Deep‐learning‐based, computer‐aided classifier developed with a small dataset of clinical images surpasses board‐certified dermatologists in skin tumour diagnosis

Fujisawa, Yasuhiro; Otomo, Yasuhiro; Ogata, Yuji; Nakamura, Yoshiyuki; Fujita, Ryo; Ishitsuka, Yosuke; Watanabe, Ryoji; Okiyama, Naoko; Ohara, Kuniaki; Fujimoto, Manabu

doi:10.1111/bjd.16924

Cited by 236 publications

(180 citation statements)

References 46 publications

Supporting

Mentioning

169

Contrasting

Unclassified

Order By: Relevance

“…In a more recent study, the classification problem was expanded to include 14 distinct malignant and benign skin conditions. The AK diagnostic accuracy was increased to 52.4% employing the pre‐trained GoogleNet CNN model (compared to 40.2% accuracy achieved by board‐certified dermatologists).…”

Section: Discussionmentioning

confidence: 99%

Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography

Spyridonos

Gaitanis

Likas

et al. 2019

Skin Research and Technology

View full text Add to dashboard Cite

Background Actinic keratosis (AK) is a common premalignant skin lesion that can potentially progress to squamous cell carcinoma. Appropriate long‐term management of AK requires close patient monitoring in addition to therapeutic interventions. Computer‐aided diagnostic systems based on clinical photography might evolve in the future into valuable adjuncts to AK patient management. The present study proposes a late fusion approach of color‐texture features (shallow features) and deep features extracted from pre‐trained convolutional neural networks (CNN) to boost AK detection accuracy on clinical photographs. Materials and Methods System uses a sliding rectangular window of 50 × 50 pixels and a classifier that assigns the window region to either the AK or the healthy skin class. 6010 and 13 915 cropped regions of interest (ROI) of 50 × 50 pixels of AK and healthy skin, respectively, from 22 patients were used for system implementation. Different support vector machine (SVM) classifiers employing shallow or deep features and their late fusion using the max rule at decision level were compared with the McNemar test and Yule's Q‐statistic. Results Support vector machine classifiers based on deep and shallow features exhibited overall competitive performances with complementary improvements in detection accuracy. Late fusion yielded significant improvement (6%) in both sensitivity (87%) and specificity (86%) compared to single classifier performance. Conclusion The parallel improvement of sensitivity and specificity is encouraging, demonstrating the potential use of our system in evaluating AK burden. The latter might be of value in future clinical studies for the comparison of field‐directed treatment interventions.

show abstract

Section: Discussionmentioning

confidence: 99%

Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography

Spyridonos

Gaitanis

Likas

et al. 2019

Skin Research and Technology

View full text Add to dashboard Cite

show abstract

“…Inspired by a breakthrough result by Esteva et. al., [7], many recent publications claim "better than dermatologist" performance of convolutional neural networks (CNNs) on a variety of skin cancer classification tasks [7,4,9,3,13,8]. If indeed such models have diagnostic performance comparable to board certified dermatologists, this heralds a new era in skin cancer care, with standardization of diagnosis and democratization of access [10,14].…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network or Dermatologist?

Young

Booth

Simpson³

et al. 2019

Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support

View full text Add to dashboard Cite

Deep learning techniques have proven high accuracy for identifying melanoma in digitised dermoscopic images. A strength is that these methods are not constrained by features that are pre-defined by human semantics. A down-side is that it is difficult to understand the rationale of the model predictions and to identify potential failure modes. This is a major barrier to adoption of deep learning in clinical practice. In this paper we ask if two existing local interpretability methods, Grad-CAM and Kernel SHAP, can shed light on convolutional neural networks trained in the context of melanoma detection. Our contributions are (i) we first explore the domain space via a reproducible, end-to-end learning framework that creates a suite of 30 models, all trained on a publicly available data set (HAM10000), (ii) we next explore the reliability of GradCAM and Kernel SHAP in this context via some basic sanity check experiments (iii) finally, we investigate a random selection of models from our suite using GradCAM and Kernel SHAP. We show that despite high accuracy, the models will occasionally assign importance to features that are not relevant to the diagnostic task. We also show that models of similar accuracy will produce different explanations as measured by these methods. This work represents first steps in bridging the gap between model accuracy and interpretability in the domain of skin cancer classification.

show abstract

“…Deep learning, especially CNNs, and its medical applications have made great progress in recent years. [8][9][10] In the field of computer-aided diagnosis for skin diseases, especially for tumours, [11][12][13][14][15] the monumental breakthroughs have been made in Ref., 16 where CNN surpassed senior dermatologists on both classification tasks (keratinocytes cancer vs. benign seborrhoeic keratosis and malignant melanoma vs. benign moles). Han et al 17 proposed to use the ResNet-152 model on clinical images to classify benign and malignant cutaneous tumours.…”

Section: Introductionmentioning

confidence: 99%

Smart identification of psoriasis by images using convolutional neural networks: a case study in China

Zhao

Xie

et al. 2019

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background Psoriasis is a chronic inflammatory skin disease, which holds a high incidence in China. However, professional dermatologists who can diagnose psoriasis early and correctly are insufficient in China, especially in the rural areas. A smart approach to identify psoriasis by pictures would be highly adaptable countrywide and could play a useful role in early diagnosis and regular treatment of psoriasis. Objectives Design and evaluation of a smart psoriasis identification system based on clinical images (without relying on a dermatoscope) that works effectively similar to a dermatologist. Methods A set of deep learning models using convolutional neural networks (CNNs) was explored and compared in the system for automatic identification of psoriasis. The work was carried out on a standardized dermatological dataset with 8021 clinical images of 9 common disorders including psoriasis along with full electronic medical records of patients built over the last 9 years in China. A two‐stage deep neural network was designed and developed to identify psoriasis. In the first stage, a multilabel classifier was trained to learn the visual patterns for each individual skin disease. In the second stage, the output of the first stage was utilized to distinguish psoriasis from other skin diseases. Results The area under the curve (AUC) of the two‐stage model reached 0.981 ± 0.015, which outperforms a single‐stage model. And, the classifier showed superior performance (missed diagnosis rate: 0.03, misdiagnosis rate: 0.04) than 25 Chinese dermatologists (missed diagnosis rate: 0.19, misdiagnosis rate: 0.10) in the diagnosis of psoriasis on 100 clinical images. Conclusions Using clinical images to identify psoriasis is feasible and effective based on CNNs, which also builds a solid technical base for smart care of skin diseases especially psoriasis using mobile/tablet applications for teledermatology in China.

show abstract

Deep‐learning‐based, computer‐aided classifier developed with a small dataset of clinical images surpasses board‐certified dermatologists in skin tumour diagnosis

Cited by 236 publications

References 46 publications

Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography

Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography

Deep Neural Network or Dermatologist?

Smart identification of psoriasis by images using convolutional neural networks: a case study in China

Contact Info

Product

Resources

About