Understanding metric-related pitfalls in image analysis validation

Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.

Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study

Imaging exams, such as chest radiography, will yield a small set of common findings and a much larger set of uncommon findings. While a trained radiologist can learn the visual presentation of rare conditions by studying a few representative examples, teaching a machine to learn from such a "long-tailed" distribution is much more difficult, as standard methods would be easily biased toward the most frequent classes. In this paper, we present a comprehensive benchmark study of the long-tailed learning problem in the specific domain of thorax diseases on chest X-rays. We focus on learning from naturally distributed chest X-ray data, optimizing classification accuracy over not only the common "head" classes, but also the rare yet critical "tail" classes. To accomplish this, we introduce a challenging new long-tailed chest X-ray benchmark to facilitate research on developing long-tailed learning methods for medical image classification. The benchmark consists of two chest X-ray datasets for 19- and 20-way thorax disease classification, containing classes with as many as 53,000 and as few as 7 labeled training images. We evaluate both standard and state-of-the-art long-tailed learning methods on this new benchmark, analyzing which aspects of these methods are most beneficial for long-tailed medical image classification and summarizing insights for future algorithm design. The datasets, trained models, and code are available at https://github.com/VITA-Group/LongTailCXR.

Improving Small Lesion Segmentation in CT Scans using Intensity Distribution Supervision: Application to Small Bowel Carcinoid Tumor

Finding small lesions is very challenging due to lack of noticeable features, severe class imbalance, as well as the size itself. One approach to improve small lesion segmentation is to reduce the region of interest and inspect it at a higher sensitivity rather than performing it for the entire region. It is usually implemented as sequential or joint segmentation of organ and lesion, which requires additional supervision on organ segmentation. Instead, we propose to utilize an intensity distribution of a target lesion at no additional labeling cost to effectively separate regions where the lesions are possibly located from the background. It is incorporated into network training as an auxiliary task. We applied the proposed method to segmentation of small bowel carcinoid tumors in CT scans. We observed improvements for all metrics (33.5% $\rightarrow$ 38.2%, 41.3% $\rightarrow$ 47.8%, 30.0% $\rightarrow$ 35.9% for the global, per case, and per tumor Dice scores, respectively.) compared to the baseline method, which proves the validity of our idea. Our method can be one option for explicitly incorporating intensity distribution information of a target in network training.

Graph-Based Small Bowel Path Tracking with Cylindrical Constraints

We present a new graph-based method for small bowel path tracking based on cylindrical constraints. A distinctive characteristic of the small bowel compared to other organs is the contact between parts of itself along its course, which makes the path tracking difficult together with the indistinct appearance of the wall. It causes the tracked path to easily cross over the walls when relying on low-level features like the wall detection. To circumvent this, a series of cylinders that are fitted along the course of the small bowel are used to guide the tracking to more reliable directions. It is implemented as soft constraints using a new cost function. The proposed method is evaluated against ground-truth paths that are all connected from start to end of the small bowel for 10 abdominal CT scans. The proposed method showed clear improvements compared to the baseline method in tracking the path without making an error. Improvements of 6.6% and 17.0%, in terms of the tracked length, were observed for two different settings related to the small bowel segmentation.

Deep Reinforcement Learning for Small Bowel Path Tracking using Different Types of Annotations

Small bowel path tracking is a challenging problem considering its many folds and contact along its course. For the same reason, it is very costly to achieve the ground-truth (GT) path of the small bowel in 3D. In this work, we propose to train a deep reinforcement learning tracker using datasets with different types of annotations. Specifically, we utilize CT scans that have only GT small bowel segmentation as well as ones with the GT path. It is enabled by designing a unique environment that is compatible for both, including a reward definable even without the GT path. The performed experiments proved the validity of the proposed method. The proposed method holds a high degree of usability in this problem by being able to utilize the scans with weak annotations, and thus by possibly reducing the required annotation cost.

Metrics reloaded: Pitfalls and recommendations for image analysis validation

The field of automatic biomedical image analysis crucially depends on robust and meaningful performance metrics for algorithm validation. Current metric usage, however, is often ill-informed and does not reflect the underlying domain interest. Here, we present a comprehensive framework that guides researchers towards choosing performance metrics in a problem-aware manner. Specifically, we focus on biomedical image analysis problems that can be interpreted as a classification task at image, object or pixel level. The framework first compiles domain interest-, target structure-, data set- and algorithm output-related properties of a given problem into a problem fingerprint, while also mapping it to the appropriate problem category, namely image-level classification, semantic segmentation, instance segmentation, or object detection. It then guides users through the process of selecting and applying a set of appropriate validation metrics while making them aware of potential pitfalls related to individual choices. In this paper, we describe the current status of the Metrics Reloaded recommendation framework, with the goal of obtaining constructive feedback from the image analysis community. The current version has been developed within an international consortium of more than 60 image analysis experts and will be made openly available as a user-friendly toolkit after community-driven optimization.

Universal Lymph Node Detection in T2 MRI using Neural Networks

Purpose: Identification of abdominal Lymph Nodes (LN) that are suspicious for metastasis in T2 Magnetic Resonance Imaging (MRI) scans is critical for staging of lymphoproliferative diseases. Prior work on LN detection has been limited to specific anatomical regions of the body (pelvis, rectum) in single MR slices. Therefore, the development of a universal approach to detect LN in full T2 MRI volumes is highly desirable. Methods: In this study, a Computer Aided Detection (CAD) pipeline to universally identify abdominal LN in volumetric T2 MRI using neural networks is proposed. First, we trained various neural network models for detecting LN: Faster RCNN with and without Hard Negative Example Mining (HNEM), FCOS, FoveaBox, VFNet, and Detection Transformer (DETR). Next, we show that the state-of-the-art (SOTA) VFNet model with Adaptive Training Sample Selection (ATSS) outperforms Faster RCNN with HNEM. Finally, we ensembled models that surpassed a 45% mAP threshold. We found that the VFNet model and one-stage model ensemble can be interchangeably used in the CAD pipeline. Results: Experiments on 122 test T2 MRI volumes revealed that VFNet achieved a 51.1% mAP and 78.7% recall at 4 false positives (FP) per volume, while the one-stage model ensemble achieved a mAP of 52.3% and sensitivity of 78.7% at 4FP. Conclusion: Our contribution is a CAD pipeline that detects LN in T2 MRI volumes, resulting in a sensitivity improvement of $\sim$14 points over the current SOTA method for LN detection (sensitivity of 78.7% at 4 FP vs. 64.6% at 5 FP per volume).

Universal Lesion Detection in CT Scans using Neural Network Ensembles

In clinical practice, radiologists are reliant on the lesion size when distinguishing metastatic from non-metastatic lesions. A prerequisite for lesion sizing is their detection, as it promotes the downstream assessment of tumor spread. However, lesions vary in their size and appearance in CT scans, and radiologists often miss small lesions during a busy clinical day. To overcome these challenges, we propose the use of state-of-the-art detection neural networks to flag suspicious lesions present in the NIH DeepLesion dataset for sizing. Additionally, we incorporate a bounding box fusion technique to minimize false positives (FP) and improve detection accuracy. Finally, to resemble clinical usage, we constructed an ensemble of the best detection models to localize lesions for sizing with a precision of 65.17% and sensitivity of 91.67% at 4 FP per image. Our results improve upon or maintain the performance of current state-of-the-art methods for lesion detection in challenging CT scans.

Universal Lesion Detection in CT Scans using NeuralNetwork Ensembles

In clinical practice, radiologists are reliant on the lesion size when distinguishing metastatic from non-metastaticlesions. A prerequisite for lesion sizing is their detection, as it promotes the downstream assessment of tumorspread. However, lesions vary in their size and appearance in CT scans, and radiologists often miss small lesionsduring a busy clinical day. To overcome these challenges, we propose the use of state-of-the-art detection neuralnetworks to flag suspicious lesions present in the NIH DeepLesion dataset for sizing. Additionally, we incorporatea bounding box fusion technique to minimize false positives (FP) and improve detection accuracy. Finally, toresemble clinical usage, we constructed an ensemble of the best detection models to localize lesions for sizingwith a precision of 65.17% and sensitivity of 91.67% at 4 FP per image. Our results improve upon or maintainthe performance of current state-of-the-art methods for lesion detection in challenging CT scans.