PyTorchKR Papers

최신 논문

총 129편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1703.05148

Random Forests and VGG-NET: An Algorithm for the ISIC 2017 Skin Lesion Classification Challenge

This manuscript briefly describes an algorithm developed for the ISIC 2017 Skin Lesion Classification Competition. In this task, participants are asked to complete two independent binary image classification tasks that involve three unique diagnoses of skin lesions (melanoma, nevus, and seborrheic keratosis). In the first binary classification task, participants are asked to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis. In the second binary classification task, participants are asked to distinguish between (a) seborrheic keratosis and (b) nevus and melanoma. The other phases of the competition are not considered. Our proposed algorithm consists of three steps: preprocessing, classification using VGG-NET and Random Forests, and calculation of a final score.

arXiv:1703.04364

Deep Learning for Skin Lesion Classification

Melanoma, a malignant form of skin cancer is very threatening to life. Diagnosis of melanoma at an earlier stage is highly needed as it has a very high cure rate. Benign and malignant forms of skin cancer can be detected by analyzing the lesions present on the surface of the skin using dermoscopic images. In this work, an automated skin lesion detection system has been developed which learns the representation of the image using Google's pretrained CNN model known as Inception-v3 \cite{cnn}. After obtaining the representation vector for our input dermoscopic images we have trained two layer feed forward neural network to classify the images as malignant or benign. The system also classifies the images based on the cause of the cancer either due to melanocytic or non-melanocytic cells using a different neural network. These classification tasks are part of the challenge organized by International Skin Imaging Collaboration (ISIC) 2017. Our system learns to classify the images based on the model built using the training images given in the challenge and the experimental results were evaluated using validation and test sets. Our system has achieved an overall accuracy of 65.8\% for the validation set.

arXiv:1703.05235

Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge

This manuscript describes our participation in the International Skin Imaging Collaboration's 2017 Skin Lesion Analysis Towards Melanoma Detection competition. We participated in Part 3: Lesion Classification. The two stated goals of this binary image classification challenge were to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis, followed by distinguishing between (a) seborrheic keratosis and (b) nevus and melanoma. We chose a deep neural network approach with a transfer learning strategy, using a pre-trained Inception V3 network as both a feature extractor to provide input for a multi-layer perceptron as well as fine-tuning an augmented Inception network. This approach yielded validation set AUC's of 0.84 on the second task and 0.76 on the first task, for an average AUC of 0.80. We joined the competition unfortunately late, and we look forward to improving on these results.

arXiv:1804.00504

Generalizability vs. Robustness: Adversarial Examples for Medical Imaging

In this paper, for the first time, we propose an evaluation method for deep learning models that assesses the performance of a model not only in an unseen test scenario, but also in extreme cases of noise, outliers and ambiguous input data. To this end, we utilize adversarial examples, images that fool machine learning models, while looking imperceptibly different from original data, as a measure to evaluate the robustness of a variety of medical imaging models. Through extensive experiments on skin lesion classification and whole brain segmentation with state-of-the-art networks such as Inception and UNet, we show that models that achieve comparable performance regarding generalizability may have significant variations in their perception of the underlying data manifold, leading to an extensive performance gap in their robustness.

arXiv:1804.00177

Webly Supervised Learning for Skin Lesion Classification

Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available web data through web-crawling. To handle noise and weak nature of web annotations, we propose a two-step transfer learning based training process with a robust loss function, termed as Webly Supervised Learning (WSL) to train deep models for the task. We also leverage search by image to improve the search specificity of our web-crawling and reduce cross-domain noise. Within WSL, we explicitly model the noise structure between classes and incorporate it to selectively distill knowledge from the web data during model training. To demonstrate improved performance due to WSL, we benchmarked on a publicly available 10-class fine-grained skin lesion classification dataset and report a significant improvement of top-1 classification accuracy from 71.25 % to 80.53 % due to the incorporation of web-supervision.

arXiv:1804.04338

MelanoGANs: High Resolution Skin Lesion Synthesis with GANs

Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking images of faces, scenery and even medical images. Unfortunately, they usually require large training datasets, which are often scarce in the medical field, and to the best of our knowledge GANs have been only applied for medical image synthesis at fairly low resolution. However, many state-of-the-art machine learning models operate on high resolution data as such data carries indispensable, valuable information. In this work, we try to generate realistically looking high resolution images of skin lesions with GANs, using only a small training dataset of 2000 samples. The nature of the data allows us to do a direct comparison between the image statistics of the generated samples and the real dataset. We both quantitatively and qualitatively compare state-of-the-art GAN architectures such as DCGAN and LAPGAN against a modification of the latter for the task of image generation at a resolution of 256x256px. Our investigation shows that we can approximate the real data distribution with all of the models, but we notice major differences when visually rating sample realism, diversity and artifacts. In a set of use-case experiments on skin lesion classification, we further show that we can successfully tackle the problem of heavy class imbalance with the help of synthesized high resolution melanoma samples.

arXiv:1805.09474

VisualBackProp for learning using privileged information with CNNs

In many machine learning applications, from medical diagnostics to autonomous driving, the availability of prior knowledge can be used to improve the predictive performance of learning algorithms and incorporate `physical,' `domain knowledge,' or `common sense' concepts into training of machine learning systems as well as verify constraints/properties of the systems. We explore the learning using privileged information paradigm and show how to incorporate the privileged information, such as segmentation mask available along with the classification label of each example, into the training stage of convolutional neural networks. This is done by augmenting the CNN model with an architectural component that effectively focuses model's attention on the desired region of the input image during the training process and that is transparent to the network's label prediction mechanism at testing. This component effectively corresponds to the visualization strategy for identifying the parts of the input, often referred to as visualization mask, that most contribute to the prediction, yet uses this strategy in reverse to the classical setting in order to enforce the desired visualization mask instead. We verify our proposed algorithms through exhaustive experiments on benchmark ImageNet and PASCAL VOC data sets and achieve improvements in the performance of $2.4\%$ and $2.7\%$ over standard single-supervision model training. Finally, we confirm the effectiveness of our approach on skin lesion classification problem.

arXiv:2610.03193v1cs.CV

연구와 실제 임상의 간극 좁히기: 임상 피부 병변 분류에서 범용 모델과 피부과 특화 모델의 체계적 평가

Bridging Research and Practice: A Systematic Evaluation of Generalist and Dermatology-Specific Models in Clinical Skin Lesion Classification

최근 몇 년 동안 피부과 분야에서의 머신러닝 활용은 개념 증명(PoC) 연구를 넘어 잠재적 응용으로 나아가며 크게 성장했습니다. 그러나 임상 피부과는 여전히 도전적이며 해결되지 않은 문제로 남아 있습니다. 진단적 평가는 모호한 경우가 많고, 피부 병변은 높은 다양성을 보이며, 획득 양식(modality), 기기 품질, 환자 인구통계학적 특성의 차이로 인해 이러한 점이 더욱 복잡해집니다. 이러한 요인들은 안전하고 공평한 임상 적용에 적합한 강건한 모델의 개발을 저해합니다. 실제 임상으로의 전환을 지원하기 위해서는 최신 모델들이 이종 데이터 소스 전반에서 어떻게 일반화되는지 체계적으로 평가하는 것이 필수적입니다. 본 연구에서는 더모스코피(dermoscopic) 이미지와 스마트폰 기반 임상 사진을 아우르는 최신 피부과 데이터셋을 바탕으로 다양한 아키텍처를 벤치마크합니다. 최신 범용 및 의료 비전-언어 모델(VLM)과 파운데이션 모델의 강건성을 평가하고, 이를 임베딩(embedding) 기반 접근법 및 합성곱 신경망(CNN)을 포함한 태스크 특화 피부과 분류기와 비교합니다. 본 연구는 분포 변화(distribution shift), 모달리티 변화, 인구통계학적 다양성 하에서의 모델 성능 평가를 제공합니다. 현재의 최고 성능(SOTA) 모델과 임상 배치 요구 조건 사이의 격차를 정량화함으로써, 피부과를 위한 신뢰할 수 있고 접근 가능하며 임상적으로 적용 가능한 AI 시스템 개발에 기여하고자 합니다.

arXiv:2606.20390v2cs.CV

메타데이터를 활용한 기하학적 인식 슈퍼픽셀 그래프 트랜스포머를 이용한 피부 병변 분류

Geometry-Aware Superpixel Graph Transformer with Metadata for Skin Lesion Classification

피부경(dermoscopic) 이미지에서의 자동 피부암 분류는 이질적인 병변 구조, 강한 클래스 내 변동성, 그리고 양성 및 악성 사례 간의 미세한 시각적 차이로 인해 여전히 어려운 과제입니다. 기존 CNN/ViT 파이프라인은 일반적으로 전역(global) 또는 패치(patch) 수준의 특징에 의존하며, 환자 메타데이터를 후기 융합(late fusion)을 통해 결합하는데, 이는 공간적으로 기반을 둔 멀티모달 추론을 제한합니다. 본 논문에서는 병변을 고정된(frozen) CNN 특징으로 표현되는 공간적으로 응집된 슈퍼픽셀(superpixel) 영역들의 그래프로 명시적으로 모델링하는 새로운 영역 기반 그래프 학습 프레임워크를 제안합니다. 세밀한 병변 구성을 포착하기 위해 영역 간 기하학을 에지(edge) 속성으로 인코딩하고, 모든 영역에 연결된 전용 메타데이터 컨텍스트 노드(node)를 도입하여 동일한 관계형 공간 내에서 인구통계학적/임상 변수의 구조화된 통합을 제공합니다. 노드(node) 표현은 에지 인지 그래프 트랜스포머(transformer)와 이어지는 어텐션(attention) 기반 전파를 사용하여 업데이트되며, 양성-악성 분류(classification)를 위한 최종 그래프 수준 임베딩(embedding)이 생성됩니다. 4개의 공개 벤치마크(benchmark)에 대한 실험 결과, 명시적인 영역 수준 관계형 모델링과 그래프 고유의 멀티모달 융합이 최신 성능(state-of-the-art) 대비 일관된 이득을 가져옴을 보여줍니다. 결과적으로, 우리는 CNN 특징이 관계형 노드로 모델링되고 맥락 통합을 통해 개선되어 더 표현력 있고 견고한 분류를 산출하는 새로운 그래프 중심적 관점을 확립했습니다.