of patients and physicians, while having built clear value propositions, value chains, and revenue models to sustainably revolutionize the healthcare and pharma industries.
Collapse
Affiliation(s)
- Alexander Schuhmacher
- Technische Hochschule Ingolstadt, THI Business School, Esplanade 10, 85049 Ingolstadt, Germany; University of St. Gallen, Institute of Technology Management, Dufourstrasse 40a, 9000 St. Gallen, Switzerland.
| | - Naomi Haefner
- University of St. Gallen, Institute of Technology Management, Dufourstrasse 40a, 9000 St. Gallen, Switzerland
| | | | - Jörg Goldhahn
- ETH Zurich, D-HEST, HCP H15.3 Leopold-Ruzicka-Weg 4, 8093 Zurich, Switzerland
| | - Oliver Gassmann
- University of St. Gallen, Institute of Technology Management, Dufourstrasse 40a, 9000 St. Gallen, Switzerland
| |
Collapse
|
89
|
Hadjiiski L, Cha K, Chan HP, Drukker K, Morra L, Näppi JJ, Sahiner B, Yoshida H, Chen Q, Deserno TM, Greenspan H, Huisman H, Huo Z, Mazurchuk R, Petrick N, Regge D, Samala R, Summers RM, Suzuki K, Tourassi G, Vergara D, Armato SG. AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging. Med Phys 2023; 50:e1-e24. [PMID: 36565447 DOI: 10.1002/mp.16188] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Revised: 11/13/2022] [Accepted: 11/22/2022] [Indexed: 12/25/2022] Open
Abstract
Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.
Collapse
Affiliation(s)
- Lubomir Hadjiiski
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Kenny Cha
- U.S. Food and Drug Administration, Silver Spring, Maryland, USA
| | - Heang-Ping Chan
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Karen Drukker
- Department of Radiology, University of Chicago, Chicago, Illinois, USA
| | - Lia Morra
- Department of Control and Computer Engineering, Politecnico di Torino, Torino, Italy
| | - Janne J Näppi
- 3D Imaging Research, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Berkman Sahiner
- U.S. Food and Drug Administration, Silver Spring, Maryland, USA
| | - Hiroyuki Yoshida
- 3D Imaging Research, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Quan Chen
- Department of Radiation Medicine, University of Kentucky, Lexington, Kentucky, USA
| | - Thomas M Deserno
- Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Braunschweig, Germany
| | - Hayit Greenspan
- Department of Biomedical Engineering, Faculty of Engineering, Tel Aviv, Israel & Department of Radiology, Ichan School of Medicine, Tel Aviv University, Mt Sinai, New York, New York, USA
| | - Henkjan Huisman
- Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Zhimin Huo
- Tencent America, Palo Alto, California, USA
| | - Richard Mazurchuk
- Division of Cancer Prevention, National Cancer Institute, National Institutes of Health, Bethesda, Maryland, USA
| | | | - Daniele Regge
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, Italy.,Department of Surgical Sciences, University of Turin, Turin, Italy
| | - Ravi Samala
- U.S. Food and Drug Administration, Silver Spring, Maryland, USA
| | - Ronald M Summers
- Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Maryland, USA
| | - Kenji Suzuki
- Institute of Innovative Research, Tokyo Institute of Technology, Tokyo, Japan
| | | | - Daniel Vergara
- Department of Radiology, Yale New Haven Hospital, New Haven, Connecticut, USA
| | - Samuel G Armato
- Department of Radiology, University of Chicago, Chicago, Illinois, USA
| |
Collapse
|
90
|
Yanagisawa Y, Shido K, Kojima K, Yamasaki K. Convolutional neural network-based skin image segmentation model to improve classification of skin diseases in conventional and non-standardized picture images. J Dermatol Sci 2023; 109:30-36. [PMID: 36658056 DOI: 10.1016/j.jdermsci.2023.01.005] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Revised: 12/07/2022] [Accepted: 01/10/2023] [Indexed: 01/13/2023]
Abstract
BACKGROUND For dermatological practices, non-standardized conventional photo images are taken and collected as a mixture of variable fields of the image view, including close-up images focusing on designated lesions and long-shot images including normal skin and background of the body surface. Computer-aided detection/diagnosis (CAD) models trained using non-standardized conventional photo images exhibit lower performance rates than CAD models that detect lesions in a localized small area, such as dermoscopic images. OBJECTIVE We aimed to develop a convolutional neural network (CNN) model for skin image segmentation to generate a skin disease image dataset suitable for CAD of multiple skin disease classification. METHODS We trained a DeepLabv3 + -based CNN segmentation model to detect skin and lesion areas and segmented out areas that satisfy the following conditions: more than 80% of the image will be the skin area, and more than 10% of the image will be the lesion area. RESULTS The generated CNN-segmented image database was examined using CAD of skin disease classification and achieved approximately 90% sensitivity and specificity to differentiate atopic dermatitis from malignant diseases and complications, such as mycosis fungoides, impetigo, and herpesvirus infection. The accuracy of skin disease classification in the CNN-segmented image dataset was almost equal to that of the manually cropped image dataset and higher than that of the original image dataset. CONCLUSION Our CNN segmentation model, which automatically extracts lesions and segmented images of the skin area regardless of image fields, will reduce the burden of physician annotation and improve CAD performance.
Collapse
Affiliation(s)
| | - Kosuke Shido
- Department of Dermatology, Tohoku University Graduate School of Medicine, Sendai, Japan
| | - Kaname Kojima
- Tohoku Medical Megabank Organization, Tohoku University, Sendai, Japan.
| | - Kenshi Yamasaki
- Department of Dermatology, Tohoku University Graduate School of Medicine, Sendai, Japan.
| |
Collapse
|
91
|
Spyridonos P, Gaitanis G, Likas A, Bassukas ID. A convolutional neural network based system for detection of actinic keratosis in clinical images of cutaneous field cancerization. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104059] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
92
|
Wang J, Luo Y, Wang Z, Hounye AH, Cao C, Hou M, Zhang J. A cell phone app for facial acne severity assessment. APPL INTELL 2023; 53:7614-7633. [PMID: 35919632 PMCID: PMC9336136 DOI: 10.1007/s10489-022-03774-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 05/15/2022] [Indexed: 11/28/2022]
Abstract
Acne vulgaris, the most common skin disease, can cause substantial economic and psychological impacts to the people it affects, and its accurate grading plays a crucial role in the treatment of patients. In this paper, we firstly proposed an acne grading criterion that considers lesion classifications and a metric for producing accurate severity ratings. Due to similar appearance of acne lesions with comparable severities and difficult-to-count lesions, severity assessment is a challenging task. We cropped facial skin images of several lesion patches and then addressed the acne lesion with a lightweight acne regular network (Acne-RegNet). Acne-RegNet was built by using a median filter and histogram equalization to improve image quality, a channel attention mechanism to boost the representational power of network, a region-based focal loss to handle classification imbalances and a model pruning and feature-based knowledge distillation to reduce model size. After the application of Acne-RegNet, the severity score is calculated, and the acne grading is further optimized by the metadata of the patients. The entire acne assessment procedure was deployed to a mobile device, and a phone app was designed. Compared with state-of-the-art lightweight models, the proposed Acne-RegNet significantly improves the accuracy of lesion classifications. The acne app demonstrated promising results in severity assessments (accuracy: 94.56%) and showed a dermatologist-level diagnosis on the internal clinical dataset.The proposed acne app could be a useful adjunct to assess acne severity in clinical practice and it enables anyone with a smartphone to immediately assess acne, anywhere and anytime.
Collapse
Affiliation(s)
- Jiaoju Wang
- School of Mathematics and Statistics, Central South University, Changsha, 410083 Hunan China
| | - Yan Luo
- Department of dermatology of Xiangya hospital, Central South University, Changsha, 410083 Hunan China
| | - Zheng Wang
- School of Mathematics and Statistics, Central South University, Changsha, 410083 Hunan China.,Science and Engineering School, Hunan First Normal University, Changsha, 410083 Hunan China
| | - Alphonse Houssou Hounye
- School of Mathematics and Statistics, Central South University, Changsha, 410083 Hunan China
| | - Cong Cao
- School of Mathematics and Statistics, Central South University, Changsha, 410083 Hunan China
| | - Muzhou Hou
- School of Mathematics and Statistics, Central South University, Changsha, 410083 Hunan China
| | - Jianglin Zhang
- Department of Dermatology of Shenzhen People's Hospital The Second Clinical Medical College of Jinan Uninversity, The First Affiliated Hospital of Southern University of Science and Technology, Shenzhen, 518020 Guangdong China.,Candidate Branch of National Clinical Research Center for Skin Diseases, Shenzhen, 518020 Guangdong China
| |
Collapse
|
93
|
Kuroda Y, Kaneko T, Yoshikawa H, Uchiyama S, Nagata Y, Matsushita Y, Hiki M, Minamino T, Takahashi K, Daida H, Kagiyama N. Artificial intelligence-based point-of-care lung ultrasound for screening COVID-19 pneumoniae: Comparison with CT scans. PLoS One 2023; 18:e0281127. [PMID: 36928805 PMCID: PMC10019704 DOI: 10.1371/journal.pone.0281127] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2022] [Accepted: 01/15/2023] [Indexed: 03/18/2023] Open
Abstract
BACKGROUND Although lung ultrasound has been reported to be a portable, cost-effective, and accurate method to detect pneumonia, it has not been widely used because of the difficulty in its interpretation. Here, we aimed to investigate the effectiveness of a novel artificial intelligence-based automated pneumonia detection method using point-of-care lung ultrasound (AI-POCUS) for the coronavirus disease 2019 (COVID-19). METHODS We enrolled consecutive patients admitted with COVID-19 who underwent computed tomography (CT) in August and September 2021. A 12-zone AI-POCUS was performed by a novice observer using a pocket-size device within 24 h of the CT scan. Fifteen control subjects were also scanned. Additionally, the accuracy of the simplified 8-zone scan excluding the dorsal chest, was assessed. More than three B-lines detected in one lung zone were considered zone-level positive, and the presence of positive AI-POCUS in any lung zone was considered patient-level positive. The sample size calculation was not performed given the retrospective all-comer nature of the study. RESULTS A total of 577 lung zones from 56 subjects (59.4 ± 14.8 years, 23% female) were evaluated using AI-POCUS. The mean number of days from disease onset was 9, and 14% of patients were under mechanical ventilation. The CT-validated pneumonia was seen in 71.4% of patients at total 577 lung zones (53.3%). The 12-zone AI-POCUS for detecting CT-validated pneumonia in the patient-level showed the accuracy of 94.5% (85.1%- 98.1%), sensitivity of 92.3% (79.7%- 97.3%), specificity of 100% (80.6%- 100%), positive predictive value of 95.0% (89.6% - 97.7%), and Kappa of 0.33 (0.27-0.40). When simplified with 8-zone scan, the accuracy, sensitivity, and sensitivity were 83.9% (72.2%- 91.3%), 77.5% (62.5%- 87.7%), and 100% (80.6%- 100%), respectively. The zone-level accuracy, sensitivity, and specificity of AI-POCUS were 65.3% (61.4%- 69.1%), 37.2% (32.0%- 42.7%), and 97.8% (95.2%- 99.0%), respectively. INTERPRETATION AI-POCUS using the novel pocket-size ultrasound system showed excellent agreement with CT-validated COVID-19 pneumonia, even when used by a novice observer.
Collapse
Affiliation(s)
- Yumi Kuroda
- Department of Respiratory Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Tomohiro Kaneko
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Hitomi Yoshikawa
- Department of Respiratory Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Saori Uchiyama
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Yuichi Nagata
- Department of Respiratory Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Yasushi Matsushita
- Department of Emergency Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
- Department of Internal Medicine and Rheumatology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Makoto Hiki
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
- Department of Emergency Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Tohru Minamino
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Kazuhisa Takahashi
- Department of Respiratory Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
| | - Hiroyuki Daida
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
- Department of Digital Health and Telemedicine R&D, Juntendo University, Bunkyo-ku, Tokyo, Japan
| | - Nobuyuki Kagiyama
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, Japan
- Department of Digital Health and Telemedicine R&D, Juntendo University, Bunkyo-ku, Tokyo, Japan
- * E-mail:
| |
Collapse
|
94
|
Shi W, Xu H, Sun C, Sun J, Li Y, Xu X, Zheng T, Zhang Y, Wang G, Wu D. AFFIRM: Affinity Fusion-Based Framework for Iteratively Random Motion Correction of Multi-Slice Fetal Brain MRI. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:209-219. [PMID: 36129858 DOI: 10.1109/tmi.2022.3208277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
Multi-slice magnetic resonance images of the fetal brain are usually contaminated by severe and arbitrary fetal and maternal motion. Hence, stable and robust motion correction is necessary to reconstruct high-resolution 3D fetal brain volume for clinical diagnosis and quantitative analysis. However, the conventional registration-based correction has a limited capture range and is insufficient for detecting relatively large motions. Here, we present a novel Affinity Fusion-based Framework for Iteratively Random Motion (AFFIRM) correction of the multi-slice fetal brain MRI. It learns the sequential motion from multiple stacks of slices and integrates the features between 2D slices and reconstructed 3D volume using affinity fusion, which resembles the iterations between slice-to-volume registration and volumetric reconstruction in the regular pipeline. The method accurately estimates the motion regardless of brain orientations and outperforms other state-of-the-art learning-based methods on the simulated motion-corrupted data, with a 48.4% reduction of mean absolute error for rotation and 61.3% for displacement. We then incorporated AFFIRM into the multi-resolution slice-to-volume registration and tested it on the real-world fetal MRI scans at different gestation stages. The results indicated that adding AFFIRM to the conventional pipeline improved the success rate of fetal brain super-resolution reconstruction from 77.2% to 91.9%.
Collapse
|
95
|
Flament F, Jiang R, Houghton J, Zhang Y, Kroely C, Jablonski NG, Jean A, Clarke J, Steeg J, Sehgal C, McParland J, Delaunay C, Passeron T. Accuracy and clinical relevance of an automated, algorithm-based analysis of facial signs from selfie images of women in the United States of various ages, ancestries and phototypes: A cross-sectional observational study. J Eur Acad Dermatol Venereol 2023; 37:176-183. [PMID: 35986708 PMCID: PMC10087370 DOI: 10.1111/jdv.18541] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2022] [Accepted: 07/27/2022] [Indexed: 12/15/2022]
Abstract
BACKGROUND Real-life validation is necessary to ensure our artificial intelligence (AI) skin diagnostic tool is inclusive across a diverse and representative US population of various ages, ancestries and skin phototypes. OBJECTIVES To explore the relevance and accuracy of an automated, algorithm-based analysis of facial signs in representative women of different ancestries, ages and phototypes, living in the same country. METHODS In a cross-sectional study of selfie images of 1041 US women, algorithm-based analyses of seven facial signs were automatically graded by an AI-based algorithm and by 50 US dermatologists of various profiles (age, gender, ancestry, geographical location). For automated analysis and dermatologist assessment, the same referential skin atlas was used to standardize the grading scales. The average values and their variability were compared with respect to age, ancestry and phototype. RESULTS For five signs, the grading obtained by the automated system were strongly correlated with dermatologists' assessments (r ≥ 0.75); cheek skin pores were moderately correlated (r = 0.63) and pigmentation signs, especially for the darkest skin tones, were weakly correlated (r = 0.40) to the dermatologist assessments. Age and ancestry had no effect on the correlations. In many cases, the automated system performed better than the dermatologist-assessed clinical grading due to 0.3-0.5 grading unit differences among the dermatologist panel that were not related to any individual characteristic (e.g. gender, age, ancestry, location). The use of phototypes, as discontinuous categorical variables, is likely a limiting factor in the assessments of grading, whether obtained by automated analysis or clinical assessment of the images. CONCLUSIONS The AI-based automatic procedure is accurate and clinically relevant for analysing facial signs in a diverse and inclusive population of US women, as confirmed by a diverse panel of dermatologists, although skin tone requires further improvement.
Collapse
Affiliation(s)
| | - Ruowei Jiang
- ModiFace - A L'Oréal Group Company, Toronto, Ontario, Canada
| | - Jeff Houghton
- ModiFace - A L'Oréal Group Company, Toronto, Ontario, Canada
| | - Yuze Zhang
- ModiFace - A L'Oréal Group Company, Toronto, Ontario, Canada
| | | | - Nina G Jablonski
- Department of Anthropology, The Pennsylvania State University, University Park, State College, Pennsylvania, USA
| | | | - Jeffrey Clarke
- Evaluative Criteria Incorporated, Tarrytown, New York, USA
| | - Jason Steeg
- Evaluative Criteria Incorporated, Tarrytown, New York, USA
| | | | | | | | - Thierry Passeron
- Department of Dermatology, Université Côte d'Azur, CHU Nice, Nice, France.,Université Côte d'Azur, INSERM, U1065, C3M, Nice, France
| |
Collapse
|
96
|
Yin W, Huang J, Chen J, Ji Y. A study on skin tumor classification based on dense convolutional networks with fused metadata. Front Oncol 2022; 12:989894. [PMID: 36601473 PMCID: PMC9806866 DOI: 10.3389/fonc.2022.989894] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Accepted: 11/21/2022] [Indexed: 12/23/2022] Open
Abstract
Skin cancer is the most common cause of death in humans. Statistics show that competent dermatologists have a diagnostic accuracy rate of less than 80%, while inexperienced dermatologists have a diagnostic accuracy rate of less than 60%. The higher rate of misdiagnosis will cause many patients to miss the most effective treatment window, risking the patients' life safety. However, the majority of the current study of neural network-based skin cancer diagnosis remains at the image level without patient clinical data. A deep convolutional network incorporating clinical patient metadata of skin cancer is presented to realize the classification model of skin cancer in order to further increase the accuracy of skin cancer diagnosis. There are three basic steps in the approach. First, the high-level features (edge features, color features, texture features, form features, etc.). Implied by the image were retrieved using the pre-trained DenseNet-169 model on the ImageNet dataset. Second, the MetaNet module is introduced, which uses metadata to control a certain portion of each feature channel in the DenseNet-169 network in order to produce weighted features. The MetaBlock module was added at the same time to improve the features retrieved from photos using metadata, choosing the most pertinent characteristics in accordance with the metadata data. The features of the MetaNet and MetaBlock modules were finally combined to create the MD-Net module, which was then used as input into the classifier to get the classification results for skin cancers. On the PAD-UFES-20 and ISIC 2019 datasets, the suggested methodology was assessed. The DenseNet-169 network model combined with this module, according to experimental data, obtains 81.4% in the balancing accuracy index, and its diagnostic accuracy is up between 8% and 15.6% compared to earlier efforts. Additionally, it solves the problem of actinic keratosis and poorly classified skin fibromas.
Collapse
Affiliation(s)
- Wenjun Yin
- School of Information and Communication, Guilin University Of Electronic Technology, Guilin, China
| | - Jianhua Huang
- School of Information and Communication, Guilin University Of Electronic Technology, Guilin, China,*Correspondence: Jianhua Huang, ; Jianlin Chen,
| | - Jianlin Chen
- Reproductive Endocrinology Clinic, Second Xiangya Hospital of Central South University, Changsha, China,*Correspondence: Jianhua Huang, ; Jianlin Chen,
| | - Yuanfa Ji
- School of Information and Communication, Guilin University Of Electronic Technology, Guilin, China
| |
Collapse
|
97
|
Zhang A, Xing L, Zou J, Wu JC. Shifting machine learning for healthcare from development to deployment and from models to data. Nat Biomed Eng 2022; 6:1330-1345. [PMID: 35788685 DOI: 10.1038/s41551-022-00898-y] [Citation(s) in RCA: 51] [Impact Index Per Article: 25.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2021] [Accepted: 05/03/2022] [Indexed: 01/14/2023]
Abstract
In the past decade, the application of machine learning (ML) to healthcare has helped drive the automation of physician tasks as well as enhancements in clinical capabilities and access to care. This progress has emphasized that, from model development to model deployment, data play central roles. In this Review, we provide a data-centric view of the innovations and challenges that are defining ML for healthcare. We discuss deep generative models and federated learning as strategies to augment datasets for improved model performance, as well as the use of the more recent transformer models for handling larger datasets and enhancing the modelling of clinical text. We also discuss data-focused problems in the deployment of ML, emphasizing the need to efficiently deliver data to ML models for timely clinical predictions and to account for natural data shifts that can deteriorate model performance.
Collapse
Affiliation(s)
- Angela Zhang
- Stanford Cardiovascular Institute, School of Medicine, Stanford University, Stanford, CA, USA. .,Department of Genetics, School of Medicine, Stanford University, Stanford, CA, USA. .,Greenstone Biosciences, Palo Alto, CA, USA. .,Department of Computer Science, Stanford University, Stanford, CA, USA.
| | - Lei Xing
- Department of Radiation Oncology, School of Medicine, Stanford University, Stanford, CA, USA
| | - James Zou
- Department of Computer Science, Stanford University, Stanford, CA, USA.,Department of Biomedical Informatics, School of Medicine, Stanford University, Stanford, CA, USA
| | - Joseph C Wu
- Stanford Cardiovascular Institute, School of Medicine, Stanford University, Stanford, CA, USA. .,Greenstone Biosciences, Palo Alto, CA, USA. .,Departments of Medicine, Division of Cardiovascular Medicine Stanford University, Stanford, CA, USA. .,Department of Radiology, School of Medicine, Stanford University, Stanford, CA, USA.
| |
Collapse
|
98
|
Attention Cost-Sensitive Deep Learning-Based Approach for Skin Cancer Detection and Classification. Cancers (Basel) 2022; 14:cancers14235872. [PMID: 36497355 PMCID: PMC9735681 DOI: 10.3390/cancers14235872] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2022] [Revised: 11/21/2022] [Accepted: 11/23/2022] [Indexed: 12/03/2022] Open
Abstract
Deep learning-based models have been employed for the detection and classification of skin diseases through medical imaging. However, deep learning-based models are not effective for rare skin disease detection and classification. This is mainly due to the reason that rare skin disease has very a smaller number of data samples. Thus, the dataset will be highly imbalanced, and due to the bias in learning, most of the models give better performances. The deep learning models are not effective in detecting the affected tiny portions of skin disease in the overall regions of the image. This paper presents an attention-cost-sensitive deep learning-based feature fusion ensemble meta-classifier approach for skin cancer detection and classification. Cost weights are included in the deep learning models to handle the data imbalance during training. To effectively learn the optimal features from the affected tiny portions of skin image samples, attention is integrated into the deep learning models. The features from the finetuned models are extracted and the dimensionality of the features was further reduced by using a kernel-based principal component (KPCA) analysis. The reduced features of the deep learning-based finetuned models are fused and passed into ensemble meta-classifiers for skin disease detection and classification. The ensemble meta-classifier is a two-stage model. The first stage performs the prediction of skin disease and the second stage performs the classification by considering the prediction of the first stage as features. Detailed analysis of the proposed approach is demonstrated for both skin disease detection and skin disease classification. The proposed approach demonstrated an accuracy of 99% on skin disease detection and 99% on skin disease classification. In all the experimental settings, the proposed approach outperformed the existing methods and demonstrated a performance improvement of 4% accuracy for skin disease detection and 9% accuracy for skin disease classification. The proposed approach can be used as a computer-aided diagnosis (CAD) tool for the early diagnosis of skin cancer detection and classification in healthcare and medical environments. The tool can accurately detect skin diseases and classify the skin disease into their skin disease family.
Collapse
|
99
|
Kriegsmann K, Lobers F, Zgorzelski C, Kriegsmann J, Janßen C, Meliß RR, Muley T, Sack U, Steinbuss G, Kriegsmann M. Deep learning for the detection of anatomical tissue structures and neoplasms of the skin on scanned histopathological tissue sections. Front Oncol 2022; 12:1022967. [PMID: 36483044 PMCID: PMC9723465 DOI: 10.3389/fonc.2022.1022967] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2022] [Accepted: 10/24/2022] [Indexed: 01/25/2023] Open
Abstract
Basal cell carcinoma (BCC), squamous cell carcinoma (SqCC) and melanoma are among the most common cancer types. Correct diagnosis based on histological evaluation after biopsy or excision is paramount for adequate therapy stratification. Deep learning on histological slides has been suggested to complement and improve routine diagnostics, but publicly available curated and annotated data and usable models trained to distinguish common skin tumors are rare and often lack heterogeneous non-tumor categories. A total of 16 classes from 386 cases were manually annotated on scanned histological slides, 129,364 100 x 100 µm (~395 x 395 px) image tiles were extracted and split into a training, validation and test set. An EfficientV2 neuronal network was trained and optimized to classify image categories. Cross entropy loss, balanced accuracy and Matthews correlation coefficient were used for model evaluation. Image and patient data were assessed with confusion matrices. Application of the model to an external set of whole slides facilitated localization of melanoma and non-tumor tissue. Automated differentiation of BCC, SqCC, melanoma, naevi and non-tumor tissue structures was possible, and a high diagnostic accuracy was achieved in the validation (98%) and test (97%) set. In summary, we provide a curated dataset including the most common neoplasms of the skin and various anatomical compartments to enable researchers to train, validate and improve deep learning models. Automated classification of skin tumors by deep learning techniques is possible with high accuracy, facilitates tumor localization and has the potential to support and improve routine diagnostics.
Collapse
Affiliation(s)
- Katharina Kriegsmann
- Department of Hematology, Oncology and Rheumatology, Heidelberg University, Heidelberg, Germany
| | - Frithjof Lobers
- Department of Clinical Immunology, Medical Faculty, University of Leipzig, Leipzig, Germany
| | | | - Jörg Kriegsmann
- MVZ Histology, Cytology and Molecular Diagnostics Trier, Trier, Germany,Proteopath Trier, Trier, Germany
| | - Charlotte Janßen
- Center for Industrial Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | | | - Thomas Muley
- Translational Lung Research Centre (TLRC) Heidelberg, Member of the German Centre for Lung Research (DZL), Heidelberg, Germany
| | - Ulrich Sack
- Department of Clinical Immunology, Medical Faculty, University of Leipzig, Leipzig, Germany
| | - Georg Steinbuss
- Department of Hematology, Oncology and Rheumatology, Heidelberg University, Heidelberg, Germany
| | - Mark Kriegsmann
- Institute of Pathology, Heidelberg University, Heidelberg, Germany,*Correspondence: Mark Kriegsmann,
| |
Collapse
|
100
|
Li Z, Koban KC, Schenck TL, Giunta RE, Li Q, Sun Y. Artificial Intelligence in Dermatology Image Analysis: Current Developments and Future Trends. J Clin Med 2022; 11:jcm11226826. [PMID: 36431301 PMCID: PMC9693628 DOI: 10.3390/jcm11226826] [Citation(s) in RCA: 27] [Impact Index Per Article: 13.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 10/24/2022] [Accepted: 10/28/2022] [Indexed: 11/22/2022] Open
Abstract
BACKGROUND Thanks to the rapid development of computer-based systems and deep-learning-based algorithms, artificial intelligence (AI) has long been integrated into the healthcare field. AI is also particularly helpful in image recognition, surgical assistance and basic research. Due to the unique nature of dermatology, AI-aided dermatological diagnosis based on image recognition has become a modern focus and future trend. Key scientific concepts of review: The use of 3D imaging systems allows clinicians to screen and label skin pigmented lesions and distributed disorders, which can provide an objective assessment and image documentation of lesion sites. Dermatoscopes combined with intelligent software help the dermatologist to easily correlate each close-up image with the corresponding marked lesion in the 3D body map. In addition, AI in the field of prosthetics can assist in the rehabilitation of patients and help to restore limb function after amputation in patients with skin tumors. THE AIM OF THE STUDY For the benefit of patients, dermatologists have an obligation to explore the opportunities, risks and limitations of AI applications. This study focuses on the application of emerging AI in dermatology to aid clinical diagnosis and treatment, analyzes the current state of the field and summarizes its future trends and prospects so as to help dermatologists realize the impact of new technological innovations on traditional practices so that they can embrace and use AI-based medical approaches more quickly.
Collapse
Affiliation(s)
- Zhouxiao Li
- Department of Plastic and Reconstructive Surgery, Shanghai 9th People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200023, China
- Division of Hand, Plastic and Aesthetic Surgery, University Hospital, LMU Munich, 80339 Munich, Germany
| | | | - Thilo Ludwig Schenck
- Division of Hand, Plastic and Aesthetic Surgery, University Hospital, LMU Munich, 80339 Munich, Germany
| | - Riccardo Enzo Giunta
- Division of Hand, Plastic and Aesthetic Surgery, University Hospital, LMU Munich, 80339 Munich, Germany
| | - Qingfeng Li
- Department of Plastic and Reconstructive Surgery, Shanghai 9th People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200023, China
- Correspondence: (Q.L.); (Y.S.)
| | - Yangbai Sun
- Department of Plastic and Reconstructive Surgery, Shanghai 9th People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200023, China
- Correspondence: (Q.L.); (Y.S.)
| |
Collapse
|