Temporal Inversion for Learning Interval Change in Chest X-Rays
Authors: Hanbin Ko, Kyungmin Jeon, Doowoong Choi, Chang Min Park
Organizations: Interdisciplinary Program in Bioengineering, Seoul National University Graduate School · Integrated Major in Innovative Medical Science, Seoul National University Graduate School · Dept. of Radiology, Seoul National University Hospital · Seoul National University College of Medicine · Inst. of Medical and Biological Engineering, Seoul National University Medical Research Center
Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyze radiographs in isolation, overlooking the key clinical task of comparing prior and current images to assess interval change. For chest radiographs (CXRs), capturing interval change is essential, as radiologists must evaluate not only the static appearance of findings but also how they evolve over time. We introduce TILA (Temporal Inversion-aware Learning and Alignment), a simple yet effective framework that uses temporal inversion, reversing image pairs, as a supervisory signal to enhance the sensitivity of existing temporal vision-language models to directional change. TILA integrates inversion-aware objectives across pretraining, fine-tuning, and inference, complementing conventional appearance modeling with explicit learning of temporal order. We also propose a unified evaluation protocol to assess order sensitivity and consistency under temporal inversion, and introduce MS-CXR-Tretrieval, a retrieval evaluation set constructed through a general protocol that can be applied to any temporal CXR dataset. Experiments on public datasets and real-world hospital cohorts demonstrate that TILA consistently improves progression classification and temporal embedding alignment when applied to multiple existing architectures.
Figures & tables
Figure 1: TILA Framework: Temporal Inversion-aware Learning and Alignment. The framework comprises three stages: pretraining, fine-tuning, and inference. (a–b) Pretraining: paired CXRs are encoded in both original and reversed orders; the Change-aware Sigmoid Loss aligns unchanged cases and separates changed ones. (c) Fine-tuning: the Bidirectional Cross-Entropy (BiCE) enforces label inversion, while the Temporal Consistency Loss (TCL) aligns probability distributions under reversal. (d) Inference: forward and reversed predictions are fused via inversion-aware scoring to enhance robustness and order consistency.
Model
MIMIC Retrieval
CheXpert Retrieval
I2T
T2I
TEM
I2T
T2I
TEM
@1
@5
@10
@1
@5
@10
@1
@5
@10
@1
@5
@10
Single-image VLPs
Ko & Park. [ 11 ]
6.6
23.2
33.8
8.4
24.5
34.7
7.4
6.2±0.1
16.1±0.2
24.7±0.1
6.6±0.2
15.9±0.2
23.0±0.2
5.7±0.4
BioViL-T (single image) [ 1 ]
3.1
10.7
17.9
3.7
11.3
18.4
3.5
2.4±0.1
8.9±0.2
14.8±0.2
2.6±0.2
7.6±0.1
13.2±0.1
4.2±0.3
ALTA (single image) [ 13 ]
6.5
18.2
27.2
11.0
28.7
41.3
9.0
6.3±0.1
17.9±0.2
26.1±0.2
8.2±0.2
22.7±0.1
32.1±0.1
10.2±0.3
Table 1: Single vs. paired-image retrieval on MIMIC and CheXpert. Retrieval performance (Recall@k for I2T/T2I) and TEM score. Single-image models process only the current image, whereas paired-image models encode ( prev , cur ). For each backbone, SigLIP denotes retraining with the sigmoid contrastive loss (baseline), and TILA adds the Change-aware Sigmoid Loss. CheXpert results are reported as mean and 95% CI across ten random subsamples of 3,000 paired CXRs.
Model
Standard
Reversed
Combined
Consistency
CON
PE
PNE
PTX
EDE
Avg
CON
PE
PNE
PTX
EDE
Avg
CON
PE
PNE
PTX
EDE
Avg
CON
PE
PNE
PTX
EDE
Avg
MS-CXR-T retrieval
BioViL-T [ 1 ]
49.1
42.8
38.3
33.1
51.8
43.1
42.8
51.7
45.1
36.2
48.2
44.8
53.7
54.3
50.8
37.1
59.8
51.2
23.4
21.9
21.7
10.1
29.2
21.3
BioViL-T SigLIP
48.9
58.3
55.6
34.4
53.6
50.2
51.7
53.2
61.0
38.1
50.7
51.0
55.6
60.0
64.5
39.0
58.1
55.5
32.8
35.3
40.1
14.2
41.0
32.7
BioViL-T TILA
55.3
58.7
58.1
40.3
58.0
54.1
55.9
59.0
61.5
37.0
56.5
54.0
58.8
62.4
65.9
46.5
62.5
59.3
39.8
39.9
43.0
22.8
44.0
37.9
ALTA [ 13 ]
46.8
33.9
36.0
31.1
40.4
37.7
44.2
47.4
43.1
37.9
41.5
42.9
54.0
54.4
60.9
35.4
51.3
51.2
18.4
11.0
9.3
4.7
10.5
10.8
Table 2: Interval-change classification results on MS-CXR-T and a private cohort. We report macro-accuracy (%) for five findings— CON : consolidation, PE : pleural effusion, PNE : pneumonia, PTX : pneumothorax, and EDE : edema—together with the average across findings for each evaluation protocol ( Standard , Reversed , Combined , Consistency ; see Section 3.3 ). For retrieval and zero-shot classification, TILA models use only the Change-aware Sigmoid pretraining loss, while in supervised settings they additionally apply inversion-aware fine-tuning (BiCE and TCL). SigLIP denotes our re-trained baselines using the sigmoid contrastive loss, and TILA refers to the corresponding models augmented with inversion-aware objectives.
Figure 2: Score Distribution Analysis for Pleural Effusion (MS-CXR-T). Distribution of prediction scores (scaled by 10) for each pleural effusion progression label, comparing baseline and TILA models in the zero-shot setting. Each boxplot separates cases by progression label ( improved , stable , worsened ) and label quality ( consensus vs. disagreement ), shown for both standard and inversion-aware (combined) scoring. Key trends illustrated: i) Changes in scores for each label ( improved , stable , worsened ). ii) Impact of applying inversion-aware scoring (combined). iii) Differences in scores based on label quality ( consensus vs. disagreement ).
Variant
Standard
Reversed
Combined
Consistency
BioViL-T (CLIP)
60.1
53.0
60.5
42.1
+ SigLIP (Baseline)
61.1
53.3
59.6
39.5
+ Change-aware SigLIP (Ours)
64.6
58.3
63.4
45.4
+ BiCE
65.2
62.0
63.4
53.1
+ BiCE + TCL
64.1
63.7
63.6
57.4
Table 3: Ablation of temporal inversion components. Each cell reports the mean macro-accuracy (%) across the five findings (CON, PE, PNE, PTX, EDE) for the indicated evaluation protocol.
Model
Mode
Test Set AUC
Private
RexGradient
BioViL-T
Fine-tune
0.734
0.565
BioViL-T
Linear probe
0.693
0.545
BioViL-T TILA
Fine-tune
0.765
0.702
BioViL-T TILA
Linear probe
0.756
0.681
Table 4: Binary interval-change screening on two external test sets. AUC is reported for fine-tuning and linear probing modes.
Train
Validation
Test
MIMIC
183,302
1,330
2,871
CheXpert
-
-
123,374
Private
-
-
2,233
Table 5: Data Distribution for MIMIC, CheXpert, and Private
Figure 3: Example workflow for constructing MS-CXR-T retrieval from the original benchmark.
Dataset
Label 0
Label 1
Total
CheXpert
49,591
53,505
103,096
MIMIC
22,527
45,370
67,897
RexGradient
8,902
10,921
19,823
Private
5,000
5,000
10,000
Table 6: Binary interval-change label distribution. Label 0 denotes no change and Label 1 denotes change .
W
Average Accuracy (%)
Standard
Reversed
Combined
Consistency
0
50.2
50.9
55.4
32.7
0.5
54.9
53.2
59.1
36.6
1
54.1
54.0
59.2
37.9
2
49.7
51.2
54.3
33.1
Table 7: Effect of pretraining weight W on MS-CXR-T retrieval . We report average macro-accuracy (%) across all findings for each evaluation protocol.
λ
Average Accuracy (%)
Standard
Reversed
Combined
Consistency
Base
61.1
53.3
59.6
39.5
0
65.2
62.0
63.4
53.1
1
65.0
61.2
63.1
53.3
50
64.1
63.7
63.6
57.3
100
62.7
63.8
61.4
55.6
Table 8: Effect of fine-tuning weight λ on MS-CXR-T supervised classification. We report average macro-accuracy (%) across all findings for each evaluation protocol.
Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China · Alliance Manchester Business School, The University of Manchester, Manchester, UK