Detection of Malignant Melanoma Using Artificial Intelligence: An Observational Study of Diagnostic Accuracy

Evaluation of an artificial intelligence-based decision support for the detection of cutaneous melanoma in primary care: a prospective real-life clinical trial

BACKGROUND

Use of artificial intelligence (AI), or machine learning, to assess dermoscopic images of skin lesions to detect melanoma has, in several retrospective studies, shown high levels of diagnostic accuracy on par with - or even outperforming - experienced dermatologists. However, the enthusiasm around these algorithms has not yet been matched by prospective clinical trials performed in authentic clinical settings. In several European countries, including Sweden, the initial clinical assessment of suspected skin cancer is principally conducted in the primary healthcare setting by primary care physicians, with or without access to teledermoscopic support from dermatology clinics.

OBJECTIVES

To determine the diagnostic performance of an AI-based clinical decision support tool for cutaneous melanoma detection, operated by a smartphone application (app), when used prospectively by primary care physicians to assess skin lesions of concern due to some degree of melanoma suspicion.

METHODS

This prospective multicentre clinical trial was conducted at 36 primary care centres in Sweden. Physicians used the smartphone app on skin lesions of concern by photographing them dermoscopically, which resulted in a dichotomous decision support text regarding evidence for melanoma. Regardless of the app outcome, all lesions underwent standard diagnostic procedures (surgical excision or referral to a dermatologist). After investigations were complete, lesion diagnoses were collected from the patients' medical records and compared with the app's outcome and other lesion data.

RESULTS

In total, 253 lesions of concern in 228 patients were included, of which 21 proved to be melanomas, with 11 thin invasive melanomas and 10 melanomas in situ. The app's accuracy in identifying melanomas was reflected in an area under the receiver operating characteristic (AUROC) curve of 0.960 [95% confidence interval (CI) 0.928-0.980], corresponding to a maximum sensitivity and specificity of 95.2% and 84.5%, respectively. For invasive melanomas alone, the AUROC was 0.988 (95% CI 0.965-0.997), corresponding to a maximum sensitivity and specificity of 100% and 92.6%, respectively.

CONCLUSIONS

The clinical decision support tool evaluated in this investigation showed high diagnostic accuracy when used prospectively in primary care patients, which could add significant clinical value for primary care physicians assessing skin lesions for melanoma.

Technology innovation to reduce health inequality in skin diagnosis and to improve patient outcomes for people of color: a thematic literature review and future research agenda

The health inequalities experienced by ethnic minorities have been a persistent and global phenomenon. The diagnosis of different types of skin conditions, e.g., melanoma, among people of color is one of such health domains where misdiagnosis can take place, potentially leading to life-threatening consequences. Although Caucasians are more likely to be diagnosed with melanoma, African Americans are four times more likely to present stage IV melanoma due to delayed diagnosis. It is essential to recognize that additional factors such as socioeconomic status and limited access to healthcare services can be contributing factors. African Americans are also 1.5 times more likely to die from melanoma than Caucasians, with 5-year survival rates for African Americans significantly lower than for Caucasians (72.2% vs. 89.6%). This is a complex problem compounded by several factors: ill-prepared medical practitioners, lack of awareness of melanoma and other skin conditions among people of colour, lack of information and medical resources for practitioners' continuous development, under-representation of people of colour in research, POC being a notoriously hard to reach group, and 'whitewashed' medical school curricula. Whilst digital technology can bring new hope for the reduction of health inequality, the deployment of artificial intelligence in healthcare carries risks that may amplify the health disparities experienced by people of color, whilst digital technology may provide a false sense of participation. For instance, Derm Assist, a skin diagnosis phone application which is under development, has already been criticized for relying on data from a limited number of people of color. This paper focuses on understanding the problem of misdiagnosing skin conditions in people of color and exploring the progress and innovations that have been experimented with, to pave the way to the possible application of big data analytics, artificial intelligence, and user-centred technology to reduce health inequalities among people of color.

The Use of Artificial Intelligence for Skin Disease Diagnosis in Primary Care Settings: A Systematic Review

The prevalence of dermatological conditions in primary care, coupled with challenges such as dermatologist shortages and rising consultation costs, highlights the need for innovative solutions. Artificial intelligence (AI) holds promise for improving the diagnostic analysis of skin lesion images, potentially enhancing patient care in primary settings. This systematic review following PRISMA guidelines examined primary studies (2012-2022) assessing AI algorithms' diagnostic accuracy for skin diseases in primary care. Studies were screened for eligibility based on their availability in the English language and exclusion criteria, with risk of bias evaluated using QUADAS-2. PubMed, Scopus, and Web of Science were searched. Fifteen studies (2019-2022), primarily from Europe and the USA, focusing on diagnostic accuracy were included. Sensitivity ranged from 58% to 96.1%, with accuracies varying from 0.41 to 0.93. AI applications encompassed triage and diagnostic support across diverse skin conditions in primary care settings, involving both patients and primary care professionals. While AI demonstrates potential for enhancing the accuracy of skin disease diagnostics in primary care, further research is imperative to address study heterogeneity and ensure algorithm reliability across diverse populations. Future investigations should prioritise robust dataset development and consider representative patient samples. Overall, AI may improve dermatological diagnosis in primary care, but careful consideration of algorithm limitations and implementation strategies is required.

Comprehensive analysis of clinical images contributions for melanoma classification using convolutional neural networks

BACKGROUND

Timely diagnosis plays a critical role in determining melanoma prognosis, prompting the development of deep learning models to aid clinicians. Questions persist regarding the efficacy of clinical images alone or in conjunction with dermoscopy images for model training. This study aims to compare the classification performance for melanoma of three types of CNN models: those trained on clinical images, dermoscopy images, and a combination of paired clinical and dermoscopy images from the same lesion.

MATERIALS AND METHODS

We divided 914 image pairs into training, validation, and test sets. Models were built using pre-trained Inception-ResNetV2 convolutional layers for feature extraction, followed by binary classification. Training comprised 20 models per CNN type using sets of random hyperparameters. Best models were chosen based on validation AUC-ROC.

RESULTS

Significant AUC-ROC differences were found between clinical versus dermoscopy models (0.661 vs. 0.869, p < 0.001) and clinical versus clinical + dermoscopy models (0.661 vs. 0.822, p = 0.001). Significant sensitivity differences were found between clinical and dermoscopy models (0.513 vs. 0.799, p = 0.01), dermoscopy versus clinical + dermoscopy models (0.799 vs. 1.000, p = 0.02), and clinical versus clinical + dermoscopy models (0.513 vs. 1.000, p < 0.001). Significant specificity differences were found between dermoscopy versus clinical + dermoscopy models (0.800 vs. 0.288, p < 0.001) and clinical versus clinical + dermoscopy models (0.650 vs. 0.288, p < 0.001).

CONCLUSION

CNN models trained on dermoscopy images outperformed those relying solely on clinical images under our study conditions. The potential advantages of incorporating paired clinical and dermoscopy images for CNN-based melanoma classification appear less clear based on our findings.

Accuracy of an artificial intelligence as a medical device as part of a UK-based skin cancer teledermatology service

Introduction

An artificial intelligence as a medical device (AIaMD), built on convolutional neural networks, has demonstrated high sensitivity for melanoma. To be of clinical value, it needs to safely reduce referral rates. The primary objective of this study was to demonstrate that the AIaMD had a higher rate of correctly classifying lesions that did not need to be referred for biopsy or urgent face-to-face dermatologist review, compared to teledermatology standard of care (SoC), while achieving the same sensitivity to detect malignancy. Secondary endpoints included the sensitivity, specificity, positive and negative predictive values, and number needed to biopsy to identify one case of melanoma or squamous cell carcinoma (SCC) by both the AIaMD and SoC.

Methods

This prospective, single-centre, single-arm, masked, non-inferiority, adaptive, group sequential design trial recruited patients referred to a teledermatology cancer pathway (clinicaltrials.gov NCT04123678). Additional dermoscopic images of each suspicious lesion were taken using a smartphone with a dermoscopic lens attachment. The images were assessed independently by a consultant dermatologist and the AIaMD. The outputs were compared with the final histological or clinical diagnosis.

Results

A total of 700 patients with 867 lesions were recruited, of which 622 participants with 789 lesions were included in the per-protocol (PP) population. In total, 63.3% of PP participants were female; 89.0% identified as white, and the median age was 51 (range 18-95); and all Fitzpatrick skin types were represented including 25/622 (4.0%) type IV-VI skin. A total of 67 malignant lesions were identified, including 8 diagnosed as melanoma. The AIaMD sensitivity was set at 91 and 92.5%, to match the literature-defined clinician sensitivity (91.46%) as closely as possible. In both settings, the AIaMD identified had a significantly higher rate of identifying lesions that did not need a biopsy or urgent referral compared to SoC (p-value = 0.001) with comparable sensitivity for skin cancer.

Discussion

The AIaMD identified significantly more lesions that did not need to be referred for biopsy or urgent face-to-face dermatologist review, compared to teledermatologists. This has the potential to reduce the burden of unnecessary referrals when used as part of a teledermatology service.

The State of Artificial Intelligence in Skin Cancer Publications

BACKGROUND

Artificial intelligence (AI) in skin cancer is a promising research field to assist physicians and to provide support to patients remotely. Physicians' awareness to new developments in AI research is important to define the best practices and scope of integrating AI-enabled technologies within a clinical setting.

OBJECTIVES

To analyze the characteristics and trends of AI skin cancer publications from dermatology journals.

METHODS

AI skin cancer publications were retrieved in June 2022 from the Web of Science. Publications were screened by title, abstract, and keywords to assess eligibility. Publications were fully reviewed. Publications were divided between nonmelanoma skin cancer (NMSC), melanoma, and skin cancer studies. The primary measured outcome was the number of citations. The secondary measured outcomes were articles' general characteristics and features related to AI.

RESULTS

A total of 168 articles were included: 25 on NMSC, 77 on melanoma, and 66 on skin cancer. The most common types of skin cancers were melanoma (134, 79.8%), basal cell carcinoma (61, 36.3%), and squamous cell carcinoma (45, 26.9%). All articles were published between 2000 and 2022, with 49 (29.2%) of them being published in 2021. Original studies that developed or assessed an algorithm predominantly used supervised learning (66, 97.0%) and deep neural networks (42, 67.7%). The most used imaging modalities were standard dermoscopy (76, 45.2%) and clinical images (39, 23.2%).

CONCLUSIONS

Most publications focused on developing or assessing screening technologies with mainly deep neural network algorithms. This indicates the eminent need for dermatologists to label or annotate images used by novel AI systems.

Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance

Introduction

Deep Ensemble for Recognition of Malignancy (DERM) is an artificial intelligence as a medical device (AIaMD) tool for skin lesion assessment.

Methods

We report prospective real-world performance from its deployment within skin cancer pathways at two National Health Service hospitals (UK) between July 2021 and October 2022.

Results

A total of 14,500 cases were seen, including patients 18-100 years old with Fitzpatrick skin types I-VI represented. Based on 8,571 lesions assessed by DERM with confirmed outcomes, versions A and B demonstrated very high sensitivity for detecting melanoma (95.0-100.0%) or malignancy (96.0-100.0%). Benign lesion specificity was 40.7-49.4% (DERM-vA) and 70.1-73.4% (DERM-vB). DERM identified 15.0-31.0% of cases as eligible for discharge.

Discussion

We show DERM performance in-line with sensitivity targets and pre-marketing authorisation research, and it reduced the caseload for hospital specialists in two pathways. Based on our experience we offer suggestions on key elements of post-market surveillance for AIaMDs.

Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review

BACKGROUND

Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma.

OBJECTIVE

The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma.

METHODS

A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives.

RESULTS

We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%.

CONCLUSIONS

Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability.

Non-Melanoma Skin Cancer Detection in the Age of Advanced Technology: A Review

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.

Quantization of extraoral free flap monitoring for venous congestion with deep learning integrated iOS applications on smartphones: a diagnostic study

BACKGROUND

Free flap monitoring is essential for postmicrosurgical management and outcomes but traditionally relies on human observers; the process is subjective and qualitative and imposes a heavy burden on staffing. To scientifically monitor and quantify the condition of free flaps in a clinical scenario, we developed and validated a successful clinical transitional deep learning (DL) model integrated application.

MATERIAL AND METHODS

Patients from a single microsurgical intensive care unit between 1 April 2021 and 31 March 2022, were retrospectively analyzed for DL model development, validation, clinical transition, and quantification of free flap monitoring. An iOS application that predicted the probability of flap congestion based on computer vision was developed. The application calculated probability distribution that indicates the flap congestion risks. Accuracy, discrimination, and calibration tests were assessed for model performance evaluations.

RESULTS

From a total of 1761 photographs of 642 patients, 122 patients were included during the clinical application period. Development (photographs =328), external validation (photographs =512), and clinical application (photographs =921) cohorts were assigned to corresponding time periods. The performance measurements of the DL model indicate a 92.2% training and a 92.3% validation accuracy. The discrimination (area under the receiver operating characteristic curve) was 0.99 (95% CI: 0.98-1.0) during internal validation and 0.98 (95% CI: 0.97-0.99) under external validation. Among clinical application periods, the application demonstrates 95.3% accuracy, 95.2% sensitivity, and 95.3% specificity. The probabilities of flap congestion were significantly higher in the congested group than in the normal group (78.3 (17.1)% versus 13.2 (18.1)%; 0.8%; 95% CI, P <0.001).

CONCLUSION

The DL integrated smartphone application can accurately reflect and quantify flap condition; it is a convenient, accurate, and economical device that can improve patient safety and management and assist in monitoring flap physiology.

New AI-algorithms on smartphones to detect skin cancer in a clinical setting-A validation study

BACKGROUND AND OBJECTIVES

The incidence of skin cancer is rising worldwide and there is medical need to optimize its early detection. This study was conducted to determine the diagnostic and risk-assessment accuracy of two new diagnosis-based neural networks (analyze and detect), which comply with the CE-criteria, in evaluating the malignant potential of various skin lesions on a smartphone. Of note, the intention of our study was to evaluate the performance of these medical products in a clinical setting for the first time.

METHODS

This was a prospective, single-center clinical study at one tertiary referral center in Graz, Austria. Patients, who were either scheduled for preventive skin examination or removal of at least one skin lesion were eligible for participation. Patients were assessed by at least two dermatologists and by the integrated algorithms on different mobile phones. The lesions to be recorded were randomly selected by the dermatologists. The diagnosis of the algorithm was stated as correct if it matched the diagnosis of the two dermatologists or the histology (if available). The histology was the reference standard, however, if both clinicians considered a lesion as being benign no histology was performed and the dermatologists were stated as reference standard.

RESULTS

A total of 238 patients with 1171 lesions (86 female; 36.13%) with an average age of 66.19 (SD = 17.05) was included. Sensitivity and specificity of the detect algorithm were 96.4% (CI 93.94-98.85) and 94.85% (CI 92.46-97.23); for the analyze algorithm a sensitivity of 95.35% (CI 93.45-97.25) and a specificity of 90.32% (CI 88.1-92.54) were achieved.

DISCUSSION

The studied neural networks succeeded analyzing the risk of skin lesions with a high diagnostic accuracy showing that they are sufficient tools in calculating the probability of a skin lesion being malignant. In conjunction with the wide spread use of smartphones this new AI approach opens the opportunity for a higher early detection rate of skin cancer with consecutive lower epidemiological burden of metastatic cancer and reducing health care costs. This neural network moreover facilitates the empowerment of patients, especially in regions with a low density of medical doctors.

REGISTRATION

Approved and registered at the ethics committee of the Medical University of Graz, Austria (Approval number: 30-199 ex 17/18).

Slit lamp polarized dermoscopy: a cost-effective tool to assess eyelid lesions

PURPOSE

Dermoscopy is a complementary examination of skin lesions, which allows the observation of anatomical features invisible to the naked eye. Its use increases the diagnostic accuracy of skin tumors. The development of polarized dermoscopy allowed the observation of deeper skin structures, without the need of skin contact. The purpose of this study was to present a low-cost prototype through the adaptation of polarized lenses on a slit lamp in order to assess anatomical aspects invisible to conventional biomicroscopy in eyelid lesions.

METHODS

Twenty two eyelid lesions were documented using a prototype, compound of two polarizing filters, orthogonal to each other, adapted to a slit lamp with an integrated digital camera. Images of the eyelid lesions were also obtained with non-polarized biomicroscopy and with a portable dermatoscope, and were compared regarding anatomical aspects.

RESULTS

Anatomical structures imperceptible to conventional ophthalmic examination were evidenced using the polarized lenses, demonstrating that this tool can be useful to the ophthalmologist when assessing eyelid lesions. We have obtained high-quality images of the lesions. The slit lamp provided higher magnification, better focus control and easier assessment of eyelid lesions than the portable dermatoscope.

CONCLUSION

Ophthalmologists already use the slit lamp in their practice. The adaptation of polarized lenses to this device is a cost-effective, fast and non-invasive method that permits to improve the diagnostic accuracy of eyelid lesions, evidencing anatomical structures imperceptible to conventional ophthalmic examination.

An Efficient Deep Learning-Based Skin Cancer Classifier for an Imbalanced Dataset

Efficient skin cancer detection using images is a challenging task in the healthcare domain. In today’s medical practices, skin cancer detection is a time-consuming procedure that may lead to a patient’s death in later stages. The diagnosis of skin cancer at an earlier stage is crucial for the success rate of complete cure. The efficient detection of skin cancer is a challenging task. Therefore, the numbers of skilful dermatologists around the globe are not enough to deal with today’s healthcare. The huge difference between data from various healthcare sector classes leads to data imbalance problems. Due to data imbalance issues, deep learning models are often trained on one class more than others. This study proposes a novel deep learning-based skin cancer detector using an imbalanced dataset. Data augmentation was used to balance various skin cancer classes to overcome the data imbalance. The Skin Cancer MNIST: HAM10000 dataset was employed, which consists of seven classes of skin lesions. Deep learning models are widely used in disease diagnosis through images. Deep learning-based models (AlexNet, InceptionV3, and RegNetY-320) were employed to classify skin cancer. The proposed framework was also tuned with various combinations of hyperparameters. The results show that RegNetY-320 outperformed InceptionV3 and AlexNet in terms of the accuracy, F1-score, and receiver operating characteristic (ROC) curve both on the imbalanced and balanced datasets. The performance of the proposed framework was better than that of conventional methods. The accuracy, F1-score, and ROC curve value obtained with the proposed framework were 91%, 88.1%, and 0.95, which were significantly better than those of the state-of-the-art method, which achieved 85%, 69.3%, and 0.90, respectively. Our proposed framework may assist in disease identification, which could save lives, reduce unnecessary biopsies, and reduce costs for patients, dermatologists, and healthcare professionals.

Cross-sectional study of acral melanoma awareness in a group of South African final phase medical students

BACKGROUND

Acral melanoma refers to melanoma arising on the palms, soles and nail unit, which are sun-protected areas and ultraviolet exposure is not a risk factor. Acral melanoma is associated with a poorer prognosis than other melanoma subtypes most likely due to the high rates of delayed diagnosis. Acral melanoma affects all skin types equally. There is a misconception that people with more pigmented skin types (Fitzpatrick 4-6) do not develop melanoma, due to the protective effect of melanin.

OBJECTIVES

The aim of the study was to determine acral melanoma knowledge and awareness of a group of South African, final phase medical students.

METHODS

This was a quantitative and cross-sectional study. A questionnaire consisting of 20 clinical images of skin lesions requiring a diagnosis and management plan was distributed. Responses to six images of melanomas were analysed. Further questions to measure acral melanoma knowledge and related issues were included in the study. A biostatistician appropriately managed statistical analysis.

RESULTS

Hundred and one final phase medical students' answers were gathered and analysed. Only 7.9% of the participants diagnosed all six melanomas correctly; 61.4% correctly diagnosed ≥50% of the melanomas. While 77.2% of the participants identified all non-acral cutaneous melanoma correctly, only 8.9% identified all acral melanomas. However, of all participants making the correct diagnosis, >90% selected the appropriate management plan (urgent referral).

LIMITATIONS

This study examined a small sample of trainee healthcare workers. The results cannot be assumed to apply to all South African healthcare workers. Responses given in a questionnaire may not reflect actual behaviour. The dermatology division in question has made acral melanoma a research priority, thus acral melanoma knowledge in this group may in fact be better than in other institutions.

CONCLUSION

The present study demonstrates that groups of imminent doctors have low rates of recognition of melanoma, particularly acral melanoma. This is consistent with high levels of primary misdiagnosis of acral melanoma reported in the literature. Fortunately, these participants managed the melanomas they diagnosed appropriately in >90% of cases. This confirms that the deficit in the participant group is awareness and knowledge. Those aware of the disease immediately acknowledged the need for urgent referral.

Artificial intelligence for segmentation of bladder tumor cystoscopic images performed by U-Net with dilated convolution

BACKGROUND

Early intravesical recurrence after transurethral resection of bladder tumors (TURBT) is often caused by overlooking of tumors during TURBT. Although narrow-band imaging and photodynamic diagnosis were developed to detect more tumors than conventional white-light imaging, the accuracy of these systems has been subjective, along with poor reproducibility due to their dependence on the physician's experience and skills. To create an objective and reproducible diagnosing system, we aimed to assess the utility of artificial intelligence (AI) with Dilated U-Net to reduce the risk of overlooked bladder tumors when compared with the conventional AI system, termed U-Net.

MATERIAL AND METHODS

We retrospectively obtained cystoscopic images by converting videos obtained from 120 patients who underwent TURBT into 1,790 cystoscopic images. The Dilated U-Net, which is an extension of the conventional U-Net, analyzed these image datasets. The diagnostic accuracy of the Dilated U-Net and conventional U-Net were compared using the following four measurements: pixel-wise sensitivity (PWSe); pixel-wise specificity (PWSp); pixel-wise positive predictive value (PWPPV), representing the AI diagnostic accuracy per pixel; and dice similarity coefficient (DSC), representing the overlap area between the bladder tumors in the ground truth images and segmentation maps.

RESULTS

The cystoscopic images were divided as follows, according to the pathological T-stage: 944, Ta; 412, T1; 329, T2; and 116, carcinoma in-situ. The PWSe, PWSp, PWPPV, and DSC of the Dilated U-Net were 84.9%, 88.5%, 86.7%, and 83.0%, respectively, which had improved when compared to that with the conventional U-Net by 1.7%, 1.3%, 2.1%, and 2.3%, respectively. The DSC values were high for elevated lesions and low for flat lesions for both Dilated and conventional U-Net.

CONCLUSIONS

Dilated U-Net, with higher DSC values than conventional U-Net, might reduce the risk of overlooking bladder tumors during cystoscopy and TURBT.

Deepening into the suitability of using pre-trained models of ImageNet against a lightweight convolutional neural network in medical imaging: an experimental study

Transfer learning (TL) has been widely utilized to address the lack of training data for deep learning models. Specifically, one of the most popular uses of TL has been for the pre-trained models of the ImageNet dataset. Nevertheless, although these pre-trained models have shown an effective performance in several domains of application, those models may not offer significant benefits in all instances when dealing with medical imaging scenarios. Such models were designed to classify a thousand classes of natural images. There are fundamental differences between these models and those dealing with medical imaging tasks regarding learned features. Most medical imaging applications range from two to ten different classes, where we suspect that it would not be necessary to employ deeper learning models. This paper investigates such a hypothesis and develops an experimental study to examine the corresponding conclusions about this issue. The lightweight convolutional neural network (CNN) model and the pre-trained models have been evaluated using three different medical imaging datasets. We have trained the lightweight CNN model and the pre-trained models with two scenarios which are with a small number of images once and a large number of images once again. Surprisingly, it has been found that the lightweight model trained from scratch achieved a more competitive performance when compared to the pre-trained model. More importantly, the lightweight CNN model can be successfully trained and tested using basic computational tools and provide high-quality results, specifically when using medical imaging datasets.

Attitudes towards Trusting Artificial Intelligence Insights and Factors to Prevent the Passive Adherence of GPs: A Pilot Study

Artificial Intelligence (AI) systems could improve system efficiency by supporting clinicians in making appropriate referrals. However, they are imperfect by nature and misdiagnoses, if not correctly identified, can have consequences for patient care. In this paper, findings from an online survey are presented to understand the aptitude of GPs (n = 50) in appropriately trusting or not trusting the output of a fictitious AI-based decision support tool when assessing skin lesions, and to identify which individual characteristics could make GPs less prone to adhere to erroneous diagnostics results. The findings suggest that, when the AI was correct, the GPs’ ability to correctly diagnose a skin lesion significantly improved after receiving correct AI information, from 73.6% to 86.8% (X² (1, N = 50) = 21.787, p < 0.001), with significant effects for both the benign (X² (1, N = 50) = 21, p < 0.001) and malignant cases (X² (1, N = 50) = 4.654, p = 0.031). However, when the AI provided erroneous information, only 10% of the GPs were able to correctly disagree with the indication of the AI in terms of diagnosis (d-AIW M: 0.12, SD: 0.37), and only 14% of participants were able to correctly decide the management plan despite the AI insights (d-AIW M:0.12, SD: 0.32). The analysis of the difference between groups in terms of individual characteristics suggested that GPs with domain knowledge in dermatology were better at rejecting the wrong insights from AI.

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5–10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy.

Molecular Biomarkers for Melanoma Screening, Diagnosis and Prognosis: Current State and Future Prospects

Despite significant progress in the development of treatment options, melanoma remains a leading cause of death due to skin cancer. Advances in our understanding of the genetic, transcriptomic, and morphologic spectrum of benign and malignant melanocytic neoplasia have enabled the field to propose biomarkers with potential diagnostic, prognostic, and predictive value. While these proposed biomarkers have the potential to improve clinical decision making at multiple critical intervention points, most remain unvalidated. Clinical validation of even the most commonly assessed biomarkers will require substantial resources, including limited clinical specimens. It is therefore important to consider the properties that constitute a relevant and clinically-useful biomarker-based test prior to engaging in large validation studies. In this review article we adapt an established framework for determining minimally-useful biomarker test characteristics, and apply this framework to a discussion of currently used and proposed biomarkers designed to aid melanoma detection, staging, prognosis, and choice of treatment.

Artificial Intelligence in Plastic Surgery: Current Applications, Future Directions, and Ethical Implications

Background:

Artificial intelligence (AI) in healthcare delivery has become an important area of research due to the rapid progression of technology, which has allowed the growth of many processes historically reliant upon human input. AI has become particularly important in plastic surgery in a variety of settings. This article highlights current applications of AI in plastic surgery and discusses future implications. We further detail ethical issues that may arise in the implementation of AI in plastic surgery.

Methods:

We conducted a systematic literature review of all electronically available publications in the PubMed, Scopus, and Web of Science databases as of February 5, 2020. All returned publications regarding the application of AI in plastic surgery were considered for inclusion.

Results:

Of the 89 novel articles returned, 14 satisfied inclusion and exclusion criteria. Articles procured from the references of those of the database search and those pertaining to historical and ethical implications were summarized when relevant.

Conclusions:

Numerous applications of AI exist in plastic surgery. Big data, machine learning, deep learning, natural language processing, and facial recognition are examples of AI-based technology that plastic surgeons may utilize to advance their surgical practice. Like any evolving technology, however, the use of AI in healthcare raises important ethical issues, including patient autonomy and informed consent, confidentiality, and appropriate data use. Such considerations are significant, as high ethical standards are key to appropriate and longstanding implementation of AI.