| 1. |
|
|
| 2. |
- Bychkov, D, et al.
(författare)
-
Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy
- 2021
-
Ingår i: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 11:1, s. 4037-
-
Tidskriftsartikel (refereegranskat)abstract
- The treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin–eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning–predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63–0.77) on 354 TMA samples and 0.67 (95% CI, 0.62–0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology–based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15–0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Lehtomaki, K, et al.
(författare)
-
Lead Time and Prognostic Role of Serum CEA, CA19-9, IL-6, CRP, and YKL-40 after Adjuvant Chemotherapy in Colorectal Cancer
- 2021
-
Ingår i: Cancers. - : MDPI AG. - 2072-6694. ; 13:15
-
Tidskriftsartikel (refereegranskat)abstract
- In colorectal cancer (CRC), 20–50% of patients relapse after curative-intent surgery with or without adjuvant therapy. We investigated the lead times and prognostic value of post-adjuvant (8 months from randomisation to adjuvant treatment) serum CEA, CA19-9, IL-6, CRP, and YKL-40. We included 147 radically resected stage II–IV CRC treated with 24 weeks of adjuvant 5-fluorouracil-based chemotherapy in the phase III LIPSYT-study (ISRCTN98405441). All 147 were included in lead time analysis, but 12 relapsing during adjuvant therapy were excluded from post-adjuvant analysis. Elevated post-adjuvant CEA, IL-6, and CRP were associated with impaired disease-free survival (DFS) with hazard ratio (HR) 5.21 (95% confidence interval 2.32–11.69); 3.72 (1.99–6.95); 2.58 (1.18–5.61), respectively, and elevated IL-6 and CRP with impaired overall survival (OS) HR 3.06 (1.64–5.73); 3.41 (1.55–7.49), respectively. Elevated post-adjuvant IL-6 in CEA-normal patients identified a subgroup with impaired DFS. HR 3.12 (1.38–7.04) and OS, HR 3.20 (1.39–7.37). The lead times between the elevated biomarker and radiological relapse were 7.8 months for CEA and 10.0–53.1 months for CA19-9, IL-6, CRP, and YKL-40, and the lead time for the five combined was 27.3 months. Elevated post-adjuvant CEA, IL-6, and CRP were associated with impaired DFS. The lead time was shortest for CEA.
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
