paper-with-me

홈 › Papers

Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions

2021-04-08 · Abhijit Guha Roy, Jie Ren, Shekoofeh Azizi, Aaron Loh, Vivek Natarajan, Basil Mustafa, Nick Pawlowski, Jan Freyberg, YuAn Liu, Zach Beaver, Nam Vo, Peggy Bui, Samantha Winter, Patricia MacWilliams, Greg S. Corrado, Umesh Telang, Yun Liu, Taylan Cemgil, Alan Karthikesalingam, Balaji Lakshminarayanan, Jim Winkens

We develop and rigorously evaluate a deep learning based system that can accurately classify skin conditions while detecting rare conditions for which there is not enough data available for training a confident classifier. We frame this task as an out-of-distribution (OOD) detection problem. Our novel approach, hierarchical outlier detection (HOD) assigns multiple abstention classes for each training outlier class and jointly performs a coarse classification of inliers vs. outliers, along with fine-grained classification of the individual classes. We demonstrate the effectiveness of the HOD loss in conjunction with modern representation learning approaches (BiT, SimCLR, MICLe) and explore different ensembling strategies for further improving the results. We perform an extensive subgroup analysis over conditions of varying risk levels and different skin types to investigate how the OOD detection performance changes over each subgroup and demonstrate the gains of our framework in comparison to baselines. Finally, we introduce a cost metric to approximate downstream clinical impact. We use this cost metric to compare the proposed method against a baseline system, thereby making a stronger case for the overall system effectiveness in a real-world deployment scenario.

📄 PDF Abstract BibTeX arXiv:2104.03829

Code (0)

등록된 구현이 없습니다.

Tasks

Outlier DetectionOut of Distribution (OOD) DetectionRepresentation Learning

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Residual Connection 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Enhanced Dermatology Image Quality Assessment via Cross-Domain Training

2025-06-19 · Ignacio Hernández Montilla, Alfonso Medela, Paola Pasquali, Andy Aguilar 외

Teledermatology has become a widely accepted communication method in daily clinical practice, enabling remote care while showing strong agreement with in-person visits. Poor image quality remains an unsolved problem in t…

Image Quality Assessment

A Global Atlas of Digital Dermatology to Map Innovation and Disparities

2025-12-27 · Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez 외 arxiv

The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and comprehensiveness of the data fueling these models. Despite rapid growth…

Addressing the Real-world Class Imbalance Problem in Dermatology

2020-10-09 · Wei-Hung Weng, Jonathan Deaton, Vivek Natarajan, Gamaleldin F. Elsayed 외

Class imbalance is a common problem in medical diagnosis, causing a standard classifier to be biased towards the common classes and perform poorly on the rare classes. This is especially true for dermatology, a specialty…

BenchmarkingFew-Shot LearningMedical Diagnosis

What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability

2022-05-23 · John Kirchenbauer, Jacob Oaks, Eric Heim

Classifier calibration has received recent attention from the machine learning community due both to its practical utility in facilitating decision making, as well as the observation that modern neural network classifier…

Classifier calibrationDecision Making

MINT: A wrapper to make multi-modal and multi-image AI models interactive

2024-01-22 · Jan Freyberg, Abhijit Guha Roy, Terry Spitz, Beverly Freeman 외

During the diagnostic process, doctors incorporate multimodal information including imaging and the medical history - and similarly medical AI development has increasingly become multimodal. In this paper we tackle a mor…

DiagnosticDisease Prediction