---
title: 'PanTrack: Pancreatic CT Benchmark'
url: https://www.emergentmind.com/topics/pantrack
type: topic
---

# PanTrack: Pancreatic CT Benchmark

PanTrack is a public longitudinal pancreatic cancer CT benchmark introduced in “Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking” [2605.23118]. It is designed for longitudinal lesion tracking in serial CT, with particular emphasis on out-of-distribution generalization: in the originating study, PanTrack is used not for training or model selection, but as an entirely unseen evaluation set for methods developed on a different longitudinal lesion domain. Within that framework, PanTrack serves two coupled purposes. First, it addresses the scarcity of public datasets with consistent, lesion-level instance annotations across multiple timepoints. Second, it provides a stress test for workflows that separate lesion retrieval from lesion delineation while still exploiting baseline lesion appearance as a longitudinal prior [2605.23118].

## 1. Origin and intended role

PanTrack was introduced as a longitudinal pancreatic cancer benchmark for oncologic follow-up in serial CT. The underlying problem is to identify a lesion in a baseline scan, retrieve the corresponding lesion in a later scan, and delineate its volume for response assessment. The benchmark is therefore embedded in a broader distinction between **retrieval** of the corresponding lesion and **delineation** of that lesion once correspondence has been established [2605.23118].

Its role in the originating work is explicitly out-of-distribution. Model development is performed exclusively on the longitudinal autoPET IV melanoma CT cohort, together with synthetic longitudinal pretraining, and PanTrack is then used as a zero-shot testbed for transfer to a different anatomy and disease presentation. This design makes PanTrack a measure of cross-domain generalization rather than in-domain optimization. A plausible implication is that PanTrack is most informative when a method claims to use longitudinal context in a way that should survive a substantial domain shift, rather than merely memorizing lesion appearance statistics from the training cohort [2605.23118].

The benchmark is also tied to a specific clinical-operational framing. It evaluates both a fully automatic setting, in which follow-up prompting is produced by registration, and a verified setting, in which a clinician accepts or corrects the proposed prompt. PanTrack is thus not a generic segmentation dataset; it is a benchmark for longitudinal retrieval-and-delineation pipelines under both automated and clinician-in-the-loop usage modes [2605.23118].

## 2. Cohort composition and annotation

PanTrack comprises **45 patients** with **pancreatic adenocarcinoma** and **161 CT examinations**. The longitudinal depth ranges from **2 to 11 scans** per patient, with a **mean of 3.6 scans per patient**. All scans are **CT** acquired in **portal-venous phase**, at a **single institution**, and under **identical Siemens protocols** [2605.23118].

The annotated lesions include **all pancreatic lesions across timepoints**, and **hepatic metastases if present**. Annotation was performed by **an experienced radiologist with pancreatic imaging expertise**, who manually segmented lesions across the longitudinal series. The cohort was constructed to include heterogeneous disease courses: some patients had **long-term stable chemotherapy courses**, while others showed **rapid progression**. The dataset therefore supports repeated longitudinal tracking beyond a simple baseline-follow-up pair design [2605.23118].

| Attribute | Value | Note |
|---|---:|---|
| Patients | 45 | Pancreatic adenocarcinoma |
| CT examinations | 161 | Portal-venous phase |
| Scans per patient | 2–11 | Mean 3.6 |
| Institution | Single institution | Identical Siemens protocols |
| Annotation scope | Pancreatic lesions; hepatic metastases if present | Manual longitudinal segmentation |
| Annotator | Experienced radiologist | Pancreatic imaging expertise |

PanTrack is publicly released and is explicitly presented as complementary to autoPET IV. Whereas autoPET IV contains melanoma lesions in whole-body CT, PanTrack focuses on pancreatic adenocarcinoma and associated hepatic metastases. The originating work emphasizes that pancreatic lesions often have **fuzzy boundaries and subtle soft-tissue contrast**, making the benchmark radiologically distinct and challenging. This suggests that PanTrack is intended not merely as another longitudinal dataset, but as a domain-shift benchmark with clinically meaningful appearance differences [2605.23118].

## 3. Evaluation design

PanTrack is evaluated under two paradigms: **Automatic Tracking** and **Verified Tracking**. In the automatic setting, the system is given only the baseline lesion prompt \(p_0\). A registration model, specifically **uniGradICON**, estimates a deformation field
\[
\phi: I_0 \to I_t,
\]
which propagates the baseline point to a follow-up candidate
\[
\hat{p}_t = \phi(p_0).
\]
That propagated point becomes the follow-up prompt [2605.23118].

In the verified setting, the clinician inspects the registration-proposed prompt and either accepts or corrects it. For benchmark evaluation, this workflow is simulated by using the **ground-truth follow-up lesion centroid** as \(p_t\). Under this construction, residual errors in verified tracking are interpreted as **delineation errors only**, because localization errors have been removed by design [2605.23118].

The benchmark reports three metrics in both settings: **DSC** (Dice Similarity Coefficient), **NSD** (Normalized Surface Distance), and **LDR** (Lesion Detection Rate). Results are given as bootstrapped mean \(\pm\) standard deviation [2605.23118].

| Evaluation mode | Prompt source | Interpretation |
|---|---|---|
| Automatic Tracking | Registration-proposed \(\hat p_t = \phi(p_0)\) | Retrieval and delineation both matter |
| Verified Tracking | Ground-truth follow-up centroid \(p_t\) | Delineation error isolated |

A central design choice is that PanTrack is **completely excluded from any form of training or model selection** in the originating paper. No internal train/validation/test split is reported because the benchmark functions there as a held-out external test set. This sharply distinguishes PanTrack from conventional dataset usage and is foundational to its status as an out-of-distribution benchmark [2605.23118].

## 4. Methodological context: Verified Tracking and longitudinal modeling

PanTrack is most intelligible in relation to the **Verified Tracking** paradigm proposed in the same work. That paradigm is intended as a middle ground between fully automatic end-to-end trackers, which offer no opportunity to correct silent failures, and decoupled registration-plus-segmentation pipelines, which allow user verification but discard baseline lesion appearance during segmentation [2605.23118].

The method extracts **Volumes of Interest (VOIs)** around the baseline and follow-up prompts and performs **early spatial prompt fusion**:
\[
X_0 = [I_0,\; G(p_0)], \quad X_t = [I_t,\; G(p_t)],
\]
where \(G(p)\) is a Gaussian heatmap centered at \(p\), with \(\sigma=1\), rescaled to unit value at the center. These inputs are passed through a **shared-weight encoder** to obtain multiscale features \(\{x_0^l\}\) and \(\{x_t^l\}\) [2605.23118].

Longitudinal context is injected through **latent temporal difference weighting**:
\[
{x'}_t^{\,l} = x_t^l \times \mathrm{InstNorm}\!\left(x_t^l - x_0^l\right) + x_t^l.
\]
This mechanism uses normalized baseline–follow-up feature differences as an attention-like modulation of the follow-up representation. The accompanying ablations argue that naive multi-timepoint fusion can collapse into effectively cross-sectional behavior, whereas difference weighting is needed to exploit longitudinal context effectively [2605.23118].

Synthetic longitudinal pretraining is also central. The model is pretrained on **2,606 CT pairs** with synthetic follow-ups simulating **tumor growth**, **tumor shrinkage**, and **acquisition variability**. Prompt simulation uses a **50/50 split** between points sampled from the ground-truth lesion mask with probability weighted by \(1/d^2\) and points derived from registered follow-up locations, which may lie outside the lesion. The paper states that synthetic pretraining improves performance by **up to 4.5 Dice points over training from scratch**, and the ablation study links that gain to the model’s ability to exploit longitudinal information under imperfect prompting [2605.23118].

Although these architectural and training details describe the evaluated method rather than the benchmark itself, they are integral to PanTrack’s function in the literature. PanTrack is the site at which the Verified Tracking formulation is tested under anatomy and disease shift, and the benchmark is explicitly used to determine whether baseline lesion appearance, prompt robustness, and clinician verification remain useful outside the training domain [2605.23118].

## 5. Reported benchmark results

The originating study evaluates multiple baselines on PanTrack. In **automatic tracking**, the compared methods are **Hering et al.**, **nnInteractive**, **LesionLocator**, and the proposed Verified Tracking model. In **verified tracking**, the compared methods are **SegVol**, **ULS Model**, **nnInteractive**, and the proposed model [2605.23118].

| Setting | Method | DSC | NSD | LDR |
|---|---|---:|---:|---:|
| Automatic | Hering et al. | \(49.9 \pm 3.2\) | \(41.3 \pm 2.9\) | \(83.1 \pm 4.7\) |
| Automatic | nnInteractive | \(34.3 \pm 3.5\) | \(27.2 \pm 2.7\) | \(59.3 \pm 5.7\) |
| Automatic | LesionLocator | \(51.7 \pm 3.4\) | \(41.3 \pm 3.3\) | \(84.0 \pm 4.2\) |
| Automatic | Proposed method | **\(58.2 \pm 3.0\)** | **\(48.6 \pm 3.0\)** | **\(93.7 \pm 3.0\)** |
| Verified | SegVol | \(43.7 \pm 2.3\) | \(33.4 \pm 2.6\) | \(87.4 \pm 4.2\) |
| Verified | ULS Model | \(53.4 \pm 2.7\) | \(42.8 \pm 2.9\) | **\(95.5 \pm 2.4\)** |
| Verified | nnInteractive | \(52.8 \pm 3.1\) | \(42.2 \pm 2.9\) | \(93.5 \pm 2.9\) |
| Verified | Proposed method | **\(60.0 \pm 2.8\)** | **\(49.7 \pm 2.9\)** | \(94.7 \pm 2.7\) |

In the automatic setting, the proposed method is best on all three metrics. Relative to the strongest automatic baseline in DSC, **LesionLocator** at **51.7**, the gain is **+6.5 DSC points**. Relative to **Hering et al.**, the gain is **+8.3 DSC points**. In the verified setting, the proposed method again achieves the best **DSC** and **NSD**, while **ULS Model** attains a slightly higher **LDR** (**95.5** versus **94.7**) [2605.23118].

The automatic-versus-verified comparison for the proposed method is numerically modest on PanTrack: verification improves performance by **+1.8 DSC**, **+1.1 NSD**, and **+1.0 LDR**. The authors interpret this as evidence that the model is already robust to registration error on this out-of-distribution dataset. They also emphasize a stronger comparative claim: the model’s **automatic** PanTrack performance, at **58.2 DSC**, exceeds the **verified** DSC of all competing models [2605.23118].

## 6. Significance, limitations, and disambiguation

PanTrack fills a specific gap in longitudinal medical imaging: the lack of public resources with **multi-timepoint CTs** and **lesion-level segmentations** suitable for combined retrieval-and-delineation evaluation. Its contribution is not simply additional sample count. Rather, it creates a publicly released pancreatic domain benchmark with serial examinations, expert longitudinal annotation, and a deliberately held-out evaluation role. This suggests that PanTrack is particularly useful for benchmarking methods that claim robustness to prompt noise, registration error, or domain shift in longitudinal lesion analysis [2605.23118].

At the same time, several limitations are explicit. PanTrack is used only as an external test benchmark in the originating work, so no internal train/validation/test protocol is reported there. The exact number of derived lesion-pair tracking instances is not given. The paper also does not describe a separate double-reader adjudication workflow for PanTrack analogous to the side-by-side verification used in autoPET IV. These are not defects of the benchmark so much as constraints on what is formally documented in its first presentation [2605.23118].

A common misconception is terminological. In the cited literature, **PanTrack** denotes the pancreatic longitudinal CT benchmark of [2605.23118]. It should not be conflated with **PlantTrack**, a plant-feature keypoint tracking system for fruits and leaves [2407.16829]; **PatchTrack**, a Transformer-based multiple object tracking method using frame patches [2201.00080]; or **PlanarTrack**, a benchmark for planar object tracking by four-corner geometry [2303.07625]. The similarity is lexical rather than conceptual.

In the broader structure of the 2026 work, PanTrack functions as the decisive out-of-distribution test for the Verified Tracking paradigm. Its reported results support the claim that longitudinal baseline context, prompt simulation, and clinician-verifiable prompting can transfer beyond the melanoma domain used for training. Whether that conclusion continues to hold across additional anatomies, acquisition conditions, and lesion taxonomies remains an open empirical question, but PanTrack establishes a concrete benchmark on which such generalization claims can be made precise [2605.23118].

Source: https://www.emergentmind.com/topics/pantrack