| 1. |
- van der Kamp, Ananda, et al.
(författare)
-
Artificial Intelligence in Pediatric Pathology: The Extinction of a Medical Profession or the Key to a Bright Future?
- 2022
-
Ingår i: Pediatric and Developmental Pathology. - : SAGE PUBLICATIONS INC. - 1093-5266 .- 1615-5742. ; 25:4, s. 380-387
-
Forskningsöversikt (refereegranskat)abstract
- Artificial Intelligence (AI) has become of increasing interest over the past decade. While digital image analysis (DIA) is already being used in radiology, it is still in its infancy in pathology. One of the reasons is that large-scale digitization of glass slides has only recently become available. With the advent of digital slide scanners, that digitize glass slides into whole slide images, many labs are now in a transition phase towards digital pathology. However, only few departments worldwide are currently fully digital. Digital pathology provides the ability to annotate large datasets and train computers to develop and validate robust algorithms, similar to radiology. In this opinionated overview, we will give a brief introduction into AI in pathology, discuss the potential positive and negative implications and speculate about the future role of AI in the field of pediatric pathology.
|
|
| 2. |
- van der Kamp, Ananda, et al.
(författare)
-
Automated Deep Learning-Based Classification of Wilms Tumor Histopathology
- 2023
-
Ingår i: Cancers. - : MDPI. - 2072-6694. ; 15:9
-
Tidskriftsartikel (refereegranskat)abstract
- Wilms tumor (WT) is the most frequent pediatric tumor in children and shows highly variable histology, leading to variation in classification. Artificial intelligence-based automatic recognition holds the promise that this may be done in a more consistent way than human observers can. We have therefore studied digital microscopic slides, stained with standard hematoxylin and eosin, of 72 WT patients and used a deep learning (DL) system for the recognition of 15 different normal and tumor components. We show that such DL system can do this task with high accuracy, as exemplified by a Dice score of 0.85 for the 15 components. This approach may allow future automated WT classification.(1) Background: Histopathological assessment of Wilms tumors (WT) is crucial for risk group classification to guide postoperative stratification in chemotherapy pre-treated WT cases. However, due to the heterogeneous nature of the tumor, significant interobserver variation between pathologists in WT diagnosis has been observed, potentially leading to misclassification and suboptimal treatment. We investigated whether artificial intelligence (AI) can contribute to accurate and reproducible histopathological assessment of WT through recognition of individual histopathological tumor components. (2) Methods: We assessed the performance of a deep learning-based AI system in quantifying WT components in hematoxylin and eosin-stained slides by calculating the Sorensen-Dice coefficient for fifteen predefined renal tissue components, including six tumor-related components. We trained the AI system using multiclass annotations from 72 whole-slide images of patients diagnosed with WT. (3) Results: The overall Dice coefficient for all fifteen tissue components was 0.85 and for the six tumor-related components was 0.79. Tumor segmentation worked best to reliably identify necrosis (Dice coefficient 0.98) and blastema (Dice coefficient 0.82). (4) Conclusions: Accurate histopathological classification of WT may be feasible using a digital pathology-based AI system in a national cohort of WT patients.
|
|
| 3. |
- van Gorp, Marloes, et al.
(författare)
-
The course of health-related quality of life after the diagnosis of childhood cancer : a national cohort study
- 2023
-
Ingår i: BMC Cancer. - 1471-2407. ; 23, s. 1-13
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Comprehensive insight in the longitudinal development of health-related quality of life (HRQOL) after childhood cancer diagnosis could improve quality of care. Thus, we aimed to study the course and biopsychosocial determinants of HRQOL in a unique national cohort of children with cancer.METHODS: HRQOL of 2154 children with cancer was longitudinally reported (median: 3 reports) between diagnosis and 5 years after, using the pediatric quality of life inventory generic core scales (PedsQL). HRQOL was modelled over time since diagnosis using mixed model analysis for children 2-7 years (caregiver-reports) and ≥ 8 years (self-reports). Differences in the course between hematological, solid and central nervous system malignancies were studied. Additional associations of demographics, disease characteristics (age at diagnosis, relapse, diagnosis after the national centralization of childhood cancer care and treatment components) and caregiver distress (Distress thermometer) were studied.RESULTS: Overall, HRQOL improved with time since diagnosis, mostly in the first years. The course of HRQOL differed between diagnostic groups. In children aged 2-7 years, children with a solid tumor had most favorable HRQOL. In children aged ≥ 8 years, those with a hematological malignancy had lower HRQOL around diagnosis, but stronger improvement over time than the other diagnostic groups. In both age-groups, the course of HRQOL of children with a CNS tumor showed little or no improvement. Small to moderate associations (β: 0.18 to 0.67, p < 0.05) with disease characteristics were found. Centralized care related to better HRQOL (β: 0.25 to 0.44, p < 0.05). Caregiver distress was most consistently associated with worse HRQOL (β: - 0.13 to - 0.48, p < 0.01).CONCLUSIONS: The HRQOL course presented can aid in identifying children who have not fully recovered their HRQOL following cancer diagnosis, enabling early recognition of the issue. Future research should focus on ways to support children, especially those with a CNS tumor, for example by decreasing distress in their caregivers.
|
|
